Optimal configuration method and system for power quality management of power distribution network, and electronic equipment
Through the method of dynamically optimizing the acquisition frequency, the real-time and accuracy of power data acquisition in smart grid systems is solved, the system burden is reduced, data processing efficiency is improved, and the distribution network power quality management is provided.
Patent Information
- Application Number
- CN202411181714.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-22
AI Technical Summary
The existing smart grid systems have problems of difficult to guarantee real-time and accuracy in power consumption data acquisition, especially when the data volume is large, it is easy to cause system burden.
The local module acquisition terminal obtains the initial acquisition frequency, combines and filters the electricity consumption data, calls the power consumption demand timing prediction model for analysis, determines the dynamic acquisition frequency, and realizes real-time acquisition data acquisition, reduces errors, and reduces system burden.
It improves the real-time and accuracy of electricity consumption data, reduces the burden on the power grid system, improves data processing efficiency, and provides an important basis for power quality governance.
Smart Images

Figure CN119010008A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power quality management optimization of distribution networks, and in particular to a method, system and electronic equipment for optimizing power quality management of distribution networks. Background Art
[0002] With the development of science and technology and the development of smart grids, smart meters are becoming more and more popular. Smart meters can collect users' electricity consumption data in real time and upload it to the data center through the communication network.
[0003] However, in the existing technology, the collection of electricity consumption data in the smart grid system is often done at a fixed time and in a quantitative manner, but the real-time and accuracy of the collected electricity consumption data cannot be guaranteed, and a large amount of collected data can easily cause a system burden. Summary of the invention
[0004] The present invention provides a method, system and electronic device for optimizing the configuration of power quality management in a distribution network, so as to realize the real-time collection of power consumption data, reduce the error in the data collection process, improve the accuracy of the data, and through the dynamic optimization of the collection frequency, reduce the burden on the power grid system and improve the data processing efficiency of the system. Efficient and accurate power data collection is the basis for optimizing the configuration of power quality management in the distribution network. Through the real-time and accurate collection of power grid operation data, power quality problems such as voltage deviation, harmonic current, three-phase imbalance and other data can be discovered in time, which provides an important basis for subsequent power quality analysis and management.
[0005] According to one aspect of the present invention, a method for optimizing power quality management of a distribution network is provided, comprising:
[0006] The local module acquisition terminal acquires a first acquisition frequency, and receives power consumption data sent by multiple application detection modules within a current preset time period based on the first acquisition frequency;
[0007] The local module collection terminal merges and filters the plurality of power consumption data to obtain power consumption data for a target period, and sends the power consumption data for the target period to a power consumption data processing server;
[0008] The power consumption data processing server responds to the power consumption data of the target period sent by the local module collection terminal, calls the power demand time series prediction model, performs prediction analysis on the power consumption data of the target period based on the power demand time series prediction model, obtains the power demand of the target period, and sends the power demand of the target period to the local module collection terminal;
[0009] The local module collection terminal obtains a mapping relationship between the power demand and the collection frequency in response to the power demand in the target period sent by the power data processing server, and determines a second collection frequency according to the mapping relationship and the power demand in the target period;
[0010] The local module collection terminal receives the power consumption data sent by the plurality of application detection modules within a next preset time period based on the second collection frequency.
[0011] According to another aspect of the present invention, a distribution network power quality management optimization configuration system is provided, comprising:
[0012] The local module collection terminal is used to obtain a first collection frequency, and receive the power consumption data sent by multiple application detection modules within a current preset time period based on the first collection frequency;
[0013] The local module collection terminal is used to merge and filter the plurality of power consumption data to obtain the power consumption data of the target period, and send the power consumption data of the target period to the power consumption data processing server;
[0014] The power consumption data processing server is used to respond to the power consumption data of the target period sent by the local module collection terminal, call the power demand time series prediction model, perform prediction analysis on the power consumption data of the target period based on the power demand time series prediction model, obtain the power demand of the target period, and send the power demand of the target period to the local module collection terminal;
[0015] The local module collection terminal is used to respond to the target period power demand sent by the power data processing server, obtain the mapping relationship between the power demand and the collection frequency, and determine the second collection frequency according to the mapping relationship and the target period power demand;
[0016] The local module collection terminal is used to receive the power consumption data sent by the multiple application detection modules within the next preset time period based on the second collection frequency.
[0017] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:
[0018] at least one processor;
[0019] and a memory communicatively connected to the at least one processor; wherein,
[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network power quality management optimization configuration method described in any embodiment of the present invention.
[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the distribution network power quality management optimization configuration method described in any embodiment of the present invention when executed.
[0022] The technical solution of the embodiment of the present invention is to obtain a first collection frequency through a local module collection terminal, and receive power consumption data sent by multiple application detection modules within a current preset time period based on the first collection frequency; the local module collection terminal merges and filters the multiple power consumption data to obtain power consumption data for a target time period, and sends the power consumption data for the target time period to a power consumption data processing server; the power consumption data processing server responds to the power consumption data for the target time period sent by the local module collection terminal, calls a power demand time series prediction model, predicts and analyzes the power consumption data for the target time period based on the power demand time series prediction model, obtains the power demand for the target time period, and sends the power demand for the target time period to the local module collection terminal; the local module collection terminal responds to the target time period sent by the power consumption data processing server The power demand for the target period is obtained, the mapping relationship between the power demand and the collection frequency is obtained, and the second collection frequency is determined according to the mapping relationship and the power demand for the target period; the local module collection terminal receives the power data sent by multiple application detection modules within the next preset time period based on the second collection frequency, which solves the technical problems in the prior art of collecting power data in a timely and quantitative manner, but the real-time and accuracy of the collected power data cannot be guaranteed, and the system burden is easily caused when the amount of collected data is large, and the real-time collection of power data is realized, the error in the data collection process is reduced, the accuracy of the data is improved, and by dynamically optimizing the collection frequency, the burden on the power grid system can be reduced, the data processing efficiency of the system can be improved, and a basis for the optimal configuration of power quality management in the distribution network is provided.
[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0025] Figure 1 A flow chart of a method for optimizing configuration of power quality management of a distribution network provided in the first embodiment of the present invention;
[0026] Figure 2 A flow chart of a method for optimizing configuration of power quality management in a distribution network provided in Embodiment 2 of the present invention;
[0027] Figure 3 A flow chart of a method for optimizing configuration of power quality management in a distribution network provided in Embodiment 3 of the present invention;
[0028] Figure 4 A flow chart of a method for optimizing configuration of power quality management in a distribution network provided in Embodiment 4 of the present invention;
[0029] Figure 5 A flowchart of a method for optimizing configuration of power quality management of a distribution network provided in Embodiment 5 of the present invention;
[0030] Figure 6 A flow chart of a method for optimizing configuration of power quality management in a distribution network provided in Embodiment 6 of the present invention;
[0031] Figure 7 A schematic diagram of the structure of a distribution network power quality management optimization configuration system provided in Embodiment 7 of the present invention;
[0032] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 8 of the present invention. DETAILED DESCRIPTION
[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.
[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0035] To facilitate understanding of the technical solutions provided in the embodiments of the present application, some key terms used in the embodiments of the present invention are explained here:
[0036] Autoregressive Integrated Moving Average (ARIMA) is a statistical model used for time series analysis and forecasting. The ARIMA model combines the autoregressive (AR) model, the moving average (MA) model, and the difference (Integrated) operation, and is suitable for non-stationary time series data.
[0037] The ADF test (Augmented Dickey-Fuller Test) is a statistical test method used to test whether time series data has a unit root, so as to determine whether the time series is stationary.
[0038] AIC (Akaike Information Criterion) is a criterion for model selection. It finds a balance between model goodness of fit and model complexity to select the optimal model. For time series models such as ARIMA, AIC can be used to automatically select the best model order (p, d, q).
[0039] The Least Squares Method is a commonly used statistical method for estimating the parameters of a linear regression model. It solves the model parameters by minimizing the residual sum of squares between the observed data and the model's predicted values, so that the model's fitting effect is optimal.
[0040] Embodiment 1
[0041] Figure 1 This is a flow chart of a method for optimizing the configuration of power quality management in a distribution network provided in the first embodiment of the present invention. This embodiment can be applied to improve the accuracy of power consumption data collection to provide a basis for optimizing the configuration of power quality management in a distribution network. This method can be executed by a system for optimizing the configuration of power quality management in a distribution network. The system device can be implemented in the form of hardware and / or software, and the system device can be configured in power equipment. Figure 1 As shown, the method includes:
[0042] S110, the local module acquisition terminal obtains a first acquisition frequency, and receives power consumption data sent by multiple application detection modules within a current preset time period based on the first acquisition frequency.
[0043] It should be noted that the distribution network power quality management optimization configuration method is applied to the distribution network power quality management optimization configuration system, wherein the distribution network power quality management optimization configuration system includes multiple application detection modules, local module collection terminals and electricity data processing servers, and the application detection modules include equipment detection meters, power load balancing modules and electricity carbon balance detection modules.
[0044] In addition, the equipment detection meter is used to measure the power consumption of the load, the power load balancing module is used to measure the power load and load temperature value of the load, and the power carbon balance detection module is used to measure the power carbon emissions of the load.
[0045] Among them, the electricity consumption data includes electricity consumption, power load, load temperature value and electricity carbon emissions, and the first collection frequency is the electricity consumption data collection frequency pre-initialized by the local module collection terminal.
[0046] In one possible implementation, the local area module acquisition terminal obtains the first acquisition frequency from the memory, then determines the time synchronization of all application detection modules and the local area module acquisition terminal, and based on the first acquisition frequency, sends a data acquisition request to all connected application detection modules within the current preset time period. Then, each application detection module sends the collected power consumption data to the local area module acquisition terminal through the wireless communication network, thereby allowing the local area module to collect and receive the power consumption data sent by multiple application detection modules.
[0047] S120, the local module collection terminal merges and filters the multiple power consumption data to obtain the power consumption data of the target period, and sends the power consumption data of the target period to the power consumption data processing server.
[0048] The target period electricity consumption data refers to all electricity consumption data collected during the current preset period.
[0049] In one possible implementation, after the local module collection terminal receives multiple electricity consumption data from various application detection modules, it formats the data from different sources into a unified format, and then merges the data from all application detection modules according to timestamps to generate a complete data set. The above complete data set is then filtered (such as deduplication, detection of outliers, aggregation, etc.) to obtain the electricity consumption data for the target period, and finally the generated electricity consumption data for the target period is sent to the electricity consumption data processing server in the form of a network request.
[0050] S130, the power consumption data processing server responds to the power consumption data of the target period sent by the local module collection terminal, calls the power demand time series prediction model, performs prediction analysis on the power consumption data of the target period based on the power demand time series prediction model, obtains the power demand of the target period, and sends the power demand of the target period to the local module collection terminal.
[0051] The target electricity demand during the collection period is the electricity demand predicted during the current preset period.
[0052] In one possible implementation, the electricity consumption data processing server responds to the target period electricity consumption data sent by the local module collection terminal, calls the electricity demand timing prediction model, then performs a prediction analysis on the target collection period electricity consumption data based on the electricity demand timing prediction model to obtain the target collection period electricity demand, and finally sends the target period electricity demand to the local module collection terminal.
[0053] S140. The local module collection terminal obtains a mapping relationship between the power demand and the collection frequency in response to the power demand in the target period sent by the power data processing server, and determines a second collection frequency according to the mapping relationship and the power demand in the target period.
[0054] The second collection frequency is a dynamic collection frequency required according to the currently predicted electricity demand in the target time period.
[0055] In one possible implementation, the local module collection terminal responds to the power demand in the target collection period sent by the power data processing server, obtains the mapping relationship between the power demand and the collection frequency, and finally calculates the new collection frequency based on the mapping relationship and the power demand in the target period to obtain the second collection frequency.
[0056] S150. The local module collection terminal receives the power consumption data sent by the plurality of application detection modules within the next preset time period based on the second collection frequency.
[0057] It should also be noted that the application detection module can be a building application detection module, which includes urban high-rise community detection modules, low-rise community detection modules, old town detection modules, industrial and commercial user mixed area detection modules, rural detection modules, etc.; the application detection module can be a traffic application detection module, which involves public traffic detection modules and port shore power detection modules; the application detection module can be an industrial application detection module, which includes a low-carbon industrial park detection module centered on clean energy.
[0058] In one possible implementation, the collection frequency of the local module collection terminal is set from the first collection frequency to the second collection frequency, and then based on the second collection frequency, the power consumption data sent by multiple application detection modules are received within the next preset time period. The technical solution of the embodiment of the present invention obtains the first collection frequency through the local module collection terminal, and receives the power consumption data sent by multiple application detection modules within the current preset time period based on the first collection frequency; the local module collection terminal merges and filters the multiple power consumption data to obtain the power consumption data for the target time period, and sends the power consumption data for the target time period to the power consumption data processing server; the power consumption data processing server responds to the power consumption data for the target time period sent by the local module collection terminal, calls the power demand timing prediction model, predicts and analyzes the power consumption data for the target time period based on the power demand timing prediction model, obtains the power demand for the target time period, and sends the power demand for the target time period to the local module collection terminal; the local module collection terminal responds to the target time period sent by the power consumption data processing server The power demand for the target period is obtained, the mapping relationship between the power demand and the collection frequency is obtained, and the second collection frequency is determined according to the mapping relationship and the power demand for the target period; the local module collection terminal receives the power data sent by multiple application detection modules within the next preset time period based on the second collection frequency, which solves the technical problems in the prior art of collecting power data in a timely and quantitative manner, but the real-time and accuracy of the collected power data cannot be guaranteed, and the system burden is easily caused when the amount of collected data is large, and the real-time collection of power data is realized, the error in the data collection process is reduced, the accuracy of the data is improved, and by dynamically optimizing the collection frequency, the burden on the power grid system can be reduced, the data processing efficiency of the system can be improved, and a basis for the optimal configuration of power quality management in the distribution network is provided.
[0059] Embodiment 2
[0060] Figure 2 This is a flow chart of a method for optimizing the configuration of power quality management in a distribution network provided in the second embodiment of the present invention. Based on the above embodiment, after determining the second acquisition frequency, this embodiment can dynamically manage the storage space of the data acquisition frequency to improve the efficiency of storage resource utilization. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiment are not repeated here. Figure 2 As shown, the method includes:
[0061] S210: Obtain the acquisition frequency storage pointer.
[0062] The pointer direction of the acquisition frequency storage pointer is the storage space address of the first acquisition frequency.
[0063] In a possible implementation, the local module acquisition terminal obtains the acquisition frequency storage pointer from the stack memory.
[0064] S220: Generate a storage space address of a second acquisition frequency.
[0065] In a possible implementation, the local area module acquisition terminal creates an initial space from the stack memory according to the second acquisition frequency, and stores the second acquisition frequency into the address of the initial space.
[0066] S230: Modify the pointer direction of the acquisition frequency storage pointer to the storage space address of the second acquisition frequency.
[0067] In a possible implementation, the local area module acquisition terminal modifies the pointer direction of the acquisition frequency storage pointer to the storage space address of the second acquisition frequency.
[0068] S240: Clear the storage space address of the first acquisition frequency.
[0069] In a possible implementation, the local module acquisition terminal clears the storage space address of the first acquisition frequency in the stack memory.
[0070] The technical solution of the embodiment of the present invention obtains the acquisition frequency storage pointer, generates the storage space address of the second acquisition frequency, modifies the pointer direction of the acquisition frequency storage pointer to the storage space address of the second acquisition frequency, and clears the storage space address of the first acquisition frequency. This can dynamically manage the storage space of the data acquisition frequency and improve the utilization efficiency of storage resources.
[0071] Embodiment 3
[0072] Figure 3 This is a flowchart of a method for optimizing the configuration of power quality management in a distribution network provided in the third embodiment of the present invention. Based on the above embodiment, this embodiment further refines the training process of the power demand time series prediction model. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiment are not repeated here. Figure 3 As shown, the method includes:
[0073] S310: Obtain a power consumption sample data set.
[0074] The electricity consumption sample data sets include electricity consumption, power load, load temperature value, electricity carbon emissions and electricity demand, and the electricity consumption sample data sets are all preset data sets.
[0075] In a possible implementation, the local module collection terminal obtains a power consumption sample data set from a database.
[0076] S320: extracting features from the electricity usage sample data set to obtain an electricity usage feature data set, and dividing the electricity usage feature data set into an electricity usage training data set and an electricity usage test data set.
[0077] In one possible implementation, the local module acquisition terminal loads the electricity consumption sample data set and performs necessary preprocessing, such as processing missing values, extracting time features, etc., and then extracts useful features from the electricity consumption data. Finally, the electricity consumption feature data set is divided into a training data set and a test data set.
[0078] S330: Initialize the original time series model.
[0079] Among them, the original time series model is the autoregressive integrated moving average model.
[0080] Specifically, the local module acquisition terminal initializes the original model of the time series, and then determines the orders of the autoregressive model part and the moving average model part through the AIC automatic order determination method to obtain the original model of the time series.
[0081] S340: Training the time series original model according to the electricity consumption training data set to obtain a time series training model.
[0082] In a possible implementation, the local module acquisition terminal trains the original time series model according to the power consumption training data set to obtain a time series training model.
[0083] S350: Verify and optimize the time series training model according to the electricity consumption test data set to obtain a time electricity consumption demand prediction model.
[0084] In a possible implementation, the local module acquisition terminal verifies and optimizes the time series training model based on the power consumption test data set to obtain a time power consumption demand prediction model.
[0085] The technical solution of the embodiment of the present invention is to obtain a power sample data set; wherein the power sample data set includes power consumption, power load, load temperature value, electric carbon emission and power demand; extract features from the power sample data set to obtain a power feature data set, and divide the power feature data set into a power training data set and a power test data set; initialize the original time series model; train the original time series model according to the power training data set to obtain a time series training model; verify and optimize the time series training model according to the power test data set to obtain the power demand prediction model. Through this model, the power consumption data of the target period can be predicted and analyzed to obtain the power demand of the target period. It is convenient for the local module collection terminal to respond to the target time period electricity demand sent by the electricity data processing server, obtain the mapping relationship between the electricity demand and the collection frequency, and determine the second collection frequency according to the mapping relationship and the target time period electricity demand; based on the second collection frequency, the local module collection terminal receives the electricity data sent by multiple application detection modules in the next preset time period, which solves the technical problems in the prior art of collecting electricity data in a timely and quantitative manner, the real-time and accuracy of the collected electricity data cannot be guaranteed, and the system burden is easily caused when the amount of collected data is large, and the real-time collection of electricity data is realized, the error in the data collection process is reduced, the accuracy of the data is improved, and by dynamically optimizing the collection frequency, the burden on the power grid system can be reduced, the data processing efficiency of the system can be improved, and the basis for the optimal configuration of power quality management of the distribution network is provided.
[0086] Embodiment 4
[0087] Figure 4 The flowchart of a method for optimizing the configuration of power quality management in a distribution network provided in the fourth embodiment of the present invention is based on the above embodiment. This embodiment further refines the process of training the original time series model according to the power training data set to obtain the time series training model. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiment are not repeated here. Figure 4 As shown, the method includes:
[0088] S410: Based on the ADF test method, the time series stability of the electricity consumption training data set is checked, and the data in the electricity consumption training data set that is checked as unstable is differentially processed to obtain a stable electricity consumption training data set.
[0089] In a possible implementation, the local module acquisition terminal uses the ADF test method to check the stability of the data to determine whether the data has a unit root. If the significance index value of the unit root is less than the significance level (such as 0.05), the null hypothesis is rejected, proving that the electricity training data set is stable; otherwise, the null hypothesis is accepted, proving that the electricity training data set is not stable. Finally, if part of the data in the electricity training data set is not stable (that is, the significance index value is greater than the significance level), this part of the data is processed by first-order difference (that is, each data point is subtracted from the value of the previous data point) to obtain a stable electricity training data set.
[0090] S420: According to the electricity consumption training stable data set, the original time series model is trained iteratively based on the autocorrelation function to obtain an initial time series training model.
[0091] In one possible implementation, the local module acquisition terminal iteratively calculates the autocorrelation coefficient of the corresponding data in the original time series model based on the autocorrelation function according to the stable data set of power consumption training, and draws an autocorrelation function graph based on the autocorrelation coefficient of each iterative data. Then, the autocorrelation function graph is observed to confirm the lag order with high autocorrelation, and the lag order is used as the order of the sliding average part in the original time series model to obtain the initial time series training model.
[0092] S430: According to the electricity consumption training stable data set, the initial time series original model is trained iteratively based on the partial autocorrelation function to obtain a time series training model.
[0093] In one possible implementation, the local module acquisition terminal iteratively calculates the partial autocorrelation coefficient of the corresponding data in the original time series model based on the partial autocorrelation function according to the stable data set of power consumption training, and draws a partial autocorrelation function graph based on the partial autocorrelation coefficient of each iterative data. Then, the partial autocorrelation function graph is observed to confirm the lag order with high partial autocorrelation, and the lag order is used as the order of the autoregressive part in the original time series model to obtain the time series training model.
[0094] The technical solution of the embodiment of the present invention performs a time series stationarity check on the electricity consumption training data set based on the ADF test method, and performs differential processing on the data in the electricity consumption training data set that is checked as being unstable, so as to obtain a stable electricity consumption training data set; based on the stable electricity consumption training data set, the original time series model is trained and iterated based on the autocorrelation function to obtain an initial time series training model; based on the stable electricity consumption training data set, the initial time series original model is trained and iterated based on the partial autocorrelation function to obtain the time series training model, thereby achieving a relatively accurate time series training model.
[0095] Embodiment 5
[0096] Figure 5 The flowchart of a method for optimizing the configuration of power quality management in a distribution network provided in the fifth embodiment of the present invention is based on the above embodiments. This embodiment further optimizes the process of verifying and optimizing the time series training model according to the power test data set to obtain the time power demand forecasting model. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiments are not repeated here. Figure 5 As shown, the method includes:
[0097] S510: Estimate the time series training model based on the least squares method according to the electricity consumption test data set to obtain a training estimation result data set.
[0098] In a possible implementation, the local module acquisition terminal determines the independent variables and dependent variables based on the power consumption test data set, and establishes a linear regression model. The independent variables are the power consumption, power load, load temperature value, and electric carbon emissions in the power consumption test data set, and the dependent variable is the power demand in the power consumption test data set. Then, the least squares method is used to fit the linear regression model, and the parameters in the linear regression model are estimated to obtain the training estimation result data set.
[0099] The training estimation result data set includes the residual sequence estimation results.
[0100] S520: According to the training estimation result data set, relevant parameters of the time series training model are adjusted to obtain a time electricity demand prediction model.
[0101] In a possible implementation, the local module acquisition terminal first evaluates the fit of the linear regression model based on the training estimation result data set. Various evaluation indicators such as mean squared error (MSE), coefficient of determination (R^2), mean absolute error (MAE), etc. can be used to evaluate the quality of model fit, and then judge whether it is necessary to adjust the parameters of the time power demand training model based on the evaluation results. If the model fit does not meet the standard, the parameters of the model are adjusted, such as adding features, introducing interaction terms, considering polynomial regression, etc. to improve the prediction performance of the model, and then, cross-validation, grid search, etc. are used to optimize the hyperparameters of the adjusted model. Finally, after the model parameters are adjusted, the fit of the time power demand training model is retrained and evaluated until the fit of the time power demand training model meets the standard, and the time power demand prediction model is obtained.
[0102] The technical solution of the embodiment of the present invention is to estimate the time series training model based on the least squares method according to the electricity consumption test data set to obtain a training estimation result data set; according to the training estimation result data set, the relevant parameters of the time series training model are adjusted to obtain the time electricity demand prediction model, thereby realizing the verification and optimization of the time series training model and improving the prediction accuracy of the time electricity demand prediction model.
[0103] Embodiment 6
[0104] Figure 6 The flowchart of a distribution network power quality management optimization configuration method provided in the sixth embodiment of the present invention is based on the above embodiment. This embodiment further optimizes the process of verifying and optimizing the time series training model according to the power test data set to obtain the time power demand forecasting model. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiments are not repeated here. Figure 6 As shown, the method includes:
[0105] S610: Obtaining a power demand data table and a collection frequency data table from a database.
[0106] In a possible implementation, the local module acquisition terminal uses a database connection library (such as pymysql, psycopg2, etc.) to connect to the database, and then uses an SQL query statement to obtain data from the power demand data table from the database, and then also uses an SQL query statement to obtain data from the collection frequency data table from the database.
[0107] S620: Obtain multiple mapping relationships according to index data between the power demand data table and the collection frequency data table.
[0108] In a possible implementation, the local module collection terminal obtains index data between the power demand data table and the collection frequency data table from the data in the power demand data table and the data in the collection frequency data table to obtain a mapping relationship between multiple power demand data tables and collection frequency data tables.
[0109] S630: According to the electricity demand in the target time period, traverse and match multiple mapping relationships to obtain matching index data corresponding to the electricity demand in the target time period.
[0110] In a possible implementation, the local module collection terminal traverses and matches multiple mapping relationships according to the electricity demand in the target time period to obtain matching index data corresponding to the electricity demand in the target time period.
[0111] S640: Based on the matching index data, query the collection frequency corresponding to the electricity demand in the target time period in the collection frequency data table to obtain a second collection frequency.
[0112] In a possible implementation, based on the matching index data, the collection frequency corresponding to the electricity demand in the target time period is searched in the collection frequency data table to obtain the second collection frequency.
[0113] The technical solution of the embodiment of the present invention is to obtain a first collection frequency through a local module collection terminal, and receive power consumption data sent by multiple application detection modules within a current preset time period based on the first collection frequency; the local module collection terminal merges and filters the multiple power consumption data to obtain power consumption data for a target time period, and sends the power consumption data for the target time period to a power consumption data processing server; the power consumption data processing server responds to the power consumption data for the target time period sent by the local module collection terminal, calls a power demand time series prediction model, predicts and analyzes the power consumption data for the target time period based on the power demand time series prediction model, obtains the power demand for the target time period, and sends the power demand for the target time period to the local module collection terminal; the local module collection terminal responds to the target time period sent by the power consumption data processing server The power demand for the target period is obtained, the mapping relationship between the power demand and the collection frequency is obtained, and the second collection frequency is determined according to the mapping relationship and the power demand for the target period; the local module collection terminal receives the power data sent by multiple application detection modules within the next preset time period based on the second collection frequency, which solves the technical problems in the prior art of collecting power data in a timely and quantitative manner, but the real-time and accuracy of the collected power data cannot be guaranteed, and the system burden is easily caused when the amount of collected data is large, and the real-time collection of power data is realized, the error in the data collection process is reduced, the accuracy of the data is improved, and by dynamically optimizing the collection frequency, the burden on the power grid system can be reduced, the data processing efficiency of the system can be improved, and a basis for the optimal configuration of power quality management in the distribution network is provided.
[0114] Embodiment 7
[0115] Figure 7 This is a schematic diagram of the structure of a distribution network power quality management optimization configuration system provided by Embodiment 7 of the present invention. Figure 7 As shown, the device comprises:
[0116] The local module collection terminal 710, the power consumption data processing server 720 and multiple application detection modules 730, the local module collection terminal 1100 is respectively connected to each application detection module 730 and the power consumption data processing server 720, wherein:
[0117] The local module collection terminal 710 is used to obtain a first collection frequency, and receive the power consumption data sent by multiple application detection modules 730 within a current preset time period based on the first collection frequency;
[0118] The local module collection terminal 710 is used to merge and filter multiple power consumption data to obtain power consumption data in a target period, and send the power consumption data in the target collection period to the power consumption data processing server 720;
[0119] The power consumption data processing server 720 is used to respond to the power consumption data of the target period sent by the local module collection terminal 710, call the power demand time series prediction model, perform prediction analysis on the power consumption data of the target collection period based on the power demand time series prediction model, obtain the power demand of the target collection period, and send the power demand of the target period to the local module collection terminal 710;
[0120] The local module collection terminal 710 is used to respond to the power demand in the target collection period sent by the power data processing server 720, obtain the mapping relationship between the power demand and the collection frequency, and determine the second collection frequency according to the mapping relationship and the power demand in the target period;
[0121] The local module collection terminal 710 is used to receive the power consumption data sent by the multiple application detection modules 730 within the next preset time period based on the second collection frequency.
[0122] The technical solution of the embodiment of the present invention is to obtain a first collection frequency through a local module collection terminal, and receive power consumption data sent by multiple application detection modules within a current preset time period based on the first collection frequency; the local module collection terminal merges and filters the multiple power consumption data to obtain power consumption data for a target time period, and sends the power consumption data for the target time period to a power consumption data processing server; the power consumption data processing server responds to the power consumption data for the target time period sent by the local module collection terminal, calls a power demand time series prediction model, predicts and analyzes the power consumption data for the target time period based on the power demand time series prediction model, obtains the power demand for the target time period, and sends the power demand for the target time period to the local module collection terminal; the local module collection terminal responds to the target time period sent by the power consumption data processing server The power demand for the target period is obtained, the mapping relationship between the power demand and the collection frequency is obtained, and the second collection frequency is determined according to the mapping relationship and the power demand for the target period; the local module collection terminal receives the power data sent by multiple application detection modules within the next preset time period based on the second collection frequency, which solves the technical problems in the prior art of collecting power data in a timely and quantitative manner, but the real-time and accuracy of the collected power data cannot be guaranteed, and the system burden is easily caused when the amount of collected data is large, and the real-time collection of power data is realized, the error in the data collection process is reduced, the accuracy of the data is improved, and by dynamically optimizing the collection frequency, the burden on the power grid system can be reduced, the data processing efficiency of the system can be improved, and a basis for the optimal configuration of power quality management in the distribution network is provided.
[0123] The distribution network power quality management optimization configuration system provided in the embodiment of the present invention can execute the distribution network power quality management optimization configuration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0124] Embodiment 8
[0125] Figure 8 A schematic diagram of the structure of an electronic device provided for Embodiment 8 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0126] like Figure 8As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0127] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0128] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as the distribution network power quality management optimization configuration method.
[0129] In some embodiments, the method for optimizing the configuration of power quality management of a distribution network may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for optimizing the configuration of power quality management of a distribution network described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for optimizing the configuration of power quality management of a distribution network by any other appropriate means (e.g., by means of firmware).
[0130] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0131] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0132] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0133] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0134] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0135] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0136] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0137] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for optimizing the configuration of power quality management in distribution networks. It is characterized in that include: The local module acquisition terminal acquires a first acquisition frequency, and receives power consumption data sent by multiple application detection modules within a current preset time period based on the first acquisition frequency; The local module collection terminal merges and filters the plurality of power consumption data to obtain power consumption data for a target period, and sends the power consumption data for the target period to a power consumption data processing server; The power consumption data processing server responds to the power consumption data of the target period sent by the local module collection terminal, calls the power demand time series prediction model, performs prediction analysis on the power consumption data of the target period based on the power demand time series prediction model, obtains the power demand of the target period, and sends the power demand of the target period to the local module collection terminal; The local module collection terminal obtains a mapping relationship between the power demand and the collection frequency in response to the power demand in the target period sent by the power data processing server, and determines a second collection frequency according to the mapping relationship and the power demand in the target period; The local module collection terminal receives the power consumption data sent by the plurality of application detection modules within a next preset time period based on the second collection frequency.
2. The method according to claim 1, It is characterized in that After determining the second acquisition frequency, the method further includes: Obtaining an acquisition frequency storage pointer; wherein the pointer direction of the acquisition frequency storage pointer is the storage space address of the first acquisition frequency; Generate a storage space address of the second acquisition frequency; Modify the pointer direction of the acquisition frequency storage pointer to the storage space address of the second acquisition frequency; Clear the storage space address of the first acquisition frequency.
3. The method according to claim 1, It is characterized in that The training process of the electricity demand time series prediction model includes: Acquire a power consumption sample data set; wherein the power consumption sample data set includes power consumption, power load, load temperature value, electric carbon emissions and power demand; Extracting features from the electricity usage sample data set to obtain an electricity usage feature data set, and dividing the electricity usage feature data set into an electricity usage training data set and an electricity usage test data set; Initialize the original time series model; The time series original model is trained according to the electricity consumption training data set to obtain a time series training model; The time series training model is verified and optimized according to the electricity consumption test data set to obtain the electricity consumption demand prediction model.
4. The method according to claim 3, It is characterized in that The training of the time series original model according to the electricity consumption training data set to obtain the time series training model includes: Based on the ADF test method, the time series stability of the electricity consumption training data set is checked, and the data in the electricity consumption training data set that is checked as unstable is subjected to differential processing to obtain a stable electricity consumption training data set; According to the electricity consumption training stable data set, the time series original model is trained iteratively based on the autocorrelation function to obtain an initial time series training model; According to the electricity consumption training stable data set, the initial time series original model is trained iteratively based on the partial autocorrelation function to obtain the time series training model.
5. The method according to claim 3, It is characterized in that The time series training model is verified and optimized according to the power consumption test data set to obtain a time power consumption demand prediction model, including: According to the electricity consumption test data set, the time series training model is estimated based on the least squares method to obtain a training estimation result data set; According to the training estimation result data set, the relevant parameters of the time series training model are adjusted to obtain the time electricity demand prediction model.
6. The method according to claim 1, It is characterized in that The determining of the second acquisition frequency according to the mapping relationship and the power demand in the target time period includes: Obtaining a data table of electricity demand and a data table of collection frequency from a database; Obtaining multiple mapping relationships according to index data between the power demand data table and the acquisition frequency data table; According to the electricity demand in the target time period, traverse and match multiple mapping relationships to obtain matching index data corresponding to the electricity demand in the target time period; Based on the matching index data, the collection frequency corresponding to the electricity demand in the target time period is searched in the collection frequency data table to obtain a second collection frequency.
7. The method according to claim 1, It is characterized in that The application detection module includes: a building application detection module, wherein: The building application detection module includes: at least one of: an urban high-rise community detection module, a low-rise community detection module, an old town area detection module, an industrial and commercial user mixed area detection module and a rural detection module.
8. The method according to claim 7, It is characterized in that The application detection module includes: a traffic application detection module and an industrial application detection module, wherein: The traffic application detection module includes a public traffic detection module and a port shore power detection module; The industrial application detection module includes a low-carbon industrial park detection module centered on clean energy.
9. A distribution network power quality management optimization configuration system, It is characterized in that include: The local module collection terminal is used to obtain a first collection frequency, and receive the power consumption data sent by multiple application detection modules within a current preset time period based on the first collection frequency; The local module collection terminal is used to merge and filter the plurality of power consumption data to obtain the power consumption data of the target period, and send the power consumption data of the target period to the power consumption data processing server; The power consumption data processing server is used to respond to the power consumption data of the target period sent by the local module collection terminal, call the power demand time series prediction model, perform prediction analysis on the power consumption data of the target period based on the power demand time series prediction model, obtain the power demand of the target period, and send the power demand of the target period to the local module collection terminal; The local module collection terminal is used to respond to the target period power demand sent by the power data processing server, obtain the mapping relationship between the power demand and the collection frequency, and determine the second collection frequency according to the mapping relationship and the target period power demand; The local module collection terminal is used to receive the power consumption data sent by the multiple application detection modules within the next preset time period based on the second collection frequency.
10. An electronic device, It is characterized in that The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network power quality management optimization configuration method described in any one of claims 1-8.
