CN118035710A - Extraction method of power generation characteristics of typical scene - Google Patents
Extraction method of power generation characteristics of typical scene Download PDFInfo
- Publication number
- CN118035710A CN118035710A CN202410198773.9A CN202410198773A CN118035710A CN 118035710 A CN118035710 A CN 118035710A CN 202410198773 A CN202410198773 A CN 202410198773A CN 118035710 A CN118035710 A CN 118035710A
- Authority
- CN
- China
- Prior art keywords
- data
- power generation
- model
- characteristic
- standardized
- 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.)
- Pending
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 152
- 238000000605 extraction Methods 0.000 title claims description 14
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims abstract description 10
- 238000012937 correction Methods 0.000 claims abstract description 10
- 238000007619 statistical method Methods 0.000 claims abstract description 9
- 238000012217 deletion Methods 0.000 claims abstract description 7
- 230000037430 deletion Effects 0.000 claims abstract description 7
- 238000004140 cleaning Methods 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 claims description 18
- 230000005611 electricity Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012300 Sequence Analysis Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000011157 data evaluation Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000013075 data extraction Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 3
- 239000000446 fuel Substances 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000003062 neural network model Methods 0.000 abstract description 5
- 238000007405 data analysis Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method for extracting power generation characteristics of a typical scene, relates to the technical field of power generation characteristics of the typical scene, and aims to solve the problem of inaccurate power generation characteristic data acquisition. According to the invention, the target characteristic data can be quantitatively described and analyzed through a statistical analysis method, the calculation efficiency of the power generation characteristic index data can be greatly improved through training the power generation characteristic index data through a neural network model, training and learning can be rapidly carried out on a large-scale data set, the collected related power generation data is subjected to missing value filling, abnormal value correction and repeated value deletion, the data can be more standard and tidy, the readability of the data is improved, the data differential bias is standardized through utilizing a preset data steady-state factor, the processing process is more stable, the stability and reliability are improved, and the collected data is more stable and accurate.
Description
Technical Field
The invention relates to the technical field of typical scene power generation characteristics, in particular to a method for extracting typical scene power generation characteristics.
Background
Typical scenario power generation characteristics refer to the operational characteristics and performance of a power plant or system under a particular power generation scenario.
The Chinese patent with publication number CN112308412B discloses a typical scene generation method of wave power generation based on evaluation indexes, which mainly comprises the steps of selecting a cluster number, comprehensively analyzing a feature vector by utilizing a cluster effectiveness index to obtain an optimal cluster number, and clustering a feature vector data set to obtain a typical scene set of wave power generation power. The above patent solves the problem of extracting scene features, but in actual operation, the following problems are also existed:
1. The data is not subjected to further model analysis, so that the power generation characteristic data in the power data cannot be accurately acquired.
2. The data is not effectively preprocessed, so that the stability of data acquisition is poor.
Disclosure of Invention
The invention aims to provide a method for extracting power generation characteristics of a typical scene, which is characterized in that the calculation efficiency of the power generation characteristic index data can be greatly improved by training the power generation characteristic index data through a neural network model, the training and the learning can be rapidly carried out on a large-scale data set, the collected related power generation data is subjected to missing value filling, abnormal value correction and repeated value deletion, the data can be more standard and tidy, the readability of the data is improved, and the problems in the prior art can be solved.
In order to achieve the above purpose, the present invention provides the following technical solutions:
The extraction method of the power generation characteristics of the typical scene comprises the following steps:
s1: collecting related power generation data, and carrying out data preprocessing on the collected related power generation data, wherein the data preprocessing comprises data cleaning and data standardization, and the data after the data preprocessing is marked as target characteristic data;
s2: extracting the power generation characteristic index data from the target characteristic data, performing model training on the extracted power generation characteristic index data, and marking a model after model training as a standard power generation characteristic model;
S3: and carrying out model evaluation on the standard power generation characteristic model, optimizing and adjusting the standard power generation characteristic model according to an evaluation result, carrying out visual conversion on the adjusted standard power generation characteristic model, and displaying the standard power generation characteristic model to a display terminal.
Preferably, for the relevant power generation data collected in S1, the method includes:
the collected data are meteorological data, power production data and power characteristic data;
the meteorological data are meteorological information of temperature, humidity, air pressure, wind speed and solar radiation;
The power production data are data of generating capacity, generating efficiency, fuel consumption and emission;
the power characteristic data are the data of electricity consumption, electricity price and electricity consumption time.
Preferably, the data cleansing for the relevant power generation data in S1 includes:
filling missing values of the collected related power generation data respectively;
carrying out abnormal value correction after filling of the missing values is completed;
repeating value deletion after the abnormal value correction is completed;
and deleting the repeated value to obtain target cleaning data.
Preferably, the data normalization processing for the relevant power generation data in S1 includes:
the target cleaning data are respectively corresponding to standardized data tables, wherein the standardized data tables are called from a database;
Splitting the standardized data table corresponding to each target cleaning data into a multi-dimensional data table;
Extracting preset data rules in the multi-dimensional data table, wherein the preset data rules are extracted from a database;
Carrying out data extraction on target cleaning data according to preset data, and obtaining data to be processed after the data extraction;
creating an original marking task, and generating a real-time marking task by taking a standard data format as a marking sequence;
labeling qualified data and unqualified data of the data to be processed according to the real-time labeling task;
And confirming the marked unqualified data as data to be standardized, and acquiring a data standardization dictionary corresponding to the data to be standardized.
Preferably, the data normalization processing for the relevant power generation data in S1 further includes:
generating a template configuration instruction by the data standardization dictionary, and responding to the template configuration instruction;
calling a preset data standardization model corresponding to the data to be standardized to acquire data information of the data to be standardized;
Importing data information into a preset data standardization model to obtain a first set of instantaneous data factors and a second set of instantaneous data factors of data to be standardized;
generating a differential data set of data to be standardized according to the first set of instantaneous data factors and the second set of instantaneous data factors;
Acquiring a data differential bias value according to a differential data set of data to be standardized;
And carrying out standardization processing on the data differential bias values by using preset data steady-state factors, respectively obtaining standardized data of the target cleaning data according to processing results, and marking the standardized data as target characteristic data.
Preferably, for the extraction of the power generation characteristic index data in S2, the method includes:
extracting power generation characteristic index data from the target characteristic data by a time sequence analysis method and a statistical analysis method;
the time sequence analysis method is to confirm the target characteristic data according to seasonality, periodicity and time period;
Removing irrelevant characteristic and redundant characteristic data from the confirmed characteristic data;
and obtaining the target time sequence characteristic data after excluding the irrelevant characteristic and the redundant characteristic data.
Preferably, for the extraction of the power generation characteristic index data in S2, the method further includes:
The statistical analysis method is to confirm the statistical value data of each data in the target characteristic data;
the statistical value data comprises a data mean value, a variance, a maximum value, a minimum value, a median, a bias value and a peak value;
Excluding irrelevant feature and redundant feature data in the statistic data;
One or more of the statistics is selected as the target statistics after the extraneous feature and the redundant feature are exhausted.
Preferably, the model training for the power generation characteristic index data in S2 includes:
The target statistical characteristic data and the target time sequence characteristic data are collectively called as power generation characteristic index data;
Acquiring a preset neural network training model, and importing the power generation characteristic index data into model nodes of the preset neural network training model;
Presetting a neural network training model to carry out operation training on each power generation characteristic index data in model nodes;
and marking the power generation characteristic index data after the operation training as a standard power generation characteristic model.
Preferably, the model training for the power generation characteristic index data in S2 further includes:
the operation training flow of each power generation characteristic index data in the model node is as follows:
Normally transmitting the parameter data of each power generation characteristic index data, wherein the forward transmission is to transmit the parameter data from a low level to a high level;
and when the forward propagation data result does not accord with the standard propagation result, performing direction propagation, wherein the direction propagation is to perform propagation training from a high level to a bottom layer, and the error data is phase difference data when the forward propagation data result does not accord with the standard propagation result.
Preferably, the optimizing and adjusting of the evaluation data in the standard power generation characteristic model in S3 includes:
Confirming the node position of each model in the standard power generation characteristic model;
acquiring node segment data between model nodes;
respectively carrying out data evaluation on each node segment;
comparing the evaluation result with a preset evaluation result in parameters;
generating optimized parameters according to the function values of the parameter comparison results;
Generating an optimized power generation characteristic model according to the optimization parameters;
And respectively performing visual conversion on the optimized power generation characteristic model and the standard power generation characteristic model.
Compared with the prior art, the invention has the following beneficial effects:
1. According to the extraction method of the typical scene power generation characteristics, the collected related power generation data is subjected to missing value filling, abnormal value correction and repeated value deletion, so that the data can be more standard and tidy, the data readability is improved, the data analysis is easier to understand, the processing process is more stable by utilizing the preset data steady-state factor to carry out standardized processing on the data differential offset, the stability and reliability are improved, and the collected data is more stable and accurate.
2. According to the extraction method of the typical scene power generation characteristics, the target characteristic data are analyzed through the time sequence analysis method, so that the internal relation and rule between the data can be better revealed, the target characteristic data can be quantitatively described and analyzed through the statistical analysis method, the power generation characteristic index data can be trained through the neural network model, the calculation efficiency of the power generation characteristic index data can be greatly improved, and the training and learning can be rapidly performed on a large-scale data set.
3. According to the extraction method of the power generation characteristics of the typical scene, data evaluation is carried out on each node section in the model data, the accuracy and the robustness of the data can be predicted more rapidly, the data evaluation comprises indexes such as accuracy, recall rate and F1 value, so that the performance and the effect of the model are determined, the standard power generation characteristic model is subjected to comparison parameter optimization according to the evaluation result, and the performance of the power generation characteristics can be improved.
Drawings
FIG. 1 is a schematic diagram of the overall process of the present invention;
fig. 2 is a schematic flow chart of the extraction method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the problem that in the prior art, after related power data is collected, the data is not effectively preprocessed, so that the stability of the data collection is poor, please refer to fig. 1 and 2, the present embodiment provides the following technical scheme:
The extraction method of the power generation characteristics of the typical scene comprises the following steps:
s1: collecting related power generation data, and carrying out data preprocessing on the collected related power generation data, wherein the data preprocessing comprises data cleaning and data standardization, and the data after the data preprocessing is marked as target characteristic data;
The method comprises the steps of acquiring a preset data standardization model corresponding to data to be standardized, carrying out targeted and rapid standardization treatment on the data to be standardized, improving treatment efficiency and precision, carrying out data preprocessing on collected related power generation data, enabling the data to be more standard and tidy, and improving the readability of the data;
s2: extracting the power generation characteristic index data from the target characteristic data, performing model training on the extracted power generation characteristic index data, and marking a model after model training as a standard power generation characteristic model;
The power generation characteristic index data is trained through the neural network model, so that the calculation efficiency of the power generation characteristic index data can be greatly improved, and training and learning can be rapidly performed on a large-scale data set, so that the accuracy and convenience of the power generation characteristic index data training are ensured;
S3: carrying out model evaluation on the standard power generation characteristic model, optimizing and adjusting the standard power generation characteristic model according to an evaluation result, carrying out visual conversion on the adjusted standard power generation characteristic model, and presenting the standard power generation characteristic model to a display terminal;
According to the data evaluation of each node section in the model data, the accuracy and the robustness of the data can be predicted more quickly, and the optimized power generation characteristic model and the standard power generation characteristic model are respectively presented with the parameter data which can enable a worker to know each power generation characteristic more quickly when checking the power generation characteristic.
For the relevant power generation data collected in S1, including:
the collected data are meteorological data, power production data and power characteristic data;
the meteorological data are meteorological information of temperature, humidity, air pressure, wind speed and solar radiation;
The power production data are data of generating capacity, generating efficiency, fuel consumption and emission;
the power characteristic data are the data of electricity consumption, electricity price and electricity consumption time.
Data cleansing for relevant power generation data in S1, comprising:
filling missing values of the collected related power generation data respectively;
carrying out abnormal value correction after filling of the missing values is completed;
repeating value deletion after the abnormal value correction is completed;
and deleting the repeated value to obtain target cleaning data.
The data normalization processing for the relevant power generation data in S1 includes:
the target cleaning data are respectively corresponding to standardized data tables, wherein the standardized data tables are called from a database;
Splitting the standardized data table corresponding to each target cleaning data into a multi-dimensional data table;
Extracting preset data rules in the multi-dimensional data table, wherein the preset data rules are extracted from a database;
Carrying out data extraction on target cleaning data according to preset data, and obtaining data to be processed after the data extraction;
creating an original marking task, and generating a real-time marking task by taking a standard data format as a marking sequence;
labeling qualified data and unqualified data of the data to be processed according to the real-time labeling task;
And confirming the marked unqualified data as data to be standardized, and acquiring a data standardization dictionary corresponding to the data to be standardized.
Generating a template configuration instruction by the data standardization dictionary, and responding to the template configuration instruction;
calling a preset data standardization model corresponding to the data to be standardized to acquire data information of the data to be standardized;
Importing data information into a preset data standardization model to obtain a first set of instantaneous data factors and a second set of instantaneous data factors of data to be standardized;
generating a differential data set of data to be standardized according to the first set of instantaneous data factors and the second set of instantaneous data factors;
Acquiring a data differential bias value according to a differential data set of data to be standardized;
And carrying out standardization processing on the data differential bias values by using preset data steady-state factors, respectively obtaining standardized data of the target cleaning data according to processing results, and marking the standardized data as target characteristic data.
Specifically, the acquisition of meteorological data has significance for evaluating the performance of a power generation system and optimizing a power generation strategy, the acquisition of electric power production data can reflect the running state and the production capacity of the power generation system, the acquisition of electric power characteristic data can reflect the market demand and the electricity utilization characteristic, references are provided for optimizing the power generation strategy, the acquired related power generation data is subjected to missing value filling, abnormal value correction and repeated value deletion, the data can be more standard and tidy, the readability of the data is improved, the data analysis is easier to understand, the error and uncertainty of the data analysis can be reduced, the accuracy and the reliability of the data analysis are improved, the standardized data can be subjected to targeted and rapid standardized processing by means of acquiring a preset data standardized model corresponding to the data to be standardized, the processing efficiency and the processing precision are improved, the processing process can be more stable and reliable by utilizing the preset data steady-state factor to perform the standardized processing on the data differential offset, and the acquired data is more stable and accurate.
In order to solve the problem that in the prior art, after collecting the power data, the data is not subjected to further model analysis, so that accurate acquisition of the power generation characteristic data in the power data cannot be achieved, please refer to fig. 1 and 2, the embodiment provides the following technical scheme:
Aiming at the extraction of the power generation characteristic index data in the step S2, the method comprises the following steps:
extracting power generation characteristic index data from the target characteristic data by a time sequence analysis method and a statistical analysis method;
the time sequence analysis method is to confirm the target characteristic data according to seasonality, periodicity and time period;
Removing irrelevant characteristic and redundant characteristic data from the confirmed characteristic data;
and obtaining the target time sequence characteristic data after excluding the irrelevant characteristic and the redundant characteristic data.
The statistical analysis method is to confirm the statistical value data of each data in the target characteristic data;
the statistical value data comprises a data mean value, a variance, a maximum value, a minimum value, a median, a bias value and a peak value;
Excluding irrelevant feature and redundant feature data in the statistic data;
One or more of the statistics is selected as the target statistics after the extraneous feature and the redundant feature are exhausted.
Specifically, the target characteristic data is analyzed by a time sequence analysis method, the influence of time factors on the electric power data is considered, the internal relation and rule between the data can be better revealed, the time sequence analysis method can dynamically reflect the change trend and rule of the data, the future development trend can be predicted, more accurate and timely information is provided for decision making, the target characteristic data can be quantitatively described and analyzed by a statistical analysis method, and therefore the phenomenon can be more accurately explained and predicted.
Model training for the power generation characteristic index data in S2, comprising:
The target statistical characteristic data and the target time sequence characteristic data are collectively called as power generation characteristic index data;
Acquiring a preset neural network training model, and importing the power generation characteristic index data into model nodes of the preset neural network training model;
Presetting a neural network training model to carry out operation training on each power generation characteristic index data in model nodes;
and marking the power generation characteristic index data after the operation training as a standard power generation characteristic model.
The operation training flow of each power generation characteristic index data in the model node is as follows:
Normally transmitting the parameter data of each power generation characteristic index data, wherein the forward transmission is to transmit the parameter data from a low level to a high level;
and when the forward propagation data result does not accord with the standard propagation result, performing direction propagation, wherein the direction propagation is to perform propagation training from a high level to a bottom layer, and the error data is phase difference data when the forward propagation data result does not accord with the standard propagation result.
Specifically, when parameter data is trained through forward propagation, the data which is finally lost can be obtained through each hidden layer when the parameter data passes through the hidden layers, when the parameter data is propagated in the reverse direction, the parameter data is fed back forward layer by layer according to a gradient decreasing formula, a reverse propagation mechanism is formed, parameters can be optimized, the calculation efficiency of the power generation characteristic index data can be greatly improved by training the power generation characteristic index data through a neural network model, and training and learning can be rapidly performed on a large-scale data set, so that the accuracy and convenience of the power generation characteristic index data training are ensured.
Optimizing and adjusting the evaluation data in the standard power generation characteristic model in the S3 comprises the following steps:
Confirming the node position of each model in the standard power generation characteristic model;
acquiring node segment data between model nodes;
respectively carrying out data evaluation on each node segment;
comparing the evaluation result with a preset evaluation result in parameters;
generating optimized parameters according to the function values of the parameter comparison results;
Generating an optimized power generation characteristic model according to the optimization parameters;
And respectively performing visual conversion on the optimized power generation characteristic model and the standard power generation characteristic model.
Specifically, according to the data evaluation of each node section in the model data, the accuracy and the robustness of the data can be predicted more quickly, the data evaluation comprises indexes such as accuracy, recall rate and F1 value, so as to determine the performance and the effect of the model, the standard power generation characteristic model is subjected to comparison parameter optimization according to the evaluation result, the performance of the power generation characteristic can be improved, and meanwhile, the optimized power generation characteristic model and the standard power generation characteristic model are respectively presented, so that a worker can know the parameter data of each power generation characteristic more quickly when looking up the power generation characteristic.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The extraction method of the power generation characteristics of the typical scene is characterized by comprising the following steps:
s1: collecting related power generation data, and carrying out data preprocessing on the collected related power generation data, wherein the data preprocessing comprises data cleaning and data standardization, and the data after the data preprocessing is marked as target characteristic data;
s2: extracting the power generation characteristic index data from the target characteristic data, performing model training on the extracted power generation characteristic index data, and marking a model after model training as a standard power generation characteristic model;
S3: and carrying out model evaluation on the standard power generation characteristic model, optimizing and adjusting the standard power generation characteristic model according to an evaluation result, carrying out visual conversion on the adjusted standard power generation characteristic model, and displaying the standard power generation characteristic model to a display terminal.
2. The method for extracting power generation characteristics of a typical scene according to claim 1, wherein: for the relevant power generation data collected in S1, including:
the collected data are meteorological data, power production data and power characteristic data;
the meteorological data are meteorological information of temperature, humidity, air pressure, wind speed and solar radiation;
The power production data are data of generating capacity, generating efficiency, fuel consumption and emission;
the power characteristic data are the data of electricity consumption, electricity price and electricity consumption time.
3. The method for extracting power generation characteristics of a typical scene according to claim 2, wherein: data cleansing for relevant power generation data in S1, comprising:
filling missing values of the collected related power generation data respectively;
carrying out abnormal value correction after filling of the missing values is completed;
repeating value deletion after the abnormal value correction is completed;
and deleting the repeated value to obtain target cleaning data.
4. A method for extracting a power generation feature of a typical scene according to claim 3, wherein: the data normalization processing for the relevant power generation data in S1 includes:
the target cleaning data are respectively corresponding to standardized data tables, wherein the standardized data tables are called from a database;
Splitting the standardized data table corresponding to each target cleaning data into a multi-dimensional data table;
Extracting preset data rules in the multi-dimensional data table, wherein the preset data rules are extracted from a database;
Carrying out data extraction on target cleaning data according to preset data, and obtaining data to be processed after the data extraction;
creating an original marking task, and generating a real-time marking task by taking a standard data format as a marking sequence;
labeling qualified data and unqualified data of the data to be processed according to the real-time labeling task;
And confirming the marked unqualified data as data to be standardized, and acquiring a data standardization dictionary corresponding to the data to be standardized.
5. The method for extracting the power generation characteristics of the typical scene as claimed in claim 4, wherein: the data normalization processing for the relevant power generation data in S1 further includes:
generating a template configuration instruction by the data standardization dictionary, and responding to the template configuration instruction;
calling a preset data standardization model corresponding to the data to be standardized to acquire data information of the data to be standardized;
Importing data information into a preset data standardization model to obtain a first set of instantaneous data factors and a second set of instantaneous data factors of data to be standardized;
generating a differential data set of data to be standardized according to the first set of instantaneous data factors and the second set of instantaneous data factors;
Acquiring a data differential bias value according to a differential data set of data to be standardized;
And carrying out standardization processing on the data differential bias values by using preset data steady-state factors, respectively obtaining standardized data of the target cleaning data according to processing results, and marking the standardized data as target characteristic data.
6. The method for extracting the power generation characteristics of the typical scene as claimed in claim 5, wherein the method comprises the following steps: aiming at the extraction of the power generation characteristic index data in the step S2, the method comprises the following steps:
extracting power generation characteristic index data from the target characteristic data by a time sequence analysis method and a statistical analysis method;
the time sequence analysis method is to confirm the target characteristic data according to seasonality, periodicity and time period;
Removing irrelevant characteristic and redundant characteristic data from the confirmed characteristic data;
and obtaining the target time sequence characteristic data after excluding the irrelevant characteristic and the redundant characteristic data.
7. The method for extracting the power generation characteristics of the typical scene as set forth in claim 6, wherein: aiming at the extraction of the power generation characteristic index data in the S2, the method further comprises the following steps:
The statistical analysis method is to confirm the statistical value data of each data in the target characteristic data;
the statistical value data comprises a data mean value, a variance, a maximum value, a minimum value, a median, a bias value and a peak value;
Excluding irrelevant feature and redundant feature data in the statistic data;
One or more of the statistics is selected as the target statistics after the extraneous feature and the redundant feature are exhausted.
8. The method for extracting power generation characteristics of a typical scene according to claim 7, wherein: model training for the power generation characteristic index data in S2, comprising:
The target statistical characteristic data and the target time sequence characteristic data are collectively called as power generation characteristic index data;
Acquiring a preset neural network training model, and importing the power generation characteristic index data into model nodes of the preset neural network training model;
Presetting a neural network training model to carry out operation training on each power generation characteristic index data in model nodes;
and marking the power generation characteristic index data after the operation training as a standard power generation characteristic model.
9. The method for extracting power generation characteristics of a typical scene according to claim 8, wherein: model training for the power generation characteristic index data in S2, further comprising:
the operation training flow of each power generation characteristic index data in the model node is as follows:
Normally transmitting the parameter data of each power generation characteristic index data, wherein the forward transmission is to transmit the parameter data from a low level to a high level;
and when the forward propagation data result does not accord with the standard propagation result, performing direction propagation, wherein the direction propagation is to perform propagation training from a high level to a bottom layer, and the error data is phase difference data when the forward propagation data result does not accord with the standard propagation result.
10. The method for extracting power generation characteristics of a typical scene according to claim 9, wherein: optimizing and adjusting the evaluation data in the standard power generation characteristic model in the S3 comprises the following steps:
Confirming the node position of each model in the standard power generation characteristic model;
acquiring node segment data between model nodes;
respectively carrying out data evaluation on each node segment;
comparing the evaluation result with a preset evaluation result in parameters;
generating optimized parameters according to the function values of the parameter comparison results;
Generating an optimized power generation characteristic model according to the optimization parameters;
And respectively performing visual conversion on the optimized power generation characteristic model and the standard power generation characteristic model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410198773.9A CN118035710A (en) | 2024-02-22 | 2024-02-22 | Extraction method of power generation characteristics of typical scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410198773.9A CN118035710A (en) | 2024-02-22 | 2024-02-22 | Extraction method of power generation characteristics of typical scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118035710A true CN118035710A (en) | 2024-05-14 |
Family
ID=90998009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410198773.9A Pending CN118035710A (en) | 2024-02-22 | 2024-02-22 | Extraction method of power generation characteristics of typical scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118035710A (en) |
-
2024
- 2024-02-22 CN CN202410198773.9A patent/CN118035710A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288136B (en) | Wind power multi-step prediction model establishment method | |
| CN111784093B (en) | Enterprise reworking auxiliary judging method based on power big data analysis | |
| CN109918364B (en) | Data cleaning method based on two-dimensional probability density estimation and quartile method | |
| CN103631681A (en) | Method for online restoring abnormal data of wind power plant | |
| CN111931834B (en) | Method, equipment and storage medium for detecting abnormal flow data in extrusion process of aluminum profile based on isolated forest algorithm | |
| CN112418687B (en) | User electricity utilization abnormity identification method and device based on electricity utilization characteristics and storage medium | |
| CN113496440B (en) | User abnormal electricity consumption detection method and system | |
| CN111639850A (en) | Quality evaluation method and system for multi-source heterogeneous data | |
| CN108683658B (en) | Industrial control network flow abnormity identification method based on multi-RBM network construction reference model | |
| CN114819374A (en) | Regional new energy ultra-short term power prediction method and system | |
| CN116821832A (en) | Abnormal data identification and correction method for high-voltage industrial and commercial user power load | |
| CN116911806A (en) | Internet + based power enterprise energy information management system | |
| CN117849700B (en) | Modular electric energy metering system capable of controlling measurement | |
| CN114595762A (en) | Photovoltaic power station abnormal data sequence extraction method | |
| CN117559443A (en) | Ordered power utilization control method for large industrial user cluster under peak load | |
| CN116796403A (en) | Building energy saving method based on comprehensive energy consumption prediction of commercial building | |
| CN116388184B (en) | Ultra-short-term wind speed revising method and system based on wind speed daily fluctuation characteristics | |
| CN112132344A (en) | Short-term wind power prediction method based on similar day and FRS-SVM | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN118035710A (en) | Extraction method of power generation characteristics of typical scene | |
| CN111475548A (en) | Power utilization abnormity analysis decision system based on big data mining technology | |
| CN108763289B (en) | Massive heterogeneous sensor format data analysis method | |
| CN114676931B (en) | Electric quantity prediction system based on data center technology | |
| CN115392663A (en) | Data acquisition and processing method based on big data | |
| CN117708720B (en) | Equipment fault diagnosis system based on knowledge graph |
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 |