Multi-communication-mode remotely-upgraded three-phase electric energy meter system

Abstract

The invention relates to the technical field of three-phase electric energy meters, in particular to a multi-communication-mode remotely-upgradable three-phase electric energy meter system which comprises a background parallel management unit, an electric energy information acquisition unit, a background remote upgrading unit, an electric energy data processing unit, a data training unit, a data self-checking unit and a load prediction unit. When a cloud upgrading instruction is generated in the background parallel management unit, the cloud upgrading information instruction is transmitted into the electric energy information acquisition unit, after the upgrading instruction is received, the electric energy information acquisition unit acquires upgrading state information and historical data packets of each electric energy meter, and the electric energy data processing unit cleans the historical data packets therein and sends the cleaned historical data packets to the background parallel management unit. Specifically, an average value of a ratio of an out-of-power range value to a rated power value and a ratio of a connection deviation rate is taken as a prediction weighting item constructed by a primary model, so that the regulation and control pre-judgment requirement of multiple risks in a future environment is met, and the service time of an electric energy meter at the position is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of three-phase electric energy meters, and particularly to a three-phase electric energy meter system with multiple communication methods and remote upgrade capabilities. Background Art

[0002] With the continuous advancement of the construction of smart grids, three-phase electric energy meters, as key data acquisition and metering devices in the power system, the advancement of their functions and the stability of the system are becoming increasingly important. To meet the continuously improving power management requirements, the remote upgrade function has become an indispensable feature of three-phase electric energy meter systems. However, the existing remote upgrade methods for three-phase electric energy meters on the market currently have significant deficiencies in terms of environmental adaptability. In areas with complete communication infrastructure such as cities, although there are high-speed and stable network conditions, the existing upgrade solutions often overly rely on specific communication networks, such as 4G or wired networks. Once the network experiences a short-term failure, signal interference, or even insufficient bandwidth due to regional network congestion, the upgrade process will be blocked. This may not only result in upgrade failures but also require a large amount of time and manpower for secondary upgrade operations, greatly affecting the efficiency of power operation and maintenance.

[0003] The existing upgrade methods for three-phase electric energy meter systems lack sufficient flexibility when facing electric energy meter terminals with different hardware configurations. Electric energy meters produced by different manufacturers have different hardware performances, storage capacities, and computing capabilities. Some upgrade solutions do not fully consider these differences, resulting in the upgrade process being interrupted due to insufficient resources on some electric energy meters with limited hardware resources, or the new functions not being able to operate properly after the upgrade, seriously affecting the user experience and the overall improvement of the intelligent level of the power system. Summary of the Invention

[0004] In view of the above-mentioned drawbacks of the prior art, the present invention provides a three-phase electric energy meter system with multiple communication methods and remote upgrade capabilities, which can effectively solve the problems in the prior art.

[0005] Technical Solution The present invention provides a three-phase electric energy meter system with multiple communication methods and remote upgrade capabilities, including a background parallel management unit, an electric energy information collection unit, a background remote upgrade unit, an electric energy data processing unit, a data training unit, a data self-check unit, and a load prediction unit. When a cloud upgrade instruction is generated in the background parallel management unit, the cloud upgrade information instruction is transmitted to the electric energy information collection unit. After receiving the upgrade instruction, the electric energy information collection unit collects the upgrade status information and historical data packets of each electric energy meter. The electric energy data processing unit cleans the historical data packets among them. Through the data training unit, a primary model construction is performed on the processed historical data packets. Through the load prediction unit, predicted data is obtained to get the data group A of the electric energy meter. Then, a secondary training model construction is performed on the data group A for the upgrade model to obtain the data group B. The data self-check unit judges the future electric energy load according to the data group B and generates the future electric energy data time series Xf and its power wave peak value. The load prediction unit compares the future electric energy data time series Xf and the power wave peak value with the maximum rated power of the electric energy meter. The data self-check unit judges the working state of the electric energy meter in the future time period and feeds it back to the background remote upgrade unit. The background remote upgrade unit issues specific remote upgrade tasks according to the future working states of each electric energy meter.

[0006] Further, the method for obtaining the upgrade status information of each electric energy meter is as follows: Based on the current version information of the electric energy meter and the internal power supply information of the electric energy meter, it is packaged into local status information, and the above local information status is fed back to the background remote upgrade unit. An upgrade plan is generated in the background remote upgrade unit. The historical data packet contains the data information of the power system, including power load data and time information data. The upgrade status information includes the version number of the current electric energy meter, the running time of this version, the specific location, and the internal power supply information of the electric energy meter.

[0007] Further, the cleaning processing steps include: making an original judgment on the historical data packet, screening and removing the electric energy data that fails to be successfully collected and duplicate data. Then, through the data concentrator, the data format is unified and accurate to three decimal places, and it is packaged into a data packet.

[0008] Furthermore, the primary model construction includes a data preparation unit and a model training unit. The data preparation unit converts data packets into data for input to the LSTM model, determines the number of LSTM layers and the number of neurons in each LSTM layer, adds a fully connected layer to map the features output by the LSTM layer to the final prediction dimension. The fully connected layer linearly transforms the feature vectors output by the LSTM layer through a weight matrix to obtain the primary prediction result, and uses a sliding window to generate time series samples. By virtue of its unique gating mechanism, including the input gate, forget gate, and output gate, the LSTM model can effectively remember data information over a long period in the past. The LSTM model can be based on data of peak and trough power consumption periods days or even weeks ago to accurately predict future load changes. The data training unit is responsible for training the LSTM model for load prediction, including model construction, training, and evaluation: The LSTM model is constructed through the hidden state at the time step and the input at the current time step, and obtains the weight matrices of the forget gate, input gate, and candidate state, and uses activation functions to activate the weight matrices of the forget gate, input gate, and candidate state.

[0009] Furthermore, the method for the load prediction unit to perform data prediction is as follows: Judge the risk operation data and state performance in the primary model construction data. The operation risk data includes power values measured far beyond the normal three-phase power range and connection deviation rates at a certain moment. The state performance data includes state performance values and operation loss values. Set the prediction rules for the secondary model construction. Take the average of the ratio of the value exceeding the power range to the rated power value and the ratio of the connection deviation rate as the prediction weighting term for the primary model construction to form data group A.

[0010] Furthermore, the secondary model construction includes a data input unit and a secondary model training unit. Inputting data group A into the LSTM model can judge and predict future situations to obtain the secondary prediction result, marked as data group B. Data group B is expanded to generate the future power data time series Xf and its power wave peak value.

[0011] Furthermore, the data self-check unit can judge the working state of the electricity meter in the future time period. The basis is that if the power wave peak value passing through in the future time period is greater than or equal to the maximum rated power of the electricity meter, it means that the electricity meter cannot meet the maximum passing electricity value in the future time period, generates an optimization and upgrade signal, and feeds it back to the background remote upgrade unit. If the power wave peak value passing through in the future time period is less than or equal to the maximum rated power of the electricity meter, it means that this electricity meter does not require remote upgrade.

[0012] Furthermore, the remote upgrade task distribution methods include, but are not limited to, software updates initiated by the remote master station, OTA updates based on the communication network, and local manual updates.

[0013] Beneficial effects In the present invention, remote upgrade task information sent by a remote upgrade background is received; power information of a target electricity meter is obtained; based on the electricity meter information, it is determined whether the target electricity meter meets the preset remote upgrade task requirements, and then an upgrade plan is returned to the remote upgrade background, where the data is used as a weighted item according to risk operation data and status performance. The upgrade plan is calculated based on the electricity meter information and the electricity meter battery information. The remote upgrade task sent by the remote upgrade background according to the upgrade plan is received; the electronic control unit is upgraded according to the remote upgrade task. The upgrade plan of the remote upgrade task can be determined more accurately, the flexibility of the remote upgrade task execution scenario is improved, and compared with manually calculating the upgrade plan of the remote upgrade task, the calculation efficiency can be greatly improved, and the cost can be reduced. At the same time, this method predicts based on the original data of the electricity meter under different usage scenarios, and the background remote upgrade unit sends specific remote upgrade tasks according to the future working states of each electricity meter, and can make inferences according to the current usage environment, which is suitable for the normal use of the electricity meter in various environments.

[0014] Compared with the existing upgrade methods, in the present invention, risk operation data and status performance are used as strengthening items. Specifically, the average value of the ratio of the value exceeding the power range to the rated power value and the connection deviation rate ratio is used as the prediction weighted item for the construction of a primary model, which meets the requirements of the regulation and prediction of multiple risks in the future environment and improves the service life of the electricity meter at this location.

[0015] In the system, by using the LSTM model through its unique gating mechanism, including an input gate, a forget gate, and an output gate, it can effectively remember data information over a long period in the past. The LSTM model can be based on the data of peak and valley power consumption periods several days or even weeks ago, so as to accurately predict future load changes. Compared with the existing neural networks, this is one of the advantages of this system, and the LSTM model can automatically learn these non-stationary features in the data and dynamically adjust the weight distribution for data at different times. During the high-temperature period in summer, large-power electrical appliances are used frequently, and the power load data fluctuates greatly. The LSTM model can analyze and predict the current data more reasonably according to the characteristics of the summer period in historical data, accurately capture the law of load changes, provide a reliable basis for power dispatching and management, provide a prediction basis for subsequent load prediction, and meet the usage functions of each electricity meter in different environments. Description of the drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of the present invention; Figure 2 It is a diagram of the steps for constructing the primary and secondary training models of the present invention. Specific embodiments

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0019] The following further describes the present invention with reference to the embodiments.

[0020] Embodiment 1: A three-phase electric energy meter system with multi-communication modes and remote upgradeability. Refer to the attached Figure 1 - attached Figure 2 , a three-phase electric energy meter system with multi-communication modes and remote upgradeability, including; a background parallel management unit, an electric energy information collection unit, a background remote upgrade unit, an electric energy data processing unit, a data training unit, a data self-check unit, and a load prediction unit; When a cloud upgrade instruction is generated in the background parallel management unit, the cloud upgrade information instruction is transmitted to the electric energy information collection unit. After receiving the upgrade instruction, the electric energy information collection unit collects the upgrade status information and historical data packets of each electric energy meter. The electric energy data processing unit cleans the historical data packets therein. Through the data training unit, a model is constructed once for the processed historical data packets. One model construction includes a data preparation unit and a model training unit. The data preparation unit converts the data packets into data for input to the LSTM model, determines the number of LSTM layers and the number of neurons in each LSTM layer, and adds a fully connected layer to map the features output by the LSTM layer to the final prediction dimension. The fully connected layer linearly transforms the feature vectors output by the LSTM layer through a weight matrix to obtain the prediction result of one time; the LSTM model can learn the commonalities and characteristics of data in different scenarios through training on a large number of diverse data sets, and has good generalization ability.

[0021] The upgrade plan is calculated based on the electricity meter information and the electricity meter battery information, and receives the remote upgrade task sent by the remote upgrade background according to the upgrade plan; upgrading the electronic control unit according to the remote upgrade task can more accurately determine the upgrade plan of the remote upgrade task, improve the flexibility of the remote upgrade task execution scenario, and compared with manually calculating the upgrade plan of the remote upgrade task, it can greatly improve the calculation efficiency and reduce costs.

[0022] Moreover, the LSTM model can remember the data of peak and valley power consumption periods several days or even weeks ago, so as to accurately predict future load changes. Compared with the existing neural networks, this is one of the advantages of this system. And the LSTM model can automatically learn these non-stationary features in the data and dynamically adjust the weight distribution for data at different times. During the high-temperature period in summer, high-power electrical appliances such as air conditioners are used frequently, and the power load data fluctuates greatly. The LSTM model can analyze and predict the current data more reasonably according to the characteristics of the summer period in historical data, accurately capture the law of load changes, provide a reliable basis for power dispatching and management, provide a prediction basis for subsequent load prediction, and meet the usage functions of each electricity meter in different environments.

[0023] Predict data through the load prediction unit. The method for the load prediction unit to perform data prediction is: judge the risk operation data and state performance in the data of one model construction. The operation risk data includes the power value measured far beyond the normal three-phase power range and the connection deviation rate at a certain moment. The state performance data includes the state performance value and the operation loss value. Set the prediction rules for the secondary model construction, and perform data processing on the rated optimization value YH and the connection deviation rate CX through the formula: Obtain the adjustment coefficient TZ, where a1 and a2 are both preset proportionality coefficients. Obtain the rated power and the excess power value of the electric energy meter, perform a difference process on them to obtain the actual power deviation, and perform a ratio process on it and the rated power of the electric energy meter to obtain the rated optimization value, which is marked as YH. Use the average value of the ratio of the excess power range value to the rated power value and the connection deviation rate ratio as the prediction weighting term for the construction of the primary model to form the data group A; Then, construct a secondary training model for the data group A for the upgrade model to obtain the data group B. The secondary model construction includes a data input unit and a secondary model training unit. Input the data group A into the LSTM model, which can judge and predict future situations to obtain the secondary prediction result, marked as the data group B. The data group B is expanded to generate the future electric energy data time series Xf and its power wave peak value; Receive the remote upgrade task information sent by the remote upgrade background; Obtain the electric energy information of the target electric energy meter; Based on the electric energy meter information, determine whether the target electric energy meter meets the preset remote upgrade task requirements, and then return the upgrade plan to the remote upgrade background, where the data is used as a weighting term according to the risk operation data and the state performance.

[0024] The method for obtaining the upgrade status information of each electric energy meter is as follows: Based on the current version information and the internal power supply information of the electric energy meter, package them as local status information and feedback the above local information status to the background remote upgrade unit. In the background remote upgrade unit, an upgrade plan is generated. The historical data packet contains the data information of the power system, including power load data and time information data. The upgrade status information includes the version number of the current electric energy meter, the running time of this version, the specific location, and the internal power supply information of this electric energy meter. The data self-checking unit judges the future electric energy load according to the data group B and generates the future electric energy data time series Xf and its power wave peak value. The load prediction unit compares the future electric energy data time series Xf and the power wave peak value with the maximum rated power of the electric energy meter. The data self-checking unit judges the working state of the electric energy meter during this future time period and feeds it back to the background remote upgrade unit. The background remote upgrade unit issues specific remote upgrade tasks according to the future working states of each electric energy meter; This method makes predictions based on the original data of the electric energy meter under different usage scenarios. The background remote upgrade unit issues specific remote upgrade tasks according to the future working states of each electric energy meter, and can make inferences according to the current usage environment, which is suitable for the normal use of electric energy meters in various environments.

[0025] Example 2: The cleaning process steps include: making an original judgment on historical data packets, screening and removing power data that fails to be successfully collected and duplicate data, and then, through a data concentrator, unifying the data format, accurate to three decimal places, and packing them into data packets; Using a sliding window to generate time series samples; the data training unit is responsible for training the LSTM model for load prediction, including model construction, training, and evaluation: The LSTM model is constructed through the hidden state of time steps and the input of the current time step, and obtains the weight matrices of the forget gate, input gate, and candidate state, and uses activation functions to activate the weight matrices of the forget gate, input gate, and candidate state; Utilizing the LSTM model through its unique gating mechanism, including the input gate, forget gate, and output gate, can effectively remember data information over a long period in the past. The LSTM model can be based on data of peak and trough power consumption periods days or even weeks ago, so as to accurately predict future load changes.

[0026] Example 3: The data self-check unit can judge the working state of the electric energy meter in the future time period, and the basis is that if the peak value of the power wave passing through in the future time period is greater than or equal to the maximum rated power of the electric energy meter, it means that the electric energy meter cannot meet the maximum passing electric energy value in the future time period, generate an optimization and upgrade signal, and feedback it to the background remote upgrade unit. If the peak value of the power wave passing through in the future time period is less than or equal to the maximum rated power of the electric energy meter, it means that this electric energy meter does not require remote upgrade; The remote upgrade task distribution methods include but are not limited to software updates initiated by the remote master station, OTA updates based on the communication network, and local manual updates; Therefore, in the present invention, risk operation data and state performance are used as strengthening items. Specifically, the average value of the ratio of the value exceeding the power range to the rated power value and the ratio of the connection deviation rate is used as the prediction weighting item for one model construction, meeting the requirements of regulatory pre-judgment for multiple risks in the future environment and improving the service life of the electric energy meter at this location.

[0027] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; And these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A three-phase electric energy meter system with multi-communication methods and remote upgradeability, characterized in that, It includes a background parallel management unit, an electric energy information collection unit, a background remote upgrade unit, an electric energy data processing unit, a data training unit, a data self-check unit, and a load prediction unit. When a cloud upgrade instruction is generated in the background parallel management unit, the cloud upgrade information instruction is transmitted to the electric energy information collection unit. After receiving the upgrade instruction, the electric energy information collection unit collects the upgrade status information and historical data packets of each electric energy meter. The electric energy data processing unit cleans the historical data packets therein. Through the data training unit, a primary model construction is performed on the processed historical data packets. The obtained data is predicted by the load prediction unit to obtain the data group A of the electric energy meter. Then, a secondary training model construction is performed on the data group A for the upgrade model to obtain the data group B. The data self-check unit judges the future electric energy load according to the data group B and generates the future electric energy data time series Xf and its power wave peak value. The load prediction unit compares the future electric energy data time series Xf and the power wave peak value with the maximum rated power of the electric energy meter. The data self-check unit feeds back to the background remote upgrade unit, and the background remote upgrade unit issues specific remote upgrade tasks according to the future working states of each electric energy meter.

2. The three-phase electric energy meter system capable of remote upgrade with multiple communication methods according to claim 1, wherein, The method for obtaining the upgrade status information of each electric energy meter is as follows: Based on the current version information of the electric energy meter and the internal power supply information of the electric energy meter, it is packaged as local status information and fed back to the background remote upgrade unit. An upgrade plan is generated in the background remote upgrade unit. The historical data packet contains the data information of the power system, including power load data and time information data. The upgrade status information includes the version number of the current electric energy meter, the running time of this version, the specific location, and the internal power supply information of the electric energy meter.

3. A three-phase watt-hour meter system capable of remote upgrade with multiple communication methods according to claim 2, characterized in that, The cleaning process steps include: making an original judgment on the historical data packet, screening and removing the electric energy data that fails to be successfully collected and duplicate data, and packaging them into a data packet.

4. A three-phase electric energy meter system with multiple communication methods and remote upgradeability according to claim 3, characterized in that The primary model construction includes a data preparation unit and a model training unit. The data preparation unit converts the data packet into the data input for the LSTM model, determines the number of LSTM layers and the number of neurons in each LSTM layer, and adds a fully connected layer to map the features output by the LSTM layer to the final prediction dimension. The fully connected layer linearly transforms the feature vector output by the LSTM layer through a weight matrix to obtain the primary prediction result, and uses a sliding window to generate time series samples.

5. A three-phase electric energy meter system with multiple communication methods and remote upgradeability according to claim 4, characterized in that, The method for the load prediction unit to perform data prediction is as follows: Judge the risk operation data and state performance in the primary model construction data. The operation risk data includes the power value measured far beyond the normal three-phase power range and the connection deviation rate at a certain moment. The state performance data includes the state performance value and the operation loss value. Set the prediction rule for the secondary model construction, and form the data group A by taking the average of the ratio of the value exceeding the power range to the rated power value and the ratio of the connection deviation rate as the prediction weighting term for the primary model construction.

6. A three-phase electric energy meter system with multiple communication methods and remote upgradeability according to claim 4, characterized in that The secondary model construction includes a data input unit and a secondary model training unit. Inputting data set A into the LSTM model can judge and predict future situations, obtaining a secondary prediction result, marked as data set B. Data set B is expanded to generate the future power data time series Xf and its power wave peak value.

7. A three-phase electric energy meter system with multi-communication modes and remote upgradeability according to claim 1, characterized in that The data self-check unit can judge the working state of the electric energy meter in the future time period. The basis is that if the power wave peak value passing through in the future time period is greater than or equal to the maximum rated power of the electric energy meter, it means that the electric energy meter cannot meet the maximum passing electric energy value in the future time period, generating an optimization and upgrade signal and feeding it back to the background remote upgrade unit. If the power wave peak value passing through in the future time period is less than or equal to the maximum rated power of the electric energy meter, it means that this electric energy meter does not require remote upgrade.

8. A three-phase electric energy meter system with multiple communication methods and remote upgradeability according to claim 1, characterized in that The remote upgrade task distribution methods include but are not limited to software updates initiated by the remote master station, OTA updates based on the communication network, and local manual updates.

9. A three-phase electric energy meter system capable of remote upgrade with multiple communication methods according to claim 3, characterized in that, When cleaning data, the historical data packets pass through the data concentrator to unify the data format and be accurate to three decimal places.

10. A three-phase electric energy meter system with multiple communication methods and remote upgradeability according to claim 4, characterized in that The data training unit is responsible for training the LSTM model for load prediction, including model construction, training, and evaluation: The LSTM model is constructed through the hidden state of the time step and the input of the current time step, and the weight matrices of the forget gate, input gate, and candidate state are obtained. The activation function is used to activate the weight matrices of the forget gate, input gate, and candidate state.

Images