Electric quantity loss compensation device and method for abnormal metering of electric energy meter

Abstract

The invention discloses an electric quantity loss compensation device and method for electric energy meter metering abnormity, and relates to the technical field of electric energy metering, and the method comprises the steps: obtaining an electric energy meter distributed network, carrying out the real-time monitoring, and generating an electric energy meter metering monitoring data set; analyzing the data set by using an abnormal probability identification model, and identifying an abnormal electric energy meter; the metering data of the abnormal electric energy meter is stored in a temporary storage module; and after the abnormal electric energy meter is recovered, the NB-IoT communication module uploads metering temporary data to the cloud database for loss compensation, so that the data integrity and metering accuracy during the abnormal period are ensured. According to the invention, the technical problem of low accuracy and efficiency of electric quantity loss compensation caused by difficulty in real-time monitoring and accurate compensation of metering abnormity of the electric energy meter in a traditional method in the prior art is solved, and the aim of quickly responding and accurately compensating the metering abnormity of the electric energy meter is achieved. And the accuracy and efficiency of power loss compensation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy metering, and in particular to a device and method for compensating for electric energy loss caused by abnormal measurement of an electric energy meter. Background Art

[0002] With the development of intelligent power system, smart energy meter, as an important terminal device for power grid measurement and management, plays a key role in power consumption monitoring, electricity bill settlement and power quality analysis. However, due to external environment (such as voltage fluctuation, electromagnetic interference) or equipment itself (such as hardware failure, communication interruption), energy meter may have measurement anomalies, resulting in inaccurate user electricity billing and economic losses in power grid operation.

[0003] Traditional methods of electricity loss compensation often rely on manual inspections and post-processing, which is not only inefficient but also difficult to achieve real-time monitoring and rapid response to abnormal metering. Summary of the invention

[0004] The present application provides an electric power loss compensation device and method for abnormal measurement of electric power meters, which is used to solve the technical problem that traditional methods in the prior art are difficult to achieve real-time monitoring and accurate compensation of abnormal measurement of electric power meters, resulting in low accuracy and efficiency of electric power loss compensation.

[0005] In a first aspect of the present application, a device for compensating for electric energy meter loss due to abnormal metering is provided, the device comprising: a distributed network acquisition module, the distributed network acquisition module is used to acquire an electric energy meter distributed network; an electric energy meter metering monitoring module, the electric energy meter metering monitoring module is used to perform real-time monitoring on the electric energy meter distributed network and output an electric energy meter metering monitoring data set; an abnormal electric energy meter identification module, the abnormal electric energy meter identification module is used to input the electric energy meter metering monitoring data set into an abnormal probability identification model, perform probability calculation according to the abnormal probability identification model, obtain an abnormal probability set, and identify abnormal electric energy meters with abnormal probabilities greater than a preset abnormal probability; a temporary storage module, the temporary storage module is used to store an electric energy meter metering temporary data set corresponding to the abnormal electric energy meter; an abnormal electric energy meter loss compensation module, the abnormal electric energy meter loss compensation module is used to upload the electric energy meter metering temporary data set to a cloud database for loss compensation through an NB-IoT communication module after detecting that the abnormal electric energy meter has recovered.

[0006] The second aspect of the present application provides a method for compensating for electricity loss due to abnormal metering of electric energy meters, the method comprising: obtaining an electric energy meter distributed network; monitoring the electric energy meter distributed network in real time, and outputting an electric energy meter metering monitoring data set; inputting the electric energy meter metering monitoring data set into an abnormal probability recognition model, performing probability calculation according to the abnormal probability recognition model, obtaining an abnormal probability set, and identifying abnormal electric energy meters with abnormal probabilities greater than a preset abnormal probability; connecting a temporary storage module, the temporary storage module being used to store an electric energy meter metering temporary data set corresponding to the abnormal electric energy meter; when it is detected that the abnormal electric energy meter has recovered, uploading the electric energy meter metering temporary data set to a cloud database through the NB-IoT communication module for loss compensation.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The present application provides an electric energy loss compensation device and method for abnormal metering of electric energy meters, which relate to the technical field of electric energy metering. The device and method monitor the electric energy meter distributed network in real time, identify abnormal electric energy meters by using an abnormal probability recognition model, store their metering data in a temporary storage module, and upload the data to a cloud database through NB-IoT for loss compensation after the abnormality is recovered, thereby ensuring the integrity of the metering data and the accuracy of the compensation. The device and method solve the technical problem that the traditional methods in the prior art are difficult to achieve real-time monitoring and accurate compensation for the abnormal metering of electric energy meters, resulting in low accuracy and efficiency of the electric energy loss compensation. The device and method achieve the technical effect of rapid response and accurate compensation for the abnormal metering of electric energy meters through real-time monitoring of the metering data of electric energy meters, thereby improving the accuracy and efficiency of the electric energy loss compensation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of the structure of a power loss compensation device for abnormal measurement of an electric energy meter provided in an embodiment of the present application;

[0011] Figure 2 A schematic flow chart of a method for compensating for power loss due to abnormal measurement of an electric energy meter provided in an embodiment of the present application.

[0012] Explanation of reference numerals: distributed network acquisition module 11 , electric energy meter measurement and monitoring module 12 , abnormal electric energy meter identification module 13 , temporary storage module 14 , abnormal electric energy meter loss compensation module 15 . DETAILED DESCRIPTION

[0013] The present application provides an electric power loss compensation device and method for abnormal measurement of electric power meters, which is used to solve the technical problem that traditional methods in the prior art are difficult to achieve real-time monitoring and accurate compensation of abnormal measurement of electric power meters, resulting in low accuracy and efficiency of electric power loss compensation.

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a device for compensating for power loss caused by abnormal measurement of an electric energy meter, the device comprising:

[0017] The distributed network acquisition module 11 is used to acquire the distributed network of the electric energy meter.

[0018] Specifically, the distributed network acquisition module 11 of the present application is used to acquire a distributed network of electric energy meters. The distributed network of electric energy meters is a multi-node system interconnected by a communication link, which is composed of multiple smart electric energy meters installed in different locations, and its purpose is to realize the functions of data collection, remote transmission and real-time monitoring. To achieve this goal, a network initialization operation must be performed first to determine the physical distribution and logical relationship of all electric energy meter nodes in the network.

[0019] Among them, network initialization can rely on network topology discovery technology. This technology scans the communication channels of the devices, identifies the connection relationship between each electric energy meter and its adjacent nodes, and generates a topological structure diagram of the entire distributed network. The topological structure contains the device identification (such as device ID), location parameters (such as geographic coordinates or installation location), and communication path information. Through this process, it is ensured that each electric energy meter is accurately identified and accessible in the network.

[0020] In the process of obtaining the network topology, low-power wide area network (LPWAN) communication technologies such as NB-IoT (narrowband Internet of Things) or LoRa technology need to be applied. These technologies can provide efficient data transmission support in a wide area, and have the characteristics of low power consumption, wide coverage and low connection cost, which are particularly suitable for large-scale distributed device management. Through the NB-IoT communication module, each electric energy meter node can reliably transmit its identity and basic status information to the monitoring center or master station.

[0021] In addition, in order to ensure the stability of the network and the accuracy of data transmission, a dynamic routing optimization algorithm needs to be introduced. This algorithm dynamically adjusts the data transmission path according to the real-time status of each node in the network (such as signal strength and bandwidth usage) to minimize network interruption and data loss.

[0022] In summary, through the combination of network topology discovery, NB-IoT communication module and dynamic routing optimization technology, the construction of the distributed network of electric energy meters was completed, laying the foundation for subsequent real-time monitoring and abnormality identification, and ensuring the full coverage and efficient operation of the electric energy meter network.

[0023] The electric energy meter measurement and monitoring module 12 is used to monitor the electric energy meter distributed network in real time and output an electric energy meter measurement and monitoring data set.

[0024] It should be understood that the electricity meter metering monitoring module 12 of the present application is used to perform real-time monitoring of the electricity meter distributed network. Through continuous data collection and transmission, the operating status and metering results of all electricity meters in the distributed network are tracked and dynamically analyzed to ensure the real-time and accuracy of the metering data.

[0025] For example, real-time monitoring of a distributed network of energy meters can rely on high-precision sensor modules built into the energy meters. These sensors can periodically collect key parameters related to the energy meters, such as voltage, current, power factor, and accumulated electricity. By collecting these parameters, the user's electricity consumption can be accurately recorded, and possible metering anomalies or equipment failures can be monitored in real time.

[0026] The collected data is transmitted to the monitoring center through low-power communication technology, such as the NB-IoT (Narrowband Internet of Things) protocol. The main advantages of this technology include low power consumption, high coverage, and support for large-scale device connections, which is very suitable for scenarios such as electric energy meters that are widely distributed and have high energy efficiency requirements. The NB-IoT module will upload the collected data regularly or triggered by events to ensure the timeliness and reliability of data transmission.

[0027] At the monitoring center, all uploaded data will be uniformly received and sorted, and finally generate an electric energy meter measurement monitoring data set. This data set is the core product of real-time monitoring, and contains information such as the device ID, timestamp, collected measurement values, and device operating status of each electric energy meter. The integrity and accuracy of the monitoring data set are crucial because it provides data support for subsequent anomaly detection and compensation calculations.

[0028] To ensure the efficient operation of the monitoring system, edge computing technology needs to be introduced. By deploying lightweight edge computing units on the energy meter or adjacent nodes, local preprocessing of data, such as denoising, anomaly filtering, and basic statistical operations, can be achieved. This not only reduces the amount of uploaded data and communication bandwidth requirements, but also improves real-time performance.

[0029] Therefore, through the comprehensive application of high-precision sensors, NB-IoT communication modules and edge computing technology, a complete real-time monitoring system was built, which effectively output the electricity meter measurement monitoring data set, providing a reliable data source and technical support for subsequent abnormal analysis and data compensation.

[0030] The abnormal energy meter identification module 13 is used to input the energy meter measurement monitoring data set into the abnormal probability identification model, perform probability calculation according to the abnormal probability identification model, obtain an abnormal probability set, and identify abnormal energy meters with abnormal probabilities greater than a preset abnormal probability.

[0031] The abnormal probability recognition model is obtained by training multiple sets of training data sets, and the multiple sets of training data sets include historical electric energy meter measurement monitoring abnormal sample sets, trigger interval time samples, and label information characterizing the size of the abnormal probability, which are trained until convergence; wherein the trigger interval time sample is the time difference between the time when each electric energy meter triggers the electric energy meter abnormality warning and the time when the electric energy meter abnormality actually occurs; according to the abnormal probability recognition model, the abnormal probability of each electric energy meter is predicted to obtain an abnormal probability set and a prediction interval time set corresponding to each electric energy meter.

[0032] Specifically, the abnormal energy meter identification module 13 of the present application is used to input the energy meter measurement monitoring data set into the abnormal probability identification model, use the model to analyze the operating status of the energy meter, calculate the abnormal probability of each energy meter, and thus identify the energy meter that may have problems. The abnormal probability identification model is an intelligent analysis tool built based on machine learning technology, which is obtained through training with multiple sets of training data sets, and ultimately has the ability to predict the probability of energy meter abnormalities. The multiple sets of training data sets include the following three key components:

[0033] Historical energy meter measurement monitoring abnormal sample set: records the metering data of the energy meter in the past under abnormal conditions, such as abnormally fluctuating voltage, current or power readings. Trigger interval time sample: defined as the time difference between the time when the energy meter triggers the abnormal warning and the actual time when the abnormality occurs. This data feature reflects the response delay between the warning and the abnormality, which helps to identify the trend characteristics of the abnormality. Label information: label information that characterizes the probability of abnormality, which is used to guide the model to learn the relationship between different data patterns and abnormal probabilities. In the process of model training, through repeated iterative optimization, the model is gradually trained to convergence, that is, the prediction ability of the model tends to be stable and has generalization ability.

[0034] In actual operation, the real-time generated electric energy meter measurement monitoring data set is input into the model. The model calculates the possibility of abnormality of each electric energy meter through comprehensive analysis of various data features, and generates an abnormal probability set. This set contains the abnormal probability value of each electric energy meter, and identifies those abnormal electric energy meters that may have problems according to the preset abnormal probability threshold. These electric energy meters will be recorded and marked separately as the focus of subsequent processing.

[0035] At the same time, the model also outputs a set of prediction intervals, which is used to reflect the time interval from the current state of each electric energy meter to the time when an abnormality may occur. The prediction interval time set provides important data support for the design of early warning and compensation strategies for abnormalities.

[0036] Furthermore, after identifying the abnormal electric energy meter with a probability greater than a preset abnormality, the abnormal electric energy meter identification module 13 is further used to perform the following steps:

[0037] P31a: Obtain the abnormal distribution position of the abnormal electric energy meter in the electric energy meter distributed network; P32a: Determine whether the abnormal electric energy meter is a discrete abnormal relationship based on the abnormal distribution position. If the abnormal electric energy meter is a discrete abnormal relationship, construct an external-data verification model; P33a: Input the electric energy meter measurement temporary data set into the external-data verification model for verification, and obtain the verification result, which includes verification pass and verification fail; P34a: If the verification result is verification pass, the NB-IoT communication module uploads the electric energy meter measurement temporary data set to the cloud database for loss compensation.

[0038] In a possible embodiment of the present application, after abnormal electric energy meters with a probability greater than a preset abnormality are identified, these abnormal electric energy meters are further analyzed and processed in detail to ensure accurate compensation of abnormal data and scientific processing.

[0039] First, obtain the abnormal distribution location of the abnormal energy meter in the distributed network of energy meters. The abnormal distribution location refers to the geographical location of the abnormal energy meter in the entire distributed network and its relative location to other energy meters. This information is located through network topology data and monitoring records. The abnormal distribution location can be used to better analyze the characteristics of the abnormality, such as whether there is a regional concentration problem or an independent abnormality of individual equipment.

[0040] Next, based on the distribution location of the abnormal energy meters, determine whether it is a discrete abnormal relationship. The discrete abnormal relationship means that there is no obvious correlation between the abnormal distribution of abnormal energy meters, which usually manifests as independent abnormalities of individual devices, rather than regional or systemic problems. If it is judged to be a discrete abnormal relationship, it is necessary to build an external-data verification model. The external-data verification model is an analysis tool used to verify the data consistency between the temporary metering data set of the abnormal energy meter and its surrounding normal equipment, so as to determine whether the abnormality is a false alarm or a special case.

[0041] When constructing the external data verification model, the historical metering data of the abnormal electricity meter and its multiple adjacent normal electricity meters can be used to identify the external feature associations of these data and establish a data accompanying relationship model, thereby effectively capturing the common operating rules between the electricity meters and providing a basis for accurate verification of abnormal data.

[0042] Subsequently, the metering temporary data set of the abnormal energy meter is input into the external-data verification model for verification. Through model analysis, the verification result is obtained, and the verification result includes two cases: verification passed and verification failed. Among them, the verification passed means that although the metering data of the abnormal energy meter has abnormal records, it complies with the equipment operation rules, and the data can be used for subsequent loss compensation. If the verification fails, it is necessary to further check the equipment hardware and communication module of the abnormal energy meter to eliminate hardware failures or external interference.

[0043] Finally, if the verification result is passed, the metering temporary data set of the abnormal electric energy meter is uploaded to the cloud database through the NB-IoT communication module (narrowband Internet of Things). The NB-IoT communication module has the advantages of low power consumption and high stability, and can ensure reliable data transmission in abnormal environments. After uploading to the cloud database, the system will perform abnormal compensation based on the uploaded data to ensure the integrity and accuracy of the metering results of the electric energy meter and reduce data losses caused by false alarms or omissions.

[0044] Further, to construct an external data verification model, step P32a of the embodiment of the present application further includes:

[0045] P32-1a: Obtain multiple adjacent abnormal electric energy meters for each abnormal electric energy meter; P32-2a: Call the historical metering monitoring data set of each abnormal electric energy meter, and the historical metering monitoring data set of the multiple adjacent abnormal electric energy meters; P32-3a: Identify the external-data accompanying relationship between the historical metering monitoring data set of the abnormal electric energy meter, and the historical metering monitoring data set of the multiple adjacent abnormal electric energy meters, and construct an external-data verification model based on the external-data accompanying relationship.

[0046] Specifically, the specific process of constructing the external-data verification model may be, first, obtaining multiple adjacent abnormal electric energy meters of each abnormal electric energy meter. In the electric energy meter distributed network, there may be a certain correlation between abnormal electric energy meters, such as group anomalies caused by external environmental changes (such as voltage fluctuations or equipment interference) in the same area. Therefore, by analyzing the electric energy meter network topology and historical monitoring records, the adjacent abnormal electric energy meters of each abnormal electric energy meter can be identified, and their correlation in spatial distribution can be clarified. The key to this step is to locate the physical location of the abnormal electric energy meter and screen out other electric energy meters that are adjacent to it and exhibit similar abnormal characteristics.

[0047] Next, call the historical metering monitoring data set of each abnormal electric energy meter, as well as the historical metering monitoring data sets of multiple adjacent abnormal electric energy meters. The historical metering monitoring data set is a record of the operation data of the electric energy meter in the past certain period of time, including voltage, current, power factor, accumulated value of electricity, and related timestamps. These data provide an important basis for the behavior pattern analysis of abnormal electric energy meters. By calling the historical data of adjacent electric energy meters, a horizontal comparison between the data can be established to reveal possible abnormal patterns.

[0048] Subsequently, the external-data association relationship between the historical metering monitoring data set of the abnormal energy meter and its neighboring energy meters is identified. The external-data association relationship refers to the similarity or correlation shown by multiple energy meters in the historical operation data, such as the synchronization of voltage fluctuations or the correlation of current changes in a specific time period. Through data mining techniques, such as time series analysis and correlation calculation, these external correlation features can be quantified, thereby revealing the common abnormal patterns of the abnormal energy meter and its neighboring devices.

[0049] Furthermore, according to the external-data accompanying relationship, an external-data verification model is constructed. The model establishes verification rules based on statistical laws and abnormal characteristics by comprehensively analyzing the historical data of the abnormal electric energy meter and its neighboring electric energy meters. The core logic of the model is to compare the data of the current abnormal electric energy meter with the data of the accompanying electric energy meter to determine whether the anomaly conforms to the operating law of the overall network, thereby screening out real anomalies and false alarms. The external-data verification model can effectively improve the verification accuracy of abnormal data, distinguish real anomalies from false alarms, and thus provide a reliable basis for subsequent compensation calculations.

[0050] Furthermore, according to the abnormal distribution position, it is determined whether the abnormal electric energy meter is in a discrete abnormal relationship, and the abnormal electric energy meter identification module 13 is further used to perform the following steps:

[0051] P32b: If the abnormal electric energy meter is a non-discrete abnormal relationship, an internal data verification model is constructed; P33b: The electric energy meter temporary data set is input into the internal data verification model for verification, and a verification result is obtained, and the verification result includes a verification pass and a verification failure; P34b: If the verification result is a verification pass, the NB-IoT communication module uploads the electric energy meter temporary data set to the cloud database for loss compensation.

[0052] Optionally, it is determined whether the abnormal energy meters are in a discrete abnormal relationship according to the abnormal distribution position. If it is determined to be a non-discrete abnormal relationship, internal data verification processing is performed on these energy meters. The non-discrete abnormal relationship means that the abnormal behavior of the abnormal energy meter does not appear independently, but shows mutual correlation or synchronization, such as multi-device abnormalities caused by the same power grid failure, regional interference or the same device setting problem.

[0053] At this time, it is necessary to adopt an internal data verification model, that is, to perform self-verification based on the historical measurement data of a single device. The core logic of the internal data verification model is based on the analysis of the time series data of a single device, and uses statistical analysis or machine learning methods to construct verification rules for internal operating characteristics. During the model training process, historical data and abnormal label information can be used to accurately distinguish normal and abnormal data through pattern recognition and anomaly detection algorithms (such as isolation forest algorithm, LSTM neural network).

[0054] The metering temporary data set of the electric energy meter is input into the internal data verification model for verification. The purpose of the verification is to detect whether there are abnormal conditions in the temporary data set that conform to the operating rules of the device itself, and to give the verification results. If the verification passes, it means that the temporary data of the abnormal electric energy meter conforms to the operating rules of the device and can be used as reliable data for subsequent processing. If the verification fails, it means that there are obvious abnormalities in the data, which may be caused by hardware failure or external interference, and further investigation and repair are required. If the verification result is that the verification passes, the verified electric energy meter metering temporary data set is uploaded to the cloud database through the NB-IoT communication module, and the cloud system compensates for the power loss.

[0055] Through the above steps, the internal data verification model can effectively filter the interference part in the abnormal data, ensure the credibility of the compensation data, and provide reliable technical support and scientific basis for the abnormal processing and subsequent loss compensation of the electric energy meter.

[0056] Further, to construct an internal data verification model, step P32b of the embodiment of the present application further includes:

[0057] P32-1b: Call the historical metering monitoring data set of each abnormal electric energy meter and output multiple historical metering monitoring data sets; P32-2b: Identify the internal-data accompanying relationship of the multiple historical metering monitoring data sets, and construct an external-data verification model based on the internal-data accompanying relationship.

[0058] It should be understood that the specific process of constructing the internal data verification model can be, first, calling the historical metering monitoring data set of each abnormal electric energy meter, and outputting multiple time series data sets. The historical metering monitoring data set is the metering data accumulated by the electric energy meter during long-term operation, including key information such as voltage, current, power factor, accumulated electricity value and timestamp. These data reflect the long-term operation law of the equipment and the characteristic change pattern under normal working conditions. When calling the data, it is necessary to ensure the integrity and accuracy of the historical data, and exclude abnormal interference or incomplete records. The original data is preprocessed through data cleaning technology (such as denoising and filling missing values) to lay the foundation for subsequent analysis.

[0059] Next, identify the internal-data accompanying relationship in the historical metering data of the abnormal electric energy meter. The internal-data accompanying relationship refers to the inherent correlation between the metering data of a single device, such as the dynamic change pattern of voltage and current, and the logical relationship between power factor and load fluctuation. This relationship reflects the operating law and working characteristics of the equipment. Identifying the internal-data accompanying relationship can be accomplished through statistical analysis or machine learning techniques. For example, statistical analysis methods (such as Pearson coefficient) or covariance analysis are used to quantify the correlation between different data items. Through dynamic time warping or frequency domain analysis, the synchronization and periodicity of each data item in the time dimension are extracted. Through the above analysis, the operating characteristics and key laws inside the electric energy meter are extracted to form an accompanying relationship model, which can intuitively reflect the normal working mode of the equipment.

[0060] Based on the internal-data accompanying relationship, an internal-data verification model is further constructed. This model detects anomalies in the metering temporary data set by capturing the internal laws of the equipment. The specific implementation methods include: establishing behavioral rules within the equipment based on statistical analysis results, setting thresholds and judgment criteria for anomaly detection. The supervised learning model (such as decision trees and support vector machines) is trained using historical data of abnormal electricity meters to achieve automatic recognition of abnormal patterns. At the same time, new monitoring data is regularly included in model training so that the model can dynamically adapt to changes in the operating laws of the equipment.

[0061] Through the above steps, the constructed internal data verification model can effectively detect whether the data of the abnormal electricity meter conforms to its own operating rules, thereby improving the accuracy of the verification and providing a reliable basis for subsequent data uploading and loss compensation.

[0062] The temporary storage module 14 is used to store the temporary data set of electric energy meter measurement corresponding to the abnormal electric energy meter.

[0063] Optionally, the temporary storage module 14 of the present application is used to store the temporary data set of the meter measurement corresponding to the abnormal meter. When the abnormal meter is identified, the temporary storage module is automatically connected. The temporary storage module is an independent storage unit for storing temporary data of abnormal meter measurement, usually composed of an embedded memory or an external storage device, and its capacity and performance can be dynamically adjusted according to the scale of the meter network. Its main function is to temporarily save the metering data of the abnormal meter to prevent data loss or overwriting.

[0064] During the connection process, the temporary storage module establishes a communication connection with the abnormal energy meter through the energy meter distributed network. After the connection is completed, the system will store the metering temporary data set of the abnormal energy meter in the temporary storage module. The metering temporary data set refers to the collection of all monitoring data of the abnormal energy meter in the abnormal state, including timestamp, voltage, current, power factor, accumulated electricity and other information. These data are the key basis for subsequent verification and compensation.

[0065] By introducing a temporary storage module, it is effectively ensured that the metering data of abnormal energy meters will not be lost or overwritten in abnormal conditions, providing complete and reliable data support for subsequent verification and compensation operations. At the same time, this design can adapt to the abnormal processing needs of large-scale energy meters in distributed networks, and has good scalability and practicality.

[0066] The abnormal electric energy meter loss compensation module 15 is used to upload the electric energy meter measurement temporary data set to the cloud database through the NB-IoT communication module for loss compensation after detecting that the abnormal electric energy meter has recovered.

[0067] Furthermore, the abnormal electric energy meter loss compensation module 15 is also used to perform the following steps:

[0068] P51: Upload the predicted interval time set to the cloud database, and the cloud database performs pre-order prediction compensation on the electric energy meter measurement temporary data set according to the predicted interval time, and outputs the compensated electric energy meter measurement temporary data set; P52: Input the compensated electric energy meter measurement temporary data set into the main chip storage module for overwriting storage.

[0069] Specifically, the abnormal energy meter loss compensation module 15 of the present application is used to upload the metering temporary data set of the energy meter to the cloud database through the NB-IoT communication module when the abnormal energy meter is detected to resume normal working state, and further complete the prediction compensation and data storage to ensure the integrity of the data and the scientific nature of the compensation. The temporary data set contains detailed metering records during the abnormal period, such as timestamp, voltage, current, power factor, etc. The uploading of these data lays the foundation for subsequent compensation calculations.

[0070] At the same time, the prediction interval time set is uploaded to the cloud database. The prediction interval time set refers to the prediction data of the possible future recovery time of the abnormal energy meter based on the abnormal probability model during the abnormal detection process. These time sets provide a key reference for the cloud database to perform pre-order compensation.

[0071] In the cloud database, the prediction interval time set is used to perform pre-order prediction compensation on the metering temporary data set. Pre-order compensation means estimating the actual power consumption during the abnormal period based on the historical operating rules of the abnormal energy meter during the abnormal state, the prediction interval time, and the average metering rate during normal operation, and making compensation adjustments to the temporary data. This process can be achieved through machine learning models (such as time series prediction models LSTM or regression models) to improve the accuracy of compensation. The compensated metering temporary data set will be output in a unified format to prepare for subsequent storage and processing.

[0072] Finally, the compensated temporary data set of the electric energy meter is input into the main chip storage module of the electric energy meter for overwriting storage. The main chip storage module is the core unit for storing metering data inside the electric energy meter, usually composed of non-volatile memory (such as EEPROM or Flash storage). Overwriting storage ensures that the metering records of the electric energy meter are complete and consistent, so that it can be used normally in subsequent meter reading, bill settlement and other links.

[0073] Through the above steps, the metering data during the abnormal period can be completely recorded and accurately compensated, providing reliable guarantee for the normal operation of the subsequent electric energy meter, while improving the scientific nature of the compensation calculation and the accuracy of the compensation data.

[0074] In summary, the embodiments of the present application have at least the following technical effects:

[0075] This application generates an electric energy meter metering monitoring data set by acquiring a distributed network of electric energy meters and monitoring them in real time. The data set is analyzed using an abnormal probability recognition model to identify abnormal electric energy meters, and the metering data of the abnormal electric energy meters is stored in a temporary storage module. When the abnormal electric energy meter is restored, the temporary metering data is uploaded to the cloud database through the NB-IoT communication module for loss compensation, thereby ensuring data integrity and metering accuracy during the abnormal period, and achieving efficient exception handling and precise compensation.

[0076] The technical effect of achieving rapid response and precise compensation for abnormal metering of the energy meter by real-time monitoring of the energy meter measurement data and improving the accuracy and efficiency of power loss compensation has been achieved.

[0077] Embodiment 2 is based on the same inventive concept as the power loss compensation device for abnormal measurement of electric energy meters in the above embodiments. Figure 2 As shown, the present application provides a method for compensating for power loss caused by abnormal measurement of electric energy meters. The device and method embodiments in the embodiments of the present application are based on the same inventive concept. The method includes:

[0078] Acquire a distributed network of electric energy meters; perform real-time monitoring on the distributed network of electric energy meters and output a metering monitoring data set of electric energy meters; input the metering monitoring data set of electric energy meters into an abnormal probability recognition model, perform probability calculation according to the abnormal probability recognition model, obtain an abnormal probability set, and identify abnormal electric energy meters with abnormal probabilities greater than a preset abnormal probability; connect a temporary storage module, the temporary storage module is used to store a temporary metering data set of electric energy meters corresponding to the abnormal electric energy meters; when it is detected that the abnormal electric energy meter has recovered, upload the temporary metering data set of electric energy meters to a cloud database through the NB-IoT communication module for loss compensation.

[0079] Furthermore, after identifying an abnormal electric energy meter with a probability greater than a preset abnormality, the method further includes:

[0080] The abnormal distribution position of the abnormal electric energy meter in the electric energy meter distributed network is obtained; according to the abnormal distribution position, whether the abnormal electric energy meter is a discrete abnormal relationship is determined, and if the abnormal electric energy meter is a discrete abnormal relationship, an external-data verification model is constructed; the electric energy meter metering temporary data set is input into the external-data verification model for verification, and a verification result is obtained, and the verification result includes a verification pass and a verification fail; if the verification result is a verification pass, the NB-IoT communication module uploads the electric energy meter metering temporary data set to the cloud database for loss compensation.

[0081] Further, an external data verification model is constructed, and the method includes:

[0082] Acquire multiple adjacent abnormal electric energy meters for each abnormal electric energy meter; call the historical metering monitoring data set of each abnormal electric energy meter and the historical metering monitoring data set of the multiple adjacent abnormal electric energy meters; identify the external-data accompanying relationship between the historical metering monitoring data set of the abnormal electric energy meter and the historical metering monitoring data set of the multiple adjacent abnormal electric energy meters, and construct an external-data verification model based on the external-data accompanying relationship.

[0083] Further, judging whether the abnormal electric energy meter is in a discrete abnormal relationship according to the abnormal distribution position, the method further includes:

[0084] If the abnormal electric energy meter is a non-discrete abnormal relationship, an internal data verification model is constructed; the electric energy meter measurement temporary data set is input into the internal data verification model for verification, and a verification result is obtained, and the verification result includes a verification pass and a verification failure; if the verification result is a verification pass, the NB-IoT communication module uploads the electric energy meter measurement temporary data set to the cloud database for loss compensation.

[0085] Furthermore, an internal data verification model is constructed, and the method includes:

[0086] The historical metering monitoring data set of each abnormal electric energy meter is called to output multiple historical metering monitoring data sets; the internal-data accompanying relationship of the multiple historical metering monitoring data sets is identified, and an external-data verification model is constructed according to the internal-data accompanying relationship.

[0087] Furthermore, the method further comprises:

[0088] The abnormal probability recognition model is obtained by training multiple sets of training data sets, and the multiple sets of training data sets include historical electric energy meter measurement monitoring abnormal sample sets, trigger interval time samples, and label information representing the size of abnormal probability, which are trained until convergence; wherein the trigger interval time sample is the time difference between the time when each electric energy meter triggers the electric energy meter abnormality warning and the time when the electric energy meter abnormality actually occurs; according to the abnormal probability recognition model, the abnormal probability of each electric energy meter is predicted to obtain an abnormal probability set and a prediction interval time set corresponding to each electric energy meter.

[0089] Furthermore, the method further comprises:

[0090] The prediction interval time set is uploaded to a cloud database, and the cloud database performs pre-order prediction compensation on the electric energy meter measurement temporary data set according to the prediction interval time, and outputs the compensated electric energy meter measurement temporary data set; the compensated electric energy meter measurement temporary data set is input into the main chip storage module for overwriting storage.

[0091] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0093] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A device for compensating for power loss caused by abnormal measurement of electric energy meters, characterized in that: The device comprises: A distributed network acquisition module, wherein the distributed network acquisition module is used to acquire a distributed network of an electric energy meter; An electric energy meter measurement and monitoring module, the electric energy meter measurement and monitoring module is used to monitor the electric energy meter distributed network in real time and output an electric energy meter measurement and monitoring data set; An abnormal electric energy meter identification module, the abnormal electric energy meter identification module is used to input the electric energy meter measurement monitoring data set into an abnormal probability identification model, perform probability calculation according to the abnormal probability identification model, obtain an abnormal probability set, and identify abnormal electric energy meters with abnormal probabilities greater than a preset abnormal probability; A temporary storage module, the temporary storage module is used to store the electric energy meter measurement temporary data set corresponding to the abnormal electric energy meter; The abnormal electric energy meter loss compensation module is used to upload the electric energy meter measurement temporary data set to the cloud database through the NB-IoT communication module for loss compensation after detecting that the abnormal electric energy meter has recovered.

2. The device for compensating for power loss caused by abnormal measurement of electric energy meter according to claim 1, characterized in that: After identifying an abnormal electric energy meter with a probability greater than a preset abnormality, the abnormal electric energy meter identification module is further used to: Acquire the abnormal distribution position of the abnormal electric energy meter in the electric energy meter distribution network; Determine whether the abnormal electric energy meter is in a discrete abnormal relationship according to the abnormal distribution position, and if the abnormal electric energy meter is in a discrete abnormal relationship, construct an external-data verification model; Inputting the temporary data set of the electric energy meter measurement into the external data verification model for verification, and obtaining a verification result, wherein the verification result includes a verification pass and a verification failure; If the verification result is passed, the NB-IoT communication module uploads the temporary data set of the electric energy meter to the cloud database for loss compensation.

3. The device for compensating for power loss caused by abnormal measurement of electric energy meter according to claim 2, characterized in that: The abnormal electric energy meter identification module is also used for: Acquire multiple adjacent abnormal electric energy meters of each abnormal electric energy meter; Calling the historical metering monitoring data set of each abnormal electric energy meter and the historical metering monitoring data sets of the plurality of adjacent abnormal electric energy meters; The external-data accompanying relationship between the historical metering monitoring data set of the abnormal electric energy meter and the historical metering monitoring data sets of the plurality of adjacent abnormal electric energy meters is identified, and an external-data verification model is constructed according to the external-data accompanying relationship.

4. The device for compensating for power loss caused by abnormal measurement of electric energy meter according to claim 2, characterized in that: According to the abnormal distribution position, it is judged whether the abnormal electric energy meter is a discrete abnormal relationship, and the abnormal electric energy meter identification module is further used to: If the abnormal electric energy meter is a non-discrete abnormal relationship, construct an internal data verification model; Inputting the temporary data set measured by the electric energy meter into the internal data verification model for verification, and obtaining a verification result, wherein the verification result includes a verification pass and a verification failure; If the verification result is passed, the NB-IoT communication module uploads the temporary data set of the electric energy meter to the cloud database for loss compensation.

5. The device for compensating for power loss caused by abnormal measurement of electric energy meter according to claim 4, characterized in that: The abnormal electric energy meter identification module is also used for: Call the historical metering monitoring data set of each abnormal electric energy meter and output multiple historical metering monitoring data sets; Identify the internal-data accompanying relationship of the multiple historical metrology monitoring data sets, and construct an external-data verification model based on the internal-data accompanying relationship.

6. The device for compensating for power loss caused by abnormal measurement of electric energy meter according to claim 1, characterized in that: Inputting the electric energy meter measurement monitoring data set into an abnormal probability recognition model, wherein the abnormal probability recognition model is obtained by training multiple sets of training data sets, and the multiple sets of training data sets include historical electric energy meter measurement monitoring abnormal sample sets, trigger interval time samples, and label information representing the abnormal probability size, and are trained until convergence; The trigger interval time sample is the time difference between the time when each electric energy meter triggers the electric energy meter abnormality warning and the time when the electric energy meter abnormality actually occurs; The abnormal probability of each electric energy meter is predicted according to the abnormal probability recognition model to obtain an abnormal probability set and a prediction interval time set corresponding to each electric energy meter.

7. The device for compensating for power loss caused by abnormal measurement of electric energy meter according to claim 6, characterized in that: The abnormal electric energy meter loss compensation module is also used for: The prediction interval time set is uploaded to a cloud database, and the cloud database performs a pre-order prediction compensation on the temporary data set of the electric energy meter measurement according to the prediction interval time, and outputs the compensated temporary data set of the electric energy meter measurement; The compensated electric energy meter measurement temporary data set is input into the main chip storage module for overwriting storage.

8. A method for compensating for power loss caused by abnormal measurement of electric energy meters, characterized in that: The method comprises: Obtaining a distributed network of energy meters; Performing real-time monitoring on the electric energy meter distributed network and outputting an electric energy meter measurement monitoring data set; Inputting the electric energy meter measurement monitoring data set into an abnormal probability identification model, performing probability calculation according to the abnormal probability identification model, obtaining an abnormal probability set, and identifying abnormal electric energy meters with abnormal probabilities greater than a preset abnormal probability; Connecting to a temporary storage module, the temporary storage module is used to store a temporary data set of electric energy meter measurement corresponding to the abnormal electric energy meter; When it is detected that the abnormal electric energy meter is restored, the temporary data set of the electric energy meter is uploaded to the cloud database through the NB-IoT communication module for loss compensation.

Images