Power grid commutation method based on edge gateway and edge gateway

Abstract

The invention discloses a power grid commutation method based on an edge gateway and the edge gateway. The method comprises the following steps: an edge gateway obtains operation associated data of a plurality of power grid nodes of a target power grid, determines operation characteristic data of the target power grid according to the operation associated data, and determines commutation prediction information of the target power grid according to the operation characteristic data; the edge gateway determines target commutation information of the target power grid according to the operation associated data and the commutation prediction information, generates a commutation control instruction according to the target commutation information, and sends the commutation control instruction to a commutation execution unit; and the commutation execution unit executes the target commutation operation according to the commutation control instruction, so that the accuracy and response speed of the commutation operation are improved, the running state of the power grid is optimized, the electric energy quality and the system stability are improved, the electric energy loss and the equipment failure rate are reduced, and the power supply efficiency is improved. And the requirements of a modern power system on high efficiency and high reliability are met.

Description

Technical Field

[0001] The present invention relates to the technical field of power system control, and in particular to a power grid phase switching method of an edge gateway and an edge gateway. Background Art

[0002] With the continuous growth of global energy demand and the increasing complexity of power systems, traditional power grid management models are facing unprecedented challenges. Driven by the Internet of Things technology, the intelligence, automation and efficiency of power systems have become an inevitable trend in the development of the industry.

[0003] However, among the related technologies, grid phase-changing technologies mostly rely on manual judgment and experience-based operations, and have problems such as slow response speed and low accuracy, which makes it difficult to meet the needs of modern power systems for efficient and stable operation. Summary of the invention

[0004] The present invention provides a power grid phase switching method of an edge gateway and an edge gateway to solve the problem in the related art that the phase switching operation relies on manual operation and is not accurate and timely enough.

[0005] According to one aspect of the present invention, a power grid phase switching method based on an edge gateway is provided, the method comprising:

[0006] The edge gateway obtains operation-related data of multiple power grid nodes of the target power grid, determines operation characteristic data of the target power grid according to the operation-related data, and determines commutation prediction information of the target power grid according to the operation characteristic data;

[0007] The edge gateway determines the target commutation information of the target power grid according to the operation-related data and the commutation prediction information, generates a commutation control instruction according to the target commutation information, and sends the commutation control instruction to the commutation execution unit, so that the commutation execution unit performs the target commutation operation according to the commutation control instruction.

[0008] According to another aspect of the present invention, a power grid phase switching device of an edge gateway is provided, the device comprising:

[0009] A commutation prediction information determination module, used for the edge gateway to obtain operation-related data of multiple grid nodes of the target grid, determine the operation characteristic data of the target grid according to the operation-related data, and determine the commutation prediction information of the target grid according to the operation characteristic data;

[0010] A target commutation operation execution module is used for the edge gateway to determine the target commutation information of the target power grid according to the operation-related data and the commutation prediction information, generate a commutation control instruction according to the target commutation information, and send the commutation control instruction to the commutation execution unit, so that the commutation execution unit performs the target commutation operation according to the commutation control instruction.

[0011] According to another aspect of the present invention, an edge gateway is provided, the edge gateway comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] 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 power grid commutation method based on the edge gateway described in any embodiment of the present invention.

[0015] 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 edge gateway-based power grid commutation method described in any embodiment of the present invention when executed.

[0016] The technical solution of the embodiment of the present invention is as follows: first, the operation-related data of multiple power grid nodes of the target power grid are obtained through the edge gateway, the operation characteristic data of the target power grid is determined according to the operation-related data, and the phase change prediction information of the target power grid is determined according to the operation characteristic data, so that real-time data collection and analysis can be performed to improve the accuracy and timeliness of phase change prediction; then, the edge gateway determines the target phase change information of the target power grid according to the operation-related data and the phase change prediction information, generates a phase change control instruction according to the target phase change information, and sends the phase change control instruction to the phase change execution unit, so that the phase change execution unit executes the target phase change operation according to the phase change control instruction, so as to realize precise phase change control, solve the problem in the related technology that the phase change operation relies on manual operation and is not accurate and timely enough, not only improves the accuracy and response speed of the phase change operation, but also optimizes the operation state of the power grid, improves the power quality and system stability, reduces power loss and equipment failure rate, and meets the requirements of modern power systems for high efficiency and high reliability.

[0017] 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

[0018] 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.

[0019] Figure 1 is a flow chart of a power grid phase switching method based on an edge gateway provided according to Embodiment 1 of the present invention;

[0020] Figure 2 is a flow chart of a power grid phase switching method based on an edge gateway provided according to Embodiment 2 of the present invention;

[0021] Figure 3 is a structural schematic diagram of a power grid phase switching device based on an edge gateway provided according to Embodiment 3 of the present invention;

[0022] Figure 4 It is a structural schematic diagram of an edge gateway for implementing the edge gateway-based power grid phase switching method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] 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.

[0024] 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.

[0025] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0027] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0028] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0030] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0031] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0032] Embodiment 1

[0033] Figure 1 A flowchart of a power grid phase switching method based on an edge gateway is provided for the first embodiment of the present invention. This embodiment is applicable to situations where dynamic optimization and management of the power grid operation status are required. The method can be executed by a power grid phase switching device based on an edge gateway. The power grid phase switching device based on the edge gateway can be implemented in the form of hardware and / or software, and optionally, can be implemented by an electronic device, which can be a mobile terminal, a PC or a server, etc.

[0034] like Figure 1 As shown, the method may specifically include:

[0035] S110. The edge gateway obtains operation-related data of multiple grid nodes of a target grid, determines operation characteristic data of the target grid according to the operation-related data, and determines commutation prediction information of the target grid according to the operation characteristic data.

[0036] Among them, the edge gateway can be understood as a device or software platform deployed at the edge of the network, which can directly interact with physical devices (such as sensors and actuators) and can also communicate with cloud services. The edge gateway can process data locally, reduce latency and relieve the pressure on cloud servers. The grid node can be understood as each measurement point or device in the grid, including but not limited to at least one of a substation and a distribution cabinet, which can provide operation-related data for evaluating the operation status of the grid and making decisions on commutation operations. The operation-related data can be understood as a data set that describes the interaction and influence between the grid nodes within the grid. The operation-related data reflects the actual working status of the grid and is the basis for evaluating the health status and performance of the grid. By analyzing the operation-related data, the real-time operation status and performance of the grid can be evaluated, potential problems of the grid can be discovered, and a basis for preventive maintenance and optimization operations can be provided. The operation-related data may include but is not limited to at least one of current data, voltage data, phase data, temperature data and vibration data. The operation characteristic data can be understood as information extracted from the operation-related data that can reflect the specific operation characteristics of the grid, including but not limited to at least one of the load level, stability and efficiency of the grid. The operation characteristic data helps to understand the working mode of the grid. The commutation prediction information can be understood as an estimate of possible commutation requirements based on the operating characteristic data of the power grid, which can be used to help plan necessary operations in advance, ensure the stable operation of the power grid, and avoid service interruptions or other adverse effects caused by sudden commutation requirements. The commutation prediction information includes, but is not limited to, load forecasting, power generation forecasting, and fault forecasting. Load forecasting refers to predicting changes in power grid load over a period of time in the future; power generation forecasting refers to predicting the power generation of renewable energy (such as wind power and solar energy); and fault prediction refers to predicting possible faults in the power grid and their impacts. Set data and prediction information as data sources.

[0037] Based on the above scheme, optionally, determining the commutation prediction information of the target power grid according to the operating characteristic data includes: inputting the operating characteristic data into a commutation prediction model to obtain the commutation prediction information of the target power grid.

[0038] Among them, the commutation prediction model can be understood as a model trained by a deep learning method, which is used to predict the future commutation demand of the power grid. The commutation prediction model can be obtained by training a pre-established deep learning model through sample feature data and target commutation information corresponding to the sample feature data. The sample feature data can be understood as data extracted from historical power grid operation, reflecting the operating status of the power grid under different conditions, and used to train the commutation prediction model. The target commutation information can be understood as known historical commutation operation information, that is, the commutation operation actually performed under specific conditions, which can be used to train the commutation prediction model so that the model can learn the commutation operation that should be taken under specific operating feature data. In this embodiment, the deep learning model can be trained through a large amount of sample feature data and corresponding target commutation information to learn the relationship between the power grid operation characteristics and the commutation demand, so that accurate commutation prediction can be performed in the application.

[0039] An optional implementation method is to train the prediction model. Specifically, the training sequence is as follows:

[0040] First, collect sample feature data from the historical database. These data may include various types of time series data such as current, voltage, power, temperature, humidity, load mode, commutation records, etc., while ensuring the integrity, accuracy and consistency of the timestamp of the data, and divide the data into training set, validation set and test set, usually in a ratio of 70%:15%:15% or similar ratios, and can be further standardized or normalized to eliminate the impact of different dimensions on model training; secondly, select a suitable deep learning prediction model according to the characteristics of the prediction task, use the training set data to train the model, calculate the predicted value through forward propagation, and update the model parameters through back propagation; finally, set a certain number of training cycles; after each training cycle, use the validation set to evaluate the model performance, and adjust the model parameters or learning rate as needed. Detect the loss value during training and the performance indicators on the validation set to determine whether the model is overfitting or underfitting. If the requirements are met, stop training and keep the model weight at this time;

[0041] For example, a LSTM-based prediction model is constructed to predict the future load demand of the power grid, with historical load data as input features and the load at a certain point in the future as the target variable.

[0042] During the training process, 100 training cycles were set, and the mean square error (MSE) on the validation set was calculated after each cycle. By observing the changing trend of MSE, we found that the model began to overfit after the 50th cycle, so we decided to stop training early and save the model weights at this time.

[0043] Finally, evaluate the quality of the model that meets the requirements. Use the test set to evaluate the trained model to test the generalization ability of the model on unknown data. Calculate and compare the performance indicators (such as accuracy, recall, F1 score, MSE, etc.) on the test set to evaluate the quality of the model.

[0044] In the above implementation, the mean square error (MSE) of the model can be calculated on the test set and compared with the benchmark model. The results show that the model has a lower MSE value when predicting future grid load demand, indicating that its prediction performance is better.

[0045] The trained model is deployed to the power grid detection system so that it can receive new power grid data in real time and output the results of predicting future power grid status and commutation requirements.

[0046] The above scheme, by inputting the operation characteristic data into the pre-trained commutation prediction model, can accurately predict the future commutation demand of the power grid, thereby optimizing the power grid operation in advance and improving the power quality and system stability.

[0047] S120, the edge gateway determines the target commutation information of the target power grid according to the operation-related data and the commutation prediction information, generates a commutation control instruction according to the target commutation information, and sends the commutation control instruction to the commutation execution unit, so that the commutation execution unit performs the target commutation operation according to the commutation control instruction.

[0048] Among them, the target commutation information can be understood as information obtained based on the operation-related data and the commutation prediction information, which is used to indicate when and where the commutation operation needs to be performed, and can provide a basis for generating specific commutation control instructions. The commutation control instruction can be understood as a command generated by the edge gateway according to the target commutation information, which is used to instruct the commutation execution unit to perform the commutation operation. The commutation control instruction contains all the information required to perform the commutation operation, ensuring that the commutation operation can be performed accurately to maintain or improve the operating state of the power grid. The commutation control instruction may include but is not limited to at least one of adjusting the switching state of the commutator, changing the commutation sequence, and adjusting the device parameters. The commutation execution unit can be understood as a device or system component responsible for executing the target commutation operation. In this embodiment, when receiving the commutation control instruction issued by the edge gateway, the commutation execution unit will adjust the current phase in the power grid according to the requirements of the instruction to achieve the purpose of optimizing the power grid performance. The target commutation operation can be understood as an operation specifically performed to convert the current phase.

[0049] On the basis of the above scheme, optionally, the communication between the edge gateway and the phase-changing execution unit is carried out by using a dual-channel communication method of wireless and carrier.

[0050] Among them, the wireless communication method can be understood as realizing data transmission without physical connection, which is suitable for communication of long distance and mobile devices. In this embodiment, wireless communication provides a flexible communication method to ensure that the data transmission between the edge gateway and the phase-changing execution unit is not restricted by the physical location. The carrier communication method can be understood as a communication method that uses power lines as transmission media and transmits data by superimposing high-frequency signals on power lines. The carrier communication uses existing power lines for data transmission without additional wiring. In this embodiment, carrier communication provides a reliable backup communication method to ensure the stability of data transmission. The dual-channel communication method can be understood as a method in which wireless and carrier communication methods can simultaneously perform data transmission. The dual-channel communication method improves the reliability and redundancy of communication. Even if one communication method fails, the other communication method can still ensure data transmission and ensure the normal operation of the power system. In this embodiment, the dual-channel communication method ensures that the communication between the edge gateway and the phase-changing execution unit will not be interrupted due to the failure of a single channel.

[0051] In an optional implementation, the commutation instruction communication is transmitted to the commutation execution unit using a dual-channel communication method of wireless and carrier, such as at least one of wireless methods such as WiFi communication or Zigbee communication, and a power line carrier communication method. The dual-channel communication method can enhance the communication reliability and flexibility between the edge gateway and the commutation execution unit, and transmit the instructions to the control execution unit through a high-reliability communication protocol (such as 5G or LoRaWAN, etc.).

[0052] In addition, before transmitting the commutation instructions, the edge gateway will also optimize the encoding of the commutation instructions to reduce the amount of transmitted data.

[0053] The above scheme uses a dual-channel communication method of wireless communication and carrier communication, so the data transmission between the edge gateway and the commutation execution unit is more reliable and flexible, which not only improves the fault tolerance of the system, but also ensures the efficiency and stability of the commutation operation.

[0054] On the basis of the above scheme, optionally, the edge gateway determines the target commutation information of the target power grid according to the operation-related data and the commutation prediction information, including: the edge gateway determines multiple commutation optimization targets and multiple commutation constraints according to the operation-related data and the commutation prediction information; determines the target commutation information of the target power grid according to multiple commutation-related parameters, a preset optimization algorithm, multiple commutation optimization targets and multiple commutation constraints.

[0055] Among them, the commutation optimization target can be understood as a specific target to be achieved in the commutation operation, which can be used to provide a basis for generating the optimal commutation control instruction, including but not limited to at least one of minimizing energy consumption, maximizing stability and reducing equipment wear. The commutation constraint condition can be understood as a restriction condition that needs to be met in the commutation operation to ensure that the commutation operation is carried out within a safe range and avoid damage to the power grid, including but not limited to at least one of voltage fluctuation range, current limit and equipment capacity. The commutation-related parameters can be understood as various parameters related to the commutation operation, which can be used to define the conditions and range of the commutation operation to ensure that the commutation operation is carried out within a reasonable range. The commutation-related parameters may include but are not limited to at least one of parameters such as power loss, harmonic suppression and power grid balance. The power loss is the energy loss caused by the presence of components such as resistors, inductors and capacitors during power transmission and distribution. The harmonic suppression can be understood as a method of reducing or eliminating the harmonic components caused by nonlinear loads in the power system. The power grid balance can be understood as the degree of symmetry of the three-phase voltage and current in the power grid. The preset optimization algorithm can be understood to refer to a predefined algorithm for optimizing the commutation operation, which is used to find the optimal commutation scheme according to the commutation optimization target and the commutation constraint conditions to ensure the efficiency and safety of the commutation operation.

[0056] An optional implementation method, if multiple optimization objectives such as minimizing power loss, harmonic suppression, and grid balance are considered, multi-objective optimization can be achieved through methods such as weighted summation or Pareto frontier analysis. The weighted summation method is a method that combines multiple objective functions into a single objective function by assigning a weight to each objective. The process of achieving multi-objective optimization through the weighted summation method is as follows:

[0057] First, define the commutation optimization objectives: f1(x): energy loss minimization function; f2(x): harmonic suppression function (may be a measure of harmonic content); f3(x): grid balance function (such as three-phase imbalance); secondly, assign weights: according to the importance of each commutation optimization objective, assign a weight w1, w2, w3 to each commutation optimization objective, and w1+w2+w3=1; then construct a comprehensive commutation optimization objective function: F(x)=w1·f1(x)+w2·f2(x)+w3·f3(x); then perform optimization solution: use an appropriate optimization algorithm (such as genetic algorithm or particle swarm optimization, etc.) to solve the minimum value of the comprehensive objective function F(x); finally, evaluate the results: analyze the optimization results to ensure that each objective is reasonably weighed under the weight distribution.

[0058] For example, in a power system, the weight of power loss is 0.5, the weight of harmonic suppression is 0.3, and the weight of grid balance is 0.2. By using the weighted summation method, a comprehensive objective function is constructed and solved to obtain a set of target commutation operations, so that the system performance is optimized when these three objectives are comprehensively considered.

[0059] Pareto frontier analysis is an effective method for dealing with multi-objective optimization problems. It aims to find a set of solutions (called Pareto optimal solution set) that cannot be completely dominated by other solutions in any objective (i.e., improving one objective without deteriorating other objectives). The process of achieving multi-objective optimization through Pareto frontier analysis is as follows: First, define the commutation optimization objectives: Same as the weighted summation method, define commutation optimization objectives such as power loss, harmonic suppression and grid balance; Second, optimize the solution: Use a multi-objective optimization algorithm (such as NSGA-II, MOEA / D, etc.) to solve. The algorithm will generate a set of Pareto optimal solutions, each of which is the result of a trade-off between different commutation optimization objectives; Next, Pareto frontier analysis: Analyze the solutions on the Pareto front to understand their trade-offs between different commutation optimization objectives. Select the most appropriate solution from the Pareto front according to actual needs or preferences; Finally, decision making: According to the solutions on the Pareto front and the decision maker's preferences, formulate the final target commutation operation.

[0060] For example, in a power system, the NSGA-II algorithm is used for multi-objective optimization. The algorithm generates a Pareto frontier containing multiple target commutation operations, each of which achieves a different trade-off between power loss, harmonic suppression, and grid balance. Decision makers can select the most appropriate target commutation operation from the Pareto frontier based on actual conditions (such as current grid status, future load forecasts, equipment limitations, etc.). For example, if the current grid harmonic problem is more serious, the decision maker may choose a target commutation operation that performs better in harmonic suppression.

[0061] In the above scheme, by considering the operation-related data and commutation prediction information, the edge gateway can determine multiple commutation optimization objectives and constraints, and use the preset optimization algorithm and commutation-related parameters to generate the optimal target commutation information, which not only improves the accuracy and efficiency of the commutation operation, but also ensures the stability and safety of the power grid, and effectively improves the power quality and overall system performance.

[0062] Based on the above scheme, optionally, after sending the phase switching control instruction to the phase switching execution unit, it also includes: the edge gateway receives the phase switching execution result of the phase switching control instruction fed back by the phase switching execution unit, and verifies the phase switching execution result to obtain the phase switching verification result.

[0063] The commutation execution result can be understood as the actual effect produced after the commutation execution unit executes the commutation control instruction. The commutation execution result reflects the actual execution of the target commutation operation, including at least one of success, execution time and specific parameters. The commutation verification result can be understood as the result obtained after verifying the commutation execution result, which can be used to evaluate the effectiveness and accuracy of the target commutation operation and ensure the stable operation of the power grid.

[0064] In an optional implementation, after the commutation execution unit executes the commutation instruction, it will continue to detect the state changes of the power grid and feedback the execution results. The edge gateway evaluates the commutation execution results. If the expected goals are not achieved, the commutation prediction model and optimization algorithm parameters are adaptively adjusted according to the feedback information to form a closed-loop control, so that the commutation strategy can be adjusted and optimized in real time according to the dynamic changes in the power grid operation status.

[0065] For example, in an electric power system, the edge gateway collects data such as the voltage, current, and harmonic content of the power grid in real time. Through the commutation prediction model, the edge gateway predicts that the load of the power grid will increase significantly in the future, and there is a risk of excessive harmonics. In response to this prediction result, the edge gateway calls the optimization algorithm for calculation and finds a commutation strategy that can both reduce power loss and effectively suppress harmonics. Subsequently, the edge gateway generates the corresponding commutation instructions and sends them to the commutation execution unit for execution. During the execution process, the edge gateway continuously detects the state of the power grid and adjusts the instructions in time according to the feedback results to ensure the stable operation and efficient energy consumption of the power grid.

[0066] In the above scheme, by receiving and verifying the commutation execution results, the edge gateway can ensure that the commutation operation is performed as expected, improve the stability and reliability of power grid operation, and promptly detect and correct potential problems.

[0067] Based on the above solution, optionally, after obtaining the phase-change verification result, it also includes: the edge gateway sends the operation-related data of the target power grid and the phase-change verification result to a server.

[0068] In an optional implementation, the edge gateway synchronizes the operation-related data and the phase-change verification results to the cloud server, and the cloud server includes a remote detection interface for managers to view the power grid status and phase-change operation status in real time, and provide remote decision support when necessary.

[0069] The above scheme, by sending the operation-related data and commutation verification results to the server, can realize the centralized management and analysis of data, facilitate the long-term detection and optimization of power grid operation, and improve the reliability and efficiency of the power system.

[0070] The technical solution of the embodiment of the present invention is as follows: first, the operation-related data of multiple power grid nodes of the target power grid are obtained through the edge gateway, the operation characteristic data of the target power grid is determined according to the operation-related data, and the phase change prediction information of the target power grid is determined according to the operation characteristic data, so that real-time data collection and analysis can be performed to improve the accuracy and timeliness of phase change prediction; then, the edge gateway determines the target phase change information of the target power grid according to the operation-related data and the phase change prediction information, generates a phase change control instruction according to the target phase change information, and sends the phase change control instruction to the phase change execution unit, so that the phase change execution unit executes the target phase change operation according to the phase change control instruction, so as to realize precise phase change control, solve the problem in the related technology that the phase change operation relies on manual operation and is not accurate and timely enough, not only improves the accuracy and response speed of the phase change operation, but also optimizes the operation state of the power grid, improves the power quality and system stability, reduces power loss and equipment failure rate, and meets the requirements of modern power systems for high efficiency and high reliability.

[0071] Embodiment 2

[0072] Figure 2 A flowchart of a power grid commutation method based on an edge gateway is provided for Embodiment 2 of the present invention. This embodiment is based on the above embodiment and further refines how to determine the operation characteristic data based on the operation-related data. Optionally, the operation characteristic data is determined based on the operation-related data, including: performing standardization processing on the operation-related data to obtain standardized data, and determining the operation characteristic data based on the standardized data; wherein the standardization processing includes at least one of data format conversion processing, data fusion processing, and data verification processing. For specific implementation methods, please refer to the description of this embodiment. Among them, the technical features that are the same or similar to those in the above embodiments are not repeated here.

[0073] like Figure 2 As shown, the method may specifically include:

[0074] S210. The edge gateway obtains operation-related data of multiple grid nodes of the target power grid, standardizes the operation-related data to obtain standardized data, determines operation characteristic data based on the standardized data, and determines commutation prediction information of the target power grid based on the operation characteristic data.

[0075] Among them, the standardization process can be understood as converting data into a unified standard format to provide a reliable data basis for subsequent feature extraction and model training, wherein the standardization process may include but is not limited to at least one of data format conversion processing, data fusion processing, and data verification processing. The standardized data can be understood as data that has been standardized and has a unified format and standard. The standardized data facilitates feature extraction and model training, and can improve the efficiency and accuracy of data processing. The data format conversion process can be understood as converting data of different formats into a unified format, which can ensure that all data can be processed and analyzed on the same platform, thereby improving the efficiency and accuracy of data processing. The data fusion process can be understood as merging data from different sources or different types into a unified data set, which can be used to integrate multi-source data, provide more comprehensive and accurate power grid operation status information, and support more complex analysis and prediction tasks. The data verification process can be understood as checking and verifying the data to ensure the accuracy and completeness of the data, and can timely discover and correct errors or anomalies in the data, improve the quality of the data, and ensure the reliability of subsequent analysis and prediction.

[0076] On the basis of the above scheme, optionally, determining the operating characteristic data of the target power grid based on the standardized data includes: performing feature extraction on the standardized data to obtain a plurality of preliminary characteristic data; determining a plurality of key characteristic data from the preliminary characteristic data based on a correlation between the plurality of preliminary characteristic data and the power grid operating status of the target power grid, and performing dimensionality reduction processing on the plurality of key characteristic data to obtain the operating characteristic data of the target power grid.

[0077] Among them, the feature extraction can be understood as the process of extracting useful features from the original data. By performing feature extraction on the standardized data, multiple preliminary feature data can be obtained. These preliminary feature data reflect the different operating characteristics of the power grid and provide a basis for further analysis and screening. The preliminary operation data can be understood as the initial feature information extracted from the standardized data, including various features reflecting the operating status of the power grid. The preliminary operation data may include at least one of load mode data, harmonic content data and phase deviation data. The load mode data can be understood as the law of load changes over time in the power grid. The load mode data is determined by calculating the average power, power factor, peak load and other statistics over a period of time. For example, for residential power grids, the average power difference between the night valley period and the daytime peak period can be extracted as a feature of the load mode. The harmonic content data can be understood as the proportion of each harmonic component in the power grid except the fundamental wave. The voltage or current signal can be spectrally analyzed using algorithms such as fast Fourier transform (FFT) to obtain the amplitude and phase of each harmonic. For example, by analyzing the voltage signal through FFT, the amplitude proportion of the main harmonics such as the 3rd, 5th, and 7th harmonics is extracted as the feature of the harmonic content. The phase deviation data can be understood as the phase difference between different nodes or different phases in the power grid, which is particularly important for the balance assessment of the three-phase power grid. For example, by comparing the phase angles of the three-phase voltages A, B, and C, the phase deviation between them is calculated as a feature of the balance of the power grid. The power grid operation state can be understood as the overall operation of the power grid at a certain moment, including but not limited to at least one of the parameters such as voltage, current, frequency, and load. The power grid operation state reflects the actual working conditions of the power grid and is an important basis for evaluating the performance of the power grid and performing optimization operations. The correlation can be understood as the degree of association between two variables, usually expressed as a correlation coefficient. By calculating the correlation between the preliminary feature data and the power grid operation state, it can be determined which preliminary feature data has the greatest impact on the power grid operation state, thereby screening out key feature data. The key feature data can be understood as feature data that is highly correlated with the power grid operation state screened from multiple preliminary feature data. The key feature data is the information that best reflects the power grid operation state. By further processing and analyzing the key feature data, the accuracy and efficiency of the model can be improved. The dimensionality reduction process can be understood as a technology for reducing data dimensions, which can reduce the complexity of data, remove redundant information, and improve the training efficiency and prediction accuracy of the model.

[0078] An optional implementation method is to extract preliminary feature data (such as load pattern data, harmonic content data, and phase deviation data, etc.) from the standardized data; then, feature selection is performed to select the features (key feature data) that have the greatest impact on the analysis target from the extracted preliminary feature data to reduce data redundancy and improve model performance. Specifically, statistical methods (such as chi-square test, ANOVA analysis), model-based methods (such as decision trees, feature importance assessment in random forests), or expert knowledge-based methods can be used. For example, in load pattern analysis, if it is found that the average power is highly correlated with the power factor, and the power factor contributes less to the load pattern classification, then only the average power can be retained as a feature; finally, feature dimensionality reduction is performed to reduce the dimension of the feature while retaining key information to improve the efficiency of data processing and model training. The dimensionality reduction method can be one of principal component analysis (PCA), linear discriminant analysis (LDA) or t-SNE. For example, PCA is used to reduce the dimensionality of the extracted harmonic content features. By calculating the covariance matrix, eigenvalues ​​and eigenvectors, the first few principal components are selected as the new feature set. These principal components can retain the information in the original data to the greatest extent.

[0079] The above scheme, through feature extraction and dimensionality reduction processing, screens out key feature data that are highly relevant to the operating status of the power grid from the standardized data, improves the efficiency of data processing and the prediction accuracy of the model, and provides a reliable basis for the optimized operation and phase change prediction of the power grid.

[0080] S220, the edge gateway determines the target commutation information of the target power grid according to the operation-related data and the commutation prediction information, generates a commutation control instruction according to the target commutation information, and sends the commutation control instruction to the commutation execution unit, so that the commutation execution unit performs the target commutation operation according to the commutation control instruction.

[0081] The technical solution of the embodiment of the present invention ensures the consistency and accuracy of the data by standardizing the operation-related data, including data format conversion, data fusion and data verification; then, feature extraction is performed based on the standardized data to obtain multiple preliminary feature data, and by analyzing the correlation between the preliminary feature data and the operation status of the power grid, key feature data is screened out and dimensionality reduction is performed, which further optimizes the data availability and the training efficiency of the model, improves the accuracy and response speed of the commutation operation, optimizes the operation status of the power grid, and improves the power quality and system stability.

[0082] Embodiment 3

[0083] Figure 3 The schematic diagram of the structure of a power grid phase switching device based on an edge gateway provided in the third embodiment of the present invention. Figure 3As shown, the device includes: a commutation prediction information determination module 310 and a target commutation operation execution module 320.

[0084] Among them, the phase switching prediction information determination module 310 is used for the edge gateway to obtain operation-related data of multiple grid nodes of the target power grid, determine the operation characteristic data of the target power grid according to the operation-related data, and determine the phase switching prediction information of the target power grid according to the operation characteristic data; the target phase switching operation execution module 320 is used for the edge gateway to determine the target phase switching information of the target power grid according to the operation-related data and the phase switching prediction information, generate a phase switching control instruction according to the target phase switching information, and send the phase switching control instruction to the phase switching execution unit, so that the phase switching execution unit performs the target phase switching operation according to the phase switching control instruction.

[0085] According to the technical solution of the embodiment of the present invention, first, the phase switching prediction information determination module 310 obtains the operation-related data of multiple grid nodes of the target power grid through the edge gateway, determines the operation characteristic data of the target power grid according to the operation-related data, and determines the phase switching prediction information of the target power grid according to the operation characteristic data, which can collect and analyze data in real time to improve the accuracy and timeliness of phase switching prediction; then, the target phase switching operation execution module 320 determines the target phase switching information of the target power grid according to the operation-related data and the phase switching prediction information through the edge gateway, generates a phase switching control instruction according to the target phase switching information, and sends the phase switching control instruction to the phase switching execution unit, so that the phase switching execution unit executes the target phase switching operation according to the phase switching control instruction, which can realize precise phase switching control, solves the problem in the related art that the phase switching operation relies on manual operation and is not accurate and timely enough, not only improves the accuracy and response speed of the phase switching operation, but also optimizes the operation state of the power grid, improves the power quality and system stability, reduces power loss and equipment failure rate, and meets the requirements of modern power systems for high efficiency and high reliability.

[0086] On the basis of the above solution, optionally, the commutation prediction information determination module includes: an operation characteristic data determination submodule.

[0087] Among them, the operation characteristic data determination submodule is used to standardize the operation-related data to obtain standardized data, and determine the operation characteristic data based on the standardized data; wherein, the standardization processing includes at least one of data format conversion processing, data fusion processing and data verification processing.

[0088] On the basis of the above solution, optionally, the operation characteristic data determination submodule includes: a characteristic extraction unit and an operation characteristic data determination unit.

[0089] Among them, the feature extraction unit is used to extract features from the standardized data to obtain multiple preliminary feature data, and the preliminary operation data at least includes load mode data, harmonic content data and phase deviation data; the operation feature data determination unit is used to determine multiple key feature data from the preliminary feature data according to the correlation between the multiple preliminary feature data and the power grid operation status of the target power grid, and perform dimensionality reduction processing on the multiple key feature data to obtain the operation feature data of the target power grid.

[0090] On the basis of the above solution, optionally, the commutation prediction information determination module includes: a commutation prediction information determination submodule.

[0091] Among them, the commutation prediction information determination submodule is used to input the operating characteristic data into the commutation prediction model to obtain the commutation prediction information of the target power grid; wherein the commutation prediction model is obtained by training a pre-established deep learning model through sample characteristic data and target commutation information corresponding to the sample characteristic data.

[0092] On the basis of the above solution, optionally, the target commutation operation execution module includes: a commutation constraint condition determination submodule and a target commutation information determination submodule.

[0093] Among them, the commutation constraint determination submodule is used for the edge gateway to determine multiple commutation optimization targets and multiple commutation constraints according to the operation-related data and the commutation prediction information; the target commutation information determination submodule is used to determine the target commutation information of the target power grid according to multiple commutation-related parameters, a preset optimization algorithm, multiple commutation optimization targets and multiple commutation constraints.

[0094] On the basis of the above solution, optionally, the edge gateway-based power grid phase switching device further includes: a verification module.

[0095] Among them, the verification module is characterized in that, after the phase switching control instruction is sent to the phase switching execution unit, the edge gateway receives the phase switching execution result of the phase switching control instruction fed back by the phase switching execution unit, and verifies the phase switching execution result to obtain the phase switching verification result.

[0096] On the basis of the above solution, optionally, the edge gateway-based power grid phase switching device further includes: a sending module.

[0097] Wherein, the sending module is used for, after the phase-change verification result is obtained, the edge gateway to send the operation-related data of the target power grid and the phase-change verification result to the server.

[0098] On the basis of the above solution, optionally, the communication between the edge gateway and the phase-changing execution unit is performed by using a dual-channel communication method of wireless and carrier.

[0099] Based on the above solution, optionally, the operation-related data includes at least one of current data, voltage data, phase data, temperature data and vibration data.

[0100] The power grid phase switching device based on edge gateway provided in the embodiment of the present invention can execute the power grid phase switching method based on edge gateway provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0101] Embodiment 4

[0102] Figure 4 A schematic diagram of the structure of an edge gateway 10 that can be used to implement an embodiment of the present invention is shown. The edge gateway 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 edge gateway can 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.

[0103] like Figure 4 As shown, the edge gateway 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 edge gateway 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0104] Multiple components in the edge gateway 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 edge gateway 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0105] 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 special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a power grid commutation method based on an edge gateway.

[0106] In some embodiments, a power grid commutation method based on an edge gateway 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 edge gateway 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 power grid commutation method based on an edge gateway described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute a power grid commutation method based on an edge gateway in any other appropriate manner (e.g., by means of firmware).

[0107] 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.

[0108] 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.

[0109] 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.

[0110] To provide interaction with a user, the systems and techniques described herein may be implemented on an edge gateway having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which a user can provide input to the edge gateway. Other types of devices may also be used to provide interaction with a 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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 power grid phase switching method based on edge gateway, characterized in that: include: The edge gateway obtains operation-related data of multiple power grid nodes of the target power grid, determines operation characteristic data of the target power grid according to the operation-related data, and determines commutation prediction information of the target power grid according to the operation characteristic data; The edge gateway determines the target commutation information of the target power grid according to the operation-related data and the commutation prediction information, generates a commutation control instruction according to the target commutation information, and sends the commutation control instruction to the commutation execution unit, so that the commutation execution unit performs the target commutation operation according to the commutation control instruction.

2. The power grid phase switching method based on edge gateway according to claim 1, characterized in that: The determining of the operation characteristic data according to the operation association data comprises: The operation-related data is standardized to obtain standardized data, and the operation characteristic data is determined according to the standardized data; wherein the standardization processing includes at least one of data format conversion processing, data fusion processing and data verification processing.

3. The power grid phase switching method based on edge gateway according to claim 2 is characterized in that: The step of determining the operating characteristic data of the target power grid according to the standardized data comprises: Extracting features from the standardized data to obtain a plurality of preliminary feature data; wherein the preliminary operation data at least includes load mode data, harmonic content data and phase deviation data; According to the correlation between the multiple preliminary characteristic data and the grid operation status of the target grid, multiple key characteristic data are determined from the preliminary characteristic data, and dimensionality reduction processing is performed on the multiple key characteristic data to obtain the operation characteristic data of the target grid.

4. The power grid phase switching method based on edge gateway according to claim 1, characterized in that: The determining the commutation prediction information of the target power grid according to the operation characteristic data includes: The operating characteristic data is input into a commutation prediction model to obtain commutation prediction information of the target power grid; wherein the commutation prediction model is obtained by training a pre-established deep learning model through sample characteristic data and target commutation information corresponding to the sample characteristic data.

5. The power grid phase switching method based on edge gateway according to claim 1, characterized in that: The edge gateway determines the target commutation information of the target power grid according to the operation-related data and the commutation prediction information, including: The edge gateway determines a plurality of commutation optimization objectives and a plurality of commutation constraint conditions according to the operation-related data and the commutation prediction information; The target commutation information of the target power grid is determined according to a plurality of commutation-related parameters, a preset optimization algorithm, a plurality of the commutation optimization objectives and a plurality of the commutation constraint conditions.

6. The power grid phase switching method based on edge gateway according to claim 1, characterized in that: After sending the commutation control instruction to the commutation execution unit, the method further includes: The edge gateway receives the commutation execution result of the commutation control instruction fed back by the commutation execution unit, and obtains a commutation verification result by verifying the commutation execution result.

7. The power grid phase switching method based on edge gateway according to claim 6, characterized in that: After the phase switching verification result is obtained, the method further includes: The edge gateway sends the operation-related data of the target power grid and the phase-change verification result to the server.

8. The power grid phase switching method based on edge gateway according to claim 1, characterized in that: The communication between the edge gateway and the phase-changing execution unit is carried out by using a dual-channel communication method of wireless and carrier.

9. The power grid phase switching method based on edge gateway according to claim 1, characterized in that: The operation-related data includes at least one of current data, voltage data, phase data, temperature data and vibration data.

10. An edge gateway, characterized in that: The edge gateway comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable 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 edge gateway-based power grid commutation method according to any one of claims 1 to 7.

Images