CN118263872A - Customized voltage sag management optimization method and system - Google Patents
Customized voltage sag management optimization method and system Download PDFInfo
- Publication number
- CN118263872A CN118263872A CN202410452152.9A CN202410452152A CN118263872A CN 118263872 A CN118263872 A CN 118263872A CN 202410452152 A CN202410452152 A CN 202410452152A CN 118263872 A CN118263872 A CN 118263872A
- Authority
- CN
- China
- Prior art keywords
- voltage sag
- voltage
- sag
- coefficient
- decision
- 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
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000005457 optimization Methods 0.000 title claims abstract description 25
- 238000011282 treatment Methods 0.000 claims abstract description 109
- 238000012544 monitoring process Methods 0.000 claims abstract description 89
- 238000009826 distribution Methods 0.000 claims abstract description 72
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 230000008447 perception Effects 0.000 claims abstract description 25
- 230000003213 activating effect Effects 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 claims description 71
- 238000011156 evaluation Methods 0.000 claims description 52
- 230000002159 abnormal effect Effects 0.000 claims description 46
- 238000005067 remediation Methods 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 25
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000013210 evaluation model Methods 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000012732 spatial analysis Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 76
- 230000008569 process Effects 0.000 description 25
- 238000004088 simulation Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003631 expected effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application relates to the technical field of power engineering, and provides a customized voltage sag management optimization method and system. The method comprises the following steps: by collecting basic information of the power system, loading voltage sag records, performing spatial feature analysis, establishing a voltage monitoring sensing array, and monitoring voltage distribution of the system. And constructing a voltage sag sensing model by using big data, and realizing voltage sag identification to obtain a sensing coefficient. Based on the perception coefficient, activating a treatment optimizing module to optimize the voltage sag treatment parameters, and obtaining a treatment decision. Transmitting the decision to a management module, and executing voltage sag management of the power system in real time. According to the application, by constructing the voltage sag sensing model, the real-time monitoring and analysis of the voltage distribution data source are realized, the technical problem of overhigh occurrence frequency of voltage sag caused by insufficient monitoring and identification of the voltage sag is solved, and the reliability and stability of the power system are ensured.
Description
Technical Field
The application relates to the technical field of power engineering, in particular to the technical field of power system monitoring and control, and particularly relates to a customized voltage sag management and optimization method and system.
Background
With the rapid development of the fields of power industry, manufacturing industry, information technology and the like, the stability and reliability of a power system are more and more important to the production operation of various industries. However, voltage sag events, one of the major problems affecting power quality, often lead to equipment failure, production interruption, and possibly even significant economic loss. The traditional voltage sag management method faces the challenges of low control precision and slow response speed in practical application, and is difficult to quickly and effectively cope with the problem that the voltage sag problem frequently occurs in a power system. This results in a threat to the reliability of the power system, and therefore effective monitoring and abatement means are needed.
Under the background, the customized voltage sag management optimization method and system are developed, and the method and system aim to realize real-time monitoring and analysis of a voltage distribution data source by building a voltage sag sensing model, and solve the technical problem that the occurrence frequency of the voltage sag is too high due to insufficient monitoring and identification of the voltage sag, so that a reliable and stable operation power system cannot be met.
Disclosure of Invention
The application provides a customized voltage sag management optimization method and system, and aims to realize real-time monitoring and analysis of a voltage distribution data source by building a voltage sag sensing model, so that the technical problem that the occurrence frequency of voltage sag is too high due to insufficient monitoring and identification of the voltage sag, and therefore a reliable and stable operation power system cannot be met is solved.
In view of the above problems, the present application provides a method and a system for optimizing customized voltage sag management.
In a first aspect of the disclosure, a method for optimizing customized voltage sag remediation is provided, the method comprising: basic information of a power system is collected, and a system distribution data set is obtained; loading a voltage sag record of the power system, and performing spatial feature analysis based on the voltage sag record to obtain voltage sag spatial feature distribution; carrying out voltage monitoring sensor arrangement on the power system based on the system distribution data set and the voltage sag spatial characteristic distribution, and constructing a voltage monitoring sensor array; monitoring and acquiring a voltage distribution data source of the power system based on the voltage monitoring and sensing array; constructing a voltage sag perception model based on big data; performing voltage sag identification on the voltage distribution data source based on the voltage sag sensing model to obtain a voltage sag sensing coefficient; activating a voltage sag control optimizing module to perform voltage sag control parameter optimization based on the voltage sag sensing coefficient to obtain a voltage sag control decision; transmitting the voltage sag management decision to a voltage sag management module, wherein the voltage sag management module executes voltage sag management of the power system according to the voltage sag management decision.
In another aspect of the present disclosure, a customized voltage sag remediation optimization system is provided, the system comprising: the information acquisition unit is used for acquiring basic information of the power system and acquiring a system distribution data set; the space analysis unit is used for loading voltage sag records of the power system, and carrying out space feature analysis based on the voltage sag records to obtain voltage sag space feature distribution; the sensing array construction unit is used for carrying out layout of voltage monitoring sensors on the power system based on the system distribution data set and the voltage sag spatial characteristic distribution to construct a voltage monitoring sensing array; the data source monitoring unit is used for monitoring and acquiring a voltage distribution data source of the power system based on the voltage monitoring sensing array; the sensing module building unit is used for building a voltage sag sensing model based on big data; the voltage sag identification unit is used for carrying out voltage sag identification on the voltage distribution data source based on the voltage sag sensing model to obtain a voltage sag sensing coefficient; the parameter optimizing unit is used for activating a voltage sag treatment optimizing module to perform voltage sag treatment parameter optimizing based on the voltage sag sensing coefficient so as to obtain a voltage sag treatment decision; the voltage sag management unit is used for transmitting the voltage sag management decision to a voltage sag management module, and the voltage sag management module executes voltage sag management of the power system according to the voltage sag management decision.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The method for optimizing the customized voltage sag management gathers and integrates core information of a power system to form an accurate system distribution data set. Through analysis of these data, the overall architecture and operating state of the system is well understood. And then, loading historical voltage sag records, precisely analyzing the spatial distribution mode of the voltage sag in the system by using a spatial feature analysis technology, and identifying the high-incidence area and the sensitive period of the voltage sag. Based on the system distribution data set and the voltage sag spatial feature distribution, the optimized layout of the voltage monitoring sensors is carried out, so that an efficient and accurate voltage monitoring sensing array is constructed, and a stable and reliable data source is provided for subsequent voltage sag identification. And (3) accurately identifying the voltage sag event by utilizing the built voltage sag sensing model and combining the real-time data acquired by the voltage monitoring sensing array, and obtaining a corresponding voltage sag sensing coefficient. Activating a voltage sag management optimizing module, optimizing management parameters through an intelligent algorithm, generating an optimal voltage sag management decision, and aiming at minimizing the influence of voltage sag on a power system and ensuring the stable and efficient operation of the system. And finally, transmitting the generated voltage sag governance decision to a governance module, wherein the module is responsible for executing specific governance measures. The flow ensures the consistency and the high efficiency from data collection to decision execution, and provides powerful guarantee for the stable operation of the power system.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a customized voltage sag remediation optimization method according to one embodiment;
FIG. 2 is a diagram of a customized voltage sag remediation optimization system architecture, according to one embodiment.
Reference numerals illustrate: the system comprises an information acquisition unit 1, a space analysis unit 2, a sensing array construction unit 3, a data source monitoring unit 4, a sensing module construction unit 5, a voltage sag identification unit 6, a parameter optimizing unit 7 and a voltage sag treatment unit 8.
Detailed Description
The embodiment of the application solves the technical problem that the occurrence frequency of voltage sag is too high due to insufficient monitoring and identification of the voltage sag, so that a reliable and stable operation power system cannot be met by providing the customized voltage sag management optimization method and system.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server 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, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a customized voltage sag management optimization method, which includes:
Basic information of a power system is collected, and a system distribution data set is obtained;
Voltage sag refers to a phenomenon in which voltage suddenly drops and recovers in a short time in a power system. It may be caused by a variety of factors such as short circuits, heavy loads, equipment start-up, new energy access, etc. Although the duration of the voltage dip is typically short, its impact on sensitive electrical equipment is enormous, potentially leading to serious consequences such as equipment damage, data loss, production interruption, etc.
In the embodiment of the application, in order to understand the running state and the structural characteristics of the power system in depth, various basic information of the power system needs to be collected and integrated widely. The system distribution data set refers to a group of data sets obtained by collecting basic information of the power system, and comprises information such as states, parameters, relations and the like of various components, nodes and equipment in the power system, and distribution conditions of the components, the nodes and the equipment in the power system. The system terminals acquire a system distribution data set by sorting and collecting basic information in the power system, and the data set describes the operation state of the power system and the interrelation of the parts in detail. This data set provides a comprehensive view of the power system for the system terminals, helping them to better understand and master the overall system operating conditions.
Loading a voltage sag record of the power system, and performing spatial feature analysis based on the voltage sag record to obtain voltage sag spatial feature distribution;
In one embodiment, after collecting the underlying information of the power system, the system terminal further loads a history of voltage sags in the power system. These records detail the time, location, duration, etc. of the occurrence of the voltage dip. In order to gain an insight into the distribution of voltage sags in the power system, the system terminals have performed a spatial signature analysis of these recordings. Spatial signature analysis is a method by which the distribution pattern of data in space is studied. The system terminal firstly performs operations such as data cleaning, denoising and standardization on the obtained voltage sag record so as to ensure the accuracy and comparability of the data. Spatial features are then extracted from the preprocessed data. This includes identifying the specific geographic location where the voltage sag occurs, the grid node or region involved, and the distribution of these events over the geographic space. And then carrying out feature analysis on the extracted spatial features. This includes calculating statistical indicators of voltage sag frequencies, durations, magnitudes, etc. for different regions or periods. By contrast analysis, the high-emission area and the period of the voltage sag, and a possible spatial distribution mode are identified. And finally, sorting the analysis result into voltage sag spatial characteristic distribution. The system terminal uses the method to carry out careful analysis on the voltage sag records, and finds out the high-frequency area, the frequent time period and the possible reasons and rules of the voltage sag in the power system. The method provides an important reference for subsequent voltage sag monitoring, so that the system terminal can take measures more pertinently, and the stability and reliability of the power system are improved.
Carrying out voltage monitoring sensor arrangement on the power system based on the system distribution data set and the voltage sag spatial characteristic distribution, and constructing a voltage monitoring sensor array;
In one embodiment, after obtaining the fundamental information dataset of the power system and the spatial signature distribution of the voltage dip, the system terminal uses these data to guide the layout of the voltage monitoring sensors. First, the system distribution dataset is analyzed to understand the overall architecture of the grid, key nodes, and potential voltage sag risk areas. And then, combining the spatial characteristic distribution of the voltage sag, and determining which areas are high-incidence areas of the voltage sag and the distribution rule of the voltage sag on the geographic space. Based on the information, the system terminal establishes a sensor layout scheme, and preferentially deploys sensors in areas and nodes with higher voltage sag risks. By the aid of the method, voltage sag events can be timely and accurately captured, and reliable data support is provided for subsequent analysis and management. Finally, by reasonably arranging the voltage monitoring sensors, the system terminal successfully constructs a voltage monitoring sensing array covering the full power system. The array can monitor the voltage state of the power system in real time, and provides powerful guarantee for the stable operation of the power system.
Monitoring and acquiring a voltage distribution data source of the power system based on the voltage monitoring and sensing array;
In one embodiment, after the voltage monitoring sensor array is constructed, the system terminal uses the sensor array to monitor the voltage distribution condition of the power system in real time, and continuously collects the voltage data of each key node in the power grid. These sensors constantly record real-time values of the voltage, trends and other relevant parameters and transmit these data to the system terminals. The system terminals integrate, analyze and process the data to generate a data source which comprehensively reflects the voltage distribution of the power system, namely, a voltage distribution data source. The data source contains information such as voltage levels, voltage fluctuation conditions, potential voltage sag events and the like of various areas in the power grid. By monitoring and analyzing the data source in real time, the system terminal has comprehensive and accurate knowledge on the voltage state of the power system, and provides powerful data support for subsequent decision making and optimization. In summary, based on the real-time monitoring of the voltage monitoring sensing array, a real-time voltage distribution data source of the power system can be obtained, so that comprehensive sensing and analysis of the voltage state of the power grid are realized.
Constructing a voltage sag perception model based on big data;
In one embodiment, the system terminal builds a voltage sag sensing model using a huge database, and accurately identifies and predicts voltage sag events through the sensing model. This database contains all voltage data generated by the power system during operation, such as normal voltage monitoring data, abnormal voltage monitoring data, voltage sag assessment coefficients, etc. In the construction process, the system terminal firstly carries out pretreatment on data in the database, including steps of cleaning, denoising, standardization and the like, so as to ensure the accuracy and consistency of the data. And then, carrying out feature extraction and pattern recognition on the data, and judging the rule and the feature of the voltage sag, so as to predict a future sag event. And then, a voltage sag sensing model is built based on the neural network, and during the period, the system terminal can continuously train and optimize the model so as to improve the prediction accuracy and generalization capability of the model. Finally, a perception model capable of monitoring and predicting voltage sag in real time is obtained. The model provides timely and accurate voltage sag information for the system terminal, helps the system terminal to make reasonable decisions and schedule, and ensures stable operation of the power system.
Further, the application provides a method for constructing a voltage sag perception model based on big data, and the method further comprises the following steps:
Loading normal voltage monitoring data records, abnormal voltage monitoring data records and voltage sag evaluation coefficient records of the power system based on big data;
Preferably, based on big data, the system terminal needs to load various types of data of the power system into its own storage. These data mainly include normal voltage monitoring data records, abnormal voltage monitoring data records, and voltage sag evaluation coefficient records. Specifically, the system terminal first extracts data from a database storing the data. The loading process can perform data reading, format conversion and cleaning, and the consistency and usability of the data are ensured. The normal voltage monitoring data record is loaded to know the voltage performance of the power system in the normal running state, and the data comprise parameters such as the amplitude, the frequency, the phase and the like of the voltage, and corresponding time stamps and geographic position information. The abnormal voltage monitoring data record is loaded to identify and analyze the abnormal voltage conditions in the power system, and the data comprise time, place and specific parameters of the abnormal voltage conditions such as sudden voltage rise, sudden voltage drop, oscillation and the like. Furthermore, the loading voltage sag assessment coefficient record is used to quantify the severity and extent of impact of the voltage sag. Loading these evaluation coefficients helps the system terminals to more accurately understand the impact of voltage sags on the power system. In summary, the normal voltage monitoring data record, the abnormal voltage monitoring data record and the voltage sag evaluation coefficient record based on the big data loading power system are used for comprehensively knowing and analyzing the voltage performance of the power system, and providing basic data support for subsequent data analysis and model construction.
Based on a support vector machine, performing anomaly identification training on the normal voltage monitoring data record and the abnormal voltage monitoring data record to generate a voltage anomaly identification model;
performing supervised learning on the abnormal voltage monitoring data record and the voltage sag evaluation coefficient record based on BP, and generating a voltage sag prediction evaluation model;
Preferably, in the context of big data, the system terminal builds two models using a Support Vector Machine (SVM) and a Back Propagation (BP) neural network: one is a voltage anomaly identification model and the other is a voltage sag prediction evaluation model. First, the system terminal classifies the normal voltage monitoring data record and the abnormal voltage monitoring data record into feature data and tag data. The characteristic data includes voltage values, time stamps, geographical locations, etc. The tag data includes normal or abnormal, etc. And then, dividing the classified data into a training set and a testing set. The training set is used for training the voltage abnormality recognition model, and the testing set is used for evaluating the performance of the model. And training a voltage abnormality recognition model by using the training set and the corresponding label data. During training, the voltage anomaly identification model learns a decision boundary that maximizes separation of normal and abnormal voltage samples. After training is completed, the test set is used to evaluate the performance of the trained voltage anomaly identification model. If the model is not performing well, the system terminal may adjust parameters of the model or try different kernel functions to improve. For example, the value of gamma in the kernel is adjusted to increase from 0.1 to 1 or decrease to 0.01 to observe changes in model performance. And repeatedly evaluating to generate a stable and accurate voltage abnormality recognition model. The model can learn and understand the distinction between normal voltage and abnormal voltage, and based on the learned characteristics, can perform abnormal recognition on new voltage monitoring data to judge whether the new voltage monitoring data belongs to a normal voltage range. In addition, the system terminal designs the structure of the BP neural network and comprises an input layer, a hidden layer and an output layer. The number of hidden layers and the number of neurons are selected according to the complexity of the actual problem and the nature of the data. And initializing the weight and bias of the neural network by using a small random number so as to avoid the problem of gradient disappearance or explosion in the training process caused by overlarge initial weight. And then using the abnormal voltage monitoring data record and the corresponding voltage sag evaluation coefficient record as training data, and training the neural network through a back propagation algorithm. In the forward propagation process, input data is passed through a neural network to obtain a predicted value, and the predicted value is compared with a preset value. In the back propagation process, the gradient of each layer of neurons is calculated according to the comparison result, and the weight and bias are updated. The forward propagation and backward propagation processes are repeated until a specified number of training rounds is reached, and a voltage sag prediction evaluation model is generated. The model learns the relation between abnormal voltage and the voltage sag evaluation coefficient in a supervised learning mode, so that the possibility and the severity of the voltage sag can be predicted and evaluated. In summary, the system terminal trains a voltage abnormality recognition model based on a support vector machine, and is used for recognizing abnormal conditions in voltage data; meanwhile, a voltage sag prediction evaluation model is trained based on the BP neural network and is used for predicting and evaluating occurrence and influence of voltage sag. The two models together form a comprehensive monitoring and evaluating system of the system terminal to the voltage state of the power system, and powerful technical support is provided for the stable operation of the power system.
And integrating the voltage abnormality identification model and the voltage sag prediction evaluation model to generate the voltage sag sensing model.
Preferably, when integrating the models, the system terminal designs a data flow, so as to ensure that data can be smoothly transferred from one model to another model. For example, when the voltage anomaly identification model detects an abnormal voltage, it may pass relevant information to the voltage sag prediction evaluation model for further evaluation. After the information transfer construction between the two models is completed, a comprehensive voltage sag sensing model is formed. The aim of this model is to achieve a more comprehensive and accurate monitoring and identification of voltage sags in the power system. The voltage anomaly identification model is responsible for capturing any unusual voltage behavior in the system, while the voltage sag prediction assessment model is intended to predict and assess voltage sag events. By integrating the two models, the voltage sag sensing model can sense the state of the power system more comprehensively, identify voltage sag events in time and provide comprehensive predictive evaluation. This enables the system terminals to more effectively cope with potential voltage sag problems, thereby improving the reliability and stability of the power system.
Further, the application provides a method for performing supervised learning on the abnormal voltage monitoring data record and the voltage sag evaluation coefficient record based on a BP neural network to generate a voltage sag prediction evaluation model, and the method further comprises the following steps:
Taking the abnormal voltage monitoring data record as input data, taking the voltage sag evaluation coefficient record as output supervision data, training the BP neural network, and acquiring a prediction evaluation loss coefficient when training is performed for preset times;
And if the predicted estimated loss coefficient is smaller than the predicted estimated loss threshold value, generating the voltage sag predicted estimated model.
Optionally, the system terminal records the abnormal voltage monitoring data as input data, and simultaneously records the voltage sag evaluation coefficient as output supervision data, that is, a target value which can be predicted from the input data by the neural network. Then, training of the BP neural network is started. In the training process, the system terminal can continuously input abnormal voltage data into the network, and compare the difference between the predicted value output by the network and the actual voltage sag evaluation coefficient. This difference is the predictive estimated loss factor, which reflects the current predictive capabilities of the network. To ensure that the network is able to gradually optimize its predictive capabilities, the system terminal sets a predictive evaluation loss threshold. After each training preset number of times, it is checked whether the current predictive evaluation loss factor is smaller than this threshold. If the voltage sag estimation coefficient is smaller than the threshold value, the network can accurately predict the voltage sag estimation coefficient, at the moment, the system terminal stops training, and the current neural network is used as a voltage sag prediction estimation model. In summary, the process is to continuously adjust network parameters to enable the BP neural network to learn to predict the voltage sag estimation coefficients from the abnormal voltage data until the prediction capability reaches a satisfactory level, thereby generating a usable voltage sag prediction estimation model.
Further, the application provides a method for identifying the voltage sag of the voltage distribution data source based on the voltage sag sensing model to obtain a voltage sag sensing coefficient, and the method further comprises the following steps:
inputting the voltage distribution data source into the voltage abnormality recognition model to obtain a common sense of voltage;
inputting the voltage abnormality identification set into the voltage sag prediction evaluation model to obtain a voltage sag prediction evaluation coefficient set;
Optionally, the system terminal first inputs the acquired voltage distribution data source into a trained voltage anomaly identification model. After training, the model can identify which voltage data are abnormal and which are normal. After the system terminal inputs the voltage distribution data into the voltage abnormality recognition model, the model judges each voltage data point and recognizes the abnormal data therein. Thus, a common set of voltage signatures is obtained that contains all voltage data points identified as anomalies by the model. The common sense subset of voltage is then input to a trained predictive evaluation model of voltage sag via a constructed transfer channel. This model is capable of predicting and evaluating the likelihood of a voltage dip based on the input abnormal voltage data. When the common voltage knowledge differential set is input into the voltage sag prediction evaluation model, the model predicts and evaluates each abnormal data point to generate a voltage sag prediction evaluation coefficient set. This set of coefficients includes predicted evaluation coefficients for each abnormal data point that reflect the likelihood and extent of voltage sag occurrence at the abnormal data point. Through the process, the system terminal can not only identify abnormal points in the voltage distribution data, but also predict and evaluate the voltage sag of the abnormal points, so that a voltage sag prediction evaluation coefficient set is obtained. The method has important significance for fault early warning and safety management of the power system, and can help the system terminal to timely know and cope with potential voltage sag risks.
And screening the voltage sag prediction evaluation coefficient set based on the voltage sag prediction evaluation constraint to obtain the voltage sag perception coefficient meeting the voltage sag prediction evaluation constraint.
Optionally, the voltage sag prediction assessment constraint refers to a series of standards, rules or conditions, including sag depth constraint, duration constraint, frequency constraint, etc., that are followed when assessing a risk of a voltage sag. The voltage sag perception coefficient refers to a voltage sag risk index meeting specific voltage sag prediction and evaluation constraint conditions after screening and constraint processing. Based on the above process, the system terminal obtains a set of voltage sag prediction evaluation coefficients that includes a sag prediction evaluation result for each abnormal voltage data point. Not all of the evaluation results require close attention from the system terminal. According to the constraint conditions of voltage sag prediction and evaluation, the system terminal only pays attention to abnormal points of which the prediction and evaluation coefficients cannot meet the constraint of voltage sag prediction and evaluation. Therefore, the system terminal screens the obtained voltage sag prediction evaluation coefficient set. The screening process is to filter out abnormal points meeting specific requirements according to constraint conditions of voltage sag prediction and evaluation. After screening, the system terminal obtains a voltage sag sensing coefficient set meeting the voltage sag prediction evaluation constraint. Each coefficient in this set represents the risk of sag of the corresponding abnormal voltage data point under certain constraints. These perceptual coefficients can help the system terminal to know more accurately which outliers may have a large impact on the stable operation of the power system, thereby providing an important basis for decision making. Summarizing, the process is a process of screening and restraining the voltage sag prediction evaluation coefficient set, and aims to find out abnormal points meeting specific conditions and obtain corresponding voltage sag perception coefficients so as to better perform fault early warning and safety management of the power system.
Performing voltage sag identification on the voltage distribution data source based on the voltage sag sensing model to obtain a voltage sag sensing coefficient;
In one embodiment, the system terminal inputs the obtained voltage distribution data source into a voltage sag aware model. The model integrates the functions of a voltage abnormality identification model and a voltage sag prediction evaluation model, and can simultaneously identify voltage abnormality and perform sag prediction evaluation. When the voltage distribution data is input into the voltage sag sensing model, the model automatically analyzes and judges each voltage data point. It identifies which data points belong to voltage anomalies and further predicts and evaluates the risk of voltage sag that these abnormal data points may cause. And the system terminal obtains a voltage sag sensing coefficient through the identification and the evaluation of the model. This coefficient is a quantized value that comprehensively reflects the risk level of the voltage sag. The higher the perception coefficient, the greater the risk of representing a voltage dip; the lower the perceptual coefficient, the less risk is indicated. Finally, the system terminal obtains a voltage sag sensing coefficient set which contains voltage sag risk information of each node or each time period in the power grid. The coefficient set can help the system terminal to quickly know which areas or time periods in the power grid have higher voltage sag risks, so that corresponding measures are taken to prevent or reduce the influence of sag events on the operation of the power grid. Summarizing, voltage sag recognition is performed on the voltage distribution data source based on the voltage sag perception model, so that voltage sag perception coefficients of all nodes or all time periods in the power grid can be obtained, and important basis is provided for safe operation of the power grid.
Activating a voltage sag control optimizing module to perform voltage sag control parameter optimization based on the voltage sag sensing coefficient to obtain a voltage sag control decision;
In one embodiment, based on the obtained voltage sag sensing coefficient, a voltage sag remediation optimization module is started to seek optimal voltage sag remediation parameters, thereby obtaining an effective voltage sag remediation decision. The voltage sag control optimizing module is an algorithm module specially used for searching the optimal voltage sag control parameters. The voltage sag management parameter optimizing refers to searching parameter configuration capable of optimally solving the voltage sag problem through a series of algorithms and calculation processes. The system terminal starts a voltage sag control optimizing module based on the previously calculated voltage sag sensing coefficient. The module is an intelligent searcher which can find the parameters which can reduce the occurrence and influence of the voltage sag in the voltage sag management registration decision library. Through the process, a set of optimal treatment schemes aiming at the voltage sag problem, namely voltage sag treatment decisions, are obtained. This decision includes adjusting the way the grid is operated, optimizing the configuration of the equipment or improving the control strategy etc. aimed at improving the stability and reliability of the power system, thus ensuring a smooth progress of the power supply.
Further, the application provides a voltage sag control decision based on the voltage sag sensing coefficient, which activates a voltage sag control optimizing module to perform voltage sag control parameter optimizing, and the method further comprises the following steps:
Performing voltage sag treatment scheme registration based on the voltage sag sensing coefficient to obtain a voltage sag treatment registration decision library;
Extracting a first voltage sag governance registration decision according to the voltage sag governance registration decision library;
Preferably, based on the voltage sag sensing coefficient, activating a voltage sag control optimizing module to perform voltage sag control parameter optimizing, and obtaining a voltage sag control decision. The voltage sag management scheme registration refers to a process of matching and calibrating the management scheme with the actual power system condition according to the voltage sag sensing coefficient. The system terminal registers the voltage sag treatment scheme based on the voltage sag sensing coefficient, which represents that the system terminal selects the most suitable decision from a plurality of historical voltage sag treatment decision groups according to the severity, frequency and influence range of the voltage sag. This registration process ensures that the chosen decisions match the specific conditions of the power system, the equipment conditions and the characteristics of the voltage sag. After registration is completed, a voltage sag governance registration decision library is obtained, wherein governance decisions aiming at different voltage sag problems are included. The decision library provides a convenient data center for the system terminal, so that the system terminal can quickly find a treatment scheme suitable for the current problem. When the actual voltage sag problem needs to be handled, the system terminal can extract the first governance scheme from the decision library as a preferred measure. This represents the choice of the solution that is most likely to be effective in solving the problem, depending on the current grid situation. The decision provides a clear action guide for the system terminal, helps the system terminal to rapidly cope with the voltage sag problem, and ensures the stable operation of the power system.
Performing voltage sag treatment effect prediction on the power system based on the first voltage sag treatment registration decision to obtain a first predicted treatment effect coefficient;
Judging whether the first predicted treatment effect coefficient meets a preset treatment effect constraint;
and if the first predicted treatment effect coefficient meets the preset treatment effect constraint, outputting the first voltage sag treatment registration decision as the voltage sag treatment decision.
Preferably, the system terminal predicts the voltage sag treatment effect of the power system according to the previously selected first voltage sag treatment registration decision. The prediction process is to simulate the treatment decision once, and the system terminal builds a simulation environment through the electric power system simulation tool for simulating the actual running condition of the electric power system. And introducing a first voltage sag management registration decision into the simulation environment, and setting related parameters. In a simulation environment, applying the specified governance measures and strategies in the first voltage sag governance registration decision, and observing and recording the influence and effect of the governance measures on the voltage sag of the power system. According to the simulation operation result, the indexes such as the inhibition degree, response time, influence duration and the like of the treatment measures on the voltage sag are analyzed, and the possible effect of the treatment measures in practical application is judged. By this prediction, a first predicted abatement effect coefficient is obtained, which reflects the magnitude of the effect that the abatement scheme may bring. And then, the system terminal judges whether the first predicted treatment effect coefficient meets the preset treatment effect constraint set before. If the first predicted abatement effect coefficient meets the preset abatement effect constraints, it is representative that the selected abatement decision is capable of achieving the desired effect. This first voltage sag remediation decision is then determined as the final voltage sag remediation decision. Otherwise, if the expected effect is not achieved, discarding the first voltage sag management registration decision, reselecting another voltage sag management registration decision, and repeating the process again until a decision meeting the expected effect is found.
Further, the application provides a voltage sag management scheme registration based on the voltage sag sensing coefficient, and a voltage sag management registration decision library is obtained, and the method further comprises the following steps:
loading a plurality of historical voltage sag management decision sets of the power system, wherein each historical voltage sag management decision set comprises a historical voltage sag sensing coefficient and a historical voltage sag management decision;
extracting a first historical voltage sag management decision set according to the plurality of historical voltage sag management decision sets, wherein the first historical voltage sag management decision set comprises a first historical voltage sag sensing coefficient and a first historical voltage sag management decision;
Optionally, the system terminal loads a plurality of historical voltage sag remediation decision sets from the power system. Each decision set includes a historical voltage sag sensing coefficient and a corresponding historical voltage sag remediation decision. These historical data are the measures and strategies taken by the power system in the past to address the voltage sag problem, and the corresponding perceptual coefficients at that time. And then, the system terminal selects a first historical voltage sag management decision group from the historical decision groups. The decision set comprises a first historical voltage sag sensing coefficient and a corresponding first historical voltage sag management decision, and a data basis is made for subsequent screening decisions.
Performing similarity analysis on the first historical voltage sag sensing coefficient and the historical voltage sag sensing coefficient to obtain a first voltage sag sensing registration coefficient;
judging whether the first voltage sag sensing registration coefficient meets a preset sensing registration constraint;
And if the first voltage sag sensing registration coefficient meets the preset sensing registration constraint, adding the first historical voltage sag management decision to the voltage sag management registration decision library.
Optionally, the system terminal performs similarity analysis on the first historical voltage sag sensing coefficient and the current historical voltage sag sensing coefficient. Key features are first extracted from the perceptual coefficients. These characteristics include the amplitude, duration, frequency, etc. of the voltage dip. The euclidean distance is chosen to quantify the degree of similarity between the two perceptual coefficients. And calculating a similarity value between the first historical voltage sag sensing coefficient and the current historical voltage sag sensing coefficient, namely the first voltage sag sensing registration coefficient. This similarity analysis represents the degree of similarity of two data points by comparing the distance between them, helping the system terminal to understand the relevance and consistency between them. And then judging whether the obtained first voltage sag sensing registration coefficient meets a preset sensing registration constraint. If the first voltage sag sensing registration coefficient meets the preset sensing registration constraints, the first historical voltage sag management decision is higher in similarity with the sensing coefficient of the current voltage sag problem. Then the first historical voltage sag remediation decision is added to the voltage sag remediation registration decision library as one of the alternative remediation decisions. In this way, when similar problems are processed later, the system terminal can refer to the historical decision, so that the decision efficiency and accuracy are improved.
Further, the present application provides a method for judging whether the first predicted treatment effect coefficient meets a preset treatment effect constraint, and the method further includes:
if the first predicted treatment effect coefficient does not meet the preset treatment effect constraint, extracting a second voltage sag treatment registration decision according to the voltage sag treatment registration decision library;
performing voltage sag treatment effect prediction on the power system based on the second voltage sag treatment registration decision to obtain a second predicted treatment effect coefficient;
Optionally, if the first predicted treatment effect coefficient does not meet the preset treatment effect constraint, it represents that the treatment scheme selected by the system terminal for the first time cannot achieve the desired treatment effect. At this point, a second voltage sag remediation registration decision needs to be extracted from the voltage sag remediation registration decision library. After the second voltage sag management registration decision is selected, the system terminal predicts the voltage sag management effect of the power system again. This process is similar to the previous predictions, and is based on selected abatement decisions, predicting the abatement effects that it may bring in the simulated environment. Through this prediction, a second predicted treatment effect coefficient is obtained, and this coefficient reflects the effect that the second treatment scheme may bring. Summarizing, the above steps are to find a more efficient solution to the current voltage sag problem.
Judging whether the second predicted treatment effect coefficient meets the preset treatment effect constraint;
and if the second predicted treatment effect coefficient meets the preset treatment effect constraint, outputting the second voltage sag treatment registration decision as the voltage sag treatment decision.
Optionally, after the second voltage sag treatment effect prediction, the system terminal obtains a second predicted treatment effect coefficient. Then, the same method as the previous method is used for judging whether the coefficient meets the preset treatment effect constraint set previously. If the second predicted treatment effect coefficient meets the constraint conditions, the second voltage sag treatment registration decision is represented as being capable of achieving the expected treatment effect. This decision is then determined as the final voltage sag remediation decision. In summary, the system terminal finds a governance decision meeting the requirement in the second prediction and applies it as a final decision to the actual power system. The control scheme is used for ensuring that the selected control scheme can effectively solve the problem of voltage sag and ensure the stable operation of the power system.
Transmitting the voltage sag management decision to a voltage sag management module, wherein the voltage sag management module executes voltage sag management of the power system according to the voltage sag management decision.
In one embodiment, after the optimal voltage sag remediation decisions are determined, they are transmitted to a voltage sag remediation module so that the module can perform voltage sag remediation operations of the power system according to the decisions. The voltage sag management module is a hardware component responsible for executing voltage sag management operation and comprises a plurality of voltage sag management devices. Through deep analysis and optimization, the system terminal determines the optimal voltage sag management decision. This decision is then transmitted to a voltage sag remediation module, which is specifically responsible for performing the voltage sag remediation task. According to the decision provided by the user, the related parameters of the power system can be automatically adjusted, so that the problem of voltage sag is effectively solved, and the normal operation of the power system is ensured.
In summary, the embodiment of the application has at least the following technical effects:
According to the embodiment of the application, the spatial characteristic analysis is performed by collecting the basic information and the voltage sag record of the system, and then the voltage monitoring sensor array is arranged to obtain the voltage distribution data source. On the basis, a voltage sag sensing model based on big data is built and used for identifying voltage sag and obtaining a sensing coefficient. Then, activating a voltage sag treatment optimizing module, optimizing treatment parameters according to the perception coefficient, and generating a treatment decision. And finally, transmitting the governance decision to a governance module to execute governance operation. The whole method integrates a plurality of links such as data acquisition, model construction, parameter optimization, treatment execution and the like, and realizes comprehensive, accurate and efficient treatment of the voltage sag problem. The technical effects jointly solve the technical problem that the occurrence frequency of the voltage sag is too high due to insufficient monitoring and identification of the voltage sag, and ensure the reliability and stability of the power system.
Example two
Based on the same inventive concept as one of the customized voltage sag management optimization methods in the previous embodiments, as shown in fig. 2, the present application provides a customized voltage sag management optimization system, which includes:
Information acquisition unit 1: the information acquisition unit 1 is used for acquiring basic information of a power system and obtaining a system distribution data set;
spatial analysis unit 2: the space analysis unit 2 is used for loading voltage sag records of the power system, and performing space feature analysis based on the voltage sag records to obtain voltage sag space feature distribution;
Sensing array construction unit 3: the sensing array construction unit 3 is used for carrying out layout of voltage monitoring sensors on the power system based on the system distribution data set and the voltage sag spatial characteristic distribution to construct a voltage monitoring sensing array;
Data source monitoring unit 4: the data source monitoring unit 4 is used for monitoring and acquiring a voltage distribution data source of the power system based on the voltage monitoring sensing array;
Perception module builds unit 5: the sensing module building unit 5 is used for building a voltage sag sensing model based on big data;
Voltage sag identification unit 6: the voltage sag identification unit 6 is used for carrying out voltage sag identification on the voltage distribution data source based on the voltage sag perception model to obtain a voltage sag perception coefficient;
Parameter optimizing unit 7: the parameter optimizing unit 7 is used for activating a voltage sag control optimizing module to perform voltage sag control parameter optimization based on the voltage sag sensing coefficient so as to obtain a voltage sag control decision;
Voltage sag management unit 8: the voltage sag management unit 8 is configured to transmit the voltage sag management decision to a voltage sag management module, where the voltage sag management module executes voltage sag management of the power system according to the voltage sag management decision.
Further, the perception module building unit 5 is configured to perform the following method:
Loading normal voltage monitoring data records, abnormal voltage monitoring data records and voltage sag evaluation coefficient records of the power system based on big data;
Based on a support vector machine, performing anomaly identification training on the normal voltage monitoring data record and the abnormal voltage monitoring data record to generate a voltage anomaly identification model;
performing supervised learning on the abnormal voltage monitoring data record and the voltage sag evaluation coefficient record based on BP, and generating a voltage sag prediction evaluation model;
and integrating the voltage abnormality identification model and the voltage sag prediction evaluation model to generate the voltage sag sensing model.
Further, the perception module building unit 5 is configured to perform the following method:
Taking the abnormal voltage monitoring data record as input data, taking the voltage sag evaluation coefficient record as output supervision data, training the BP neural network, and acquiring a prediction evaluation loss coefficient when training is performed for preset times;
And if the predicted estimated loss coefficient is smaller than the predicted estimated loss threshold value, generating the voltage sag predicted estimated model.
Further, the perception module building unit 5 is configured to perform the following method:
inputting the voltage distribution data source into the voltage abnormality recognition model to obtain a common sense of voltage;
inputting the voltage abnormality identification set into the voltage sag prediction evaluation model to obtain a voltage sag prediction evaluation coefficient set;
And screening the voltage sag prediction evaluation coefficient set based on the voltage sag prediction evaluation constraint to obtain the voltage sag perception coefficient meeting the voltage sag prediction evaluation constraint.
Further, the parameter optimizing unit 7 is configured to perform the following method:
Performing voltage sag treatment scheme registration based on the voltage sag sensing coefficient to obtain a voltage sag treatment registration decision library;
Extracting a first voltage sag governance registration decision according to the voltage sag governance registration decision library;
Performing voltage sag treatment effect prediction on the power system based on the first voltage sag treatment registration decision to obtain a first predicted treatment effect coefficient;
Judging whether the first predicted treatment effect coefficient meets a preset treatment effect constraint;
and if the first predicted treatment effect coefficient meets the preset treatment effect constraint, outputting the first voltage sag treatment registration decision as the voltage sag treatment decision.
Further, the parameter optimizing unit 7 is configured to perform the following method:
loading a plurality of historical voltage sag management decision sets of the power system, wherein each historical voltage sag management decision set comprises a historical voltage sag sensing coefficient and a historical voltage sag management decision;
extracting a first historical voltage sag management decision set according to the plurality of historical voltage sag management decision sets, wherein the first historical voltage sag management decision set comprises a first historical voltage sag sensing coefficient and a first historical voltage sag management decision;
Performing similarity analysis on the first historical voltage sag sensing coefficient and the historical voltage sag sensing coefficient to obtain a first voltage sag sensing registration coefficient;
judging whether the first voltage sag sensing registration coefficient meets a preset sensing registration constraint;
And if the first voltage sag sensing registration coefficient meets the preset sensing registration constraint, adding the first historical voltage sag management decision to the voltage sag management registration decision library.
Further, the parameter optimizing unit 7 is configured to perform the following method:
if the first predicted treatment effect coefficient does not meet the preset treatment effect constraint, extracting a second voltage sag treatment registration decision according to the voltage sag treatment registration decision library;
performing voltage sag treatment effect prediction on the power system based on the second voltage sag treatment registration decision to obtain a second predicted treatment effect coefficient;
judging whether the second predicted treatment effect coefficient meets the preset treatment effect constraint;
and if the second predicted treatment effect coefficient meets the preset treatment effect constraint, outputting the second voltage sag treatment registration decision as the voltage sag treatment decision.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying drawings do not necessarily require the particular order shown, nor the sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. A method for optimizing customized voltage sag remediation, the method comprising:
Basic information of a power system is collected, and a system distribution data set is obtained;
Loading a voltage sag record of the power system, and performing spatial feature analysis based on the voltage sag record to obtain voltage sag spatial feature distribution;
Carrying out voltage monitoring sensor arrangement on the power system based on the system distribution data set and the voltage sag spatial characteristic distribution, and constructing a voltage monitoring sensor array;
monitoring and acquiring a voltage distribution data source of the power system based on the voltage monitoring and sensing array;
Constructing a voltage sag perception model based on big data;
Performing voltage sag identification on the voltage distribution data source based on the voltage sag sensing model to obtain a voltage sag sensing coefficient;
Activating a voltage sag control optimizing module to perform voltage sag control parameter optimization based on the voltage sag sensing coefficient to obtain a voltage sag control decision;
Transmitting the voltage sag management decision to a voltage sag management module, wherein the voltage sag management module executes voltage sag management of the power system according to the voltage sag management decision.
2. The method of claim 1, wherein building a voltage sag aware model based on big data comprises:
Loading normal voltage monitoring data records, abnormal voltage monitoring data records and voltage sag evaluation coefficient records of the power system based on big data;
Based on a support vector machine, performing anomaly identification training on the normal voltage monitoring data record and the abnormal voltage monitoring data record to generate a voltage anomaly identification model;
Performing supervised learning on the abnormal voltage monitoring data record and the voltage sag evaluation coefficient record based on a BP neural network to generate a voltage sag prediction evaluation model;
and integrating the voltage abnormality identification model and the voltage sag prediction evaluation model to generate the voltage sag sensing model.
3. The method of claim 2, wherein the supervised learning of the abnormal voltage monitor data record and the voltage sag estimation coefficient record based on a BP neural network generates a voltage sag prediction estimation model, comprising:
Taking the abnormal voltage monitoring data record as input data, taking the voltage sag evaluation coefficient record as output supervision data, training the BP neural network, and acquiring a prediction evaluation loss coefficient when training is performed for preset times;
And if the predicted estimated loss coefficient is smaller than the predicted estimated loss threshold value, generating the voltage sag predicted estimated model.
4. The method of claim 2, wherein performing voltage sag identification on the voltage distribution data source based on the voltage sag sensing model to obtain a voltage sag sensing coefficient comprises:
inputting the voltage distribution data source into the voltage abnormality recognition model to obtain a common sense of voltage;
inputting the voltage abnormality identification set into the voltage sag prediction evaluation model to obtain a voltage sag prediction evaluation coefficient set;
And screening the voltage sag prediction evaluation coefficient set based on the voltage sag prediction evaluation constraint to obtain the voltage sag perception coefficient meeting the voltage sag prediction evaluation constraint.
5. The method of claim 1, wherein activating a voltage sag remediation optimization module for voltage sag remediation parameter optimization based on the voltage sag perception coefficient, obtaining a voltage sag remediation decision, comprises:
Performing voltage sag treatment scheme registration based on the voltage sag sensing coefficient to obtain a voltage sag treatment registration decision library;
Extracting a first voltage sag governance registration decision according to the voltage sag governance registration decision library;
Performing voltage sag treatment effect prediction on the power system based on the first voltage sag treatment registration decision to obtain a first predicted treatment effect coefficient;
Judging whether the first predicted treatment effect coefficient meets a preset treatment effect constraint;
and if the first predicted treatment effect coefficient meets the preset treatment effect constraint, outputting the first voltage sag treatment registration decision as the voltage sag treatment decision.
6. The method of claim 5, wherein performing voltage sag remediation scheme registration based on the voltage sag perception coefficients, obtaining a voltage sag remediation registration decision library, comprises:
loading a plurality of historical voltage sag management decision sets of the power system, wherein each historical voltage sag management decision set comprises a historical voltage sag sensing coefficient and a historical voltage sag management decision;
extracting a first historical voltage sag management decision set according to the plurality of historical voltage sag management decision sets, wherein the first historical voltage sag management decision set comprises a first historical voltage sag sensing coefficient and a first historical voltage sag management decision;
Performing similarity analysis on the first historical voltage sag sensing coefficient and the historical voltage sag sensing coefficient to obtain a first voltage sag sensing registration coefficient;
judging whether the first voltage sag sensing registration coefficient meets a preset sensing registration constraint;
And if the first voltage sag sensing registration coefficient meets the preset sensing registration constraint, adding the first historical voltage sag management decision to the voltage sag management registration decision library.
7. The method of claim 5, wherein determining whether the first predicted abatement effect coefficient satisfies a preset abatement effect constraint comprises:
if the first predicted treatment effect coefficient does not meet the preset treatment effect constraint, extracting a second voltage sag treatment registration decision according to the voltage sag treatment registration decision library;
performing voltage sag treatment effect prediction on the power system based on the second voltage sag treatment registration decision to obtain a second predicted treatment effect coefficient;
judging whether the second predicted treatment effect coefficient meets the preset treatment effect constraint;
and if the second predicted treatment effect coefficient meets the preset treatment effect constraint, outputting the second voltage sag treatment registration decision as the voltage sag treatment decision.
8. A customized voltage sag remediation optimization system, the system comprising:
information acquisition unit: basic information of a power system is collected, and a system distribution data set is obtained;
Spatial analysis unit: loading a voltage sag record of the power system, and performing spatial feature analysis based on the voltage sag record to obtain voltage sag spatial feature distribution;
the sensing array construction unit: carrying out voltage monitoring sensor arrangement on the power system based on the system distribution data set and the voltage sag spatial characteristic distribution, and constructing a voltage monitoring sensor array;
A data source monitoring unit: monitoring and acquiring a voltage distribution data source of the power system based on the voltage monitoring and sensing array;
The perception module building unit: constructing a voltage sag perception model based on big data;
a voltage sag identification unit: performing voltage sag identification on the voltage distribution data source based on the voltage sag sensing model to obtain a voltage sag sensing coefficient;
parameter optimizing unit: activating a voltage sag control optimizing module to perform voltage sag control parameter optimization based on the voltage sag sensing coefficient to obtain a voltage sag control decision;
Voltage sag management unit: transmitting the voltage sag management decision to a voltage sag management module, wherein the voltage sag management module executes voltage sag management of the power system according to the voltage sag management decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410452152.9A CN118263872A (en) | 2024-04-16 | 2024-04-16 | Customized voltage sag management optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410452152.9A CN118263872A (en) | 2024-04-16 | 2024-04-16 | Customized voltage sag management optimization method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118263872A true CN118263872A (en) | 2024-06-28 |
Family
ID=91606762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410452152.9A Pending CN118263872A (en) | 2024-04-16 | 2024-04-16 | Customized voltage sag management optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118263872A (en) |
-
2024
- 2024-04-16 CN CN202410452152.9A patent/CN118263872A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Javed et al. | State of the art and taxonomy of prognostics approaches, trends of prognostics applications and open issues towards maturity at different technology readiness levels | |
| Ma et al. | Discriminative deep belief networks with ant colony optimization for health status assessment of machine | |
| Smarsly et al. | Machine learning techniques for structural health monitoring | |
| Jouin et al. | Prognostics of PEM fuel cell in a particle filtering framework | |
| Chen et al. | A health index construction framework for prognostics based on feature fusion and constrained optimization | |
| CN117375237B (en) | Substation operation and maintenance method and system based on digital twin technology | |
| CN115098962A (en) | Method for predicting residual life of mechanical equipment in degradation state based on hidden half Markov model | |
| CN117273440A (en) | Engineering construction Internet of things monitoring and managing system and method based on deep learning | |
| CN111079348B (en) | Method and device for detecting slowly-varying signal | |
| Hu et al. | A hybrid model for predicting the degradation trend of hydropower units based on deep learning | |
| CN115793590A (en) | Data processing method and platform suitable for system safety operation and maintenance | |
| CN117609836A (en) | Electromagnetic sensitivity prediction and health management method for integrated module | |
| Sadoughi et al. | A deep learning approach for failure prognostics of rolling element bearings | |
| CN117007977B (en) | Energy storage battery health state diagnosis method | |
| CN117674128A (en) | Automatic fault removal method based on power dispatching system | |
| Dang et al. | seq2graph: Discovering dynamic non-linear dependencies from multivariate time series | |
| Melendez et al. | Self-supervised Multi-stage Estimation of Remaining Useful Life for Electric Drive Units | |
| CN112580254A (en) | Multi-dimensional analysis and early warning method for converter transformer based on multi-level decision fusion | |
| Bond et al. | A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data | |
| Alsumaidaee et al. | Fault detection for medium voltage switchgear using a deep learning Hybrid 1D-CNN-LSTM model | |
| Jobi-Taiwo et al. | Mahalanobis-Taguchi system for multiclass classification of steel plates fault | |
| CN118263872A (en) | Customized voltage sag management optimization method and system | |
| Singh et al. | Predicting the remaining useful life of ball bearing under dynamic loading using supervised learning | |
| CN117272844B (en) | Method and system for predicting service life of distribution board | |
| Verbeke et al. | Fleet-Based Remaining Useful Life Prediction of Safety-critical Electronic Devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |