Intelligent monitoring method, device and equipment for operation state of power distribution network and medium

Abstract

The invention provides a power distribution network operation state intelligent monitoring method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining original operation index data corresponding to a power distribution network through a data interrogation technology; performing data processing on the original operation index data by adopting an empirical mode decomposition algorithm, and performing data analysis on the operation index data after data preprocessing based on a data analysis model to obtain an operation index trend prediction result; a long short-term memory network algorithm and a whale optimization algorithm are adopted to carry out prediction optimization processing on the operation index trend prediction result, and a power distribution network operation trend prediction result is obtained; and generating and pushing alarm information based on the prediction result of the operation trend of the power distribution network. The intelligent monitoring scheme for the operation state of the power distribution network can be suitable for power distribution networks of different scales and types, comprehensive monitoring and intelligent analysis of key operation indexes of the power distribution network are achieved, and therefore the operation efficiency and reliability of the power distribution network are effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of distribution network monitoring, and in particular to a method, device, electronic device and storage medium for intelligent monitoring of the operating status of a distribution network. Background Art

[0002] As global energy demand grows, the stability and efficiency of distribution networks, as an important part of power supply, have a vital impact on economic development and social life. Key operating indicators of distribution networks, such as terminal online rate, remote control success rate, fault self-healing time, etc., are directly related to the reliability and power supply quality of the power grid.

[0003] However, under the current technical framework, the monitoring and management of these key indicators face a series of challenges. First, the real-time perception capability of key operating indicators of the distribution network is insufficient. Existing technologies often have difficulty in capturing the dynamic changes of power grid operation data in a timely manner, resulting in the inability to obtain accurate data in real time, which in turn affects the accurate assessment of the power grid status. Secondly, the existing analysis tools have poor performance when processing massive and complex distribution network data. They lack effective mining and analysis capabilities, making it difficult to deeply analyze the valuable information in the data, and thus unable to make accurate predictions of future operating trends. In addition, the insufficient ability to predict power grid operation trends limits early warning and timely response to potential problems. Finally, the untimely and inadequate communication of alarm information results in the inability of operation and maintenance personnel to respond quickly to power grid anomalies, affecting the operating efficiency and reliability of the distribution network. Therefore, a new method is urgently needed to solve the above problems in order to improve the intelligent management level of the distribution network, reduce the need for manual intervention, and improve power supply reliability and user satisfaction.

[0004] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the invention

[0005] In response to the above-mentioned technical problems, the present application provides a method, device, electronic device and storage medium for intelligent monitoring of the operating status of a distribution network, which solves the deficiencies of the existing technology in real-time perception, data analysis, trend prediction and alarm communication, realizes comprehensive monitoring and intelligent analysis of key operating indicators of the distribution network, and effectively improves the operating efficiency and reliability of the distribution network.

[0006] In order to solve the above technical problems, the present application provides a method for intelligently monitoring the operation status of a distribution network, comprising the following steps:

[0007] Respond to the data call request sent to the distribution network OCS system, and obtain the original operating indicator data corresponding to the distribution network through the data call technology;

[0008] Using an empirical mode decomposition algorithm to process the original operating index data to obtain processed operating index data;

[0009] Performing data analysis on the pre-processed operation index data based on a pre-built data analysis model to obtain an operation index trend prediction result corresponding to the distribution network;

[0010] The long short-term memory network algorithm and the whale optimization algorithm are used to perform prediction and optimization processing on the operation index trend prediction results to obtain the distribution network operation trend prediction results;

[0011] Based on the distribution network operation trend prediction results, corresponding alarm information is generated and pushed.

[0012] Further, in some embodiments of the present application, the responding to the data call request sent to the distribution network OCS system, and obtaining the original operation indicator data corresponding to the distribution network through the data call technology, includes:

[0013] Send a data call test request to the distribution network OCS system through an external interface, wherein the data call test request includes a target data type and a target parameter;

[0014] In response to the data call request, the distribution network OCS system extracts the original operation index data corresponding to the distribution network from the data source, and filters and aggregates the original operation index data;

[0015] The original operation indicator data after filtering and aggregation is returned to the requester through the external interface.

[0016] Furthermore, in some embodiments of the present application, the adopting of the empirical mode decomposition algorithm to process the original operation index data to obtain the processed operation index data includes:

[0017] Performing data preprocessing on the original operation indicator data;

[0018] The original operating index data after data preprocessing is used as the initialization signal sequence, and the parameters of the empirical mode decomposition algorithm are set;

[0019] Perform extreme point detection on the initialization signal sequence to obtain and record the extreme point corresponding to each operation indicator data sequence;

[0020] Based on the extreme value points corresponding to each of the operation indicator data sequences, corresponding upper and lower envelopes are constructed and corresponding mean envelopes are calculated;

[0021] Subtracting the mean envelope from the original operating index data to obtain a target data sequence;

[0022] The target data sequence is iteratively decomposed to obtain an empirical mode decomposition result corresponding to the original operating data.

[0023] Further, in some embodiments of the present application, the pre-built data analysis model is used to perform data analysis on the pre-processed operation index data to obtain the operation index trend prediction result corresponding to the distribution network, including:

[0024] Obtaining the operating indicator characteristics corresponding to the operating indicator data after the data preprocessing;

[0025] The operating indicator characteristics are input into a pre-built data analysis model, and the operating indicator trend prediction results corresponding to the various operating indicators in the distribution network are output, wherein the operating indicator trend prediction results include the real-time status of the operating indicator and the corresponding trend prediction results.

[0026] Furthermore, in some embodiments of the present application, the data analysis model is constructed by:

[0027] Obtain historical operating indicator data of the distribution network and perform data preprocessing to obtain training set data and test set data;

[0028] Define the network structure of the long short-term memory network algorithm and configure the parameters of the data analysis model to build the initial data analysis model;

[0029] Training the initial data analysis model based on the training set data to obtain a trained data analysis model;

[0030] Evaluate the trained data analysis model based on the test set data, and optimize the model according to the obtained evaluation results to obtain a final data analysis model;

[0031] The data analysis model is updated and iterated regularly.

[0032] Further, in some embodiments of the present application, the long short-term memory network algorithm and the whale optimization algorithm are used to perform prediction optimization processing on the operation index trend prediction result to obtain the distribution network operation trend prediction result, including:

[0033] Randomly generate a group of whale positions, each position represents a hyperparameter combination of the LSTM algorithm model, and set the parameters of the whale optimization algorithm;

[0034] Using each whale position as a hyperparameter combination of the long short-term memory network algorithm model, training the long short-term memory network algorithm model, and using the validation set data to evaluate the performance of the model;

[0035] Calculate the fitness value of each whale based on the performance of the LSTM algorithm model;

[0036] Adjust the position of the whale according to the update rules of the whale optimization algorithm;

[0037] In each iteration, the whale with the highest fitness value is selected as the current optimal solution, and the optimal solution and its fitness value are recorded;

[0038] Repeat the process of calculating fitness value, updating position and selecting the optimal solution until the preset conditions are met;

[0039] After a preset number of iterations, the optimal hyperparameter combination is determined by the whale optimization algorithm;

[0040] Reconstructing the long short-term memory network algorithm model using the optimal parameter combination, and evaluating it based on the test set to obtain a model evaluation result;

[0041] Based on the model evaluation results, the optimal long short-term memory network algorithm model and its prediction results are determined.

[0042] Further, in some embodiments of the present application, the generating and pushing corresponding alarm information based on the distribution network operation trend prediction result includes:

[0043] After any operating indicator is detected to exceed a preset threshold based on the distribution network operation trend prediction result, a corresponding alarm message is generated and pushed to the corresponding terminal device of the operation and maintenance personnel;

[0044] After receiving the processing information returned by the operation and maintenance personnel, performing a secondary test on the operation indicator to generate a secondary test result;

[0045] If it is detected based on the secondary detection result that the operating indicator still exceeds the preset threshold, a secondary alarm message is generated and pushed.

[0046] Accordingly, the present application also provides an intelligent monitoring device for the operation status of a distribution network, comprising:

[0047] The data call test module is used to respond to the data call test request sent to the distribution network OCS system and obtain the original operation indicator data corresponding to the distribution network through the data call test technology;

[0048] A data processing module, used to process the original operation index data using an empirical mode decomposition algorithm to obtain the operation index data after data processing;

[0049] A data analysis module is used to analyze the operation index data after data preprocessing based on a pre-built data analysis model to obtain the operation index trend prediction result corresponding to the distribution network;

[0050] A prediction and optimization module, used to use a long short-term memory network algorithm and a whale optimization algorithm to perform prediction and optimization processing on the operation indicator trend prediction results to obtain a distribution network operation trend prediction result;

[0051] The alarm push module is used to generate and push corresponding alarm information based on the distribution network operation trend prediction result.

[0052] The present application also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for intelligently monitoring the operating status of a distribution network as described above are implemented.

[0053] The present application also provides a storage medium storing a computer program that can be loaded by a processor and execute the above-mentioned method for intelligently monitoring the operating status of a distribution network.

[0054] Implementing the embodiments of the present application has the following beneficial effects:

[0055] As described above, the present application provides a method, device, electronic device and storage medium for intelligent monitoring of the operating status of a distribution network. The method for intelligent monitoring of the operating status of a distribution network includes: responding to a data call request sent to a distribution network OCS system, and obtaining original operating index data corresponding to the distribution network through data call technology; using an empirical mode decomposition algorithm to perform data processing on the original operating index data to obtain data-processed operating index data; performing data analysis on the data-preprocessed operating index data based on a pre-built data analysis model to obtain an operating index trend prediction result corresponding to the distribution network; using a long short-term memory network algorithm and a whale optimization algorithm to perform predictive optimization processing on the operating index trend prediction result to obtain a distribution network operating trend prediction result; based on the distribution network operating trend prediction result, generating corresponding alarm information and pushing it. The intelligent monitoring solution for the operation status of the distribution network provided by this application realizes real-time perception and information collection of key operation indicators such as terminal online rate, remote control success rate, fault self-healing time, etc. through data call technology; adopts empirical mode decomposition algorithm for data processing, and uses long short-term memory network algorithm to conduct in-depth analysis of data and establish models, so as to solve the problems of lack of analysis and statistical tools, slow data processing speed and low accuracy in the existing technology; introduces whale optimization algorithm, and improves the ability to predict the operation trend of the power grid by optimizing the prediction model; adopts a variety of alarm communication methods to ensure that operation and maintenance personnel can receive alarm information in time. It can be seen that this application can realize comprehensive monitoring and intelligent analysis of key operation indicators of the distribution network, improve the intelligent management level of the distribution network, reduce the need for manual intervention, and effectively improve the operation efficiency and reliability of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0057] Figure 1 It is a schematic diagram of an application scenario of the method for intelligently monitoring the operation status of a distribution network provided in an embodiment of the present application;

[0058] Figure 2 It is a flow chart of a method for intelligently monitoring the operation status of a distribution network provided in an embodiment of the present application;

[0059] Figure 3 It is a schematic diagram of the process of collecting key operating indicator data of the distribution network OCS system provided in an embodiment of the present application;

[0060] Figure 4 It is a schematic diagram of a process of performing data processing using an empirical mode decomposition (EMD) algorithm provided in an embodiment of the present application;

[0061] Figure 5 It is a flowchart of constructing a data analysis model using the LSTM algorithm provided in the embodiment of the present application;

[0062] Figure 6 It is a flowchart of the whale optimization algorithm combined with the LSTM algorithm provided in the embodiment of the present application;

[0063] Figure 7 It is a flowchart of alarm information transmission and processing provided by an embodiment of the present application;

[0064] Figure 8 It is another flow chart of the method for intelligently monitoring the operation status of a distribution network provided in an embodiment of the present application;

[0065] Fig. 9 It is a structural diagram of an intelligent monitoring device for distribution network operation status provided in an embodiment of the present application;

[0066] Fig.10 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0067] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0068] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0069] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0070] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0071] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0072] The present application provides a method, device, electronic device and storage medium for intelligent monitoring of the operating status of a distribution network.

[0073] Among them, the intelligent monitoring device for the operation status of the distribution network can be specifically integrated in an electronic device, and the electronic device can be a smart phone, a tablet computer, a laptop or a desktop computer, but is not limited to this. The electronic device can be directly or indirectly connected to the server through wired or wireless communication. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. This application does not limit this.

[0074] See also Figure 1 , Figure 1 FIG. 1 is an application environment diagram of a method for intelligently monitoring the operation status of a distribution network in an embodiment. Figure 1 , the intelligent monitoring method for the operation status of the distribution network can be applied to the intelligent monitoring system for the operation status of the distribution network. Among them, the intelligent monitoring system for the operation status of the distribution network can include a terminal 110 and a server 120. The terminal 110 and the server 120 are connected through a network. The terminal 110 can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server 120 can be implemented by an independent server or a server cluster composed of multiple servers. The terminal 110 is used to respond to the data call request sent to the distribution network OCS system, and obtain the original operation index data corresponding to the distribution network through the data call technology; the original operation index data is processed by the empirical mode decomposition algorithm to obtain the operation index data after data processing; the operation index data after data preprocessing is analyzed based on the pre-built data analysis model to obtain the operation index trend prediction result corresponding to the distribution network; the operation index trend prediction result is predicted and optimized by the long short-term memory network algorithm and the whale optimization algorithm to obtain the distribution network operation trend prediction result; based on the distribution network operation trend prediction result, the corresponding alarm information is generated and pushed.

[0075] With the continuous expansion of power supply demand, people have higher requirements for the operation monitoring and management of distribution networks. Among them, the key operation indicators of the distribution network play a vital role in ensuring the stable and efficient operation of the power grid. These key operation indicators include terminal online rate, remote control success rate, fault self-healing time, etc. However, the current technical situation has many shortcomings. On the one hand, there is a lack of effective real-time perception means for the key operation indicators of the distribution network. The power grid operation data changes rapidly, and the existing technical architecture cannot capture the dynamic changes of these data in time, resulting in the inability to obtain accurate data in time; on the other hand, there is a serious lack of analysis tools, and in the face of massive and complex distribution network data, it is impossible to conduct effective mining and analysis. This leads to the inability to deeply analyze the valuable information in the data during data processing, making it difficult to make accurate predictions about future operation trends. In the existing technical research, although there are directions related to the prediction of key operation indicators and the processing and analysis of distribution network data, there are still limitations and cannot effectively solve the current problems. Therefore, a new method is urgently needed to solve these problems.

[0076] It should be noted that the order of description of the following embodiments is not intended to limit the priority order of the embodiments.

[0077] The present application provides a method for intelligently monitoring the operation status of a distribution network, comprising: responding to a data call request sent to a distribution network OCS system, and obtaining original operation index data corresponding to the distribution network through a data call technology; performing data processing on the original operation index data using an empirical mode decomposition algorithm to obtain the operation index data after data processing; performing data analysis on the operation index data after data preprocessing based on a pre-built data analysis model to obtain an operation index trend prediction result corresponding to the distribution network; performing prediction and optimization processing on the operation index trend prediction result using a long short-term memory network algorithm and a whale optimization algorithm to obtain a distribution network operation trend prediction result; and generating corresponding alarm information based on the distribution network operation trend prediction result and pushing it.

[0078] See also Figure 2 , Figure 2 1 is a flow chart of a method for intelligently monitoring the operating status of a distribution network provided in an embodiment of the present application. The method for intelligently monitoring the operating status of a distribution network provided in this embodiment can be applied to a distribution network and can specifically include the following steps:

[0079] S1. Respond to the data call request sent to the distribution network OCS system, and obtain the original operating indicator data corresponding to the distribution network through the data call technology;

[0080] Specifically, for step S1, a data call request is first sent to the distribution network OCS system (Operational Control System), and the original operating indicator data of the distribution network is obtained through data call technology. This step is the basis of the entire monitoring method, ensuring that the data source for subsequent analysis is real-time and accurate. In addition to data call technology, the use of Internet of Things (IoT) technology can also be considered to enhance the real-time and comprehensiveness of data collection by deploying more smart sensors.

[0081] S2. Using the empirical mode decomposition algorithm to process the original operation index data to obtain the operation index data after data processing;

[0082] Specifically, for step S2, the Empirical Mode Decomposition (EMD) algorithm is used to pre-process the original operating index data to reduce data errors and improve the accuracy of analysis. The EMD algorithm can decompose complex data signals and provide a clearer data basis for subsequent data analysis.

[0083] S3. Perform data analysis on the pre-processed operation index data based on the pre-built data analysis model to obtain the operation index trend prediction results corresponding to the distribution network;

[0084] Specifically, for step S3, based on the pre-built data analysis model, the pre-processed data is analyzed to obtain the trend prediction results of the distribution network operation indicators. This step is the core of the intelligent monitoring method, which predicts future trends by analyzing historical data.

[0085] S4. Use the long short-term memory network algorithm and the whale optimization algorithm to perform forecast optimization processing on the operation index trend forecast results to obtain the distribution network operation trend forecast results;

[0086] Specifically, for step S4, the Long Short-Term Memory (LSTM) algorithm and the Whale Optimization Algorithm (WOA) are used to optimize the operation indicator trend prediction results to improve the prediction accuracy and response speed.

[0087] S5. Generate and push corresponding alarm information based on the distribution network operation trend prediction results;

[0088] Specifically, for step S5, based on the distribution network operation trend prediction results, alarm information is generated and pushed to the operation and maintenance personnel. This step ensures that the operation and maintenance personnel can respond to potential problems in a timely manner and improve the operation efficiency and reliability of the distribution network. By developing an alarm system, including multi-level alarms, adaptive threshold settings, and intelligent alarm suppression functions, false alarms can be reduced and the relevance of alarms can be improved.

[0089] Through real-time data collection and rapid data processing, this embodiment can respond to the operation changes of the distribution network in a timely manner, thereby improving the real-time monitoring. By using the EMD algorithm and the LSTM algorithm, the method can effectively process and analyze large-scale distribution network data, thereby improving the depth and breadth of data processing. By combining the LSTM algorithm and the WOA algorithm, it is possible to more accurately predict the operation trend of the distribution network, thereby providing more reliable support for operation and maintenance decisions. Through intelligent alarm push, it is possible to ensure that the operation and maintenance personnel are aware of the abnormal conditions of the distribution network in a timely manner, thereby improving the operation efficiency and reliability of the distribution network. Through the automated monitoring and alarm system, the need for manual intervention is reduced, and the operation and maintenance costs and the possibility of human errors are reduced.

[0090] Further, in some embodiments, step S1 "responding to the data call request sent to the distribution network OCS system, and obtaining the original operation indicator data corresponding to the distribution network through the data call technology" may specifically include:

[0091] Send a data call test request to the distribution network OCS system through an external interface, where the data call test request includes target data type and target parameters;

[0092] In response to data call request, the distribution network OCS system extracts the original operation index data corresponding to the distribution network from the data source, and filters and aggregates the original operation index data;

[0093] The original operation indicator data after filtering and aggregation is returned to the requester through the external interface.

[0094] Specifically, for step S1, data transmission between the distribution network OCS system and other systems is realized through an external interface, including request and response data packets; a data call request is sent to the distribution network OCS system through the external interface, and the request contains the type of data and related parameters to be obtained. After receiving the request, the distribution network OCS system extracts data from the corresponding data source according to the content of the request, and performs necessary processing, such as filtering and aggregation. The processed data is returned to the requester through the external interface for further analysis and use. At the same time, in order to improve the real-time perception capability of key operating indicators of the distribution network, the real-time perception capability can be improved by increasing the deployment of intelligent devices such as sensors, so that the distribution network OCS system can obtain more relevant data for subsequent analysis.

[0095] Among them, the distribution network OCS system is an automated system for monitoring and managing the operating status of the distribution network. It realizes remote monitoring, control and optimization management of distribution network equipment by real-time collection and processing of various data in the distribution network. Its key operating indicators are the core parameters for evaluating the operating status and performance of the distribution network. By monitoring and analyzing these indicators, potential problems can be identified and solved in a timely manner, thereby improving the operating efficiency and reliability of the distribution network. Therefore, this embodiment obtains key indicator-related data from the distribution network OCS system in a relatively accurate and comprehensive manner, mainly focusing on the four indicators of terminal online rate, remote control success rate, fault self-healing time, and dispatching operation efficiency. Examples and explanations:

[0096] 1) Terminal online rate: It is to obtain relevant data from the equipment monitoring module or data acquisition module in the distribution network OCS system, including the online status information of all terminal devices, that is, the real-time communication data of smart meters, sensors, circuit breakers and other devices;

[0097] 2) Remote control success rate: It is to obtain relevant data from the command execution module or log recording module in the distribution network OCS system, including the time, target device, command type and execution result of each remote control command;

[0098] 3) Fault self-recovery time: Relevant data is obtained from the fault management module or automatic processing module in the distribution network OCS system, including the time when the fault occurred, the time when the fault was isolated, and the time when normal power supply was restored;

[0099] 4) Dispatching operation efficiency: It is obtained from the dispatching management module or operation log module in the distribution network OCS system, including the issuance time of the dispatching command, the execution start and end time, and the feedback of the operation effect.

[0100] In a specific embodiment, Figure 3 As shown, Figure 3 The process of data collection and key operating indicator prediction in the distribution network OCS system is as follows: The distribution network OCS system is responsible for monitoring and managing the operating status of the distribution network, including key operating indicators such as fault isolation time, target equipment, dispatch time, remote control success rate, fault self-healing time, remote control command time, and dispatch operation efficiency. When executing the data collection task, an external interface is used to obtain data from the distribution network OCS system. These data include relevant data of key operating indicators such as terminal online rate, remote control success rate, and fault self-healing time. The prepared request package (the type and range of data to be obtained) is sent to the OCS system through the interface. After the OCS system processes the request, it will return the requested data. Data call measurement technology is used during the data transmission process to ensure the real-time and accuracy of the data, providing a basis for subsequent analysis and prediction. Finally, key operating indicators are predicted, including terminal online rate, remote control success rate, fault self-healing time, and dispatch operation efficiency.

[0101] This embodiment uses precise data call request and effective data preprocessing to obtain more accurate and reliable distribution network operation data; filtering and aggregation processing improves data availability, so that the data analysis model can process and analyze data more effectively; optimized data call technology and intelligent filtering aggregation strategy can reduce data transmission and processing time, thereby improving the response speed of the system; high-quality original operation indicator data provides a solid foundation for subsequent data analysis, thereby improving the quality of data analysis and the accuracy of prediction; diversified data sources and intelligent processing strategies enable the system to adapt to different operating environments and analysis requirements, and improve the flexibility and adaptability of the system.

[0102] Furthermore, in some embodiments, step S2 of "using an empirical mode decomposition algorithm to process the original operating index data to obtain the processed operating index data" may specifically include:

[0103] Perform data preprocessing on the original operation indicator data;

[0104] The original operating index data after data preprocessing is used as the initialization signal sequence, and the parameters of the empirical mode decomposition algorithm are set;

[0105] Perform extreme point detection on the initialization signal sequence, obtain the extreme point corresponding to each operating indicator data sequence and record it;

[0106] Based on the extreme points corresponding to each operating indicator data sequence, the corresponding upper and lower envelopes are constructed and the corresponding mean envelope is calculated;

[0107] Subtract the mean envelope from the original operating index data to obtain the target data sequence;

[0108] The target data sequence is iteratively decomposed to obtain the empirical mode decomposition result corresponding to the original operating data.

[0109] Specifically, for step S2, although the data obtained through data call testing is processed by the distribution network OCS system and is all key data, in order to improve the efficiency of analysis and decision-making, this embodiment uses the empirical mode decomposition (EMD) algorithm to further process the data, and then uses the LSTM (long short-term memory network) algorithm to analyze the data, which can grasp the status and trend of key operating indicators in real time. Step S2 mainly uses the empirical mode decomposition (EMD) algorithm for data processing, which can quickly screen, classify and preliminarily organize the data, and can accurately decompose complex data signals and reduce data errors. For example, classifying data according to different key indicators improves the accuracy of analysis.

[0110] In a specific embodiment, Figure 4 As shown, Figure 4 This is a flow chart of data processing using the empirical mode decomposition (EMD) algorithm. The specific process includes:

[0111] (1) Data collection and preprocessing

[0112] Data collection: Ensure that a complete data set of key operating indicators such as terminal online rate, remote control success rate, fault self-healing time, and scheduling operation efficiency is collected.

[0113] Data cleaning: remove outliers, fill in missing values, and ensure data quality.

[0114] Data normalization: Normalize the data to make it suitable for the input requirements of the EMD algorithm.

[0115] (2) EMD initialization

[0116] Initialize signal sequence: Use the preprocessed data as the initial signal sequence.

[0117] Parameter setting: Set the parameters of the EMD algorithm, such as screening threshold, number of iterations, etc.

[0118] (3) Extreme point detection

[0119] Maximum and minimum value detection: For each key operating indicator data series, detect the maximum and minimum points in it.

[0120] Record extreme points: record the positions of these extreme points and the corresponding function values.

[0121] (4) Construction and calculation of upper and lower envelopes

[0122] Envelope construction: Using the detected extreme points, construct the upper and lower envelopes of each data series.

[0123] Mean envelope calculation: Calculate the mean of the upper and lower envelopes of each data sequence to obtain the mean envelope.

[0124] New data series acquisition: Subtract the mean envelope from the original data to obtain a new data series.

[0125] (5) Iterative decomposition and output

[0126] Repeat the steps: perform extreme point detection, envelope construction and mean envelope calculation on the newly obtained data sequence again.

[0127] IMF component extraction: Each iteration will get a new data sequence, which represents an intrinsic mode function (IMF) component in the original data. When the stop condition is met, the iteration ends.

[0128] Result output: Combine all the IMF components obtained by iteration and add the final residual term to get the complete EMD decomposition result of the original data.

[0129] This embodiment decomposes the original data through the EMD algorithm, which can more accurately capture the inherent laws and trends of the data; the preprocessing and iterative decomposition steps improve the availability of the data and provide a clearer data basis for subsequent data analysis; the data processed by EMD is more suitable for the subsequent data analysis model, which can improve the performance of the model and the accuracy of prediction; the EMD algorithm can effectively reduce errors in the data and improve the signal-to-noise ratio of the data.

[0130] Further, in some embodiments, step S3 "performing data analysis on the pre-processed operation index data based on the pre-built data analysis model to obtain the operation index trend prediction result corresponding to the distribution network" may specifically include:

[0131] Obtaining the operating indicator characteristics corresponding to the operating indicator data after data preprocessing;

[0132] The operating indicator characteristics are input into a pre-built data analysis model, and the operating indicator trend prediction results corresponding to various operating indicators in the distribution network are output. The operating indicator trend prediction results include the real-time status of the operating indicators and the corresponding trend prediction results.

[0133] Specifically, for step S3, since the operating status of the distribution network changes dynamically, it is difficult for traditional analysis methods to accurately capture these changes at every time point. The LSTM algorithm has the advantage of processing time series data. By building a data analysis model and learning historical data, it can accurately analyze the real-time status of key indicators such as terminal online rate, remote control success rate, fault self-healing time, scheduling operation efficiency, and planned power outage perception, identify abnormal patterns in the data, and predict the corresponding development trend.

[0134] In a specific embodiment, key features are extracted from the preprocessed operating index data, and these features can represent the operating status of the distribution network. The extracted operating index features are input into a pre-built data analysis model, and after the data analysis model processes the input features, it outputs the real-time status of each operating index in the distribution network and the corresponding trend prediction results.

[0135] This embodiment improves the accuracy of distribution network operation trend prediction through precise feature extraction and advanced data analysis models; provides more accurate operation indicator trend prediction results, and provides strong data support for distribution network operation and maintenance decisions.

[0136] Furthermore, in some embodiments, the data analysis model may be constructed in the following manner:

[0137] Obtain historical operating indicator data of the distribution network and perform data preprocessing to obtain training set data and test set data;

[0138] Define the network structure of the long short-term memory network algorithm and configure the parameters of the data analysis model to build the initial data analysis model;

[0139] The initial data analysis model is trained based on the training set data to obtain a trained data analysis model;

[0140] Evaluate the trained data analysis model based on the test set data, and optimize the model according to the evaluation results to obtain the final data analysis model;

[0141] Update and iterate data analysis models regularly.

[0142] Specifically, this embodiment also provides a method for constructing a data analysis model. It can be understood that the data analysis model in this embodiment can be a data analysis model constructed based on a long short-term memory network algorithm network, such as Figure 5 As shown, Figure 5 The process of building a data analysis model for the LSTM algorithm is as follows:

[0143] First, you need to prepare a data set containing historical data of key operating indicators of the distribution network. Preprocess the data set, including data cleaning and normalization, to ensure data quality and make it suitable for the input requirements of the LSTM model. Then build the model, select a suitable deep learning framework, and define the LSTM network structure, including the input layer, several LSTM layers, and fully connected layers. Configure model parameters, such as loss function and optimizer. Then train the model and use the training set data to train the LSTM model. During the training process, continuously adjust the model parameters to minimize the loss function value. Monitor indicators such as loss value and accuracy during the training process, as well as performance on the validation set, so as to promptly discover and solve problems such as overfitting. Then test the model and use the test set data to evaluate the trained LSTM model and calculate indicators such as the error between the predicted result and the true value; according to the evaluation results, tune the model, adjust the network structure, change the learning rate, etc. Finally, generate the model and deploy the trained LSTM model to the actual application scenario. Update and iterate the model regularly to adapt to new data and requirements.

[0144] Through meticulous model training and evaluation steps, the data analysis model constructed in this embodiment can more accurately predict the operating trend of the distribution network; the model is regularly updated and iterated so that the model can adapt to new data distribution and improve the generalization ability of the model.

[0145] Further, in some embodiments, step S4 "using the long short-term memory network algorithm and the whale optimization algorithm to perform prediction optimization processing on the operation index trend prediction results to obtain the distribution network operation trend prediction results" may specifically include:

[0146] Randomly generate a group of whale positions, each position represents a hyperparameter combination of the LSTM algorithm model, and set the parameters of the whale optimization algorithm;

[0147] Use each whale position as a hyperparameter combination of the long short-term memory network algorithm model, train the long short-term memory network algorithm model, and use the validation set data to evaluate the performance of the model;

[0148] Calculate the fitness value of each whale based on the performance of the LSTM algorithm model;

[0149] Adjust the position of the whale according to the update rules of the whale optimization algorithm;

[0150] In each iteration, the whale with the highest fitness value is selected as the current optimal solution, and the optimal solution and its fitness value are recorded;

[0151] Repeat the process of calculating fitness value, updating position and selecting the optimal solution until the preset conditions are met;

[0152] After a preset number of iterations, the optimal hyperparameter combination is determined through the whale optimization algorithm;

[0153] Use the optimal parameter combination to rebuild the long short-term memory network algorithm model, and evaluate it based on the test set to obtain the model evaluation results;

[0154] Based on the model evaluation results, the optimal long short-term memory network algorithm model and its prediction results are determined.

[0155] Specifically, for step S4, the LSTM algorithm is used to perform real-time analysis and prediction of key indicators, but due to its high complexity, it takes longer to train, and the response speed cannot keep up, which affects the prediction accuracy. In order to further improve the ability to predict the operation trend of the power grid, this embodiment introduces the whale optimization algorithm. The whale optimization algorithm is an optimization algorithm based on swarm intelligence, which has the characteristics of fast convergence speed and strong global search capability. The whale optimization algorithm can improve the prediction accuracy of the power grid operation trend by optimizing the parameters of the LSTM model, and can more accurately capture the nonlinear relationships and dynamic changes in the power grid operation, thereby improving the stability of the model, so that it can adapt to different data sets and tasks and improve the generalization ability of the model.

[0156] like Figure 6 As shown, Figure 6A flowchart of the whale optimization algorithm combined with the LSTM algorithm is provided. The specific process is as follows:

[0157] The figure shows the process of the Whale Optimization Algorithm (WOA) combined with the Long Short-Term Memory Network (LSTM) algorithm to optimize the intelligent analysis and alarm method of key operating indicators of the distribution network OCS system. The following is a detailed description of the flow chart, combined with the technical features in the document:

[0158] (1) Initialization: Randomly generate a group of whale positions, each of which represents a possible hyperparameter combination of the LSTM model. Set the algorithm parameters, such as population size, maximum number of iterations, and the scope of the search space.

[0159] (2) Calculate the fitness value: Use each whale position as a hyperparameter combination of the LSTM model, train the LSTM model, and use the validation set data to evaluate the performance of the model. Calculate the fitness value of each whale based on the performance of the model. In this technical solution, the fitness value may be related to the prediction accuracy of the model, that is, the smaller the error, the higher the fitness value.

[0160] (3) Update position: Adjust the position of the whale according to the update rules of the whale optimization algorithm. These rules usually simulate the hunting behavior of whales, including strategies such as surrounding prey, spiral bubble attack, and searching for prey. By simulating these behaviors, the algorithm can explore the search space and find a better combination of hyperparameters.

[0161] (4) Select the optimal solution: In each iteration, select the whale with the highest fitness value as the current optimal solution, and record its solution and its fitness value. Repeat the process of calculating fitness value, updating position, and selecting the optimal solution until the maximum number of iterations is reached or other stopping conditions are met.

[0162] (5) Output the optimal solution: After a certain number of iterations, the whale optimization algorithm finds the optimal hyperparameter combination. The LSTM model is rebuilt using this hyperparameter combination and evaluated on the test set. The optimal LSTM model and its prediction results are output, which will be used for trend prediction and alarm of key operating indicators of the distribution network.

[0163] This embodiment optimizes the hyperparameters of the LSTM model through the whale optimization algorithm, which can significantly improve the prediction accuracy of the distribution network operation trend; the optimized LSTM model can better adapt to different data sets and tasks, and improve the generalization ability of the model; the automated hyperparameter adjustment process reduces the time of model training and computing resource consumption; the optimized model can adapt to changes in the operating status of the distribution network, and improves the flexibility and adaptability of the system; accurate operation trend prediction results provide strong data support for the operation and maintenance decisions of the distribution network, helping operation and maintenance personnel make more reasonable decisions.

[0164] Further, in some embodiments, step S5 "generating and pushing corresponding alarm information based on the distribution network operation trend prediction result" may specifically include:

[0165] When any operating indicator is detected to exceed the preset threshold based on the distribution network operation trend prediction results, the corresponding alarm information is generated and pushed to the corresponding terminal device of the operation and maintenance personnel;

[0166] After receiving the processing information returned by the operation and maintenance personnel, the operation indicators are re-tested to generate the re-test results;

[0167] If the operating indicator is still beyond the preset threshold value based on the secondary detection result, a secondary alarm message is generated and pushed.

[0168] Specifically, for step S5, after trend prediction of key indicators, in order to facilitate timely processing by operation and maintenance personnel, a corresponding threshold needs to be set for the operation trend. When the operation trend reaches this threshold, the operation and maintenance personnel need to handle it in time so as to respond in time and improve the stability of distribution network power supply.

[0169] For alarm information transmission, the alarm threshold is set first. It does not rely solely on a single indicator to set the threshold, but rather considers multiple key operating indicators. For example, multiple indicators such as terminal online rate, remote control success rate, and fault self-healing time are monitored simultaneously. When multiple indicators exceed the preset threshold range at the same time, the alarm is triggered, which can improve the accuracy and reliability of the alarm. The alarm information includes abnormal indicator prompts and operations that have not been resolved for a long time. In order to prevent the operation and maintenance personnel from missing this alarm, the operation and maintenance personnel are notified by combining visual display, SMS notification, and voice notification.

[0170] For alarm processing and response. When handling alarms, operation and maintenance personnel can export alarm monitoring results according to the problem type, that is, export them according to the key operation indicator analysis results, which can be analyzed more intuitively and facilitated by operation and maintenance personnel. For example: if the remote control success rate is low, the number of remote control failures will inevitably increase. When this number exceeds a certain preset threshold, an alarm will be triggered. For example, if the number of remote control failures exceeds 3 times every 5 minutes, an alarm will be triggered; if the remote control operation is not completed within the specified time, it is considered a timeout. Statistics are kept for the cumulative duration of remote control timeouts over a period of time. If it exceeds the set threshold, an alarm is also required. For example, an alarm is triggered when the average total duration of remote control timeouts per hour exceeds 10 minutes. After the operation and maintenance personnel handle it, the system will detect it again. If there are still indicators that exceed the set threshold, a second alarm will be issued to allow the operation and maintenance personnel to further operate and maintain.

[0171] In a specific embodiment, Figure 7 As shown, Figure 7A flowchart of alarm information transmission and processing is provided. The specific process is as follows:

[0172] The transmission of alarm information is to notify the operation and maintenance personnel through various channels to ensure that they can obtain the alarm information of the distribution network in a timely manner. The alarm threshold is set by comprehensively considering multiple key operating indicators, such as terminal online rate, remote control success rate, fault self-healing time, etc., to improve the accuracy and reliability of the alarm. When the threshold conditions are met, the system generates an alarm message, which includes abnormal indicator prompts and operations that have not been released for a long time. The operation and maintenance personnel are notified through various channels, including visual display in the distribution network OCS system, SMS notification and voice notification, to ensure that the operation and maintenance personnel can be informed of the alarm information in a timely manner.

[0173] After the operation and maintenance personnel handle the alarm, the system will check the relevant indicators again. If the problem still exists, a secondary warning will be issued to ensure that the problem is completely resolved. When the operation and maintenance personnel handle the alarm, the alarm monitoring results can be exported according to the problem type for intuitive analysis. For specific problems, such as low remote control success rate, the system will monitor the number of remote control failures and the cumulative duration of remote control timeouts. When these indicators exceed the preset thresholds, an alarm is triggered. If the operation and maintenance personnel complete the handling of the alarm problem, if the system detects that there are still indicators exceeding the set thresholds, a secondary alarm will be triggered to prompt the operation and maintenance personnel to further operate and maintain.

[0174] Through timely push of alarm information, this embodiment enables operation and maintenance personnel to quickly respond to abnormal conditions in the distribution network and improve processing speed; adaptive threshold adjustment and intelligent alarm suppression reduce false alarms and missed alarms, and improve the accuracy of the alarm system; multi-channel alarm push and context-related information enhance the user experience of operation and maintenance personnel, enabling them to handle alarms more effectively; secondary detection and secondary alarm mechanisms ensure that the system can continuously monitor the status of the distribution network, thereby improving the reliability of the system.

[0175] In order to facilitate understanding of the technical solution of this application, Figure 8 As shown, this embodiment also provides a specific implementation method of a distribution network operation status intelligent monitoring method, which collects data from the distribution network OCS system, uses external interfaces and data call technology to obtain key operation indicator data, uses the empirical mode decomposition (EMD) algorithm for data processing, and then uses the long short-term memory network (LSTM) algorithm for data analysis to grasp the status and trend of key indicators in real time. In order to improve the prediction accuracy and model stability, the whale optimization algorithm (WOA) is introduced to optimize the LSTM model parameters. Finally, by setting the alarm threshold and combining multi-dimensional indicators to trigger the alarm, the operation and maintenance personnel can receive the alarm information through visual display, SMS notification and voice notification, and export the monitoring results according to the problem type for processing. The secondary alarm mechanism ensures that the problem is completely resolved and improves the operating efficiency and reliability of the distribution network.

[0176] The intelligent monitoring method for the operation status of the distribution network provided in this embodiment aims to comprehensively solve multiple problems existing in the key operation indicators of the distribution network, specifically including four aspects: First, in view of the problem of lack of real-time perception means, by increasing the deployment density of sensors, sending requests to the distribution network OCS system to collect data, designing external interfaces and applying data call technology, the real-time perception and information collection of key operation indicators such as terminal online rate, remote control success rate, and fault self-healing time are realized. Secondly, in the face of the lack of analytical statistical tools, slow data processing speed and low accuracy, this embodiment uses the empirical mode decomposition (EMD) algorithm and the LSTM algorithm to process and analyze data respectively, improve the data processing speed and accuracy, accurately obtain the status and trend of key operation indicators, and then establish an effective data analysis model. Third, in order to solve the problem of insufficient prediction ability of power grid operation trend, this embodiment introduces the whale optimization algorithm, uses the whale optimization algorithm to optimize the prediction process, realizes early warning of potential problems, changes the previous situation of lagging response to potential problems, and significantly improves the prediction ability of power grid operation trend. Finally, in order to address the problems of untimely and inadequate alarm information transmission and inconvenient processing, this embodiment ensures that the alarm information can be transmitted in a timely manner by transmitting alarm information including abnormal indicator prompts, long-term unresolved operations, etc. to the distribution network OCS system for visual display, sending text messages and voice notifications to operation and maintenance personnel, etc., and the detection results can be exported by problem type to facilitate intuitive analysis. After the operation and maintenance personnel handle the early warning operation and maintenance, the system checks again. If the indicator still exceeds the threshold, a second warning will be issued, thereby optimizing the alarm processing process and ensuring the reliable operation of the distribution network.

[0177] In summary, this embodiment provides an intelligent monitoring method for the operating status of a distribution network. The method responds to a data call request sent to a distribution network OCS system, and obtains original operating index data corresponding to the distribution network through data call technology; the original operating index data is processed by an empirical mode decomposition algorithm to obtain the processed operating index data; the pre-processed operating index data is analyzed based on a pre-built data analysis model to obtain the operating index trend prediction result corresponding to the distribution network; the long short-term memory network algorithm and the whale optimization algorithm are used to perform predictive optimization processing on the operating index trend prediction result to obtain the distribution network operating trend prediction result; based on the distribution network operating trend prediction result, corresponding alarm information is generated and pushed. The intelligent monitoring solution for the distribution network operation status provided in this embodiment realizes real-time perception and information collection of key operation indicators such as terminal online rate, remote control success rate, fault self-healing time, etc. through data call measurement technology; adopts empirical mode decomposition algorithm for data processing, and uses long short-term memory network algorithm to conduct in-depth analysis of data and establish models, so as to solve the problems of lack of analysis and statistical tools, slow data processing speed and low accuracy in the prior art; introduces whale optimization algorithm, and improves the prediction ability of power grid operation trend by optimizing the prediction model; adopts multiple alarm communication methods to ensure that operation and maintenance personnel can receive alarm information in time.

[0178] In order to facilitate better implementation of the distribution network operation status intelligent monitoring method of the embodiment of the present application, the embodiment of the present application also provides a distribution network operation status intelligent monitoring device. The meanings of the terms are the same as those in the above distribution network operation status intelligent monitoring method, and the specific implementation details can refer to the description in the method embodiment.

[0179] See also Fig. 9 , Fig. 9 A schematic diagram of the structure of the intelligent monitoring device for the operation status of the distribution network provided in an embodiment of the present application, wherein the intelligent monitoring device for the operation status of the distribution network may specifically include a data call module 201, a data processing module 202, a data analysis module 203, a prediction optimization module 204 and an alarm push module 205, which may be specifically as follows:

[0180] The data call test module 201 is used to respond to the data call test request sent to the distribution network OCS system, and obtain the original operation index data corresponding to the distribution network through the data call test technology;

[0181] The data processing module 202 is used to process the original operation index data using an empirical mode decomposition algorithm to obtain the operation index data after data processing;

[0182] The data analysis module 203 is used to analyze the operation index data after data preprocessing based on the pre-built data analysis model to obtain the operation index trend prediction result corresponding to the distribution network;

[0183] The prediction and optimization module 204 is used to use the long short-term memory network algorithm and the whale optimization algorithm to perform prediction and optimization processing on the operation index trend prediction results to obtain the distribution network operation trend prediction results;

[0184] The alarm push module 205 is used to generate and push corresponding alarm information based on the distribution network operation trend prediction results.

[0185] Furthermore, in some embodiments, the data calling module 201 may specifically include:

[0186] A request unit, used to send a data call request to the distribution network OCS system through an external interface, where the data call request includes a target data type and target parameters;

[0187] The data extraction unit is used to respond to the data call request, extract the original operation index data corresponding to the distribution network from the data source through the distribution network OCS system, and filter and aggregate the original operation index data;

[0188] The data return unit is used to return the original operation indicator data after filtering and aggregation to the requester through the external interface.

[0189] Further, in some embodiments, the data processing module 202 can be specifically used to: perform data preprocessing on the original operating index data; use the original operating index data after data preprocessing as the initialization signal sequence, and set the parameters of the empirical mode decomposition algorithm; perform extreme point detection on the initialization signal sequence to obtain and record the extreme points corresponding to each operating index data sequence; based on the extreme points corresponding to each operating index data sequence, construct corresponding upper and lower envelopes and calculate the corresponding mean envelope; subtract the mean envelope from the original operating index data to obtain the target data sequence; perform iterative decomposition processing on the target data sequence to obtain the empirical mode decomposition result corresponding to the original operating data.

[0190] Furthermore, in some embodiments, the data analysis module 203 may specifically include:

[0191] A feature extraction unit, used to obtain the operating index features corresponding to the operating index data after data preprocessing;

[0192] The analysis unit is used to input the operating indicator characteristics into a pre-built data analysis model, and output the operating indicator trend prediction results corresponding to various operating indicators in the distribution network. The operating indicator trend prediction results include the real-time status of the operating indicator and the corresponding trend prediction results.

[0193] Furthermore, in some embodiments, a model building module may also be included, which is specifically used to: obtain historical operating indicator data of the distribution network and perform data preprocessing to obtain training set data and test set data; define the network structure of the long short-term memory network algorithm and configure the parameters of the data analysis model to build an initial data analysis model; train the initial data analysis model based on the training set data to obtain a trained data analysis model; evaluate the trained data analysis model based on the test set data, and optimize the model according to the evaluation results to obtain a final data analysis model; and regularly update and iterate the data analysis model.

[0194] Further, in some embodiments, the prediction optimization module 204 is specifically used to: randomly generate a group of whale positions, each position represents a hyperparameter combination of the long short-term memory network algorithm model, and set the parameters of the whale optimization algorithm; use each whale position as a hyperparameter combination of the long short-term memory network algorithm model, train the long short-term memory network algorithm model, and use the validation set data to evaluate the performance of the model; calculate the fitness value of each whale according to the performance of the long short-term memory network algorithm model; adjust the position of the whale according to the update rule of the whale optimization algorithm; in each iteration, select the whale with the highest fitness value as the current optimal solution, and record the optimal solution and its fitness value; repeat the process of calculating the fitness value, updating the position and selecting the optimal solution until the preset conditions are met; after a preset number of iterations, determine the optimal hyperparameter combination through the whale optimization algorithm; use the optimal parameter combination to reconstruct the long short-term memory network algorithm model, and evaluate it based on the test set to obtain the model evaluation result; based on the model evaluation result, determine the optimal long short-term memory network algorithm model and its prediction result.

[0195] Further, in some embodiments, the alarm push module 205 may specifically include:

[0196] The first alarm unit is used to generate corresponding alarm information and push it to the corresponding terminal device of the operation and maintenance personnel after detecting that any operation indicator exceeds a preset threshold based on the distribution network operation trend prediction result;

[0197] The secondary detection unit is used to perform secondary detection on the operation indicators and generate secondary detection results after receiving the processing information returned by the operation and maintenance personnel;

[0198] The second alarm unit is used to generate and push secondary alarm information if it is detected based on the secondary detection result that the operating index still exceeds the preset threshold.

[0199] To summarize, the intelligent monitoring device for the operation status of the distribution network provided in this embodiment responds to the data call request sent to the distribution network OCS system through the data call module 201, and obtains the original operation index data corresponding to the distribution network through the data call technology; the data processing module 202 uses the empirical mode decomposition algorithm to process the original operation index data to obtain the operation index data after data processing; the data analysis module 203 performs data analysis on the operation index data after data preprocessing based on a pre-built data analysis model to obtain the operation index trend prediction result corresponding to the distribution network; the prediction optimization module 204 uses the long short-term memory network algorithm and the whale optimization algorithm to perform prediction and optimization processing on the operation index trend prediction result to obtain the distribution network operation trend prediction result; the alarm push module 205 generates corresponding alarm information based on the distribution network operation trend prediction result and pushes it. It can be seen that the intelligent monitoring device for the operation status of the distribution network provided in this embodiment realizes real-time perception and information collection of key operation indicators such as terminal online rate, remote control success rate, fault self-healing time, etc. through data call technology; adopts empirical mode decomposition algorithm for data processing, and uses long short-term memory network algorithm to conduct in-depth analysis of data and establish models, so as to solve the problems of lack of analysis and statistical tools, slow data processing speed and low accuracy in the prior art; introduces the whale optimization algorithm, and improves the prediction ability of power grid operation trend by optimizing the prediction model; adopts a variety of alarm communication methods to ensure that operation and maintenance personnel can receive alarm information in time.

[0200] In addition, the present application also provides an electronic device, such as Fig.10 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application. Specifically, the electronic device may include a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, an input unit 304 and other components. Those skilled in the art can understand that Fig.10 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0201] The processor 301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0202] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and the intelligent monitoring method of the operation status of the power distribution network by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0203] The electronic device also includes a power supply 303 for supplying power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so as to manage charging, discharging, power consumption and other functions through the power management system. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0204] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0205] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0206] In response to the data call request sent to the distribution network OCS system, the original operation index data corresponding to the distribution network is obtained through the data call technology; the original operation index data is processed by the empirical mode decomposition algorithm to obtain the operation index data after data processing; the operation index data after data preprocessing is analyzed based on the pre-built data analysis model to obtain the operation index trend prediction results corresponding to the distribution network; the operation index trend prediction results are predicted and optimized by the long short-term memory network algorithm and the whale optimization algorithm to obtain the distribution network operation trend prediction results; based on the distribution network operation trend prediction results, the corresponding alarm information is generated and pushed.

[0207] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0208] The embodiment of the present application uses data call detection technology to achieve real-time perception and information collection of key operating indicators such as terminal online rate, remote control success rate, and fault self-healing time; adopts empirical mode decomposition algorithm for data processing, and uses long short-term memory network algorithm to conduct in-depth analysis of data and establish models, so as to solve the problems of lack of analysis and statistical tools, slow data processing speed and low accuracy in the prior art; introduces whale optimization algorithm, and improves the prediction ability of power grid operation trend by optimizing prediction model; adopts multiple alarm communication methods to ensure that operation and maintenance personnel can receive alarm information in time.

[0209] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0210] To this end, an embodiment of the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the methods for intelligently monitoring the operating status of a distribution network provided in the embodiment of the present application. For example, the instructions can execute the following steps:

[0211] In response to the data call request sent to the distribution network OCS system, the original operation index data corresponding to the distribution network is obtained through the data call technology; the original operation index data is processed by the empirical mode decomposition algorithm to obtain the operation index data after data processing; the operation index data after data preprocessing is analyzed based on the pre-built data analysis model to obtain the operation index trend prediction results corresponding to the distribution network; the operation index trend prediction results are predicted and optimized by the long short-term memory network algorithm and the whale optimization algorithm to obtain the distribution network operation trend prediction results; based on the distribution network operation trend prediction results, the corresponding alarm information is generated and pushed.

[0212] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0213] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. Since the instructions stored in the storage medium can execute the steps in any of the distribution network operation status intelligent monitoring methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the distribution network operation status intelligent monitoring methods provided in the embodiments of the present application can be achieved. For details, please refer to the previous embodiments and will not be repeated here.

[0214] The above is a detailed introduction to a distribution network operation status intelligent monitoring method, device, electronic device and storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for intelligently monitoring the operation status of a distribution network, characterized in that: The steps include: Respond to the data call request sent to the distribution network OCS system, and obtain the original operating indicator data corresponding to the distribution network through the data call technology; Using an empirical mode decomposition algorithm to process the original operating index data to obtain processed operating index data; Performing data analysis on the pre-processed operation index data based on a pre-built data analysis model to obtain an operation index trend prediction result corresponding to the distribution network; The long short-term memory network algorithm and the whale optimization algorithm are used to perform prediction and optimization processing on the operation index trend prediction results to obtain the distribution network operation trend prediction results; Based on the distribution network operation trend prediction results, corresponding alarm information is generated and pushed.

2. The method for intelligently monitoring the operation status of a distribution network according to claim 1, characterized in that: The responding to the data call request sent to the distribution network OCS system, and obtaining the original operation index data corresponding to the distribution network through the data call technology, includes: Send a data call test request to the distribution network OCS system through an external interface, wherein the data call test request includes a target data type and a target parameter; In response to the data call request, the distribution network OCS system extracts the original operation index data corresponding to the distribution network from the data source, and filters and aggregates the original operation index data; The original operation indicator data after filtering and aggregation is returned to the requester through the external interface.

3. The method for intelligently monitoring the operation status of a distribution network according to claim 1, characterized in that: The adopting of the empirical mode decomposition algorithm to process the original operation index data to obtain the operation index data after data processing includes: Performing data preprocessing on the original operation indicator data; The original operating index data after data preprocessing is used as the initialization signal sequence, and the parameters of the empirical mode decomposition algorithm are set; Perform extreme point detection on the initialization signal sequence to obtain and record the extreme point corresponding to each operation indicator data sequence; Based on the extreme value points corresponding to each of the operation indicator data sequences, corresponding upper and lower envelopes are constructed and corresponding mean envelopes are calculated; Subtracting the mean envelope from the original operating index data to obtain a target data sequence; The target data sequence is iteratively decomposed to obtain an empirical mode decomposition result corresponding to the original operating data.

4. The method for intelligently monitoring the operation status of a distribution network according to claim 1, characterized in that: The pre-built data analysis model is used to analyze the pre-processed operation index data to obtain the operation index trend prediction result corresponding to the distribution network, including: Obtaining the operating indicator characteristics corresponding to the operating indicator data after the data preprocessing; The operating indicator characteristics are input into a pre-built data analysis model, and the operating indicator trend prediction results corresponding to the various operating indicators in the distribution network are output, wherein the operating indicator trend prediction results include the real-time status of the operating indicator and the corresponding trend prediction results.

5. The method for intelligently monitoring the operation status of a distribution network according to claim 1, characterized in that: The data analysis model is constructed in a manner including: Obtain historical operating indicator data of the distribution network and perform data preprocessing to obtain training set data and test set data; Define the network structure of the long short-term memory network algorithm and configure the parameters of the data analysis model to build the initial data analysis model; Training the initial data analysis model based on the training set data to obtain a trained data analysis model; Evaluate the trained data analysis model based on the test set data, and optimize the model according to the obtained evaluation results to obtain a final data analysis model; The data analysis model is updated and iterated regularly.

6. The method for intelligently monitoring the operation status of a distribution network according to claim 1, characterized in that: The long short-term memory network algorithm and the whale optimization algorithm are used to perform prediction optimization processing on the operation index trend prediction results to obtain the distribution network operation trend prediction results, including: Randomly generate a group of whale positions, each position represents a hyperparameter combination of the LSTM algorithm model, and set the parameters of the whale optimization algorithm; Using each whale position as a hyperparameter combination of the long short-term memory network algorithm model, training the long short-term memory network algorithm model, and using the validation set data to evaluate the performance of the model; Calculate the fitness value of each whale based on the performance of the LSTM algorithm model; Adjust the position of the whale according to the update rules of the whale optimization algorithm; In each iteration, the whale with the highest fitness value is selected as the current optimal solution, and the optimal solution and its fitness value are recorded; Repeat the process of calculating fitness value, updating position and selecting the optimal solution until the preset conditions are met; After a preset number of iterations, the optimal hyperparameter combination is determined by the whale optimization algorithm; Reconstructing the long short-term memory network algorithm model using the optimal parameter combination, and evaluating it based on the test set to obtain a model evaluation result; Based on the model evaluation results, the optimal long short-term memory network algorithm model and its prediction results are determined.

7. The method for intelligently monitoring the operation status of a distribution network according to claim 1, characterized in that: The generating and pushing corresponding alarm information based on the distribution network operation trend prediction result includes: After any operating indicator is detected to exceed a preset threshold based on the distribution network operation trend prediction result, a corresponding alarm message is generated and pushed to the corresponding terminal device of the operation and maintenance personnel; After receiving the processing information returned by the operation and maintenance personnel, performing a secondary test on the operation indicator to generate a secondary test result; If it is detected based on the secondary detection result that the operating indicator still exceeds the preset threshold, a secondary alarm message is generated and pushed.

8. An intelligent monitoring device for the operation status of a distribution network, characterized in that: include: The data call test module is used to respond to the data call test request sent to the distribution network OCS system and obtain the original operation indicator data corresponding to the distribution network through the data call test technology; A data processing module, used to process the original operation index data using an empirical mode decomposition algorithm to obtain the operation index data after data processing; A data analysis module is used to analyze the operation index data after data preprocessing based on a pre-built data analysis model to obtain the operation index trend prediction result corresponding to the distribution network; A prediction and optimization module, used to use a long short-term memory network algorithm and a whale optimization algorithm to perform prediction and optimization processing on the operation indicator trend prediction results to obtain a distribution network operation trend prediction result; The alarm push module is used to generate and push corresponding alarm information based on the distribution network operation trend prediction result.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for intelligently monitoring the operating status of a distribution network as described in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method for intelligently monitoring the operating status of a distribution network as described in any one of claims 1 to 7.

Images