Method for maintaining electric energy metering

Abstract

The invention belongs to the technical field of power systems, and discloses a method for maintaining electric energy metering, which comprises the following steps of: acquiring electric energy metering related data; preprocessing the electric energy metering related data to obtain an electric energy metering comprehensive characteristic data set; according to the electric energy metering comprehensive feature data set, training to obtain an electric energy metering error prediction model, and based on the electric energy metering error prediction model, predicting to obtain an electric energy metering error; judging whether error correction is needed or not according to the predicted electric energy metering error; if error correction needs to be carried out, early warning information is generated, and electric energy metering error data is automatically collected; training to obtain an error type identification model according to the electric energy metering error data, and predicting to obtain electric energy metering error type data based on the error type identification model; based on the electric energy metering error type data, utilizing a distribution calibration algorithm to correct the electric energy metering error; the requirement for manual intervention is reduced, and the working efficiency of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power systems, and more particularly to a method for maintaining electric energy metering. Background Art

[0002] Patent announcement number CN101871967A discloses a metering method for an electric energy meter, including the following steps: a. The microprocessor monitors the voltage of the working power supply. Once the voltage value is lower than a voltage setting value, the electric energy meter enters the electricity theft metering mode; b. After a first set time has passed, the microprocessor starts current detection, performs current detection within a second set time, multiplies the measured current value by the rated voltage value of the electric energy meter and then by the total time length of the first set time and the second set time as the electric quantity of the time period, and accumulates the electric quantity of the time period to the total electric quantity; c. The microprocessor monitors the voltage of the working power supply. If the voltage value remains lower than the voltage setting value, return to step b; otherwise, multiply the measured current value by the rated voltage value of the electric energy meter and then by the total time length from the last metering moment to the present as the electric quantity of the time period, and return to the normal working mode. Thus, the electric quantity in the case of electricity theft will not be under-recorded.

[0003] The existing methods for maintaining electric energy metering have the following defects: Lack of targeted correction strategies and failure to select appropriate correction strategies based on error types may result in a single correction method being used for different types of errors. This will make the error correction inaccurate and unable to cope with complex energy metering error situations; failure to define appropriate correction functions for each node may result in the correction process being too rough; The error propagation path is unclear, the electric energy metering system has not been converted into a graph structure, and there is a lack of effective error propagation paths; the correction information between nodes cannot be propagated through directed edges, resulting in the inability to gradually propagate and correct the errors in the system on a global scale, and the inability to accurately track the error propagation process of each node, which reduces the correction effect and efficiency; without a clear error propagation path, it is difficult for the system to trace the root cause of the error, making it difficult to locate the problem node and the correction efficiency is low; the correction amount is not dynamically adjusted according to the error value of the adjacent node, and the correction amount of the node may be fixed or inaccurate; the fixed correction amount cannot reflect the mutual influence between nodes, and cannot flexibly respond to the error type and the actual situation of the system, which leads to over-correction or under-correction, affecting the accuracy of the system; Failure to dynamically adjust according to the actual errors of adjacent nodes will result in some nodes with larger errors not being fully corrected, or some nodes with smaller errors being over-corrected, affecting the accuracy of the entire electric energy metering system; without considering the topological structure, the interaction between nodes is not effectively reflected. Each node in the system may not be able to fully utilize the information of adjacent nodes, resulting in poor results of the correction strategy; without a mechanism to dynamically adjust the correction factor, some nodes may cause excessive changes in their electric energy metering errors due to over-correction, thereby causing system oscillations; especially when the errors of some nodes in the system are large, failure to adjust the correction amplitude according to the actual error will result in over-correction of the error, and even interfere with the entire system, affecting stability; the global error correction formula is not used to achieve error consistency, resulting in the inability to synchronize the error correction of each node; The correction information is not transmitted to other nodes through PLC communication, resulting in the inability to effectively propagate and correct errors, which in turn affects global consistency; errors may gradually accumulate in some nodes, eventually leading to a decrease in the accuracy of electric energy metering of the entire system; if there is a lack of mutual correction mechanism between nodes, some nodes may not be able to obtain correction information from other nodes, resulting in local accumulation of errors; especially when the network topology is complex or the number of nodes is large, the errors of isolated nodes may continue to expand, thus affecting the overall performance of the entire system; without a global error synchronization mechanism, the correction process between nodes may not have appropriate timing and pace, resulting in an uneven distribution of errors; without mutual correction and information transmission between nodes, relying solely on the initial correction of the node itself may ignore the influence of other nodes; without dynamic synchronization of errors between nodes through information propagation mechanism, errors may continue to accumulate in some nodes, affecting the correction process of other nodes; without dynamic correction factors and information propagation mechanism, the system cannot make adaptive adjustments according to changes in the network topology of the electric energy metering system; Without a mechanism to gradually make the error value close to global consistency, the error correction of each node may remain at the local optimum and fail to effectively integrate global information; without an error correction synchronization formula, the final correction error of the node may be inconsistent, resulting in uneven correction effects between different nodes; the error may change with changes in electric energy metering equipment and network environment; without a dynamic adjustment mechanism, the system cannot be optimized in real time according to the change in error, resulting in a decrease in system accuracy.

[0004] In view of this, the present invention proposes a method for maintaining electric energy metering to solve the above problem. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for maintaining electric energy metering, comprising: S1. Collect data related to electric energy measurement; S2. Preprocess the data related to electric energy measurement to obtain a comprehensive feature data set for electric energy measurement; S3, training an electric energy metering error prediction model according to the electric energy metering comprehensive feature data set, and predicting the electric energy metering error based on the electric energy metering error prediction model; S4. Determine whether error correction is required based on the predicted electric energy metering error; if error correction is required, generate warning information and automatically collect electric energy metering error data; S5. Train an error type identification model based on the electric energy metering error data, and predict the electric energy metering error type data based on the error type identification model; correct the electric energy metering error based on the electric energy metering error type data using a distributed calibration algorithm, and transmit the electric energy metering error correction result to other nodes through distributed topology and PLC communication, so that the electric energy metering of all nodes is consistent; S6. Verify all the correction results of the electric energy metering errors. If errors still exist, the electric energy metering control terminal issues a secondary correction instruction until the corrected electric energy metering error reaches a preset electric energy metering error threshold.

[0006] Furthermore, the electric energy metering related data includes electrical parameter data, equipment status data and network parameter data; the electrical parameter data includes line voltage, phase voltage, line current, phase current, power transmission power, grid frequency and total electric energy; the equipment status data includes equipment operating status, equipment temperature and equipment operating time; the network parameter data includes communication network bandwidth, network delay, communication protocol, data packet loss rate, signal strength and network load.

[0007] Furthermore, the method of preprocessing the electric energy metering related data to obtain the electric energy metering comprehensive feature data set includes: By using a density clustering algorithm, outliers existing in the electrical parameter data, device status data, and network parameter data included in the electric energy metering related data are identified and eliminated, and an electrical parameter feature data set, a device status feature data set, and a network parameter feature data set are obtained; The electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are denoised by Kalman filtering, and the denoised electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1 to obtain the normalized electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set; the normalized electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are fused by a weighted model to obtain a comprehensive characteristic data set for electric energy metering.

[0008] Furthermore, the method of fusing the normalized electrical parameter characteristic data set, the device state characteristic data set and the network parameter characteristic data set through a weighted model to obtain an electric energy metering comprehensive characteristic data set includes: The electrical parameter characteristic data set is recorded as , the device status feature data set is recorded as , the network parameter feature data set is recorded as ; The weighted model is: ;in, It is a comprehensive feature dataset for electric energy measurement; is the weight coefficient of the electrical parameter characteristic data set; is the weight coefficient of the equipment status feature data set; is the weight coefficient of the network parameter feature data set.

[0009] Furthermore, the training method of the electric energy metering error prediction model includes: The data set is divided into a training set, a validation set and a test set, and an electric energy metering error prediction model is constructed; the sample set is a subset of the data set, and each sample set includes a historical electric energy metering comprehensive feature data set and the corresponding electric energy metering error; the electric energy metering error prediction model includes an input layer, a GRU layer, a fully connected layer and an output layer; the input layer of the model is used to input the historical electric energy metering comprehensive feature data set, and the number of neurons in the input layer matches the number of features of the historical electric energy metering comprehensive feature data set; The GRU layer is used to process the historical electric energy metering comprehensive feature data set, and the number of GRU layers and the number of neurons are adjusted according to the complexity of the task; the fully connected layer is used to provide additional nonlinear transformation; the model output layer is used to output the electric energy metering error, and the predicted value is output through a neuron, and the identity function is used as the activation function; the electric energy metering error prediction model is a gated recurrent unit model; Use mean absolute error as the loss function to measure the error between the model's predicted value and the actual value; use the training set data to train the model and minimize the loss function through the Adam optimizer; use the validation set to evaluate the performance of the model and tune the model's hyperparameters until the model performance no longer improves or reaches the preset stopping condition; The test set is used to evaluate the performance of the electric energy metering error prediction model in the prediction task. The current electric energy metering comprehensive feature data set is input into the trained electric energy metering error prediction model to obtain the electric energy metering error.

[0010] Furthermore, the method for determining whether error correction is required based on the predicted electric energy metering error includes: If the predicted electric energy metering error is less than or equal to the preset electric energy metering error threshold, it is determined that error correction is not required; If the predicted electric energy metering error is greater than a preset electric energy metering error threshold, it is determined that error correction is required.

[0011] Furthermore, the training method of the error type identification model includes: The data set is divided into a training set, a test set and a validation set, and an error type recognition model is constructed. The error type recognition model includes an input layer, a hidden layer and an output layer; the input layer of the model is used to input historical electric energy metering error data, and the output layer is used to output electric energy metering error type data; the output layer is set with neurons equal to the number of electric energy metering error types, each neuron corresponds to the predicted probability of an electric energy metering error type, and a softmax function is used as an activation function; the error type recognition model is a multi-layer perceptron MLP model; Use multi-classification cross entropy as the model's loss function to measure the difference between the model's predicted value and the actual value; use the training set to train the error type recognition model, and update the model parameters through the back propagation algorithm to minimize the loss function; use the validation set to evaluate the performance of the error type recognition model by calculating the accuracy index; The SGD optimization algorithm is selected as the optimizer, and the model is tuned according to the performance feedback of the validation set. The model parameters are adjusted until the performance no longer improves or the preset stopping condition is reached. The test set is used to evaluate the performance of the model in the prediction task, and the trained error type recognition model is used to predict the current electricity metering error data to obtain the electricity metering error type data.

[0012] Furthermore, the electric energy metering error type data includes measurement deviation error, equipment failure error, environmental impact error, network communication error, algorithm error, clock synchronization error and power grid fluctuation error.

[0013] Furthermore, the method for correcting the electric energy metering error by using a distribution calibration algorithm based on the electric energy metering error type data includes: S91. Record the electric energy metering error type data as a data set ;in, For the Electric energy metering error type data; is the index of the electric energy measurement error type data, ; The total number of electric energy measurement error type data; S92, based on the data of electric energy measurement error type , select the corresponding correction strategy; set the correction function corresponding to different types of electric energy measurement error data : ;in, For the Correction function corresponding to each type of electric energy measurement error data; For the The energy measurement error value of each node; S93, constructing each node corresponding to the electric energy metering error type data in the electric energy metering system into a distributed topology graph through a directed graph ;in, is a node set, representing the energy metering system Energy metering nodes; is a set of edges, representing the directed communication relationship between nodes; The node set ;in, For the nodes; is the number of nodes; the edge set ;in, For the nodes; For the nodes; Representation Node To the adjacent node Sending error correction information; and is the index of the node; S94. For each node , the error correction amount of the node is calculated by the error correction amount calculation formula; the error correction amount calculation formula is: ;in, is the error correction amount of the node; For Node The set of adjacent nodes, that is, all nodes pointing to The parent node set of For the The energy measurement error of adjacent nodes; is the correction amount influencing factor; is the correction function The weight factor of is the index of the adjacent node; S95. Dynamically adjust and design the correction amount influence factor through the correction amount influence factor adjustment formula. The correction amount influence factor adjustment formula is: ;in, For Node The number of adjacent nodes of A constant that controls the size of the overall weight factor; is the influence of the number of adjacent nodes on the weight factor; S96. Correction function by error sensitivity adjustment formula The weight factor is constrained, and the error sensitivity adjustment formula is: ;in, is the post-limit correction function The weight factor of is the maximum value of the electric energy measurement error of all nodes in the electric energy measurement system; To control the error size, the weight factor Influencing factors.

[0014] Furthermore, the method of transmitting the electric energy metering error correction result to other nodes through distributed topology and PLC communication to make the electric energy metering of all nodes consistent includes: Through PLC communication, the corrected energy metering error of each node is transmitted to its adjacent nodes through the signal transmission formula, and the preset node The initial correction error is , the signal transmission formula is: ;in, For Node The initial correction error of In each round of calibration, the node The error is initially corrected by PLC Sent to its downstream node, i.e. , while the node Receive the correction error from the upstream node and update its own energy metering error according to the error correction information formula; the error correction information formula is: ;in, For the updated node The energy measurement error; For Node The energy metering error before receiving the error correction information; As error correction information propagates through the energy metering system, nodes While updating its own energy metering error according to the error correction information from other nodes, the consistency of global error is gradually achieved through the global error correction formula; the global error correction formula is: ;in, For Node The global error value of All nodes continue to synchronize errors through the error correction synchronization formula, and eventually the energy metering errors of all nodes tend to be consistent; the error correction synchronization formula is: ;in, For Node The final correction error of A correction factor for adjusting the size of the final correction amount; The correction factor that adjusts the final correction amount is dynamically adjusted and designed through the correction factor adaptive formula. The correction factor adaptive formula is: ;in, For the The correction factor for adjusting the size of the final correction amount at the iteration; is the coefficient that affects the degree of influence of the error mean on the correction factor; is the mean value of the energy measurement error of all nodes in the system; is the attenuation factor that affects the number of iterations during the correction process; is the current iteration number; is the maximum number of iterations.

[0015] The technical effects and advantages of a method for maintaining electric energy metering of the present invention are as follows: The present invention can uniformly manage and analyze the errors of the entire system by collecting the electric energy metering error data of all nodes into a set; provides a basis for subsequent data processing and analysis, and ensures that the errors of each node can be independently identified and corrected; selects a corresponding correction strategy based on the error type, sets a correction function for data of different error types, and corrects according to the electric energy metering error value of the node; defines a suitable correction function for each node, making the correction process more accurate and effective; The electric energy metering system is converted into a graph structure, so that the correction information of each node can be propagated through the directed edges in the graph, promoting the mutual influence between nodes; the directed graph provides a structured way to track the error propagation path of each node and its adjacent nodes, improving the efficiency and accuracy of error correction; the correction amount calculation formula can dynamically adjust the correction amount of the target node according to the error value of the adjacent node, ensuring that the correction strategy of the entire system can be adjusted according to the actual situation; by calculating the correction amount of each node, the error of each node is gradually reduced, and the overall accuracy of the system is improved; the influencing factor of the number of adjacent nodes can be dynamically adjusted according to the system topology, ensuring that the adjustment of the correction factor can reflect the interaction between the nodes in the network under different network environments; the dynamic adjustment of the correction amount influencing factor helps to balance the stability of the system and avoid oscillation or unnecessary correction caused by over-correction of some nodes; through error sensitivity adjustment, it can avoid over-correction of the electric energy metering system during correction, resulting in system instability; Each node transmits the initially corrected energy metering error to the adjacent nodes through PLC communication. This process ensures that the correction information of each node can be propagated throughout the system, thereby affecting the error correction of other nodes; through this information transmission, the system can gradually converge to global error consistency; in each round of correction, the node updates its own energy metering error after receiving the error correction information from the upstream node; this mechanism ensures that the error of each node in the system is gradually adjusted and corrected, avoiding the local problem of single-point correction; through mutual correction between nodes, it ensures that the error of the entire energy metering system gradually converges; through PLC signal transmission, the errors of all nodes are effectively synchronized, reducing error accumulation or local deviation; through multiple rounds of information propagation and update, each node can be updated according to the correction information of other nodes in the system, rather than relying solely on its own preliminary correction, avoiding the amplification effect of isolated node errors; this method is distributed and has no single control center, so it can avoid the impact of single-point failures and improve the reliability and robustness of the system; On the basis of information transmission and node update, each node gradually makes the error value close to global consistency through the global error correction formula. This ensures that as the correction proceeds, the system error can be adjusted globally, thereby improving the accuracy of the overall system; through the error correction synchronization formula, the final correction error of each node tends to be consistent, thus achieving the goal of error synchronization; eventually, the power metering errors of all nodes tend to be consistent, ensuring the overall accuracy of the system; according to the mean value of the power metering error of all nodes in the system and the number of iterations, the correction factor at each iteration is dynamically adjusted; this adjustment mechanism takes into account factors such as the distribution of errors and the attenuation of correction factors, making the error correction process more flexible and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a method for maintaining electric energy metering; Figure 2 A schematic diagram of the system structure for maintaining electric energy measurement. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1 See also Figure 1 As shown, a method for maintaining electric energy metering in this embodiment includes: S1. Collect data related to electric energy measurement; S2. Preprocess the data related to electric energy measurement to obtain a comprehensive feature data set for electric energy measurement; S3, training an electric energy metering error prediction model according to the electric energy metering comprehensive feature data set, and predicting the electric energy metering error based on the electric energy metering error prediction model; S4. Determine whether error correction is required based on the predicted electric energy metering error; if error correction is required, generate warning information and automatically collect electric energy metering error data; S5. Train an error type identification model based on the electric energy metering error data, and predict the electric energy metering error type data based on the error type identification model; correct the electric energy metering error based on the electric energy metering error type data using a distributed calibration algorithm, and transmit the electric energy metering error correction result to other nodes through distributed topology and PLC communication, so that the electric energy metering of all nodes is consistent; S6. Verify all the correction results of the electric energy metering errors. If errors still exist, the electric energy metering control terminal issues a secondary correction instruction until the corrected electric energy metering error reaches a preset electric energy metering error threshold.

[0019] The data related to electric energy metering include electrical parameter data, equipment status data and network parameter data; electrical parameter data include line voltage, phase voltage, line current, phase current, power transmission power, grid frequency and total electric energy; equipment status data include equipment operating status, equipment temperature and equipment operating time; network parameter data include communication network bandwidth, network delay, communication protocol, data packet loss rate, signal strength and network load.

[0020] The method of preprocessing the electric energy metering related data to obtain the electric energy metering comprehensive feature data set includes: By using a density clustering algorithm, outliers existing in the electrical parameter data, device status data, and network parameter data included in the electric energy metering related data are identified and eliminated, and an electrical parameter feature data set, a device status feature data set, and a network parameter feature data set are obtained; The electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are denoised by Kalman filtering, and the denoised electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1 to obtain the normalized electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set; the normalized electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are fused by a weighted model to obtain a comprehensive characteristic data set for electric energy metering.

[0021] The method of fusing the normalized electrical parameter characteristic data set, the device state characteristic data set and the network parameter characteristic data set through a weighted model to obtain the electric energy metering comprehensive characteristic data set includes: The electrical parameter characteristic data set is recorded as , the device status feature data set is recorded as , the network parameter feature data set is recorded as ; The weighted model is: ;in, It is a comprehensive feature dataset for electric energy measurement; is the weight coefficient of the electrical parameter characteristic data set; is the weight coefficient of the equipment status feature data set; is the weight coefficient of the network parameter feature data set.

[0022] The training method of the energy metering error prediction model includes: The data set is divided into a training set, a validation set and a test set, and an electric energy metering error prediction model is constructed; the sample set is a subset of the data set, and each sample set includes a historical electric energy metering comprehensive feature data set and the corresponding electric energy metering error; the electric energy metering error prediction model includes an input layer, a GRU layer, a fully connected layer and an output layer; the input layer of the model is used to input the historical electric energy metering comprehensive feature data set, and the number of neurons in the input layer matches the number of features of the historical electric energy metering comprehensive feature data set; The GRU layer is used to process the historical electric energy metering comprehensive feature data set, and the number of GRU layers and neurons are adjusted according to the complexity of the task; the fully connected layer is used to provide additional nonlinear transformation; the model output layer is used to output the electric energy metering error, and the predicted value is output through a neuron, and the identity function is used as the activation function; the electric energy metering error prediction model is a gated recurrent unit model; Use mean absolute error as the loss function to measure the error between the model's predicted value and the actual value; use the training set data to train the model and minimize the loss function through the Adam optimizer; use the validation set to evaluate the performance of the model and tune the model's hyperparameters until the model performance no longer improves or reaches the preset stopping condition; The test set is used to evaluate the performance of the electric energy metering error prediction model in the prediction task. The current electric energy metering comprehensive feature data set is input into the trained electric energy metering error prediction model to obtain the electric energy metering error.

[0023] Methods for determining whether error correction is required based on the predicted energy metering error include: If the predicted electric energy metering error is less than or equal to the preset electric energy metering error threshold, it is determined that error correction is not required; If the predicted electric energy metering error is greater than a preset electric energy metering error threshold, it is determined that error correction is required.

[0024] The training method of the error type recognition model includes: The data set is divided into training set, test set and validation set, and an error type recognition model is constructed. The error type recognition model includes an input layer, a hidden layer and an output layer. The input layer of the model is used to input historical electric energy metering error data, and the output layer is used to output electric energy metering error type data. The output layer is set with neurons equal to the number of electric energy metering error types, and each neuron corresponds to the predicted probability of an electric energy metering error type. The softmax function is used as the activation function. The error type recognition model is a multi-layer perceptron MLP model. Use multi-classification cross entropy as the model's loss function to measure the difference between the model's predicted value and the actual value; use the training set to train the error type recognition model, and update the model parameters through the back propagation algorithm to minimize the loss function; use the validation set to evaluate the performance of the error type recognition model by calculating the accuracy index; The SGD optimization algorithm is selected as the optimizer, and the model is tuned according to the performance feedback of the validation set. The model parameters are adjusted until the performance no longer improves or the preset stopping condition is reached. The test set is used to evaluate the performance of the model in the prediction task, and the trained error type recognition model is used to predict the current electricity metering error data to obtain the electricity metering error type data.

[0025] The energy metering error type data includes measurement deviation error, equipment failure error, environmental impact error, network communication error, algorithm error, clock synchronization error and grid fluctuation error.

[0026] Measurement deviation errors are usually caused by design, manufacturing or calibration problems of electric energy metering equipment. The equipment may have nonlinear errors, zero drift, sensitivity errors, etc. Such errors generally accumulate gradually during long-term use, or the calibration errors of the equipment itself are not fully corrected when leaving the factory.

[0027] Equipment failure errors are caused by hardware failure, abnormal operation or aging of the energy metering equipment itself. For example, sensor damage, loose wiring, internal circuit failure of the equipment, and excessive temperature may affect the accuracy of the equipment. Monitoring is carried out through equipment status data, including the equipment's operating status, temperature, operating time, etc. When a device fails, the monitoring system can record information such as the failure time, type, and fault code. In addition, the equipment's fault history and alarm log can also provide such data.

[0028] When the energy metering equipment is running under different environmental conditions, environmental factors such as temperature, humidity, and vibration will affect its accuracy. For example, excessively high temperature may cause electronic components to drift, and a humid environment may cause poor electrical contact. Environmental sensors are used to monitor environmental data such as temperature, humidity, and vibration around the equipment, while recording the working environment conditions of the energy metering equipment. These environmental data can be compared with the energy metering data to analyze whether there is an environmental impact error.

[0029] Network communication errors are usually caused by the instability or unreliability of the communication network. For example, insufficient bandwidth, high network latency, packet loss, signal attenuation and other factors may lead to data transmission errors from the energy metering device to the data concentration system. By monitoring network communication parameters such as bandwidth, latency, packet loss rate, signal strength, network load and other data, it is possible to diagnose whether there are communication problems. This data can be collected through regular network quality checks, network diagnostic tools and logs.

[0030] Algorithmic errors are usually caused by assumptions or calculation deviations of the algorithm itself during the processing and calibration of electric energy metering data. For example, limitations in data preprocessing, signal filtering, and distribution calibration algorithms may lead to inaccurate correction results. Algorithmic errors can be evaluated by comparing and analyzing different algorithms, monitoring data changes before and after algorithm processing, or by verifying data sets (such as standard data sets). The collected data includes the input and output data of the algorithm, model parameters, and debugging logs.

[0031] The timestamp of energy metering equipment is usually provided by a built-in clock or synchronization system. If the clocks between multiple devices are not synchronized or the clocks drift, it may cause timestamp errors, thus affecting the accuracy of energy metering data. Monitor the clock error by collecting the time synchronization signal of the device. The clock synchronization error can be detected by comparing with a standard time source (such as GPS, NTP server, etc.), and the accuracy of the clock can be monitored by recording the clock drift and error. Monitor the clock error by collecting the time synchronization signal of the device. The clock synchronization error can be detected by comparing with a standard time source (such as GPS, NTP server, etc.), and the accuracy of the clock can be monitored by recording the clock drift and error.

[0032] Power system problems such as frequency fluctuations, voltage instability, harmonics, etc. in the power grid may affect the readings of power metering equipment. For example, frequency fluctuations may cause power errors measured by the power meter, and voltage instability may cause inaccurate voltage readings of the metering equipment. The fluctuations of the power grid can be monitored by collecting data such as the voltage, frequency, and power factor of the power grid. Detailed data on power grid fluctuations can be obtained using dedicated power monitoring equipment (such as power quality analyzers). In addition, real-time collection of current, voltage, frequency and other data of the power grid and comparison with power metering data can identify the impact of power grid fluctuations on metering results.

[0033] Based on the electric energy metering error type data, the method of correcting the electric energy metering error by using the distribution calibration algorithm includes: S91. Record the electric energy metering error type data as a data set ;in, For the Electric energy metering error type data; is the index of the electric energy measurement error type data, ; The total number of electric energy measurement error type data; S92, based on the data of electric energy measurement error type , select the corresponding correction strategy; set the correction function corresponding to different types of electric energy measurement error data : ;in, For the Correction function corresponding to each type of electric energy measurement error data; For the The energy measurement error value of each node; S93, constructing each node corresponding to the electric energy metering error type data in the electric energy metering system into a distributed topology graph through a directed graph ;in, is a node set, representing the energy metering system Energy metering nodes; is a set of edges, representing the directed communication relationship between nodes; Node Collection ;in, For the nodes; is the number of nodes; the edge set ;in, For the nodes; For the nodes; Representation Node To the adjacent node Sending error correction information; and is the index of the node; S94. For each node , the error correction amount of the node is calculated by the error correction amount calculation formula; the error correction amount calculation formula is: ;in, is the error correction amount of the node; For Node The set of adjacent nodes, that is, all nodes pointing to The parent node set of For the The energy measurement error of adjacent nodes; is the correction factor, which indicates the influence of the energy measurement error of the adjacent node on the node Weighting factor of the effect of the correction amount; is the correction function The weight factor of is the index of the adjacent node; S95. Dynamically adjust and design the correction amount influence factor through the correction amount influence factor adjustment formula. The correction amount influence factor adjustment formula is: ;in, For Node The number of adjacent nodes of A constant that controls the size of the overall weight factor; is the influence of the number of adjacent nodes on the weight factor; As the system scales As the size of the system increases (i.e., the total number of nodes increases), the impact of each individual node on the global error correction usually decreases. Because the information between nodes is transmitted through adjacent nodes, as the system size increases, the error correction effect of local nodes will be interfered by more nodes. Therefore, Appearing in the denominator means that the larger the system size, The smaller the value of is, the smaller the correction weight of the local node is, which avoids the error correction of a single node in a large-scale system from having too much impact on the overall system, ensuring global consistency and robustness; the number of adjacent nodes of each node is It reflects the connection strength of the node in the network. The number of neighboring nodes is large, which means that the node may exchange information with more other nodes. Therefore, the error correction of this node should not be determined by itself alone, but the influence of neighboring nodes should be considered.

[0034] For example, the total number of nodes For 10 nodes The number of adjacent nodes is 3, the number of adjacent nodes of other nodes in the energy metering system may be different. Assume that node Connect to 5 neighboring nodes; a constant that controls the size of the overall weight factor =10, the influence of the number of adjacent nodes on the weight factor is 2; Compute Node The weight factor ; Therefore, the node The weight factor is ; Compute Node The weight factor ; Therefore, the node The weight factor is ; node The number of adjacent nodes is small ( =3), so its weight factor is 0.625, which is relatively large. This means that the node The error correction of node will depend more on the errors of its neighboring nodes. The number of adjacent nodes is large ( =5), so its weight factor 0.5, which is relatively small, indicating that the node The error correction impact on adjacent nodes is relatively small.

[0035] S96. Correction function by error sensitivity adjustment formula The weight factor is constrained, and the error sensitivity adjustment formula is: ;in, is the post-limit correction function The weight factor of is the maximum value of the electric energy measurement error of all nodes in the electric energy measurement system; To control the error size, the weight factor Influencing factors.

[0036] When the error of a node is large, it means that it may have more serious problems in the system (such as equipment failure, system deviation, etc.). In this case, the impact of the node should be greater, so its correction weight Increase, so that the correction function can correct it more strongly. For nodes with smaller errors, the correction strength should be relatively reduced, because these nodes may already be relatively accurate, and strong correction may lead to over-correction. Therefore, The dynamic adjustment mechanism can adaptively reflect the error of each node in the system, ensuring that important nodes (nodes with large errors) receive more corrections without excessive interference with nodes with smaller errors.

[0037] For example, suppose there is an energy metering system consisting of 5 energy metering nodes, and the energy metering error of each node is as follows: node : =5 (the error value is 5); node : =3 (the error value is 3); node : =7 (the error value is 7); node : =4 (the error value is 4); node : =6 (the error value is 6); Correction function The weight factor 1, controlling the error size to the weight factor Factors that influence is 0.5, the maximum value of all node errors in the energy metering system is 7; Calculate the correction function after each restriction The weight factor is: ; ; ; ; .

[0038] Methods for transmitting the energy metering error correction result to other nodes through distributed topology and PLC communication to make the energy metering of all nodes consistent include: Through PLC communication, the corrected energy metering error of each node is transmitted to its adjacent nodes through the signal transmission formula, and the preset node The initial correction error is , the signal transmission formula is: ;in, For Node The initial correction error of In each round of calibration, the node The error is initially corrected by PLC Sent to its downstream node, i.e. , while the node Receive the correction error from the upstream node and update its own energy metering error according to the error correction information formula; the error correction information formula is: ;in, For the updated node The energy measurement error; For Node The energy metering error before receiving the error correction information; As error correction information propagates through the energy metering system, nodes While updating its own energy metering error according to the error correction information from other nodes, the consistency of global error is gradually achieved through the global error correction formula; the global error correction formula is: ;in, For Node The global error value represents the energy metering error after information propagation and error correction; For example, suppose there are three nodes in the energy metering system. , and The energy measurement errors are , , 3, and these error values ​​become after correction , ,and ; Then, the node The global error value that is: ; This means that the node After considering the corrected error information of other nodes, the global error value is updated to 5.17.

[0039] All nodes continue to synchronize errors through the error correction synchronization formula, and eventually the energy metering errors of all nodes tend to be consistent; the error correction synchronization formula is: ;in, For Node The final correction error of A correction factor that adjusts the size of the final correction; it determines the degree of influence of the difference between the initial correction error and the global error. The larger the value, the smaller the difference between the final correction error and the global error; the smaller the value, the more the node's correction will depend on its own correction result.

[0040] The correction factor that adjusts the final correction amount is dynamically adjusted and designed through the correction factor adaptive formula. The correction factor adaptive formula is: ;in, For the The correction factor for adjusting the size of the final correction amount at the iteration; is the coefficient that affects the degree of influence of the mean error on the correction factor. The larger the mean control error is, the stronger the correction factor is adjusted. is the mean value of the energy measurement error of all nodes in the system; To influence the attenuation factor of the number of iterations during the correction process, control the speed at which the correction factor decreases during the iteration process; is the current iteration number; is the maximum number of iterations.

[0041] Combined with the error mean and iterative attenuation mechanism, the entire formula achieves adaptive adjustment. This adaptive mechanism can adjust the value of the correction factor according to the current system error and the progress of the correction. When the error is large, the correction factor will increase to strengthen the correction process. As the number of iterations increases, the correction factor It will gradually decrease to avoid overcorrection and system oscillation. In this way, the correction factor will not be too strong throughout the process, avoiding the risk of overcorrection. Instead, it will correct large errors in the early stage and gradually decrease in the later stage to ensure that the system gradually converges; For example, suppose there are 5 nodes in the energy metering system, and the energy metering error of each node has different values ​​at different time points. The correction factor that adjusts the final correction amount is 0.5, the total maximum error of the energy metering system is 100, and the maximum number of iterations is The coefficient of the influence of the error mean on the correction factor is 10 times The attenuation factor is 0.1, which affects the number of iterations during the correction process. is 0.05; Assume that the initial energy measurement errors of the five nodes in the energy measurement system are as follows: node Error ; node Error ; node Error ; node Error ; node Error ; The mean value of the energy measurement error of all nodes ; Calculate the correction factor that adjusts the final correction amount: The first round of calibration ( ), ; The second round of calibration ( ), Assume that after the first round of correction, the node error becomes: node Error ; node Error ; node Error ; node Error ; node Error ; The mean value of the energy measurement error of all nodes ; Recalculate the correction factor to adjust the final correction amount: ; At this time, the correction factor increases, indicating that the error of the electric energy metering system is large and the correction force is stronger.

[0042] The preset electric energy metering error threshold is set by the staff, and different electric energy metering errors are collected through the electric energy metering control terminal, and the average value of multiple electric energy metering errors is taken as the preset electric energy metering error threshold.

[0043] This embodiment can uniformly manage and analyze the errors of the entire system by collecting the electric energy metering error data of all nodes into a set; provides a basis for subsequent data processing and analysis, and ensures that the errors of each node can be independently identified and corrected; selects a corresponding correction strategy based on the error type, sets a correction function for data of different error types, and corrects according to the electric energy metering error value of the node; defines a suitable correction function for each node, making the correction process more accurate and effective; The electric energy metering system is converted into a graph structure, so that the correction information of each node can be propagated through the directed edges in the graph, promoting the mutual influence between nodes; the directed graph provides a structured way to track the error propagation path of each node and its adjacent nodes, improving the efficiency and accuracy of error correction; the correction amount calculation formula can dynamically adjust the correction amount of the target node according to the error value of the adjacent node, ensuring that the correction strategy of the entire system can be adjusted according to the actual situation; by calculating the correction amount of each node, the error of each node is gradually reduced, and the overall accuracy of the system is improved; the influencing factor of the number of adjacent nodes can be dynamically adjusted according to the system topology, ensuring that the adjustment of the correction factor can reflect the interaction between the nodes in the network under different network environments; the dynamic adjustment of the correction amount influencing factor helps to balance the stability of the system and avoid oscillation or unnecessary correction caused by over-correction of some nodes; through error sensitivity adjustment, it can avoid over-correction of the electric energy metering system during correction, resulting in system instability; Each node transmits the initially corrected energy metering error to the adjacent nodes through PLC communication. This process ensures that the correction information of each node can be propagated throughout the system, thereby affecting the error correction of other nodes; through this information transmission, the system can gradually converge to global error consistency; in each round of correction, the node updates its own energy metering error after receiving the error correction information from the upstream node; this mechanism ensures that the error of each node in the system is gradually adjusted and corrected, avoiding the local problem of single-point correction; through mutual correction between nodes, it ensures that the error of the entire energy metering system gradually converges; through PLC signal transmission, the errors of all nodes are effectively synchronized, reducing error accumulation or local deviation; through multiple rounds of information propagation and update, each node can be updated according to the correction information of other nodes in the system, rather than relying solely on its own preliminary correction, avoiding the amplification effect of isolated node errors; this method is distributed and has no single control center, so it can avoid the impact of single-point failures and improve the reliability and robustness of the system; On the basis of information transmission and node update, each node gradually makes the error value close to global consistency through the global error correction formula. This ensures that as the correction proceeds, the system error can be adjusted globally, thereby improving the accuracy of the overall system; through the error correction synchronization formula, the final correction error of each node tends to be consistent, thus achieving the goal of error synchronization; eventually, the power metering errors of all nodes tend to be consistent, ensuring the overall accuracy of the system; according to the mean value of the power metering error of all nodes in the system and the number of iterations, the correction factor at each iteration is dynamically adjusted; this adjustment mechanism takes into account factors such as the distribution of errors and the attenuation of correction factors, making the error correction process more flexible and efficient.

[0044] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment can be seen from the description of embodiment 1, which provides a system for maintaining electric energy metering, including: Data acquisition module, used to collect data related to electric energy measurement; A data processing module is used to pre-process the electric energy metering related data to obtain a comprehensive characteristic data set of electric energy metering; An error prediction module is used to obtain an electric energy metering error prediction model based on the electric energy metering comprehensive feature data set training, and predict the electric energy metering error based on the electric energy metering error prediction model; The calibration evaluation module is used to determine whether error correction is required based on the predicted electric energy metering error; if error correction is required, it generates warning information and automatically collects electric energy metering error data; The error calibration module is used to obtain an error type identification model according to the electric energy metering error data training, and predict the electric energy metering error type data based on the error type identification model; based on the electric energy metering error type data, the electric energy metering error is corrected by using a distributed calibration algorithm, and the electric energy metering error correction result is transmitted to other nodes through distributed topology and PLC communication, so that the electric energy metering of all nodes is consistent; The feedback verification module is used to verify all the correction results of the electric energy metering errors. If errors still exist, the electric energy metering control terminal issues a secondary correction instruction until the corrected electric energy metering error reaches a preset electric energy metering error threshold. The modules are connected to each other by wire and / or wireless means.

[0045] Since the electronic device introduced in this embodiment is an electronic device used to implement a method for maintaining electric energy measurement in the embodiment of the present application, based on the method for maintaining electric energy measurement introduced in the embodiment of the present application, a person skilled in the art can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as a person skilled in the art implements an electronic device used in a method for maintaining electric energy measurement in the embodiment of the present application, it belongs to the scope of protection of the present application.

[0046] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0047] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for maintaining electric energy measurement, characterized in that: include: S1. Collect data related to electric energy measurement; S2. Preprocess the data related to electric energy measurement to obtain a comprehensive feature data set for electric energy measurement; S3, training an electric energy metering error prediction model according to the electric energy metering comprehensive feature data set, and predicting the electric energy metering error based on the electric energy metering error prediction model; S4. Determine whether error correction is required based on the predicted electric energy metering error; if error correction is required, generate warning information and automatically collect electric energy metering error data; S5. Train an error type identification model based on the electric energy metering error data, and predict the electric energy metering error type data based on the error type identification model; correct the electric energy metering error based on the electric energy metering error type data using a distributed calibration algorithm, and transmit the electric energy metering error correction result to other nodes through distributed topology and PLC communication, so that the electric energy metering of all nodes is consistent; S6. Verify all the correction results of the electric energy metering errors. If errors still exist, the electric energy metering control terminal issues a secondary correction instruction until the corrected electric energy metering error reaches a preset electric energy metering error threshold.

2. The method for maintaining electric energy measurement according to claim 1, characterized in that: The electric energy metering related data include electrical parameter data, equipment status data and network parameter data; the electrical parameter data include line voltage, phase voltage, line current, phase current, power transmission power, grid frequency and total electric energy; the equipment status data include equipment operating status, equipment temperature and equipment operating time; the network parameter data include communication network bandwidth, network delay, communication protocol, data packet loss rate, signal strength and network load.

3. The method for maintaining electric energy measurement according to claim 2, characterized in that: The method for preprocessing the electric energy metering related data to obtain the electric energy metering comprehensive feature data set includes: By using a density clustering algorithm, outliers existing in the electrical parameter data, device status data, and network parameter data included in the electric energy metering related data are identified and eliminated, and an electrical parameter feature data set, a device status feature data set, and a network parameter feature data set are obtained; The electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are denoised by Kalman filtering, and the denoised electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1 to obtain the normalized electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set; the normalized electrical parameter characteristic data set, the equipment state characteristic data set and the network parameter characteristic data set are fused by a weighted model to obtain a comprehensive characteristic data set for electric energy metering.

4. The method for maintaining electric energy measurement according to claim 3, characterized in that: The method of fusing the normalized electrical parameter characteristic data set, the device state characteristic data set and the network parameter characteristic data set through a weighted model to obtain an electric energy metering comprehensive characteristic data set includes: The electrical parameter characteristic data set is recorded as , the device status feature data set is recorded as , the network parameter feature data set is recorded as ; The weighted model is: ;in, It is a comprehensive feature dataset for electric energy measurement; is the weight coefficient of the electrical parameter characteristic data set; is the weight coefficient of the equipment status feature data set; is the weight coefficient of the network parameter feature data set.

5. The method for maintaining electric energy measurement according to claim 4, characterized in that: The training method of the electric energy metering error prediction model includes: The data set is divided into a training set, a validation set and a test set, and an electric energy metering error prediction model is constructed; the sample set is a subset of the data set, and each sample set includes a historical electric energy metering comprehensive feature data set and the corresponding electric energy metering error; the electric energy metering error prediction model includes an input layer, a GRU layer, a fully connected layer and an output layer; the input layer of the model is used to input the historical electric energy metering comprehensive feature data set, and the number of neurons in the input layer matches the number of features of the historical electric energy metering comprehensive feature data set; The GRU layer is used to process the historical electric energy metering comprehensive feature data set, and the number of GRU layers and the number of neurons are adjusted according to the complexity of the task; the fully connected layer is used to provide additional nonlinear transformation; the model output layer is used to output the electric energy metering error, and the predicted value is output through a neuron, and the identity function is used as the activation function; the electric energy metering error prediction model is a gated recurrent unit model; Use mean absolute error as the loss function to measure the error between the model's predicted value and the actual value; use the training set data to train the model and minimize the loss function through the Adam optimizer; use the validation set to evaluate the performance of the model and tune the model's hyperparameters until the model performance no longer improves or reaches the preset stopping condition; The test set is used to evaluate the performance of the electric energy metering error prediction model in the prediction task. The current electric energy metering comprehensive feature data set is input into the trained electric energy metering error prediction model to obtain the electric energy metering error.

6. The method for maintaining electric energy measurement according to claim 5, characterized in that: The method for determining whether error correction is required based on the predicted electric energy metering error includes: If the predicted electric energy metering error is less than or equal to the preset electric energy metering error threshold, it is determined that error correction is not required; If the predicted electric energy metering error is greater than a preset electric energy metering error threshold, it is determined that error correction is required.

7. The method for maintaining electric energy measurement according to claim 6, characterized in that: The training method of the error type identification model includes: The data set is divided into a training set, a test set and a validation set, and an error type recognition model is constructed. The error type recognition model includes an input layer, a hidden layer and an output layer; the input layer of the model is used to input historical electric energy metering error data, and the output layer is used to output electric energy metering error type data; the output layer is set with neurons equal to the number of electric energy metering error types, each neuron corresponds to the predicted probability of an electric energy metering error type, and a softmax function is used as an activation function; the error type recognition model is a multi-layer perceptron MLP model; Use multi-classification cross entropy as the model's loss function to measure the difference between the model's predicted value and the actual value; use the training set to train the error type recognition model, and update the model parameters through the back propagation algorithm to minimize the loss function; use the validation set to evaluate the performance of the error type recognition model by calculating the accuracy index; The SGD optimization algorithm is selected as the optimizer, and the model is tuned according to the performance feedback of the validation set. The model parameters are adjusted until the performance no longer improves or the preset stopping condition is reached. The test set is used to evaluate the performance of the model in the prediction task, and the trained error type recognition model is used to predict the current electricity metering error data to obtain the electricity metering error type data.

8. The method for maintaining electric energy measurement according to claim 7, characterized in that: The electric energy metering error type data includes measurement deviation error, equipment failure error, environmental impact error, network communication error, algorithm error, clock synchronization error and power grid fluctuation error.

9. The method for maintaining electric energy measurement according to claim 8, characterized in that: The method for correcting the electric energy metering error by using a distribution calibration algorithm based on the electric energy metering error type data comprises: S91. Record the electric energy metering error type data as a data set ;in, For the Electric energy metering error type data; is the index of the electric energy measurement error type data, ; The total number of electric energy measurement error type data; S92, based on the data of electric energy measurement error type , select the corresponding correction strategy; set the correction function corresponding to different types of electric energy measurement error data : ;in, For the Correction function corresponding to each type of electric energy measurement error data; For the The energy measurement error value of each node; S93, constructing each node corresponding to the electric energy metering error type data in the electric energy metering system into a distributed topology graph through a directed graph ;in, is a node set, representing the energy metering system Energy metering nodes; is a set of edges, representing the directed communication relationship between nodes; The node set ;in, For the nodes; is the number of nodes; the edge set ;in, For the nodes; For the nodes; Representation Node To the adjacent node Sending error correction information; and is the index of the node; S94. For each node , the error correction amount of the node is calculated by the error correction amount calculation formula; the error correction amount calculation formula is: ;in, is the error correction amount of the node; For Node The set of adjacent nodes, that is, all nodes pointing to The parent node set of For the The energy measurement error of adjacent nodes; is the correction amount influencing factor; is the correction function The weight factor of is the index of the adjacent node; S95. Dynamically adjust and design the correction amount influence factor through the correction amount influence factor adjustment formula. The correction amount influence factor adjustment formula is: ;in, For Node The number of adjacent nodes of A constant that controls the size of the overall weight factor; is the influence of the number of adjacent nodes on the weight factor; S96. Correction function by error sensitivity adjustment formula The weight factor is constrained, and the error sensitivity adjustment formula is: ;in, is the post-limit correction function The weight factor of is the maximum value of the electric energy measurement error of all nodes in the electric energy measurement system; To control the error size, the weight factor Influencing factors.

10. The method for maintaining electric energy measurement according to claim 9, characterized in that: The method of transmitting the electric energy metering error correction result to other nodes through distributed topology and PLC communication to make the electric energy metering of all nodes consistent includes: Through PLC communication, the corrected energy metering error of each node is transmitted to its adjacent nodes through the signal transmission formula, and the preset node The initial correction error is , the signal transmission formula is: ;in, For Node The initial correction error of In each round of calibration, the node The error is initially corrected by PLC Sent to its downstream node, i.e. , while the node Receive the correction error from the upstream node and update its own energy metering error according to the error correction information formula; the error correction information formula is: ;in, For the updated node The energy measurement error; For Node The energy metering error before receiving the error correction information; As error correction information propagates through the energy metering system, nodes While updating its own energy metering error according to the error correction information from other nodes, the consistency of global error is gradually achieved through the global error correction formula; the global error correction formula is: ;in, For Node The global error value of All nodes continue to synchronize errors through the error correction synchronization formula, and eventually the energy metering errors of all nodes tend to be consistent; the error correction synchronization formula is: ;in, For Node The final correction error of A correction factor for adjusting the size of the final correction amount; The correction factor that adjusts the final correction amount is dynamically adjusted and designed through the correction factor adaptive formula. The correction factor adaptive formula is: ;in, For the The correction factor for adjusting the size of the final correction amount at the iteration; is the coefficient that affects the degree of influence of the error mean on the correction factor; is the mean value of the energy measurement error of all nodes in the system; is the attenuation factor that affects the number of iterations during the correction process; is the current iteration number; is the maximum number of iterations.

Images