CN117543791A - Power supply detection method, device, equipment and storage medium for power supply - Google Patents
Power supply detection method, device, equipment and storage medium for power supply Download PDFInfo
- Publication number
- CN117543791A CN117543791A CN202311484835.4A CN202311484835A CN117543791A CN 117543791 A CN117543791 A CN 117543791A CN 202311484835 A CN202311484835 A CN 202311484835A CN 117543791 A CN117543791 A CN 117543791A
- Authority
- CN
- China
- Prior art keywords
- power supply
- data
- data set
- proportion
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003860 storage Methods 0.000 title claims abstract description 76
- 238000001514 detection method Methods 0.000 title claims abstract description 57
- 238000004458 analytical method Methods 0.000 claims abstract description 117
- 238000010219 correlation analysis Methods 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims description 120
- 239000013598 vector Substances 0.000 claims description 35
- 238000000605 extraction Methods 0.000 claims description 28
- 230000015654 memory Effects 0.000 claims description 18
- 230000004927 fusion Effects 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 230000002068 genetic effect Effects 0.000 claims description 11
- 230000002457 bidirectional effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013211 curve analysis Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 230000002776 aggregation Effects 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 5
- 238000013433 optimization analysis Methods 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 17
- 238000007726 management method Methods 0.000 description 15
- 230000000875 corresponding effect Effects 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/40—Testing power supplies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/34—Parallel operation in networks using both storage and other dc sources, e.g. providing buffering
- H02J7/35—Parallel operation in networks using both storage and other dc sources, e.g. providing buffering with light sensitive cells
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J9/00—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting
- H02J9/04—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source
- H02J9/06—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source with automatic change-over, e.g. UPS systems
- H02J9/068—Electronic means for switching from one power supply to another power supply, e.g. to avoid parallel connection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Power Engineering (AREA)
- Physiology (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Genetics & Genomics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention relates to the field of power supply detection, and discloses a power supply detection method, device, equipment and storage medium for a power supply, which are used for realizing intelligent power supply management of the power supply so as to improve the charging reliability and efficiency of the power supply. The method comprises the following steps: detecting a power supply mode of a target power supply, and acquiring a first power supply data set if the power supply mode is mains supply; performing correlation analysis on the first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result; inputting the state influence parameters into a power supply state analysis model to perform power supply state analysis, so as to obtain a power supply state analysis result; carrying out power utilization load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power utilization load data; and setting first power supply proportion data between the mains supply and the emergency supply according to the power supply load data, and switching the power supply mode into the hybrid power supply mode according to the first power supply proportion data.
Description
Technical Field
The present invention relates to the field of power supply detection, and in particular, to a power supply detection method, apparatus, device, and storage medium for a power supply.
Background
With the development of the internet of things technology and smart power grids, a power supply becomes an important component of an intelligent power supply system. Power sources are becoming increasingly important as the primary charging devices for electric vehicles. In order to meet the ever-increasing charging demands of electric vehicles, the design and management of power supplies has become critical. The power supply may typically be charged by different modes of power supply, including mains power, solar power, battery power, etc. Different power supply modes have different characteristics, such as stable commercial power supply but high cost, sustainable solar power supply but weather influence, stable storage battery power supply and limited capacity. Therefore, an intelligent power supply management method is needed to switch the power supply modes according to different situations so as to meet the charging requirement of the electric automobile.
Determining the state of supply of the power source is critical to efficiently managing the charging process. If the power supply state is abnormal, emergency measures such as switching to a standby power supply or notifying maintenance personnel need to be taken. Therefore, the development of the power supply state detection method can accurately analyze the power supply condition of the power supply and is important for improving the reliability and the efficiency of the power supply.
Disclosure of Invention
The invention provides a power supply detection method, a device, equipment and a storage medium for a power supply, which are used for realizing intelligent power supply management of the power supply so as to improve the charging reliability and efficiency of the power supply.
The first aspect of the present invention provides a power supply detection method for a power supply, where the power supply detection method for a power supply includes:
detecting a power supply mode of a target power supply, and if the power supply mode is mains supply, acquiring a first power supply data set of the target power supply;
performing correlation analysis on the first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result;
inputting the state influence parameters into a preset power supply state analysis model to perform power supply state analysis, so as to obtain a power supply state analysis result;
carrying out power utilization load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power utilization load data;
and setting first power supply proportion data between mains supply power supply and emergency power supply according to the power supply power load data, and switching the power supply mode to a hybrid power supply mode of the mains supply power supply and the emergency power supply according to the first power supply proportion data.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the inputting the state influencing parameter into a preset power supply state analysis model to perform power supply state analysis, to obtain a power supply state analysis result, includes:
performing time sequence association and vector mapping on the state influence parameters to obtain time sequence state parameter vectors;
inputting the time sequence state parameter vector into a preset power supply state analysis model, wherein the power supply state analysis model comprises the following components: two layers of bidirectional long-short-time memory networks and two layers of full-connection networks;
extracting hidden state characteristics of the time sequence state parameter vector through the two layers of bidirectional long-short-time memory networks to obtain a hidden state characteristic vector;
inputting the hidden state feature vector into the two-layer fully-connected network to predict the power supply state, so as to obtain a target probability value S;
if the target probability value S is larger than a preset target value T, determining that the power supply state analysis result is abnormal in the mains supply power supply load;
and if the target probability value S is less than or equal to the preset target value T, determining that the power supply state analysis result is that the commercial power supply load is normal.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the setting, according to the power load data, first power supply proportion data between mains power supply and emergency power supply, and switching, according to the first power supply proportion data, the power supply mode to a hybrid power supply mode of mains power supply and emergency power supply includes:
Creating an initialized power supply proportion population through a preset genetic algorithm, wherein the initialized power supply proportion population comprises a plurality of candidate power supply proportion data;
according to the power supply electricity load data, performing fitness calculation on the plurality of candidate power supply proportion data to obtain a fitness value of each candidate power supply proportion data;
according to the fitness value, carrying out optimization analysis on the plurality of candidate power supply proportion data to obtain first power supply proportion data between mains supply power supply and emergency power supply;
and switching the power supply mode to a hybrid power supply mode of mains supply and emergency power supply according to the first power supply proportion data.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the power supply detection method of the power supply further includes:
when the power supply mode is a hybrid power supply mode, a second power supply data set of emergency power supply is collected;
classifying the second power supply data set to obtain a solar power supply data set and a storage battery power supply data set;
performing feature extraction on the solar power supply data set to generate a first feature matrix, performing feature extraction on the storage battery power supply data set to generate a second feature matrix, and performing matrix fusion on the first feature matrix and the second feature matrix to obtain a target feature matrix;
And inputting the target feature matrix into a preset emergency power supply proportion analysis model to perform emergency power supply proportion analysis, and obtaining second power supply proportion data between solar power supply and storage battery power supply.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the classifying the data set of the second power supply data set to obtain a solar power supply data set and a battery power supply data set includes:
determining a first clustering center corresponding to solar power supply and a second clustering center corresponding to storage battery power supply according to the correlation analysis result;
inputting the second power supply data set into a preset first clustering model, calculating distance data between a plurality of original data points in the second power supply data set and the first clustering center to obtain first distance data, and screening and integrating the plurality of original data points according to the first distance data to obtain a solar power supply data set;
inputting the second power supply data set into a preset second aggregation model, calculating distance data between a plurality of original data points in the second power supply data set and the second aggregation center to obtain second distance data, and screening and integrating the plurality of original data points according to the second distance data to obtain a storage battery power supply data set.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the performing feature extraction on the solar power supply data set to generate a first feature matrix, performing feature extraction on the battery power supply data set to generate a second feature matrix, and performing matrix fusion on the first feature matrix and the second feature matrix to obtain a target feature matrix, where the performing step includes:
performing curve fitting on the solar power supply data set to obtain a plurality of corresponding solar power supply curves, and performing curve fitting on the storage battery power supply data set to obtain a plurality of corresponding storage battery power supply curves;
performing curve analysis on the plurality of solar power supply curves to obtain a plurality of first curve characteristic values, and performing characteristic extraction on the plurality of solar power supply curves according to the plurality of first curve characteristic values to generate a first characteristic matrix;
performing curve analysis on the storage battery power supply curves to obtain a plurality of second curve characteristic values, and performing characteristic extraction on the storage battery power supply curves according to the plurality of second curve characteristic values to generate a second characteristic matrix;
acquiring illumination environment data of an emergency power supply system, setting matrix weight data of the first feature matrix and the second feature matrix according to the illumination environment data, and carrying out matrix fusion on the first feature matrix and the second feature matrix according to the matrix weight data to obtain a target feature matrix.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, inputting the target feature matrix into a preset emergency power supply proportion analysis model to perform emergency power supply proportion analysis, to obtain second power supply proportion data between solar power supply and battery power supply, includes:
inputting the target feature matrix into a preset emergency power supply proportion analysis model, wherein the emergency power supply proportion analysis model comprises a first input layer, a plurality of strategy updating networks and a first output layer, and each strategy updating network comprises a second input layer, a strategy prediction layer and a second output layer;
identifying the target feature matrix through the first input layer and sending the target feature matrix to the plurality of policy updating networks;
identifying through a second input layer in the plurality of strategy updating networks, extracting features through a strategy prediction layer in the plurality of strategy updating networks, performing emergency power supply proportion distribution prediction through a second output layer in the plurality of strategy updating networks, and outputting a plurality of predicted power supply proportion data;
and carrying out weighted average operation on the plurality of predicted power supply proportion data through the first output layer to obtain second power supply proportion data between solar power supply and storage battery power supply.
A second aspect of the present invention provides a power supply detection apparatus of a power supply, the power supply detection apparatus of the power supply including:
the detection module is used for detecting a power supply mode of a target power supply, and acquiring a first power supply data set of the target power supply if the power supply mode is mains supply;
the correlation analysis module is used for carrying out correlation analysis on the first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result;
the power supply state analysis module is used for inputting the state influence parameters into a preset power supply state analysis model to carry out power supply state analysis, so as to obtain a power supply state analysis result;
the operation module is used for carrying out power load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power load data;
and the switching module is used for setting first power supply proportion data between the mains supply and the emergency power supply according to the power supply load data, and switching the power supply mode to a hybrid power supply mode of the mains supply and the emergency power supply according to the first power supply proportion data.
A third aspect of the present invention provides a power supply detection apparatus of a power supply, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the power detection apparatus of the power supply to perform the power detection method of the power supply described above.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein that, when run on a computer, cause the computer to perform the power supply detection method of a power supply described above.
In the technical scheme provided by the invention, the power supply mode of the target power supply is detected, and if the power supply mode is mains supply, a first power supply data set is obtained; performing correlation analysis on the first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result; inputting the state influence parameters into a power supply state analysis model to perform power supply state analysis, so as to obtain a power supply state analysis result; carrying out power utilization load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power utilization load data; according to the invention, the power supply reliability of the power supply is ensured by monitoring the power supply states of different power supply modes and the power supply. The electric vehicle charging system can rapidly detect and cope with the problems of interruption or abnormality of mains supply, insufficient power supply capacity of solar energy and storage batteries and the like, thereby reducing interruption and faults of electric vehicle charging. Through analysis of the power load data, the proportion of the mains supply power supply and the emergency power supply can be intelligently adjusted according to actual demands, so that the satisfaction degree of the power load is maximized. The charging cost of the electric automobile can be reduced by reasonably distributing the proportion of different power supply sources. Through the power supply state of real-time supervision power, can early warn potential problem in advance, make the fortune dimension more high-efficient, and then realized the intelligent power management of power to the reliability and the efficiency of charging of power have been improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a power supply detection method of a power supply according to an embodiment of the present invention;
FIG. 2 is a flowchart of setting first power supply ratio data according to an embodiment of the present invention;
FIG. 3 is a flow chart of matrix fusion in an embodiment of the invention;
FIG. 4 is a flow chart of emergency power supply ratio analysis in an embodiment of the invention;
FIG. 5 is a schematic diagram of an embodiment of a power supply detection apparatus of a power supply according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a power supply detection apparatus of a power supply according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a power supply detection method, device and equipment of a power supply and a storage medium, which are used for realizing intelligent power supply management of the power supply so as to improve the charging reliability and efficiency of the power supply. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and one embodiment of a power supply detection method of a power supply in an embodiment of the present invention includes:
s101, detecting a power supply mode of a target power supply, and if the power supply mode is mains supply, acquiring a first power supply data set of the target power supply;
it is to be understood that the execution body of the present invention may be a power supply detection device of a power supply, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
In particular, the server selects appropriate sensors, such as voltage sensors, frequency sensors, and current sensors, to continuously monitor the power supply parameters of the power supply. These sensors will constantly measure voltage, frequency and current data and transmit these data to a data acquisition unit, typically an embedded system or computer. In this system, the server develops a power mode detection algorithm that determines the current power mode based on the sensor data. For example, if the voltage and frequency are within a certain range, the server may determine to be in mains supply mode. When the power mode is detected as mains powered, the server will initiate the data acquisition step. With the sensors installed, the server will record and store data relating to power supply, such as current, voltage, power, etc. in real time. These data are consolidated into a first power supply data set for subsequent analysis and control. Taking an electric car power supply as an example, when mains supply is detected, the server starts to monitor current and voltage. The current sensor provides a charging current measurement and the voltage sensor provides a voltage measurement. These data are recorded and stored for subsequent performance monitoring and analysis. By means of the system, the server can continuously monitor the power supply mode, and acquire a first power supply data set when mains supply is supplied. This helps ensure that the power supply is operating properly in mains power mode and provides data for performance monitoring and analysis. This approach may be applied to a variety of power management and monitoring systems to ensure their reliability and stability in different power modes.
S102, performing correlation analysis on a first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result;
specifically, the server prepares a first power supply data set. This data set contains data relating to the power supply, such as current, voltage, power, etc. obtained from the power sensor. Before correlation analysis is performed, it is necessary to ensure that the data set is complete, accurate, and that pre-processing has been performed, including data cleansing, outlier processing, and data normalization, among others. For example, assume that the server has a power data set containing the power of the electric vehicle during a week, including current, voltage and power measurements per hour. These data have been carefully processed to ensure quality and consistency of the data. The server performs a correlation analysis to determine which parameters are related to the status impact of the power supply. Correlation analysis typically involves calculating a correlation coefficient or other correlation index between individual parameters. The following are some commonly used correlation analysis methods: pearson correlation coefficient: for measuring the linear relationship between two consecutive variables. The correlation coefficient ranges from-1 to 1, negative values indicate a negative correlation, positive values indicate a positive correlation, and 0 indicates no correlation; spearman correlation coefficient: for measuring monotonic relationships between two variables, it is not required that the data be continuous. It is based on the rank of the data instead of the original value; determination coefficient (R≡2): the scale used to measure the variance of one variable that can explain another is commonly used in linear regression analysis; correlation matrix: correlations between multiple variables may be calculated at one time, generating a correlation matrix. For example, assume that a server performs pearson correlation coefficient analysis on a dataset of an electric vehicle power supply to look at the correlation between current, voltage, and power. The analysis showed that the correlation between current and power was high, the correlation coefficient was 0.85, and the correlation between voltage and power was low, the correlation coefficient was 0.23. After performing the correlation analysis, the server selects a state impact parameter according to the result of the correlation analysis. The correlation analysis results tell the server which parameters are closely related to the state change of the power supply, and therefore these parameters should be considered in the state analysis. For example, based on the results of the correlation analysis, the server decides to select the current as the state-affecting parameter because of its higher correlation with power. The change of the current has a great influence on the performance and the state of the power supply, so that the server takes the current as a key parameter of state analysis. When the state-affecting parameters are selected, the server inputs these parameters into a power state analysis model to further analyze the state and performance of the power supply. This model can predict the behavior of the power supply under different supply conditions based on selected parameters. For example, the server uses the selected current as an input parameter, which is input into a power state analysis model to evaluate the performance of the power supply at high currents. This helps the server to know the operation of the power supply under different current conditions, taking appropriate measures to optimize its performance or improve the power supply strategy.
S103, inputting the state influence parameters into a preset power supply state analysis model to perform power supply state analysis, so as to obtain a power supply state analysis result;
the server collects data related to power supply of the power source, and the data includes time sequence data of current, voltage, power and the like. These data require preprocessing, including data cleansing and normalization, to ensure their quality and consistency. The server then calculates a time series state parameter vector. The server collates the collected time series data into a vector form for subsequent analysis. For example, the current, voltage, and power data may be represented as timing vectors SI, SU, and SP, respectively, and correlated according to a time step. The server establishes a power supply state analysis model which comprises two Bi-LSTM layers and two fully connected networks. The Bi-LSTM layer is used to learn long-term dependencies in the time series data, while the fully connected network is used to map the extracted features to probability values S of the power states. Through two layers of Bi-LSTM networks, the model can extract hidden state characteristics of the time sequence state parameter vector. This step helps the model understand patterns and features in the time series data to aid in the prediction of the power state. Finally, the model maps the hidden state feature vector to the probability value S of the power supply state through a two-layer fully connected network. If S is larger than the preset target value T, the power supply state analysis result is that the commercial power supply load is abnormal; and if S is less than or equal to T, the power supply state analysis result is that the commercial power supply load is normal. For example, assume that the server has a data set of one power source including current, voltage and power data for a week. These data have been cleaned and preprocessed. The server collates these data into time-series state parameter vectors SI, SU and SP and inputs them into a preset power supply state analysis model. In the model, the Bi-LSTM network learns the characteristics of time sequence data, extracts the hidden state characteristic vector, and then predicts the power supply state through the fully connected network. If the target probability value S output by the model is 0.8 and the preset target value T is 0.7, the server determines that the power supply state analysis result is abnormal in the power supply load of the mains supply, and the power supply has a problem, and emergency measures are needed to repair or adjust the operation of the power supply. On the other hand, if the target probability value S is 0.6 and is smaller than the preset target value T, the power supply state analysis result indicates that the mains supply load is normal, and the power supply works normally in the mains supply mode without obvious problems.
S104, carrying out power load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power load data;
specifically, the server corresponds the power supply state analysis result to the first power supply data set. This may be accomplished by a time stamp or other related information. The purpose is to ensure that the server only selects data points that match the mains supply load status for the purpose of power load calculation. After the data preparation phase is completed, the server enters a phase of electricity load calculation. The core of this step is to calculate the power usage of the power supply in the mains supply state. By using the filtered data, the server calculates the power consumption at each point in time. The power can generally be calculated by means of current and voltage data, applying the basic power formula p=vi. In this way, the server can obtain the time series data of the power. And summarizing the power data of each time point to obtain the time sequence data of the power load. This data sequence reflects the power usage of the power supply in the mains powered state. The electrical load data needs to be stored for future analysis and application. The storage may be performed in a database or in a file, depending on the requirements and design of the system. Finally, the resulting electrical load data may be used for a variety of purposes including performance monitoring, energy management, and fault detection. And (3) performance monitoring: by analyzing the power load data, the server knows the power consumption pattern of the power supply, as well as the load fluctuations over different time periods. This helps to formulate a more efficient energy management strategy, optimizing the operation of the power supply system; and (3) energy management: the electricity load data can also be used for energy management, and the energy distribution is optimized by identifying the high load period and the low load period, so that the energy utilization rate is improved, and the energy cost is reduced; and (3) fault detection: if the electrical load data shows an abnormal power peak or other unusual pattern, this indicates that the power supply has a problem of failure or load imbalance. This can trigger an alarm and timely take maintenance or adjustment measures to ensure the reliability of the system. For example, assume that the server has an electric automobile power supply, and the power supply state analysis result is that the commercial power supply load is normal. The server first screens out data related to the normal condition of the mains supply load from the first power supply data set. The server then calculates the power consumption at each point in time based on the current and voltage data. The server then sums the power data to obtain power load timing data for the power source. By analyzing the electrical load data, the server identifies peaks and valleys to determine which periods of higher power usage by the power source and which periods are lower. This helps the server to optimize the energy management strategy, for example, performing maintenance operations during low load periods and ensuring adequate power supply during high load periods. If the electrical load data shows an abnormal power peak, this indicates that the power supply has a problem of failure or load imbalance. This triggers an alarm, allowing the server to act in time, maintain or repair the power supply, ensuring continuity and reliability of the charging service.
And S105, setting first power supply proportion data between the mains supply and the emergency power supply according to the power supply load data, and switching the power supply mode to a hybrid power supply mode of the mains supply and the emergency power supply according to the first power supply proportion data.
Specifically, the server creates an initialized power proportion population using a preset genetic algorithm. This population includes a plurality of candidate power supply proportion data, each proportion representing a proportion of the distribution between mains power supply and emergency power supply. These initialization scale data are the starting points for the algorithm to begin searching. For example, assume that the server creates an initialized supply ratio population comprising 50 different candidate supply ratio data, each ratio representing a distribution ratio of utility supply to emergency supply. These proportions may vary between 0 and 1, for example 0.7 representing 70% of mains supply and 30% of emergency supply. The server uses the power source electrical load data to make fitness calculations on these candidate power supply proportion data. The purpose of fitness calculation is to evaluate the performance of each candidate proportion to determine its merits in power mode switching. For example, assume that the server has acquired power load data for the power source, including power consumption, current, voltage, etc. Using this data, the server calculates the power load conditions for each candidate power supply ratio, such as the power consumption conditions for mains and emergency power supplies. The fitness value may be calculated based on some criteria, such as power consumption balance, energy efficiency, etc. An optimization analysis is then performed to determine first power supply ratio data between utility power supply and emergency power supply. This can be achieved using an optimization method such as a genetic algorithm. For example, genetic algorithms are a common optimization method that can be applied to this problem. In the genetic algorithm, candidate power supply ratio data will be combined, mutated and selected to find the optimal power supply ratio. The algorithm evaluates and adjusts the candidate scale according to the fitness value, gradually converging to the optimal solution. And finally, according to the obtained first power supply proportion data of the mains supply and the emergency power supply, the server switches the power supply mode to a mixed power supply mode of the mains supply and the emergency power supply. This means that the power supply will receive both mains and emergency power in this proportion to ensure the continuity and reliability of the charging service. For example, if the first power supply proportion data determined finally is 80% of the mains supply and 20% of the emergency supply, the power supply will receive power from both the mains supply and the emergency power supply in this proportion.
In the embodiment of the invention, a power supply mode of a target power supply is detected, and if the power supply mode is mains supply, a first power supply data set is obtained; performing correlation analysis on the first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result; inputting the state influence parameters into a power supply state analysis model to perform power supply state analysis, so as to obtain a power supply state analysis result; carrying out power utilization load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power utilization load data; according to the invention, the power supply reliability of the power supply is ensured by monitoring the power supply states of different power supply modes and the power supply. The electric vehicle charging system can rapidly detect and cope with the problems of interruption or abnormality of mains supply, insufficient power supply capacity of solar energy and storage batteries and the like, thereby reducing interruption and faults of electric vehicle charging. Through analysis of the power load data, the proportion of the mains supply power supply and the emergency power supply can be intelligently adjusted according to actual demands, so that the satisfaction degree of the power load is maximized. The charging cost of the electric automobile can be reduced by reasonably distributing the proportion of different power supply sources. Through the power supply state of real-time supervision power, can early warn potential problem in advance, make the fortune dimension more high-efficient, and then realized the intelligent power management of power to the reliability and the efficiency of charging of power have been improved.
In a specific embodiment, the process of executing step S103 may specifically include the following steps:
(1) Performing time sequence association and vector mapping on the state influence parameters to obtain time sequence state parameter vectors;
(2) Inputting the time sequence state parameter vector into a preset power supply state analysis model, wherein the power supply state analysis model comprises the following components: two layers of bidirectional long-short-time memory networks and two layers of full-connection networks;
(3) Extracting hidden state characteristics of the time sequence state parameter vector through two layers of bidirectional long-short time memory networks to obtain a hidden state characteristic vector;
(4) Inputting the hidden state feature vector into a two-layer fully connected network to predict the power supply state, and obtaining a target probability value S;
(5) If the target probability value S is larger than the preset target value T, determining that the power supply state analysis result is abnormal in the mains supply load;
(6) If the target probability value S is less than or equal to the preset target value T, determining that the power supply state analysis result is that the commercial power supply load is normal.
In particular, the server gathers state-affecting parameters of the power supply, including current, voltage, frequency, power factor, etc. The data for these parameters typically exist in time series, so timing correlations and vector mappings are required to construct timing state parameter vectors. Timing correlations may be used to take into account the relationships between different parameters, while vector mapping helps to convert the timing data into a format that can be analyzed. For example, assume that a server monitors the power state of an electric vehicle power supply. The server collects current, voltage and power factor data per minute. By time-series correlating and vector mapping these data, the server obtains a time-series state parameter vector containing current, voltage and power factor per minute. The power state analysis model is a key component for predicting the power state of a power supply. This model typically includes multiple layers, such as two layers of bidirectional long short time memory networks (LSTM) and two layers of fully connected networks. The hierarchical design helps to extract important features in the data and make predictions of the power state. A bidirectional long and short term memory network (LSTM) is a deep learning model suitable for processing time series data. Two layers of bi-directional LSTM may be used to capture long-term and short-term dependencies in the timing state parameter vector and extract hidden state features. The two-layer fully connected network is used for mapping the hidden state features extracted by the LSTM layer to a final power supply state prediction result. For example, the power state analysis model of the server includes two layers of bi-directional LSTM and two layers of fully connected networks. This model is trained to extract features from the time series state parameter vector and predict the power supply state. And extracting hidden state characteristics of the time sequence state parameter vector by the server through a two-layer bidirectional LSTM network. This process helps translate complex time series data into a representation of features with a higher level in order to predict the power state. And the server inputs the hidden state feature vector into a two-layer fully-connected network to predict the power supply state. The fully connected network will learn how to map the extracted features to the target probability value S. This probability value represents the nature of the mains supply load anomaly. For example, based on the extracted hidden state features, the fully connected network will generate a target probability value S that represents the nature of the power supply state anomaly. If S is larger than a preset target value T, the server determines that the power supply state analysis result is abnormal in the mains supply power supply load; if S is less than or equal to T, the server determines that the power supply state analysis result is that the commercial power supply load is normal. And finally, according to the calculation result of the target probability value S, the server judges the power supply state of the power supply. If the power supply state analysis result is that the commercial power supply load is abnormal, an alarm can be triggered or emergency measures can be taken. If the power supply state is normal, normal operation can be continued. For example, based on the calculated target probability value S, if S is 0.9 (greater than the preset target value T), the server will determine that the power supply state analysis result is abnormal in the mains power supply load, and take corresponding maintenance measures.
In a specific embodiment, as shown in fig. 2, the process of performing step S105 may specifically include the following steps:
s201, creating an initialized power supply proportion population through a preset genetic algorithm, wherein the initialized power supply proportion population comprises a plurality of candidate power supply proportion data;
s202, performing fitness calculation on a plurality of candidate power supply proportion data according to power supply power consumption load data to obtain a fitness value of each candidate power supply proportion data;
s203, carrying out optimization analysis on a plurality of candidate power supply proportion data according to the fitness value to obtain first power supply proportion data between mains supply and emergency power supply;
s204, switching the power supply mode to a hybrid power supply mode of mains supply and emergency power supply according to the first power supply proportion data.
Specifically, the server uses a preset genetic algorithm to create an initialized power supply proportion population. This population consists of a number of different candidate power supply ratio data, each ratio representing the ratio of the distribution between mains supply and emergency supply. These initialization scale data are the starting points for the algorithm to begin searching. For example, assume that the server creates an initialized supply ratio population containing 50 different candidate supply ratio data. Each proportion data is a vector comprising a mains supply proportion and an emergency supply proportion, e.g. [0.7,0.3], representing 70% of the mains supply and 30% of the emergency supply. The server uses the power load data of the power source to calculate the adaptability of the candidate power supply proportion data. The purpose of fitness calculation is to evaluate the performance of each candidate proportion to determine its merits in power mode switching. For example, the server has obtained power load data for the power source, including power consumption, current, voltage, etc. Using these data, the server calculates the power load conditions for each candidate power supply ratio, such as the power consumption conditions for mains and emergency power supplies. The fitness value may be calculated based on some criteria, such as power consumption balance, energy efficiency, etc. When the server calculates the fitness value of each candidate power supply ratio, optimization analysis is performed next to determine first power supply ratio data between the mains supply and the emergency power supply. This can be achieved using an optimization method such as a genetic algorithm. For example, genetic algorithms are a common optimization method that can be applied to this problem. In the genetic algorithm, candidate power supply ratio data will be combined, mutated and selected to find the optimal power supply ratio. The algorithm evaluates and adjusts the candidate scale according to the fitness value, gradually converging to the optimal solution. And finally, according to the obtained first power supply proportion data of the mains supply and the emergency power supply, the server switches the power supply mode to a mixed power supply mode of the mains supply and the emergency power supply. The power supply can simultaneously receive the power supply of the commercial power and the emergency power supply according to the proportion so as to ensure the continuity and the reliability of the charging service. For example, if the first power supply proportion data determined finally is 80% of the mains supply and 20% of the emergency supply, the power supply will receive power from both the mains supply and the emergency power supply in this proportion.
In a specific embodiment, the process of executing the power supply detection method of the power supply may specifically include the following steps:
(1) When the power supply mode is a hybrid power supply mode, collecting a second power supply data set of emergency power supply;
(2) Classifying the second power supply data set to obtain a solar power supply data set and a storage battery power supply data set;
(3) Performing feature extraction on the solar power supply data set to generate a first feature matrix, performing feature extraction on the storage battery power supply data set to generate a second feature matrix, and performing matrix fusion on the first feature matrix and the second feature matrix to obtain a target feature matrix;
(4) And inputting the target feature matrix into a preset emergency power supply proportion analysis model for emergency power supply proportion analysis to obtain second power supply proportion data between solar power supply and storage battery power supply.
Specifically, in the hybrid power supply mode, the server receives mains supply and emergency power supply at the same time. For the analysis of the emergency power supply ratio, a second power supply data set of the emergency power supply is first acquired. This data set includes information about the current, voltage, power, etc. of the emergency power supply, as well as the power load data of the power supply. For example, assume that the power supply of the server is in hybrid power mode, and the emergency power is provided by solar energy and a battery. The server collects data of current, voltage, power and the like of the solar energy and the storage battery, and electricity load data of the power supply. The server classifies the second power supply data set into a solar power supply data set and a storage battery power supply data set. This classification process may be based on the source and characteristics of the data. For example, the server divides the second power supply data set into a solar power supply data set and a battery power supply data set according to the data tag or feature. For example, a solar powered dataset contains data from a solar panel, while a battery powered dataset contains data from a battery. And for the solar power supply data set and the storage battery power supply data set, the server performs feature extraction to generate a first feature matrix and a second feature matrix. The purpose of feature extraction is to extract useful features from the raw data for subsequent analysis. For example, for a solar powered dataset, feature extraction includes calculating features of the power output of the solar panel, solar radiation intensity, and the like. For a battery powered dataset, feature extraction may include features of battery charge, voltage fluctuations, etc. of the battery. These features will be used for subsequent analysis. After the first feature matrix and the second feature matrix are generated, the server performs matrix fusion on the first feature matrix and the second feature matrix to obtain a target feature matrix. Matrix fusion is the process of combining two or more feature matrices into a single feature matrix. This may be achieved by some mathematical operation such as matrix stitching or weighted averaging. For example, assume that the first feature matrix is a 3x3 matrix containing solar-related features, and the second feature matrix is a 3x3 matrix containing battery-related features. The server merges them into a 6x3 target feature matrix by matrix stitching or weighted averaging, where the first three rows are solar features and the last three rows are battery features. And finally, inputting the target feature matrix into a preset emergency power supply proportion analysis model for analysis. The purpose of this model is to predict second power supply ratio data between solar power supply and battery power supply based on the feature matrix. For example, assume that the server emergency power proportion analysis model is a machine learning model, such as a neural network or decision tree. It accepts the target feature matrix as input and outputs second power supply ratio data between solar power supply and battery power supply, e.g. [0.6,0.4], indicating 60% solar power supply and 40% battery power supply.
In a specific embodiment, the performing step classifies the second power supply data set into a solar power supply data set and a storage battery power supply data set, and the process of obtaining the solar power supply data set and the storage battery power supply data set may specifically include the following steps:
(1) Determining a first clustering center corresponding to solar power supply and a second clustering center corresponding to storage battery power supply according to the correlation analysis result;
(2) Inputting a second power supply data set into a preset first clustering model, calculating distance data between a plurality of original data points in the second power supply data set and a first clustering center to obtain first distance data, and screening and integrating the plurality of original data points according to the first distance data to obtain a solar power supply data set;
(3) Inputting a second power supply data set into a preset second aggregation model, calculating distance data between a plurality of original data points in the second power supply data set and a second aggregation center to obtain second distance data, and screening and integrating the plurality of original data points according to the second distance data to obtain a storage battery power supply data set.
Specifically, according to the correlation analysis result, the server determines a first clustering center and a second clustering center of solar power supply and storage battery power supply. This process may be implemented using a clustering algorithm, such as K-means clustering. For example, assume that the server has a second power supply data set that includes solar power and battery power data points. The server uses a K-means clustering algorithm to divide the data points into two clusters, wherein one cluster corresponds to solar power supply and the other cluster corresponds to storage battery power supply. The center point of each cluster is a first cluster center and a second cluster center. And inputting the second power supply data set into a preset first clustering model and a preset second clustering model, and respectively calculating distance data between each data point and the first clustering center and the second clustering center. This may be done using a euclidean distance, manhattan distance equidistance metric. The plurality of raw data points are then screened and integrated based on the distance data to obtain a solar powered data set and a battery powered data set. For example, for a solar powered data set, the server calculates the distance of each data point from the first cluster center and screens out data points with a distance less than a certain threshold value to form the solar powered data set. The same strategy is also used for battery powered datasets. Finally, according to the screening and integration process of the distance data, the server obtains a solar power supply data set and a storage battery power supply data set. The data sets comprise raw data points subjected to clustering and distance screening, and correspond to the solar power supply and storage battery power supply conditions respectively. For example, assume that there are 100 data points in the second power supply data set, and after distance screening, the server obtains a solar power supply data set and a battery power supply data set, each of which contains 30 data points and 70 data points. These data sets can be used for subsequent energy management and distribution to ensure that the power supply is able to efficiently utilize solar and battery power when the power supply mode is switched.
In a specific embodiment, as shown in fig. 3, the performing step performs feature extraction on a solar power supply data set to generate a first feature matrix, performs feature extraction on a battery power supply data set to generate a second feature matrix, and performs matrix fusion on the first feature matrix and the second feature matrix, so that the process of obtaining the target feature matrix may specifically include the following steps:
s301, performing curve fitting on a solar power supply data set to obtain a plurality of corresponding solar power supply curves, and performing curve fitting on a storage battery power supply data set to obtain a plurality of corresponding storage battery power supply curves;
s302, performing curve analysis on a plurality of solar power supply curves to obtain a plurality of first curve characteristic values, and performing characteristic extraction on the plurality of solar power supply curves according to the plurality of first curve characteristic values to generate a first characteristic matrix;
s303, performing curve analysis on the power supply curves of the plurality of storage batteries to obtain a plurality of second curve characteristic values, and performing characteristic extraction on the power supply curves of the plurality of storage batteries according to the plurality of second curve characteristic values to generate a second characteristic matrix;
s304, acquiring illumination environment data of the emergency power supply system, setting matrix weight data of a first feature matrix and a second feature matrix according to the illumination environment data, and carrying out matrix fusion on the first feature matrix and the second feature matrix according to the matrix weight data to obtain a target feature matrix.
Specifically, the server performs curve fitting on the solar power supply data set and the storage battery power supply data set to obtain a corresponding solar power supply curve and a corresponding storage battery power supply curve. Curve fitting is a method of fitting data points to a mathematical model or curve to better describe the trend and pattern of the data. For example, for a solar powered dataset, the server uses polynomial fitting, exponential fitting, or other curve fitting methods to derive the solar powered curve. Also, the same method can be used to fit the battery-powered data set. And performing curve analysis on the plurality of solar power supply curves to obtain a plurality of first curve characteristic values, and performing characteristic extraction on the plurality of solar power supply curves according to the characteristic values to generate a first characteristic matrix. And performing curve analysis on the plurality of storage battery power supply curves to obtain a plurality of second curve characteristic values, and performing characteristic extraction on the plurality of storage battery power supply curves according to the characteristic values to generate a second characteristic matrix. For example, curve analysis may include calculating a mean, variance, periodicity, etc. characteristic of the curve. For a solar power supply curve, feature extraction can include extracting the characteristics of the curve such as the average power of the day, the maximum power point and the like. For a battery power supply curve, feature extraction may include extracting features such as battery charge-discharge efficiency, voltage fluctuation, and the like. And acquiring illumination environment data of the emergency power supply system, and setting matrix weight data of the first feature matrix and the second feature matrix according to the data. The matrix weights may reflect the importance of different features to the lighting environment. And then, carrying out matrix fusion on the first feature matrix and the second feature matrix according to the matrix weight to obtain a target feature matrix. For example, if the lighting environment data indicates that the sunlight is sufficient, the solar powered weight may be set higher and the battery powered weight set lower. Conversely, if the illumination is insufficient, the weight distribution is reversed. Through weighted fusion, the server obtains a target feature matrix reflecting the power supply condition of the power supply so as to facilitate subsequent decision and management.
In a specific embodiment, as shown in fig. 4, the step of inputting the target feature matrix into a preset emergency power supply proportion analysis model to perform emergency power supply proportion analysis, and the process of obtaining the second power supply proportion data between the solar power supply and the storage battery power supply may specifically include the following steps:
s401, inputting a target feature matrix into a preset emergency power supply proportion analysis model, wherein the emergency power supply proportion analysis model comprises a first input layer, a plurality of strategy updating networks and a first output layer, and each strategy updating network comprises a second input layer, a strategy prediction layer and a second output layer;
s402, identifying a target feature matrix through a first input layer, and sending the target feature matrix to a plurality of strategy updating networks;
s403, identifying through a second input layer in the plurality of strategy updating networks, extracting features through a strategy prediction layer in the plurality of strategy updating networks, carrying out emergency power supply proportion distribution prediction through a second output layer in the plurality of strategy updating networks, and outputting a plurality of predicted power supply proportion data;
s404, performing weighted average operation on the plurality of predicted power supply proportion data through the first output layer to obtain second power supply proportion data between solar power supply and storage battery power supply.
Specifically, the server emergency power supply proportion analysis model comprises a first input layer, a plurality of strategy updating networks and a first output layer. Each policy update network includes a second input layer, a policy prediction layer, and a second output layer. This hierarchy facilitates hierarchical processing and feature extraction. And inputting the target feature matrix into a first input layer of the emergency power supply proportion analysis model for identification. The target feature matrix is generated in the previous step and reflects the features of the power supply condition of the power supply. The target feature matrix is transmitted to a plurality of policy update networks. Each policy update network is responsible for handling and policy prediction of features of different aspects. Where the server focuses on the process of one policy update network, the other network is similar. In the policy update network, the target feature matrix is again input to the second input layer for identification. This hierarchy helps to refine and process the features further. At the policy prediction layer of the policy update network, the feature extraction process begins. The aim here is to extract information about the emergency power supply strategy from the features of the second input layer. This may be accomplished through neural networks, machine learning models, or other algorithms. And finally, predicting emergency power supply proportion at a second output layer of the strategy updating network. This layer predicts second power supply ratio data between the solar power supply and the battery power supply based on the extracted features and the policy prediction information. Each policy update network outputs a predicted power supply proportion data. Thus, multiple policy updating networks may generate multiple predicted power ratio data representing different policies or schemes. These data may reflect the emergency power supply ratio in different situations. And finally, carrying out weighted average operation on the plurality of predicted power supply proportion data through the first output layer to obtain second power supply proportion data between solar power supply and storage battery power supply. This process reflects the importance of different strategies or schemes through weight allocation. For example, assume that the server has three policy update networks, each based on different characteristics and policies to make predictions of emergency power supply proportions. The first network outputs solar power with the power supply ratio of 0.6 and the power supply ratio of the storage battery of 0.4. The second network outputs solar power with the power supply ratio of 0.7 and the power supply ratio of the storage battery of 0.3. The third network outputs solar power with the power supply ratio of 0.5 and the power supply ratio of the storage battery of 0.5. The final power supply ratio data, for example, the solar power supply ratio is 0.6 and the battery power supply ratio is 0.4, can be obtained through weighted average.
The power supply detection method of the power supply in the embodiment of the present invention is described above, and the power supply detection apparatus of the power supply in the embodiment of the present invention is described below, referring to fig. 5, where an embodiment of the power supply detection apparatus of the present invention includes:
the detection module 501 is configured to detect a power supply mode of a target power supply, and acquire a first power supply data set of the target power supply if the power supply mode is mains supply;
the correlation analysis module 502 is configured to perform correlation analysis on the first power supply data set to obtain a correlation analysis result, and select a state influence parameter according to the correlation analysis result;
the power supply state analysis module 503 is configured to input the state influencing parameter into a preset power supply state analysis model to perform power supply state analysis, so as to obtain a power supply state analysis result;
the operation module 504 is configured to perform power load operation on the first power supply data set according to the power supply state analysis result, so as to obtain power supply power load data;
the switching module 505 is configured to set first power supply proportion data between the mains supply and the emergency power supply according to the power supply load data, and switch the power supply mode to a hybrid power supply mode of the mains supply and the emergency power supply according to the first power supply proportion data.
Detecting a power supply mode of a target power supply through the cooperation of the components, and acquiring a first power supply data set if the power supply mode is mains supply; performing correlation analysis on the first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result; inputting the state influence parameters into a power supply state analysis model to perform power supply state analysis, so as to obtain a power supply state analysis result; carrying out power utilization load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power utilization load data; according to the invention, the power supply reliability of the power supply is ensured by monitoring the power supply states of different power supply modes and the power supply. The electric vehicle charging system can rapidly detect and cope with the problems of interruption or abnormality of mains supply, insufficient power supply capacity of solar energy and storage batteries and the like, thereby reducing interruption and faults of electric vehicle charging. Through analysis of the power load data, the proportion of the mains supply power supply and the emergency power supply can be intelligently adjusted according to actual demands, so that the satisfaction degree of the power load is maximized. The charging cost of the electric automobile can be reduced by reasonably distributing the proportion of different power supply sources. Through the power supply state of real-time supervision power, can early warn potential problem in advance, make the fortune dimension more high-efficient, and then realized the intelligent power management of power to the reliability and the efficiency of charging of power have been improved.
The power supply detection apparatus for a power supply in the embodiment of the present invention is described in detail above in fig. 5 from the point of view of a modularized functional entity, and the power supply detection device for a power supply in the embodiment of the present invention is described in detail below from the point of view of hardware processing.
Fig. 6 is a schematic structural diagram of a power supply detection device according to an embodiment of the present invention, where the power supply detection device 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the power supply detection device 600 of the power supply. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the power supply detection device 600 of the power supply.
The power supply detection apparatus 600 of the power supply may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the configuration of the power supply detection apparatus of the power supply shown in fig. 6 does not constitute a limitation of the power supply detection apparatus of the power supply, and may include more or less components than those illustrated, or may combine certain components, or may be arranged in different components.
The invention also provides a power supply detection device of the power supply, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the power supply detection method of the power supply in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the power supply detection method of the power supply.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The power supply detection method of the power supply is characterized by comprising the following steps of:
detecting a power supply mode of a target power supply, and if the power supply mode is mains supply, acquiring a first power supply data set of the target power supply;
performing correlation analysis on the first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result;
inputting the state influence parameters into a preset power supply state analysis model to perform power supply state analysis, so as to obtain a power supply state analysis result;
carrying out power utilization load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power utilization load data;
And setting first power supply proportion data between mains supply power supply and emergency power supply according to the power supply power load data, and switching the power supply mode to a hybrid power supply mode of the mains supply power supply and the emergency power supply according to the first power supply proportion data.
2. The power supply detection method of claim 1, wherein the step of inputting the state-affecting parameter into a preset power supply state analysis model to perform power supply state analysis, to obtain a power supply state analysis result, includes:
performing time sequence association and vector mapping on the state influence parameters to obtain time sequence state parameter vectors;
inputting the time sequence state parameter vector into a preset power supply state analysis model, wherein the power supply state analysis model comprises the following components: two layers of bidirectional long-short-time memory networks and two layers of full-connection networks;
extracting hidden state characteristics of the time sequence state parameter vector through the two layers of bidirectional long-short-time memory networks to obtain a hidden state characteristic vector;
inputting the hidden state feature vector into the two-layer fully-connected network to predict the power supply state, so as to obtain a target probability value S;
if the target probability value S is larger than a preset target value T, determining that the power supply state analysis result is abnormal in the mains supply power supply load;
And if the target probability value S is less than or equal to the preset target value T, determining that the power supply state analysis result is that the commercial power supply load is normal.
3. The power supply detection method according to claim 1, wherein the setting of the first power supply ratio data between the utility power supply and the emergency power supply according to the power supply load data, and the switching of the power supply mode to the hybrid power supply mode of the utility power supply and the emergency power supply according to the first power supply ratio data, includes:
creating an initialized power supply proportion population through a preset genetic algorithm, wherein the initialized power supply proportion population comprises a plurality of candidate power supply proportion data;
according to the power supply electricity load data, performing fitness calculation on the plurality of candidate power supply proportion data to obtain a fitness value of each candidate power supply proportion data;
according to the fitness value, carrying out optimization analysis on the plurality of candidate power supply proportion data to obtain first power supply proportion data between mains supply power supply and emergency power supply;
and switching the power supply mode to a hybrid power supply mode of mains supply and emergency power supply according to the first power supply proportion data.
4. The power supply detection method of claim 1, wherein the power supply detection method of the power supply further comprises:
When the power supply mode is a hybrid power supply mode, a second power supply data set of emergency power supply is collected;
classifying the second power supply data set to obtain a solar power supply data set and a storage battery power supply data set;
performing feature extraction on the solar power supply data set to generate a first feature matrix, performing feature extraction on the storage battery power supply data set to generate a second feature matrix, and performing matrix fusion on the first feature matrix and the second feature matrix to obtain a target feature matrix;
and inputting the target feature matrix into a preset emergency power supply proportion analysis model to perform emergency power supply proportion analysis, and obtaining second power supply proportion data between solar power supply and storage battery power supply.
5. The method for detecting power supplied by a power supply according to claim 4, wherein said classifying the second power supply data set into a solar power supply data set and a battery power supply data set, comprises:
determining a first clustering center corresponding to solar power supply and a second clustering center corresponding to storage battery power supply according to the correlation analysis result;
inputting the second power supply data set into a preset first clustering model, calculating distance data between a plurality of original data points in the second power supply data set and the first clustering center to obtain first distance data, and screening and integrating the plurality of original data points according to the first distance data to obtain a solar power supply data set;
Inputting the second power supply data set into a preset second aggregation model, calculating distance data between a plurality of original data points in the second power supply data set and the second aggregation center to obtain second distance data, and screening and integrating the plurality of original data points according to the second distance data to obtain a storage battery power supply data set.
6. The method for detecting power supply of a power supply according to claim 5, wherein the performing feature extraction on the solar power supply data set to generate a first feature matrix, performing feature extraction on the battery power supply data set to generate a second feature matrix, and performing matrix fusion on the first feature matrix and the second feature matrix to obtain a target feature matrix includes:
performing curve fitting on the solar power supply data set to obtain a plurality of corresponding solar power supply curves, and performing curve fitting on the storage battery power supply data set to obtain a plurality of corresponding storage battery power supply curves;
performing curve analysis on the plurality of solar power supply curves to obtain a plurality of first curve characteristic values, and performing characteristic extraction on the plurality of solar power supply curves according to the plurality of first curve characteristic values to generate a first characteristic matrix;
Performing curve analysis on the storage battery power supply curves to obtain a plurality of second curve characteristic values, and performing characteristic extraction on the storage battery power supply curves according to the plurality of second curve characteristic values to generate a second characteristic matrix;
acquiring illumination environment data of an emergency power supply system, setting matrix weight data of the first feature matrix and the second feature matrix according to the illumination environment data, and carrying out matrix fusion on the first feature matrix and the second feature matrix according to the matrix weight data to obtain a target feature matrix.
7. The method for detecting power supply of power supply according to claim 6, wherein inputting the target feature matrix into a preset emergency power supply proportion analysis model for emergency power supply proportion analysis to obtain second power supply proportion data between solar power supply and storage battery power supply, comprises:
inputting the target feature matrix into a preset emergency power supply proportion analysis model, wherein the emergency power supply proportion analysis model comprises a first input layer, a plurality of strategy updating networks and a first output layer, and each strategy updating network comprises a second input layer, a strategy prediction layer and a second output layer;
Identifying the target feature matrix through the first input layer and sending the target feature matrix to the plurality of policy updating networks;
identifying through a second input layer in the plurality of strategy updating networks, extracting features through a strategy prediction layer in the plurality of strategy updating networks, performing emergency power supply proportion distribution prediction through a second output layer in the plurality of strategy updating networks, and outputting a plurality of predicted power supply proportion data;
and carrying out weighted average operation on the plurality of predicted power supply proportion data through the first output layer to obtain second power supply proportion data between solar power supply and storage battery power supply.
8. A power supply detection apparatus of a power supply, characterized in that the power supply detection apparatus of a power supply includes:
the detection module is used for detecting a power supply mode of a target power supply, and acquiring a first power supply data set of the target power supply if the power supply mode is mains supply;
the correlation analysis module is used for carrying out correlation analysis on the first power supply data set to obtain a correlation analysis result, and selecting state influence parameters according to the correlation analysis result;
The power supply state analysis module is used for inputting the state influence parameters into a preset power supply state analysis model to carry out power supply state analysis, so as to obtain a power supply state analysis result;
the operation module is used for carrying out power load operation on the first power supply data set according to the power supply state analysis result to obtain power supply power load data;
and the switching module is used for setting first power supply proportion data between the mains supply and the emergency power supply according to the power supply load data, and switching the power supply mode to a hybrid power supply mode of the mains supply and the emergency power supply according to the first power supply proportion data.
9. A power supply detection apparatus of a power supply, characterized in that the power supply detection apparatus of the power supply comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause a power detection apparatus of the power supply to perform the power detection method of the power supply of any one of claims 1-7.
10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the power supply detection method of the power supply of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311484835.4A CN117543791B (en) | 2023-11-08 | 2023-11-08 | Power supply detection method, device, equipment and storage medium for power supply |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311484835.4A CN117543791B (en) | 2023-11-08 | 2023-11-08 | Power supply detection method, device, equipment and storage medium for power supply |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117543791A true CN117543791A (en) | 2024-02-09 |
| CN117543791B CN117543791B (en) | 2024-07-12 |
Family
ID=89793069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311484835.4A Active CN117543791B (en) | 2023-11-08 | 2023-11-08 | Power supply detection method, device, equipment and storage medium for power supply |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117543791B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118174435A (en) * | 2024-05-14 | 2024-06-11 | 安徽徽电科技股份有限公司 | Integrated low-voltage fast-cutting complete system for dual-power supply switching |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108957359A (en) * | 2018-08-15 | 2018-12-07 | 合肥工业大学 | The test method of hybrid power system momentary efficiency under a kind of environment for vehicle |
| CN112528113A (en) * | 2020-12-16 | 2021-03-19 | 国网经济技术研究院有限公司 | Terminal user dividing method and system based on power supply reliability multi-dimensional big data |
| WO2022141871A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Time sequence data anomaly detection method, apparatus and device, and storage medium |
| CN115811051A (en) * | 2022-11-13 | 2023-03-17 | 国网内蒙古东部电力有限公司经济技术研究院 | Complementary coordination method for charging load and distributed power supply of electric automobile |
-
2023
- 2023-11-08 CN CN202311484835.4A patent/CN117543791B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108957359A (en) * | 2018-08-15 | 2018-12-07 | 合肥工业大学 | The test method of hybrid power system momentary efficiency under a kind of environment for vehicle |
| CN112528113A (en) * | 2020-12-16 | 2021-03-19 | 国网经济技术研究院有限公司 | Terminal user dividing method and system based on power supply reliability multi-dimensional big data |
| WO2022141871A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Time sequence data anomaly detection method, apparatus and device, and storage medium |
| CN115811051A (en) * | 2022-11-13 | 2023-03-17 | 国网内蒙古东部电力有限公司经济技术研究院 | Complementary coordination method for charging load and distributed power supply of electric automobile |
Non-Patent Citations (1)
| Title |
|---|
| 姜克隽: "多种发电情景下高可靠度电力供应模式分析", 中国能源, no. 10, 25 October 2022 (2022-10-25), pages 40 - 46 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118174435A (en) * | 2024-05-14 | 2024-06-11 | 安徽徽电科技股份有限公司 | Integrated low-voltage fast-cutting complete system for dual-power supply switching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117543791B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3770620B1 (en) | Deterioration estimation device and deterioration estimation method | |
| EP3770619B1 (en) | Degradation estimating device and degradation estimating method | |
| CN117543791B (en) | Power supply detection method, device, equipment and storage medium for power supply | |
| CN116643178B (en) | SOC estimation method and related device of battery management system | |
| CN116976707B (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
| US20230305073A1 (en) | Method and apparatus for providing a predicted aging state of a device battery based on a predicted usage pattern | |
| CN115514100A (en) | Hybrid energy storage system based on multi-element energy storage and control | |
| CN116125204A (en) | Fault prediction system based on power grid digitization | |
| CN116466672B (en) | Data center machine room parameter regulation and control method based on artificial intelligence and related device | |
| CN117458544B (en) | Optimization cooperative regulation and control method based on multi-type energy storage resource dynamic aggregation | |
| CN116885763B (en) | Energy management device and method suitable for distributed energy storage system | |
| CN117893059A (en) | Energy storage data acquisition and analysis method and system based on sensor | |
| EP3839743B1 (en) | System-state monitoring method and device and storage medium | |
| CN117630672A (en) | Method and device for predicting a device battery of a diagnostic device using a converter model | |
| CN116842464A (en) | Battery system SOC estimation method | |
| KR20230105316A (en) | Method and system for efficiently monitoring battery cells of a device battery in a device-external central unit using a digital twin | |
| JP7458183B2 (en) | Energy demand fluctuation pattern classification method and system | |
| Ding et al. | Reliability evaluation of direct current distribution system for intelligent buildings based on big data analysis | |
| WO2024057996A1 (en) | Electricity storage element degradation state calculating device, degradation state calculating method, degradation state calculating program, degradation state estimating device, degradation state estimating method, abnormality detecting device, and abnormality detecting method | |
| CN111337764A (en) | Charging pile fault diagnosis system and method and storage medium | |
| CN117439146B (en) | Data analysis control method and system for charging pile | |
| KR102420120B1 (en) | Electronic meter measuring device of abnormal condition monitoring system | |
| CN117394409B (en) | Intelligent assessment method and system for equipment state of energy storage power station | |
| EP4300109A1 (en) | Device and method for predicting low voltage failure of secondary battery, and battery control system comprising same device | |
| WO2023182019A1 (en) | Information processing device, information processing method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |