Electric power marketing digital inspection method and system
By obtaining real-time power data and using preset audit models to identify potential abnormal behaviors, the problem of limited accuracy of power usage inspection in the prior art is solved, and efficient identification of complex power usage situations and reduction of power losses are achieved.
Patent Information
- Application Number
- CN202411531116.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-30
- Publication Date
- 2025-02-25
AI Technical Summary
The accuracy of power consumption inspection in existing power marketing inspections is limited, resulting in increased power loss. Especially when faced with complex and changing power consumption, it is difficult for the existing technology to effectively identify potential abnormal behaviors.
By obtaining real-time power data feedback from smart meter and sensors at key nodes of the power grid, a preset audit model is used to identify potential abnormal behaviors, and corresponding power adjustment measures are triggered according to the behavior type.
It improves the accuracy of power marketing audits, can be applied to complex and changeable electricity usage, quickly identify potential abnormal behaviors, reduce power losses, and reduce economic losses through timely power adjustment measures.
Smart Images

Figure CN119513760A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of power marketing technology, and in particular to a power marketing digital audit method and system. Background Art
[0002] Power companies play a vital role in my country's economic and social development. With the continuous development of the market economy and technological advancement, power companies are facing new challenges and opportunities. Power marketing is an important part of the development of power companies. It not only affects the economic benefits of power companies, but also directly affects the power experience of the majority of users and the stable operation of society.
[0003] The power marketing audit mainly revolves around direct marketing business related to "quantity, price, and fee". The key is a process that targets the implementation of various marketing policies, as well as electricity prices and charges, electricity consumption inspections, and electric energy calculations.
[0004] At present, the electricity consumption inspection in the power marketing audit in the existing technology is mainly completed by presetting a series of rules. For example, to determine whether there are potential abnormal behaviors such as electricity theft or illegal power supply in the power data, it will be determined by comparing with the normal thresholds preset for different potential abnormal behaviors. However, this method is easily affected by the rule setting, and has limited accuracy when facing complex and changeable electricity consumption situations, resulting in increased power losses for power companies. Summary of the invention
[0005] In view of the above problems, the present application provides a method and system for digital auditing of power marketing, the main purpose of which is to improve the accuracy of power marketing auditing and reduce power losses.
[0006] In order to solve the above technical problems, this application proposes the following solutions:
[0007] In a first aspect, the present application provides a method for digital auditing of power marketing, the method comprising:
[0008] Acquire real-time power data of a specified area, wherein the real-time power data includes real-time power consumption data fed back by smart meters and real-time power transmission data fed back by sensors installed at key nodes of the power grid;
[0009] Obtaining an audit result corresponding to the real-time power data using a preset audit model, wherein the audit model is used to identify potential abnormal behaviors corresponding to the real-time power data;
[0010] If the potential abnormal behavior exists in the audit result, corresponding power adjustment measures are triggered according to the behavior type corresponding to the potential abnormal behavior.
[0011] In a second aspect, the present application provides a power marketing digital audit system, the system comprising:
[0012] An acquisition module is used to acquire real-time power data of a specified area, wherein the real-time power data includes real-time power consumption data fed back by smart meters and real-time power transmission data fed back by sensors installed at key nodes of the power grid;
[0013] An audit module, used to obtain an audit result corresponding to the real-time power data using a preset audit model, wherein the audit model is used to identify potential abnormal behaviors corresponding to the real-time power data;
[0014] The processing module is used to trigger corresponding power adjustment measures according to the behavior type corresponding to the potential abnormal behavior if the potential abnormal behavior exists in the audit result.
[0015] In order to achieve the above-mentioned purpose, according to the third aspect of the present application, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the power marketing digital audit method of the above-mentioned first aspect.
[0016] In order to achieve the above-mentioned purpose, according to the fourth aspect of the present application, a processor is provided, wherein the processor is used to run a program, wherein the power marketing digital audit method of the above-mentioned first aspect is executed when the program is running.
[0017] By means of the above technical scheme, a method and system for digital auditing of power marketing provided by the present application is to obtain real-time power data including real-time power consumption data fed back by smart meters and real-time power transmission data fed back by sensors installed at key nodes of the power grid in a specified area when digital auditing of power marketing is required, and to obtain audit results corresponding to the real-time power data by using a preset audit model, that is, to identify potential abnormal behaviors corresponding to the real-time power data, and if there are potential abnormal behaviors in the audit results, trigger corresponding power adjustment measures according to the behavior type corresponding to the potential abnormal behaviors. Through the technical scheme provided by the present application, it is possible to use the audit model trained based on the characteristic performance of historical power consumption data and historical power transmission data in the specified area to identify potential abnormal behaviors in the specified area, so that the potential abnormal behavior inspection can be applied to complex and changeable power consumption situations, and accurately and quickly identify potential abnormal behaviors, thereby improving the accuracy of power marketing audits, and at the same time, when there are potential abnormal behaviors, corresponding power adjustment measures are executed according to the behavior type, thereby effectively reducing the power losses of power companies.
[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0020] Figure 1 A flow chart of a power marketing digital audit method provided in an embodiment of the present application is shown;
[0021] Figure 2 Another flow chart of a digital audit method for power marketing provided by an embodiment of the present application is shown;
[0022] Figure 3 A block diagram of a power marketing digital audit system provided by an embodiment of the present application is shown;
[0023] Figure 4 A block diagram of another power marketing digital audit system provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0024] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to enable the scope of the present application to be fully conveyed to those skilled in the art.
[0025] At present, the electricity consumption inspection in the power marketing audit in the existing technology is mainly completed by presetting a series of rules. For example, to determine whether there are potential abnormal behaviors such as electricity theft or illegal power supply in the power data, it will be determined by comparing with the normal thresholds preset for different potential abnormal behaviors. However, this method is easily affected by the rule setting, and has limited accuracy when facing complex and changeable electricity consumption situations, resulting in increased power losses for power companies.
[0026] Based on the above problems, the embodiment of the present application provides a method for digital auditing of power marketing, which can improve the accuracy of power marketing auditing and reduce power loss. The specific execution steps are as follows: Figure 1 As shown, including at least:
[0027] 101. Obtain real-time power data for a specified area.
[0028] Among them, real-time power data includes real-time power consumption data fed back by smart meters and real-time power transmission data fed back by sensors installed at key nodes of the power grid.
[0029] In this step, the designated area can be any specific geographical area or part of the power network in the power system, including but not limited to urban areas (such as commercial areas, industrial areas or residential areas in cities), administrative divisions (such as provinces, cities, counties or towns), designated communities or communities (such as a closed community or commercial complex), and designated power grids (such as the service area covered by a substation).
[0030] Real-time power consumption data, including but not limited to power consumption and power consumption patterns, are automatically collected through all smart meters in the designated area. At the same time, corresponding sensors are pre-installed at key nodes of the power grid (such as substations, line intersections, etc.) in the designated area to collect real-time power transmission data, including but not limited to current, voltage, power factor, etc. It should be noted that the collection frequency can be customized according to actual needs, such as collecting data every quarter hour or every half hour, to ensure the real-time and accuracy of power data.
[0031] 102. Use the preset audit model to obtain the audit results corresponding to the real-time power data.
[0032] Among them, the audit model is used to identify potential abnormal behaviors corresponding to real-time power data based on the characteristic performance of real-time power consumption data and real-time power transmission data.
[0033] In this step, the audit model is pre-trained with historical power data. The historical data can be the historical power data within the most recent preset period. The preset period can be customized according to actual needs, and the selected historical power data is the historical power consumption data fed back by the smart meters in the specified area and the historical power transmission data fed back by the sensors installed at the key nodes of the power grid. It should be noted that the selected historical power data is determined by feature analysis and includes historical power consumption data and historical power transmission data under normal and abnormal conditions. A machine learning algorithm (such as support vector machine, neural network, etc.) is used to build an audit model so that it can learn the characteristics of normal behavior and potential abnormal behavior from historical power data. Specifically, features related to normal behavior and abnormal behavior can be extracted from historical power consumption data and historical power transmission data, such as learning consumption features from real-time power consumption data to distinguish normal consumption from abnormal consumption, and learning transmission features from historical power transmission data to distinguish normal transmission from abnormal transmission. The consumption features include but are not limited to power consumption, power consumption mode, etc., and the transmission features include but are not limited to average power, peak power, voltage fluctuation and current anomaly, etc. Therefore, the corresponding potential abnormal behaviors can be accurately identified based on the learned consumption characteristics and transmission characteristics, and the potential abnormal behaviors include but are not limited to electricity theft and illegal power supply.
[0034] It should be noted that the audit model in this embodiment outputs the audit result only when it is determined that there is a potential abnormal behavior, and does not output it when it is determined that there is no potential abnormal behavior. Specifically, a decision logic can be set at the output stage of the audit model, such as setting a judgment threshold for the probability of the existence of potential abnormal behavior. When the probability of the existence of potential abnormal behavior is greater than the judgment threshold, the potential abnormal behavior is considered to be truly present, and the behavior type of the potential abnormal behavior with a probability greater than the judgment threshold and the judgment of the existence of potential abnormal behavior are used as the final audit result and output.
[0035] After obtaining the real-time power consumption data and the real-time power transmission data, the two are input into the audit model to obtain the corresponding audit result, which includes the judgment of the existence of potential abnormal behavior and the behavior type of the potential abnormal behavior, so as to execute step 103.
[0036] 103. If there is potential abnormal behavior in the audit results, the corresponding power adjustment measures will be triggered according to the behavior type corresponding to the potential abnormal behavior.
[0037] According to the information in the audit results, the specific behavior types of potential abnormal behaviors are identified, including but not limited to electricity theft and illegal power supply. According to the identified behavior types, the corresponding power adjustment measures are triggered, and the power adjustment measures are used to characterize the power supply control measures of the power system to abnormal power consumption or abnormal power supply. Exemplarily, for power theft, temporary power restriction measures can be taken, such as limiting power consumption within a set time, adjusting power supply frequency or voltage, etc. For illegal power supply, temporary power outage measures can be taken, such as stopping power supply within a set time. It should be emphasized that the power adjustment measures can be set according to actual conditions to ensure that potential abnormal behaviors can be effectively handled without excessively affecting normal power supply. Specifically, a detection mechanism for continuously triggering potential abnormal behaviors can be set, that is, measures are taken only when the same abnormal behavior is detected multiple times, so as to avoid excessive sensitivity of power adjustment and affect the stability of the power system, while effectively reducing the power loss of power companies in the power system.
[0038] Based on the above Figure 1It can be seen from the implementation method that the digital audit method for power marketing provided by the present application is to obtain the real-time power data including the real-time power consumption data fed back by the smart meter and the real-time power transmission data fed back by the sensors installed at the key nodes of the power grid in the specified area when it is necessary to conduct a digital audit on power marketing, and use the preset audit model to obtain the audit result corresponding to the real-time power data, that is, to identify the potential abnormal behavior corresponding to the real-time power data. If there is potential abnormal behavior in the audit result, the corresponding power adjustment measures are triggered according to the behavior type corresponding to the potential abnormal behavior. Through the technical solution provided by the present application, the audit model trained based on the characteristic performance of the historical power consumption data and the historical power transmission data in the specified area can be used to identify the potential abnormal behavior in the specified area, so that the potential abnormal behavior inspection can be applicable to complex and changeable power consumption conditions, and the potential abnormal behavior can be accurately and quickly identified, thereby improving the accuracy of power marketing audits. At the same time, when there is potential abnormal behavior, the corresponding power adjustment measures are executed according to the behavior type, thereby effectively reducing the power loss of power companies.
[0039] Further, the preferred embodiment of the present application is in the above Figure 1 Based on this, a detailed description of the process of digital auditing of power marketing is given. The specific steps are as follows: Figure 2 As shown, including:
[0040] 201. Obtain historical power data of a specified area.
[0041] Among them, historical electricity data includes historical electricity consumption data fed back by smart meters and historical electricity transmission data fed back by sensors installed at key nodes of the power grid.
[0042] In this step, combined with the description of the designated area in step 101, after the designated area is determined, the historical power consumption data and historical power transmission data of the most recent preset period can be extracted from the data collection records of the smart meters and sensors of the key nodes in the designated area. The preset period can be customized according to the actual power situation in the designated area, such as one month or one quarter.
[0043] 202. Extract consumption characteristics corresponding to historical power consumption data and transmission characteristics corresponding to historical power transmission data respectively.
[0044] In this step, the consumption feature is a feature that reflects the change in the power consumption or power consumption mode within a unit time, while the transmission feature is a feature that reflects the change in the transmission of current, voltage, and power factor within a unit time. After obtaining the historical power consumption data and historical power transmission data, we can use the expertise in the power field or correlation analysis to determine which features are most relevant to potential abnormal behaviors, and use these features as features to be extracted.
[0045] In actual environments, users may bypass smart meters and connect to electricity directly, which will cause the electricity consumption records to be inconsistent with the actual electricity consumption. In other words, sudden changes in electricity consumption (such as a significant decrease or increase) may be a sign of electricity theft. In addition, users' electricity consumption patterns usually have a certain regularity, such as the difference in electricity consumption between weekdays and weekends, and electricity theft may cause this pattern to change. Illegal power supply usually refers to unauthorized power supply to a third party, that is, there is additional power use, which may also cause an abnormal increase in a user's electricity consumption. In addition, if the key nodes of the power grid find that the current suddenly decreases or increases in a certain period of time, or that the voltage fluctuates frequently or abnormally fluctuates during abnormal time periods, etc., there may be electricity theft, and illegal power supply may also cause abnormal current increases or voltage fluctuations in the power grid. Therefore, changes in power consumption or power consumption patterns can be used as consumption characteristics, and changes in current, voltage fluctuations, and power factor changes can be used as transmission characteristics. Specifically, consumption characteristics can be extracted from historical power consumption data, and transmission characteristics can be extracted from historical power transmission data. Data preprocessing is performed using methods such as Z-score standardization or minimum and maximum scaling to obtain standardized consumption characteristics and transmission characteristics to execute subsequent step 203.
[0046] 203. Analyze the consumption characteristics and transmission characteristics for potential abnormal behaviors, and mark the historical power data positively or negatively based on the analysis results.
[0047] In this step, cluster analysis, principal component analysis or anomaly detection algorithms can be used to analyze consumption characteristics and transmission characteristics to identify potential abnormal behaviors. According to the obtained analysis results, the normal data and abnormal data in the historical power data are determined. Normal data means data without potential abnormal behaviors, and abnormal data means data with potential abnormal behaviors. Among them, positive and negative marking refers to marking normal data and abnormal data in historical power data with behavior types. For normal data, "no abnormality" can be used as a behavior type for marking. For abnormal data, since there are many types of potential abnormal behaviors, such as electricity theft, illegal power supply, etc., different behavior types such as "electricity theft" and "illegal power supply" can be used to mark them separately.
[0048] 204. The audit model corresponding to the designated area is trained using the marked historical power data so that the audit model can identify potential abnormal behaviors.
[0049] In this step, a suitable machine learning model can be selected as the audit model according to the nature of the problem, and specifically, logistic regression, support vector machine, random forest or deep learning model can be selected. Since there are many types of potential abnormal behaviors in this embodiment, in order to accurately realize multi-classification prediction and recognition, the convolutional neural network model in the deep neural model is preferably used as the audit model.
[0050] Since the historical power data already includes normal data marked as "no abnormality" behavior type, as well as abnormal data of different behavior types such as "electricity theft" and "illegal power supply". Therefore, the historical power data marked as different behavior types can be used as training samples, and the training samples can be divided into training sets and test sets. The samples of different behavior types in the training sets and test sets are reasonably distributed. The audit model is trained using the training set. Specifically, cross-validation can be used to improve the generalization ability of the audit model. At the same time, the performance of the audit model is evaluated on the test set, and the audit model parameters are continuously adjusted according to the evaluation results to ensure the accuracy of the audit model. After the audit model is trained, a model library can be preset to store the audit model, and a unique identifier can be assigned to the audit model so that it can be called in the subsequent audit process based on real-time power data.
[0051] As an example, the construction process of using a convolutional neural network model as an audit model is as follows:
[0052] The convolutional neural network model consists of an input layer, a convolutional layer, and an output layer.
[0053] The input layer is used to receive the original input of historical power data. Specifically, the historical power data can be converted into a time series vector of a fixed length, for example, the hourly power consumption and power consumption pattern in the past week.
[0054] The convolution layer is used to extract features from historical power data, namely consumption features and transmission features. It captures the features of power consumption and power consumption patterns included in historical power consumption data, as well as the features of voltage, current, and power factor included in historical power transmission data by applying a series of convolution kernels to the historical power data. Due to the large number of features, multi-channel convolution can be used, that is, each feature is transmitted through a different channel to capture the complex relationship between features such as power consumption, power consumption patterns, voltage, current, and power factor in the time series.
[0055] The output layer is used to extract the features of power consumption, power consumption mode, voltage, current and power factor based on the convolution layer for final classification, so as to realize anomaly detection. Since the historical power data has been marked with multiple behavior types such as "no abnormality", "electricity theft" and "illegal power supply", in order to identify the multiple behavior types, the output layer is specifically a softmax layer, which is used to convert the output into the existence probability of each behavior type, and the number of outputs is equal to the number of types of behavior types. Since the existence probability of the abnormal behavior type "electricity theft" or "illegal power supply" is usually exclusive with the existence probability of the normal behavior type "no abnormality", that is, when the existence probability of "electricity theft" or "illegal power supply" is very low, the existence probability of "no abnormality" will be very high. Then it is meaningless to still output the corresponding audit result at this time. Therefore, in order to reduce the output interference of the normal behavior type "no abnormality", an output decision logic is also deployed in the output layer, which is used to determine whether the corresponding potential abnormal behavior is output as the final audit result according to the existence probability. Specifically, a judgment threshold of the existence probability can be set, and the existence probability of each behavior type can be compared with the judgment threshold. If the probability of occurrence of the potential abnormal behavior is higher than the judgment threshold, it is determined that the potential abnormal behavior is real. At this time, the behavior type of the potential abnormal behavior with an existence probability greater than the judgment threshold and the judgment of the existence of the potential abnormal behavior are taken as the final audit result and output.
[0056] 205. Build the association between the specified area and the audit model.
[0057] In this step, based on the description of the designated area in step 101, it can be known that the designated area has clear boundaries and scopes. Specifically, a database or file system can be used to store relevant information of the designated area, including the area name, geographical location, list of smart meters and sensors included, etc. A unique identifier is assigned to each designated area. The above-mentioned audit model is trained and optimized corresponding to the actual power consumption of the designated area, which means that the accuracy of the audit model can only be guaranteed when it is used in the designated area. Therefore, the unique identifier of the audit model can be associated with the unique identifier of the designated area and stored, and a table or field is created in the database to record this association. In the subsequent audit based on real-time power data, the designated area to which the real-time power data belongs is first determined based on the identifier of the source of the real-time power data, and then the corresponding audit model is called from the model library through the unique identifier of the designated area. Thereby ensuring the accuracy and efficiency of identifying potential abnormal behaviors in the designated area.
[0058] In addition, corresponding audit models can be set for different areas and called through the above method. Especially when new areas need to be added in the future, it is only necessary to train the corresponding audit model and associate it with the new area, which improves the flexibility and scalability of the overall audit.
[0059] Exemplarily, assuming that the designated area is a commercial area, and its identifier is Region_ID:001, a table Regions is created in the database, and relevant information is entered for the commercial area of Region_ID:001. In the model library, an audit model is trained and saved for Region_ID:001, and its identifier is Model_ID. A table Models is created in the database, containing fields Model_ID, Region_ID, Model_Path, etc. Model_Path refers to the file path of Region_ID, for example / models / Region_001 / model_v1.pkl. When real-time power data is collected from the commercial area of Region_ID:001, first query the Regions table to confirm which region the real-time power data belongs to, and then query the Model_Path in the Models table according to Region_ID to find the file path of the corresponding audit model, and determine its storage location, and finally load the model file from the storage location to apply the audit model to identify potential abnormal behaviors of real-time power data.
[0060] 206. Obtain real-time power data for a specified area.
[0061] This step is combined with the description of step 101 in the above method, and the same contents will not be repeated here.
[0062] 207. Use the preset audit model to obtain the audit results corresponding to the real-time power data.
[0063] This step is combined with the description of step 102 in the above method, and the same content is not repeated here. It should be noted that the specific execution process of using the preset audit model to obtain the audit result corresponding to the real-time power data is: determine the audit model corresponding to the specified area according to the association relationship; input the real-time power data into the audit model to obtain the audit result corresponding to the real-time power data.
[0064] According to the description of the association relationship in step 105, the audit model corresponding to the specified area can be found by querying the association relationship. After determining the audit model, the real-time power data can be preprocessed as necessary, such as data cleaning, missing value processing, etc. The preprocessed real-time power data is input into the loaded audit model to generate an audit result, which includes the judgment of whether there is potential abnormal behavior and the behavior type of potential abnormal behavior.
[0065] 208. Determine an abnormal power consumption end based on abnormal smart meters and / or abnormal key nodes related to potential abnormal behaviors, or determine an abnormal power supply end based on abnormal smart meters and / or abnormal key nodes related to potential abnormal behaviors.
[0066] In this step, since the real-time power data is derived from smart meters in the specified area or sensors installed at key nodes of the power grid. Therefore, when it is determined that there is potential abnormal behavior, the location where the potential abnormal behavior occurs may be a smart meter or a key node. Therefore, the smart meter or key node where the potential abnormal behavior occurs is confirmed as an abnormal smart meter or an abnormal key node, and the specific location is determined based on the location information of the abnormal smart meter or the abnormal key node. Exemplarily, the abnormal power consumption end or abnormal power supply end is quickly located by combining geographic information system (GIS) technology and the ID or location information of the abnormal smart meter or abnormal key node.
[0067] 209. If the behavior type is electricity theft, an abnormal electricity usage alarm instruction corresponding to the abnormal electricity user is triggered, and temporary power restriction is performed on the abnormal electricity user when the abnormal electricity usage alarm instruction is continuously triggered.
[0068] In this step, when the audit result shows that the behavior type is electricity theft, the abnormal power consumption alarm instruction is automatically triggered. Specifically, the alarm instruction can be sent to the power dispatching system in the form of a message queue or direct notification, and the alarm instruction is monitored to see whether it is received and confirmed by the power dispatching system. At the same time, a continuous alarm number threshold is set. When the number threshold is reached, the temporary power restriction process is initiated for the abnormal power consumption end.
[0069] Since electricity theft usually involves illegal electricity use by bypassing smart meters, this will cause economic losses to power companies. Temporary power restrictions can reduce illegal electricity use without affecting normal users, thereby reducing economic losses to power companies. Power restrictions can maintain the stable operation of the power grid to a certain extent and avoid the imbalance of power supply and demand caused by electricity theft. Therefore, when it is determined to start the temporary power restriction processing process, the power supply can be adjusted through the remote control system, that is, a temporary power restriction instruction is sent to the power dispatching system to limit the power supply of abnormal power users. The temporary power restriction instruction includes the start time and end time of the power restriction and the corresponding power restriction method. The power restriction method includes limiting the power consumption of abnormal power users or adjusting the power supply frequency or voltage. In addition, the abnormal power usage alarm instruction can also be sent directly to the abnormal power user to prompt it that there is potential abnormal behavior. For example, if there is electricity theft in the smart meter of a family, the abnormal power usage alarm instruction can be sent to the owner.
[0070] 210. If the behavior type is illegal power supply behavior, the abnormal power supply alarm instruction corresponding to the abnormal power supply end is triggered, and the abnormal power supply end is temporarily powered off when the abnormal power supply alarm instruction is continuously triggered.
[0071] In this step, when the audit result shows that the behavior type is illegal power supply behavior, the abnormal power supply alarm instruction is automatically triggered. As in step 209, the alarm instruction is sent to the power dispatching system through a message queue or direct notification, and the alarm instruction is monitored to see whether it is received and confirmed by the power dispatching system. A continuous alarm number threshold is set, and when the number threshold is reached, the temporary power outage processing flow is started.
[0072] Since illegal power supply usually refers to supplying power to a third party without permission, this may lead to instability of the power grid structure and even cause safety accidents. Illegal power supply violates power regulations and must be strictly stopped. Therefore, when it is determined to initiate the temporary power outage process, the power supply to the abnormal power supply end can be completely cut off through the remote control system, that is, a temporary power outage instruction is sent to the power dispatching system to cut off the power supply to the abnormal power supply end. The temporary power outage instruction includes the start time of the power outage and the expected recovery time.
[0073] It should be noted that the use of power rationing to deal with electricity theft and power outages to deal with illegal power supply are based on the different impacts of the two potential abnormal behaviors on the power system and the different purposes of treatment. Power rationing can be used as a relatively mild measure to reduce the economic losses of power companies and give electricity theft users a chance to correct their mistakes. Power outages are to ensure the security of the power grid and comply with the requirements of laws and regulations, and quickly resolve the problems caused by illegal power supply. Such measures are helpful in maintaining the stability and security of the power system.
[0074] Furthermore, in order to determine the authenticity of the potential abnormal behavior and ensure the accuracy of the power marketing audit, the execution process of steps 208-210 also includes: triggering a verification instruction corresponding to the abnormal power consumption end or abnormal power supply end to the auditors in the designated area, and lifting the temporary power restriction corresponding to the abnormal power consumption end or the temporary power outage corresponding to the abnormal power supply end when the feedback result corresponding to the verification instruction is an error result.
[0075] In this step, since each area is equipped with corresponding inspectors, when an abnormal power consumption end or abnormal power supply end is determined, a verification instruction is automatically generated, which includes the specific location of the abnormal power consumption end or abnormal power supply end, the type of abnormal behavior, the time when the abnormal behavior occurs, and other information. The verification instruction is sent to the inspectors in the designated area by e-mail, text message, mobile application push, etc., to ensure that the inspectors can receive the verification instruction in time. At the same time, the sending time, recipient and other information of the verification instruction are recorded to track the execution of the verification instruction. The inspectors go to the abnormal power consumption end or abnormal power supply end for on-site verification according to the information provided by the verification instruction. The content of the verification includes but is not limited to the operating status of the power consumption equipment, the connection status of the power supply line, etc. When the inspectors complete the on-site verification, they need to feed back the verification results to the power dispatching system, and record the feedback results of the verification instructions, including the verification time, verification results (whether it is a potential abnormal behavior), and information such as the inspectors. According to the feedback results of the inspectors, it is judged whether it is an error result, which refers to the situation where the inspectors confirm that there is no potential abnormal behavior in the abnormal power consumption end or abnormal power supply end. If so, the temporary power restriction at the abnormal power consumption end or the temporary power outage at the abnormal power supply end is automatically lifted, that is, a power restriction / power outage lifting instruction is sent to the power dispatching system to restore normal power supply.
[0076] Furthermore, in order to ensure the accuracy of the audit model in identifying potential abnormal behaviors, after obtaining the error result, the method further includes: when the error result reaches a specified number of times, triggering an update instruction of the audit model corresponding to the specified area based on the historical power data containing the error result, so as to retrain the audit model.
[0077] In this step, the specified number of times can be customized according to the actual situation, such as three times in a row or five times cumulatively. In the process of determining whether the error result reaches the specified number of times, it can be carried out according to a customized time window, such as the number of error results in the past month. When the error result reaches the specified number of times, it means that the potential abnormal behavior identification of the audit model may have generated multiple false alarms, which also increases the audit cost. Therefore, at this time, a model update instruction can be triggered, and the update instruction includes information such as the identifier, version number and update reason (i.e., the statistical number of error results) of the audit model that needs to be updated. The model update instruction is sent to the maintenance personnel responsible for maintaining and updating the audit model through e-mail, internal message system, etc., so that they can collect relevant historical power data that cause the error results, and use it to retrain the audit model, so that the audit model can continuously adapt to the complex and changeable electricity consumption situation, ensure the accuracy of potential abnormal behavior identification, and then ensure the accuracy of power marketing audit.
[0078] Furthermore, as a response to the above Figure 1-2The implementation of the method embodiment shown in the figure, the embodiment of the present application provides a power marketing digital audit system, which is used to improve the accuracy of power marketing audit and reduce power loss. The embodiment of the system corresponds to the aforementioned method embodiment. For ease of reading, this embodiment will no longer repeat the details of the aforementioned method embodiment one by one, but it should be clear that the system in this embodiment can correspond to all the contents of the aforementioned method embodiment. Specifically, Figure 3 As shown, the device comprises:
[0079] An acquisition module 31 is used to acquire real-time power data of a specified area, wherein the real-time power data includes real-time power consumption data fed back by smart meters and real-time power transmission data fed back by sensors installed at key nodes of a power grid;
[0080] An audit module 32, used to obtain an audit result corresponding to the real-time power data using a preset audit model, wherein the audit model is used to identify potential abnormal behaviors corresponding to the real-time power data based on characteristic performances of the real-time power consumption data and the real-time power transmission data;
[0081] The processing module 33 is used to trigger corresponding power adjustment measures according to the behavior type corresponding to the potential abnormal behavior if the potential abnormal behavior exists in the audit result.
[0082] Further, such as Figure 4 As shown, the system also includes:
[0083] The acquisition module 31 is further used to acquire historical power data of the designated area before acquiring the real-time power data of the designated area, wherein the historical power data includes historical power consumption data fed back by smart meters and historical power transmission data fed back by sensors installed at key nodes of the power grid;
[0084] An extraction module 34, configured to extract consumption characteristics corresponding to the historical power consumption data and transmission characteristics corresponding to the historical power transmission data;
[0085] A marking module 35, for performing potential abnormal behavior analysis on the consumption characteristics and the transmission characteristics, and marking the historical power data positively or negatively according to the analysis results;
[0086] The training module 36 is used to train the audit model corresponding to the designated area using the marked historical power data, so that the audit model can identify the potential abnormal behavior.
[0087] Further, such as Figure 4 As shown, the system also includes:
[0088] The association module 37 is used to construct an association relationship between the designated area and the audit model after the audit model corresponding to the designated area is obtained by training the marked historical power data.
[0089] Further, such as Figure 4 As shown, the audit module 32 includes:
[0090] A first determination submodule 321 is used to determine the audit model corresponding to the designated area according to the association relationship;
[0091] The audit submodule 322 is used to input the real-time power data into the audit model corresponding to the designated area to obtain the audit result corresponding to the real-time power data.
[0092] Further, such as Figure 4 As shown, the behavior types of the potential abnormal behavior at least include electricity theft and illegal power supply; the processing module 33 includes:
[0093] The first processing submodule 331 is used for triggering the abnormal power consumption alarm instruction corresponding to the abnormal power consumption terminal if the behavior type is the power theft behavior, and performing temporary power restriction processing on the abnormal power consumption terminal when the abnormal power consumption alarm instruction is continuously triggered, and the abnormal power consumption terminal is determined according to the abnormal smart meter and / or abnormal key node related to the potential abnormal behavior;
[0094] The second processing submodule 332 is used to trigger the abnormal power supply alarm instruction corresponding to the abnormal power supply end if the behavior type is the illegal power supply behavior, and temporarily cut off the power supply to the abnormal power supply end when the abnormal power supply alarm instruction is continuously triggered. The abnormal power supply end is determined based on the abnormal smart meter and / or abnormal key node related to the potential abnormal behavior.
[0095] Further, such as Figure 4 As shown, the system also includes:
[0096] The third processing submodule 333 is used to trigger the verification instruction corresponding to the abnormal power consumption end or the abnormal power supply end to the auditor in the designated area, and to lift the temporary power restriction corresponding to the abnormal power consumption end or the temporary power outage corresponding to the abnormal power supply end when the feedback result corresponding to the verification instruction is an error result.
[0097] Further, such as Figure 4 As shown, the system also includes:
[0098] The fourth processing submodule 334 is used to trigger an update instruction of the audit model corresponding to the specified area based on the historical power data containing the error results when the error results reach a specified number, so as to retrain the audit model.
[0099] Furthermore, an embodiment of the present application further provides a storage medium, wherein the storage medium is used to store a computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the above Figure 1-2 The digital audit method for power marketing described in .
[0100] Furthermore, the embodiment of the present application also provides a processor, the processor is used to run a program, wherein the program executes the above Figure 1-2 The digital audit method for power marketing described in .
[0101] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0102] It is understandable that the related features in the above methods and systems can be referenced to each other. In addition, the "first", "second" and the like in the above embodiments are used to distinguish the embodiments, and do not represent the advantages and disadvantages of the embodiments.
[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0104] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the application is not directed to any specific programming language either. It should be understood that various programming languages can be utilized to realize the content of the application described herein, and the description of the specific language above is for the purpose of disclosing the best mode of implementation of the application.
[0105] In addition, the memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0106] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0107] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0108] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0110] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0111] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0112] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0113] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0114] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0115] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.
Claims
1. A method for auditing power marketing numbers, characterized in that: The method comprises: Acquire real-time power data of a specified area, wherein the real-time power data includes real-time power consumption data fed back by smart meters and real-time power transmission data fed back by sensors installed at key nodes of the power grid; Obtaining an audit result corresponding to the real-time power data using a preset audit model, wherein the audit model is used to identify potential abnormal behaviors corresponding to the real-time power data based on characteristic performances of the real-time power consumption data and the real-time power transmission data; If the potential abnormal behavior exists in the audit result, corresponding power adjustment measures are triggered according to the behavior type corresponding to the potential abnormal behavior.
2. The method according to claim 1, characterized in that Before acquiring the real-time power data of the designated area, the method further includes: Acquiring historical power data of the designated area, wherein the historical power data includes historical power consumption data fed back by smart meters and historical power transmission data fed back by sensors installed at key nodes of the power grid; respectively extracting consumption characteristics corresponding to the historical power consumption data and transmission characteristics corresponding to the historical power transmission data; Performing potential abnormal behavior analysis on the consumption characteristics and the transmission characteristics, and marking the historical power data positively or negatively according to the analysis results; The audit model corresponding to the designated area is obtained by training the marked historical power data, so that the audit model can identify the potential abnormal behavior.
3. The method according to claim 2, characterized in that After obtaining the audit model corresponding to the designated area by training the marked historical power data, the method further includes: Construct an association relationship between the designated area and the audit model.
4. The method according to claim 3, characterized in that The audit results corresponding to the real-time power data are obtained by using a preset audit model, including: Determine the audit model corresponding to the designated area according to the association relationship; The real-time power data is input into the audit model corresponding to the designated area to obtain the audit result corresponding to the real-time power data.
5. The method according to claim 1, characterized in that The types of potential abnormal behaviors include at least electricity theft and illegal power supply; The corresponding power adjustment measures are triggered according to the behavior type corresponding to the potential abnormal behavior, including: If the behavior type is the electricity theft behavior, an abnormal electricity consumption alarm instruction corresponding to the abnormal electricity consumption terminal is triggered, and temporary power restriction is performed on the abnormal electricity consumption terminal when the abnormal electricity consumption alarm instruction is continuously triggered. The abnormal electricity consumption terminal is determined according to the abnormal smart meter and / or abnormal key node related to the potential abnormal behavior; If the behavior type is the illegal power supply behavior, the abnormal power supply alarm instruction corresponding to the abnormal power supply end is triggered, and the abnormal power supply end is temporarily powered off when the abnormal power supply alarm instruction is continuously triggered. The abnormal power supply end is determined based on the abnormal smart meter and / or abnormal key node related to the potential abnormal behavior.
6. The method according to claim 5, characterized in that The method further comprises: A verification instruction corresponding to the abnormal power consumption end or the abnormal power supply end is triggered to the inspector in the designated area, and when the feedback result corresponding to the verification instruction is an error result, the temporary power restriction corresponding to the abnormal power consumption end or the temporary power outage corresponding to the abnormal power supply end is lifted.
7. The method according to claim 6, characterized in that The method further comprises: When the error result reaches a specified number of times, an update instruction of the audit model corresponding to the specified area is triggered based on the historical power data containing the error result to retrain the audit model.
8. A power marketing digital audit system, characterized in that: The system comprises: An acquisition module is used to acquire real-time power data of a specified area, wherein the real-time power data includes real-time power consumption data fed back by smart meters and real-time power transmission data fed back by sensors installed at key nodes of the power grid; An audit module, used to obtain an audit result corresponding to the real-time power data using a preset audit model, wherein the audit model is used to identify potential abnormal behaviors corresponding to the real-time power data based on characteristic performances of the real-time power consumption data and the real-time power transmission data; The processing module is used to trigger corresponding power adjustment measures according to the behavior type corresponding to the potential abnormal behavior if the potential abnormal behavior exists in the audit result.
9. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the power marketing digital audit method as described in any one of claims 1 to claim 7.
10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the power marketing digital audit method as described in any one of claims 1 to claim 7.
Citation Information
Cited By
Intelligent power consumption behavior inspection method and device based on multi-source data and storage medium
CN120234745A
Electric power marketing business online auditing all-in-one machine digital auditing system and method
CN120449070A
Group marketing collaborative management system based on process driving
CN120894056A
