Intelligent power grid data processing method, system and equipment based on edge calculation and medium
Through edge computing, the processing of smart grid data, and the use of random forest algorithms and neural network optimization, the problem of insufficient timeliness and reliability of cloud computing is solved, and efficient smart grid data processing and power system scheduling is achieved.
Patent Information
- Application Number
- CN202411314855.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2025-01-03
AI Technical Summary
The existing cloud computing smart grid data processing methods have shortcomings in terms of timeliness and reliability, and cannot meet the rapid response to energy demand in modern society and the improvement of data processing efficiency.
Using edge computing methods, we preprocess smart grid data, call random forest algorithms for classification, input data to neural network for analysis, iteratively optimize neural network structure, generate smart grid prediction results and scheduling schemes, and improve data processing efficiency and reliability sex.
While ensuring the reliability and timeliness of data processing, it significantly improves the efficiency of smart grid data processing, and can respond to energy needs more quickly and optimize power system operations.
Smart Images
Figure CN119250435A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart grid data processing technology, and specifically, to a smart grid data processing method, system, device and medium based on edge computing. Background Art
[0002] Smart grid is one of the research hotspots in academia and industry today. Its main goal is to provide two-way communication so that power and information can be exchanged between the cloud control center and users. Smart grid enhances the infrastructure of traditional power grids, allowing grid operators to better communicate with users to meet their power needs. Smart grid is not only an improved framework for grid operation, but also allows users to understand their power usage and choose better energy utilization plans. Based on user usage data, smart grid can manage its operations, including on-demand response, prediction, availability, customer billing, interruptions and mitigation of potential security threats. However, with the continuous growth of energy demand, traditional power grids can no longer meet the energy needs of modern society. Therefore, smart grids have gradually grown and integrated with technologies such as artificial intelligence, cloud computing, blockchain, and big data to meet the requirements of current energy development.
[0003] Edge computing is an open platform that integrates network, computing, storage, application and intelligence. It cooperates with cloud computing to promote the digital transformation of the industry. In the context of big data, the comprehensive processing of smart grid asset information includes the evaluation and scheduling of relevant data. Its essence is to analyze the time series distribution of smart grid asset information based on big data mining, and combine it with optimization scheduling and control methods to achieve the evaluation and processing of smart grid asset information. Most traditional analysis methods are based on big data prediction and scheduling methods, combined with correlation and adaptive evaluation methods to process grid asset information. However, due to the continuous expansion of information scale, traditional cloud computing smart grid data processing methods have exposed certain problems in terms of timeliness and reliability. Summary of the invention
[0004] Aiming at the problem that the existing cloud computing smart grid data processing method is insufficient in timeliness and reliability, the present invention proposes a smart grid data processing method, system, device and medium based on edge computing; firstly, the smart grid data obtained from the edge node is preprocessed; secondly, the random forest algorithm is called to classify the preprocessed smart grid data to obtain the classified smart grid data; then the classified smart grid data are respectively input into the constructed neural network to obtain the processing result; finally, the neural network structure is adjusted according to the processing result to obtain the optimized neural network, the smart grid prediction result is obtained, and the smart grid scheduling plan is generated; while ensuring the reliability and timeliness of data processing, the data processing efficiency is improved.
[0005] The specific implementation contents of the present invention are as follows: A smart grid data processing method based on edge computing specifically includes the following steps: Step S1: preprocessing smart grid data obtained from edge nodes; Step S2: calling the random forest algorithm to classify the preprocessed smart grid data to obtain the classified smart grid data; Step S3: inputting the classified smart grid data into the constructed neural network respectively to obtain processing results; Step S4: Adjust the neural network structure according to the processing results to obtain an optimized neural network, obtain the smart grid prediction results according to the optimized neural network, and generate a smart grid scheduling plan.
[0006] In order to better implement the present invention, further, the step S2 specifically includes the following steps: Step S21: extracting the preprocessed smart grid data features to obtain smart grid data feature quantities; Step S22: obtaining a smart grid data set according to the set tags and smart grid data feature quantities; Step S23: training a classifier of a random forest decision tree according to a subset of the smart grid data set to obtain a midpoint classification function of the decision tree; Step S24: dividing the smart grid data set into a left subtree and a right subtree according to the midpoint classification function of the decision tree and the set threshold; Step S25: Calculate the partition Gini coefficient according to the partitioned left subtree and right subtree; Step S26: Calculate the minimum characteristic value according to the Gini coefficient, classify the smart grid data according to the minimum characteristic value, and obtain the classified smart grid data.
[0007] In order to better implement the present invention, further, the classified smart grid data includes load data, user information data, grid equipment data, and system operation information data.
[0008] In order to better implement the present invention, further, the step S3 specifically includes the following steps: Step S31: setting the number of nodes in the neural network input layer, the number of nodes in the hidden layer, and the number of nodes in the output layer to construct a neural network; Step S32: Obtain the hidden layer output function according to the weight from the input layer to the hidden layer and the bias from the input layer to the hidden layer; Step S33: obtaining the output layer output function according to the hidden layer output function, the weight from the hidden layer to the output layer, and the bias from the hidden layer to the output layer; Step S34: According to the output function of the output layer, the classified smart grid data is input into the constructed neural network to obtain the processing result.
[0009] In order to better implement the present invention, further, the step S4 specifically includes the following steps: Step S41: construct a loss function according to the output function of the output layer and the set error bias; Step S42: calling the gradient descent method to update the neural network weights to obtain an updated neural network; Step S43: adjusting the updated neural network structure according to the processing result to obtain an optimized neural network; Step S44: obtaining a smart grid prediction result according to the optimized neural network; Step S45: Generate a smart grid dispatching plan based on the smart grid prediction results.
[0010] In order to better implement the present invention, further, the step S42 specifically includes the following steps: Step S421: calling the gradient descent method to update the output layer weight gradient and the output layer bias gradient; Step S422: updating the hidden layer weight gradient and the hidden layer bias gradient according to the chain rule; Step S423: Repeat steps S421 and S422 until the loss value of the loss function is less than the set loss function threshold, and obtain an updated neural network.
[0011] In order to better implement the present invention, further, the specific operation of step S1 is: first, the smart grid data is collected from the edge node, and then the collected smart grid data is normalized according to the mean of the collected smart grid data and the standard deviation of the collected smart grid data to obtain the preprocessed smart grid data.
[0012] Based on the above-mentioned smart grid data processing method based on edge computing, in order to better realize the present invention, further, a smart grid data processing system based on edge computing is proposed, which is used to execute the above-mentioned smart grid data processing method based on edge computing; including a preprocessing unit, a classification unit, a processing unit, and a prediction unit; The preprocessing unit is used to preprocess the smart grid data obtained from the edge node; The classification unit is used to call the random forest algorithm to classify the preprocessed smart grid data to obtain the classified smart grid data; The processing unit is used to input the classified smart grid data into the constructed neural network to obtain processing results; The prediction unit is used to adjust the neural network structure according to the processing results to obtain an optimized neural network, obtain the smart grid prediction result according to the optimized neural network, and generate a smart grid scheduling plan.
[0013] Based on the above-mentioned smart grid data processing method based on edge computing, in order to better realize the present invention, further, an electronic device is proposed, including a memory and a processor; a computer program is stored on the memory; when the computer program is executed on the processor, the above-mentioned smart grid data processing method based on edge computing is implemented.
[0014] Based on the above-mentioned smart grid data processing method based on edge computing, in order to better realize the present invention, further, a computer-readable storage medium is proposed, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned smart grid data processing method based on edge computing is implemented.
[0015] The present invention has the following beneficial effects: The present invention deploys edge computing nodes close to the smart grid data source, uses the random forest algorithm to classify the smart grid data, and inputs it into the constructed neural network for analysis and learning, and continuously iterates and optimizes to obtain the corresponding power system service demand results, thereby improving data processing efficiency while ensuring the reliability and timeliness of data processing. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 A schematic block diagram of the overall process of the smart grid data processing method based on edge computing provided by the present invention. DETAILED DESCRIPTION
[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the technical solutions 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. It should be understood that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments, and therefore should not be regarded as limiting the scope of protection. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technical personnel in this field without making creative work are within the scope of protection of the present invention.
[0018] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "disposed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0019] Embodiment 1: This embodiment proposes a smart grid data processing method based on edge computing, a smart grid data processing method based on edge computing, specifically comprising the following steps: Step S1: Preprocessing the smart grid data obtained from the edge nodes.
[0020] The specific operation of step S1 is: first, collect smart grid data from the edge node, and then normalize the collected smart grid data according to the mean value of the collected smart grid data and the standard deviation of the collected smart grid data to obtain pre-processed smart grid data.
[0021] Step S2: calling the random forest algorithm to classify the preprocessed smart grid data to obtain the classified smart grid data; The step S2 specifically includes the following steps: Step S21: extracting the preprocessed smart grid data features to obtain smart grid data feature quantities; Step S22: obtaining a smart grid data set according to the set tags and smart grid data feature quantities; Step S23: training a classifier of a random forest decision tree according to a subset of the smart grid data set to obtain a midpoint classification function of the decision tree; Step S24: dividing the smart grid data set into a left subtree and a right subtree according to the midpoint classification function of the decision tree and the set threshold; Step S25: Calculate the partition Gini coefficient according to the partitioned left subtree and right subtree; Step S26: Calculate the minimum characteristic value according to the Gini coefficient, classify the smart grid data according to the minimum characteristic value, and obtain the classified smart grid data.
[0022] The classified smart grid data includes load data, user information data, grid equipment data, and system operation information data.
[0023] Step S3: inputting the classified smart grid data into the constructed neural network respectively to obtain processing results; The step S3 specifically comprises the following steps: Step S31: setting the number of nodes in the neural network input layer, the number of nodes in the hidden layer, and the number of nodes in the output layer to construct a neural network; Step S32: Obtain the hidden layer output function according to the weight from the input layer to the hidden layer and the bias from the input layer to the hidden layer; Step S33: obtaining the output layer output function according to the hidden layer output function, the weight from the hidden layer to the output layer, and the bias from the hidden layer to the output layer; Step S34: According to the output function of the output layer, the classified smart grid data is input into the constructed neural network to obtain the processing result.
[0024] Step S4: Adjust the neural network structure according to the processing results to obtain an optimized neural network, obtain the smart grid prediction results according to the optimized neural network, and generate a smart grid scheduling plan.
[0025] The step S4 specifically comprises the following steps: Step S41: construct a loss function according to the output function of the output layer and the set error bias; Step S42: calling the gradient descent method to update the neural network weights to obtain an updated neural network; The step S42 specifically includes the following steps: Step S421: calling the gradient descent method to update the output layer weight gradient and the output layer bias gradient; Step S422: updating the hidden layer weight gradient and the hidden layer bias gradient according to the chain rule; Step S423: Repeat steps S421 and S422 until the loss value of the loss function is less than the set loss function threshold, and obtain an updated neural network.
[0026] Step S43: adjusting the updated neural network structure according to the processing result to obtain an optimized neural network; Step S44: obtaining a smart grid prediction result according to the optimized neural network; Step S45: Generate a smart grid dispatching plan based on the smart grid prediction results.
[0027] Working principle: This embodiment deploys edge computing nodes close to the smart grid data source, uses the random forest algorithm to classify the smart grid data, and inputs it into the constructed neural network for analysis and learning, and continuously iterates and optimizes to obtain the corresponding power system service demand results, while ensuring the reliability and timeliness of data processing, while improving data processing efficiency.
[0028] Embodiment 2: This embodiment is based on the above embodiment 1. Figure 1As shown, a specific embodiment is described in detail.
[0029] Step S1: Preprocessing the smart grid data obtained from the edge nodes.
[0030] First, the smart grid data is collected from the edge nodes, and then the collected smart grid data is normalized according to the mean value and standard deviation of the collected smart grid data to obtain the pre-processed smart grid data. The specific operations are as follows: s' = (s - μ) / δ Among them, s' represents the preprocessed smart grid data, s represents the collected smart grid data, μ represents the mean of the collected smart grid data, and δ represents the standard deviation of the collected smart grid data.
[0031] Step S2: calling the random forest algorithm to classify the preprocessed smart grid data to obtain the classified smart grid data; Step S21: extract the pre-processed smart grid data features to obtain the smart grid data feature quantity s t ; Step S22: Obtaining a smart grid data set Y according to the set labels and smart grid data feature quantities; Y={y t =(s t ,b t )} Among them, y t represents a sample of the smart grid dataset, b t Indicates the setting label.
[0032] Step S23: training a classifier of a random forest decision tree according to a subset of the smart grid data set to obtain a midpoint classification function of the decision tree; f(s t ) = left subtree S 1 ;(s t （i） <s 0 ) f(s t ) = right subtree S 2 ; (s t （i） ≥s 0 ) Step S24: According to the decision tree midpoint classification function and the set threshold, the smart grid data set is divided into the left subtree S 1 , right subtree S 2 ; Step S25: Calculate the partition Gini coefficient according to the partitioned left subtree and right subtree; G s (Y) = |S1 | / |Y|G(S 1 )+|S 2 | / |Y|G(S 2 ) Step S26: Calculate the minimum characteristic value according to the Gini coefficient, classify the smart grid data according to the minimum characteristic value, and obtain the classified smart grid data.
[0033] If the smart grid data sets are of the same type, the Gini coefficient takes the minimum value; if the smart grid data sets are evenly distributed, the Gini coefficient takes the maximum value; on each edge node, several features and thresholds are randomly selected for testing to obtain the minimum G ｓ Features and thresholds are used to divide samples.
[0034] The classified smart grid data includes load data, user information data, grid equipment data, and system operation information data.
[0035] Step S3: inputting the classified smart grid data into the constructed neural network respectively to obtain processing results; The step S3 specifically comprises the following steps: Step S31: setting the number of nodes in the neural network input layer, the number of nodes in the hidden layer, and the number of nodes in the output layer to construct a neural network; Step S32: Obtain the hidden layer output function according to the weight from the input layer to the hidden layer and the bias from the input layer to the hidden layer; Step S33: obtaining the output layer output function according to the hidden layer output function, the weight from the hidden layer to the output layer, and the bias from the hidden layer to the output layer; Step S34: According to the output function of the output layer, the classified smart grid data is input into the constructed neural network to obtain the processing result.
[0036] Step S4: Adjust the neural network structure according to the processing results to obtain an optimized neural network, obtain the smart grid prediction results according to the optimized neural network, and generate a smart grid scheduling plan.
[0037] The step S4 specifically comprises the following steps: Step S41: construct a loss function according to the output function of the output layer and the set error bias; Step S42: calling the gradient descent method to update the neural network weights to obtain an updated neural network; The step S42 specifically includes the following steps: Step S421: calling the gradient descent method to update the output layer weight gradient and the output layer bias gradient; Step S422: updating the hidden layer weight gradient and the hidden layer bias gradient according to the chain rule; Step S423: Repeat steps S421 and S422 until the loss value of the loss function is less than the set loss function threshold, and obtain an updated neural network.
[0038] Step S43: adjusting the updated neural network structure according to the processing result to obtain an optimized neural network; Step S44: obtaining a smart grid prediction result according to the optimized neural network; Step S45: Generate a smart grid dispatching plan based on the smart grid prediction results.
[0039] The other parts of this embodiment are the same as those of the above-mentioned embodiment 1, and thus will not be described in detail.
[0040] Embodiment 3: Based on any one of the above-mentioned embodiments 1-2, this embodiment proposes a smart grid data processing system based on edge computing, which is used to execute the above-mentioned smart grid data processing method based on edge computing; including a preprocessing unit, a classification unit, a processing unit, and a prediction unit; The preprocessing unit is used to preprocess the smart grid data obtained from the edge node; The classification unit is used to call the random forest algorithm to classify the preprocessed smart grid data to obtain the classified smart grid data; The processing unit is used to input the classified smart grid data into the constructed neural network to obtain processing results; The prediction unit is used to adjust the neural network structure according to the processing results to obtain an optimized neural network, obtain the smart grid prediction result according to the optimized neural network, and generate a smart grid scheduling plan.
[0041] This embodiment also proposes an electronic device, including a memory and a processor; a computer program is stored on the memory; when the computer program is executed on the processor, the above-mentioned smart grid data processing method based on edge computing is implemented.
[0042] This embodiment also proposes a computer-readable storage medium, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned smart grid data processing method based on edge computing is implemented.
[0043] The other parts of this embodiment are the same as any one of the above-mentioned embodiments 1-2, so they will not be repeated here.
[0044] The processor involved in the embodiments of the present application may be a chip. For example, it may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.
[0045] The memory involved in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.
[0046] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0047] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0048] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0049] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0050] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one device or distributed on multiple devices. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.
[0051] In addition, each functional module in each embodiment of the present application may be integrated into one device, or each module may exist physically separately, or two or more modules may be integrated into one device.
[0052] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or may include one or more servers, data centers and other data storage devices that can be integrated with the medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).
[0053] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A smart grid data processing method based on edge computing, characterized in that: The specific steps include: Step S1: preprocessing smart grid data obtained from edge nodes; Step S2: calling the random forest algorithm to classify the preprocessed smart grid data to obtain the classified smart grid data; Step S3: inputting the classified smart grid data into the constructed neural network respectively to obtain processing results; Step S4: Adjust the neural network structure according to the processing results to obtain an optimized neural network, obtain the smart grid prediction results according to the optimized neural network, and generate a smart grid scheduling plan.
2. According to the method for processing smart grid data based on edge computing in claim 1, it is characterized in that: The step S2 specifically includes the following steps: Step S21: extracting the preprocessed smart grid data features to obtain smart grid data feature quantities; Step S22: obtaining a smart grid data set according to the set tags and smart grid data feature quantities; Step S23: training a classifier of a random forest decision tree according to a subset of the smart grid data set to obtain a midpoint classification function of the decision tree; Step S24: dividing the smart grid data set into a left subtree and a right subtree according to the midpoint classification function of the decision tree and the set threshold; Step S25: Calculate the partition Gini coefficient according to the partitioned left subtree and right subtree; Step S26: Calculate the minimum characteristic value according to the Gini coefficient, classify the smart grid data according to the minimum characteristic value, and obtain the classified smart grid data.
3. According to claim 2, a smart grid data processing method based on edge computing is characterized in that: The classified smart grid data includes load data, user information data, grid equipment data, and system operation information data.
4. The method for processing smart grid data based on edge computing according to claim 1, characterized in that: The step S3 specifically comprises the following steps: Step S31: setting the number of nodes in the neural network input layer, the number of nodes in the hidden layer, and the number of nodes in the output layer to construct a neural network; Step S32: Obtain the hidden layer output function according to the weight from the input layer to the hidden layer and the bias from the input layer to the hidden layer; Step S33: obtaining the output layer output function according to the hidden layer output function, the weight from the hidden layer to the output layer, and the bias from the hidden layer to the output layer; Step S34: According to the output function of the output layer, the classified smart grid data is input into the constructed neural network to obtain the processing result.
5. The method for processing smart grid data based on edge computing according to claim 4, characterized in that: The step S4 specifically comprises the following steps: Step S41: construct a loss function according to the output function of the output layer and the set error bias; Step S42: calling the gradient descent method to update the neural network weights to obtain an updated neural network; Step S43: adjusting the updated neural network structure according to the processing result to obtain an optimized neural network; Step S44: obtaining a smart grid prediction result according to the optimized neural network; Step S45: Generate a smart grid dispatching plan based on the smart grid prediction results.
6. A smart grid data processing method based on edge computing according to claim 5, characterized in that: The step S42 specifically includes the following steps: Step S421: calling the gradient descent method to update the output layer weight gradient and the output layer bias gradient; Step S422: updating the hidden layer weight gradient and the hidden layer bias gradient according to the chain rule; Step S423: Repeat steps S421 and S422 until the loss value of the loss function is less than the set loss function threshold, and obtain an updated neural network.
7. The method for processing smart grid data based on edge computing according to claim 1, characterized in that: The specific operation of step S1 is: first, collect smart grid data from the edge node, and then normalize the collected smart grid data according to the mean value of the collected smart grid data and the standard deviation of the collected smart grid data to obtain pre-processed smart grid data.
8. A smart grid data processing system based on edge computing, used to execute a smart grid data processing method based on edge computing as claimed in claim 1; characterized in that: It includes a preprocessing unit, a classification unit, a processing unit, and a prediction unit; The preprocessing unit is used to preprocess the smart grid data obtained from the edge node; The classification unit is used to call the random forest algorithm to classify the preprocessed smart grid data to obtain the classified smart grid data; The processing unit is used to input the classified smart grid data into the constructed neural network to obtain processing results; The prediction unit is used to adjust the neural network structure according to the processing results to obtain an optimized neural network, obtain the smart grid prediction result according to the optimized neural network, and generate a smart grid scheduling plan.
9. An electronic device, characterized in that: It comprises a memory and a processor; a computer program is stored in the memory; when the computer program is executed on the processor, the smart grid data processing method based on edge computing as described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions; when the computer instructions are executed on the electronic device as described in claim 9, the edge computing-based smart grid data processing method as described in any one of claims 1-7 is implemented.