Power grid marketing side system platform data processing and analyzing method based on edge calculation

Abstract

The invention relates to the technical field of smart power grids, and particularly discloses a power grid marketing side system platform data processing and analyzing method based on edge computing, which collects power consumption and power factor data of a user in real time through a smart electric meter, and performs efficient processing by using an edge computing node close to a data source. Analyzing the power consumption change rate by adopting Haar wavelet transform, analyzing the power factor fluctuation degree by adopting fast Fourier transform, constructing a power consumption change rate characteristic value and a power factor characteristic value so as to evaluate the power utilization stability of a power grid and the stability of a power system, and integrating the characteristic values into a comprehensive characteristic vector so as to evaluate the power utilization stability of the power grid and the stability of the power system. And as the input of the support vector machine model, the power grid marketing response speed is evaluated, and a power grid operator can dynamically adjust a marketing strategy according to an evaluation result.

Description

Technical Field

[0001] This invention relates to the field of smart grid technology, and more specifically to a data processing and analysis method for a power grid marketing-side system platform based on edge computing. Background Technology

[0002] With the rapid development of smart grids and the increasing demands of users for higher quality electricity services, traditional power grid management systems are gradually showing their limitations in processing real-time data, optimizing operational efficiency, and improving service quality. Traditional systems primarily rely on centralized data processing and basic statistical analysis methods to monitor grid status and user electricity consumption behavior. However, facing increasingly complex electricity demands, the widespread integration of distributed energy resources, and the growing demand for personalized services, existing systems struggle to provide sufficient flexibility and responsiveness. Particularly on the power grid marketing side, how to efficiently utilize real-time data for precise marketing and rapid response to changes in market demand has become a pressing issue. Based on this, this invention proposes a data processing and analysis method for a power grid marketing-side system platform based on edge computing, aiming to improve the overall efficiency of power grid management through intelligent data processing and analysis.

[0003] The existing technology has the following shortcomings: Traditional data processing methods typically employ a centralized architecture, resulting in high data transmission latency and failing to meet the demands of real-time data analysis, particularly when rapid response to market changes or grid anomalies is required. Secondly, existing technologies, when analyzing key indicators such as electricity consumption and power factor, largely rely on basic statistical methods, lacking the effective extraction of deeper fluctuation characteristics and failing to accurately identify potential instability factors. Furthermore, existing marketing strategy adjustment mechanisms are relatively fixed, lacking the ability to dynamically adjust based on real-time data analysis results, thus limiting the effectiveness of marketing activities and improving user experience. These problems make existing technologies ill-suited to the modern power grid's requirements for high efficiency, high stability, and personalized services, highlighting the necessity of developing new data processing and analysis methods. Summary of the Invention

[0004] The purpose of this invention is to provide a data processing and analysis method for a power grid marketing side system platform based on edge computing, so as to solve the problems mentioned above.

[0005] The objective of this invention can be achieved through the following technical solutions: The data processing and analysis method of the power grid marketing-side system platform based on edge computing includes the following steps: S1: Collect electricity consumption data and power factor data in real time through smart meters installed at the user end, and transmit these data to edge computing nodes close to the user; S2: Edge computing nodes process the received electricity consumption data, calculate the rate of change of electricity consumption, and assess the stability of the power grid based on the rate of change of electricity consumption. S3: Edge computing nodes process the received power factor data and assess the stability of the power grid system based on the degree of power factor fluctuation. S4: Conduct a comprehensive analysis of the power consumption data and power factor data of the power grid. Based on the analysis results, establish a response speed evaluation model to evaluate the power grid marketing response speed and provide power grid operators with guidance on adjusting marketing strategies based on the evaluation results.

[0006] As a further aspect of the present invention: the edge computing node processes the received electricity consumption data, specifically including: According to the time series, obtain the electricity consumption data of the power grid marketing within the monitoring period, calculate the rate of change of electricity consumption, calculate the characteristic value of the rate of change of electricity consumption based on the trend of the rate of change of electricity consumption, and evaluate the stability of power grid electricity consumption based on the characteristic value of the rate of change of electricity consumption.

[0007] As a further aspect of the present invention: the process for obtaining the characteristic value of the electricity consumption change rate is as follows: Obtain a time-series dataset of electricity consumption within a monitoring period using smart meters; Perform a difference operation on the time series data of electricity consumption to calculate the rate of change of electricity consumption between adjacent time points. Specifically, for each time point, calculate the electricity consumption of the next time point minus the electricity consumption of the current time point to obtain the rate of change of electricity consumption within the corresponding time period. The electricity consumption change rate data is decomposed using Haar wavelet transform to extract information from different frequency components. Specifically, the electricity consumption change rate data is first decomposed into approximation coefficients and detail coefficients, and then the approximation coefficients are recursively decomposed further. By averaging the absolute values ​​of all detail coefficients across all wavelet decomposition layers, a single value representing the degree of fluctuation in the rate of change of electricity consumption is obtained, namely, the characteristic value of the rate of change of electricity consumption.

[0008] As a further aspect of the present invention: the assessment of power grid stability specifically includes: Determine whether the characteristic value of the electricity consumption change rate during the power grid marketing process is greater than or equal to a preset threshold. If it is, the power grid electricity consumption is unstable; otherwise, the power grid electricity consumption is stable.

[0009] As a further aspect of the present invention: the edge computing node processes the received power factor data, specifically including: According to the time series, the power factor data of the power grid marketing during the monitoring period is obtained. Based on the fluctuation of the power factor, the characteristic value of the power factor is calculated. Based on the characteristic value of the power factor, the stability of the power grid power system is evaluated.

[0010] As a further aspect of the present invention: the process for obtaining the power factor characteristic value is as follows: Use smart meters to obtain a power factor time series dataset for a monitoring period; Applying Fast Fourier Transform to the power factor time series data converts the time-domain signal into a frequency-domain representation, including: calculating the corresponding Fourier coefficients for each frequency component; the Fourier coefficients are obtained by multiplying each data point in the original time series by a complex exponential function and summing the results. Based on the Fourier coefficients, the amplitude square of each frequency component is calculated to obtain the power spectral density, wherein the amplitude square is the modulus of each Fourier coefficient and then squared. Obtain the frequencies corresponding to the maximum and minimum power spectral density values, calculate the difference between the power spectral densities to obtain the power spectral density range, and calculate the ratio of the power spectral density range to the mean of all power spectral densities to obtain the power factor characteristic value.

[0011] As a further aspect of the present invention: the evaluation of the stability of the power grid system specifically includes: Determine whether the power factor characteristic value during the power grid marketing process is greater than or equal to a preset threshold. If it is, the corresponding power grid system is unstable; otherwise, the power grid system is stable.

[0012] As a further aspect of the present invention: the comprehensive analysis of the power consumption data and power factor data of the power grid, and the establishment of a response speed evaluation model based on the analysis results, specifically includes: The characteristic values ​​of electricity consumption change rate and power factor in the power grid marketing process are obtained. The characteristic values ​​of electricity consumption change rate and power factor are used to construct a comprehensive feature vector as input to the response speed evaluation model. The training objective is to minimize the error between the predicted marketing response speed score and the actual marketing response speed score. Based on the trained model, the marketing response speed score is output. The response speed evaluation model is a support vector machine model.

[0013] As a further aspect of the present invention: the assessment of the power grid marketing response speed specifically includes: Determine whether the marketing response speed score output by the response speed evaluation model in the power grid marketing process is greater than or equal to a preset threshold. If yes, the power grid marketing response speed is normal; otherwise, the power grid marketing response speed is abnormal.

[0014] The beneficial effects of this invention are: (1) By collecting users' electricity consumption and power factor data in real time and at high frequency, and utilizing edge computing nodes deployed close to the data source for instant and efficient data processing, this invention innovatively achieves accurate assessment of power grid stability and power system stability. Specifically, we innovatively employ Haar wavelet transform to analyze the rate of change in electricity consumption and fast Fourier transform to analyze the fluctuation characteristics of the power factor. These two methods can not only meticulously capture subtle fluctuations in electricity consumption patterns, but also keenly identify potential instability factors, providing grid operators with unprecedented insights. Based on these in-depth data analysis results, grid operators can not only quickly locate and resolve potential threats to the safety and stability of the grid and ensure the robust operation of the entire system, but also dynamically adjust marketing strategies based on accurate assessment results.

[0015] (2) This invention constructs a comprehensive feature vector as input and uses a support vector machine model to accurately evaluate the power grid marketing response speed, thereby providing power grid operators with a scientific basis for optimizing marketing strategies. This method not only significantly reduces prediction errors but also, with its real-time data analysis capabilities, enables rapid response to market dynamics and precise delivery of personalized services. Specifically, when an anomaly in the power grid marketing response speed is detected, this invention enables power grid operators to monitor changes in user demand trends in real time, flexibly formulate instant interactive activities or launch customized preferential policies, thereby rapidly improving user participation and response speed. This method not only greatly improves marketing efficiency and service quality but also empowers power grid operators to maintain a leading position in a highly competitive market environment. Furthermore, through in-depth analysis of electricity consumption change rate and power factor fluctuation, combined with advanced machine learning technology, this invention achieves intelligent processing of the entire process from data collection and feature extraction to decision support. This agile technical framework for responding to changes in market demand not only enhances the flexibility and adaptability of power grid operations but also lays a solid foundation for achieving more efficient, reliable, and intelligent power services. Attached Figure Description

[0016] The invention will now be further described with reference to the accompanying drawings.

[0017] Figure 1 This is a flowchart illustrating the specific steps of the data processing and analysis method for the power grid marketing side system platform based on edge computing, as described in this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Please see Figure 1 As shown, this invention is a data processing and analysis method for a power grid marketing-side system platform based on edge computing, comprising the following steps: S1: Collect electricity consumption data and power factor data in real time through smart meters installed at the user end, and transmit these data to edge computing nodes close to the user; S2: Edge computing nodes process the received electricity consumption data, calculate the rate of change of electricity consumption, and assess the stability of the power grid based on the rate of change of electricity consumption. S3: Edge computing nodes process the received power factor data and assess the stability of the power grid system based on the degree of power factor fluctuation. S4: Conduct a comprehensive analysis of the power consumption data and power factor data of the power grid. Based on the analysis results, establish a response speed evaluation model to evaluate the power grid marketing response speed and provide power grid operators with guidance on adjusting marketing strategies based on the evaluation results.

[0020] In S1, electricity consumption data and power factor data are collected in real time through smart meters installed at the user's end, and this data is transmitted to an edge computing node closer to the user, specifically including: First, electricity consumption and power factor data are collected in real time through smart meters installed at the user's location. These smart meters are equipped with advanced sensors and metering technology, enabling them to accurately measure the user's real-time electricity consumption and calculate the power factor. These smart devices typically read data automatically at preset time intervals (e.g., every 15 minutes) and have sufficient storage capacity to temporarily store data records over a period of time. Furthermore, smart meters have built-in communication modules that support multiple communication protocols (such as PLC, ZigBee, Wi-Fi, or cellular networks), ensuring stable and efficient data transmission.

[0021] The collected electricity consumption and power factor data are sent to edge computing nodes located close to the users. These edge computing nodes, acting as local data processing centers, are situated near the data source, reducing data transmission latency and improving response speed. These nodes receive data streams from multiple smart meters and perform preliminary data processing tasks, such as data cleaning, format conversion, and simple statistical analysis. This design not only reduces the burden on the core network but also enables rapid decision-making based on real-time data, providing a solid foundation for subsequent, more complex analyses.

[0022] In S2, the edge computing nodes process the received electricity consumption data, calculate the rate of change in electricity consumption, and assess the stability of the power grid based on the rate of change in electricity consumption. Specifically, this includes: According to the time series, obtain the electricity consumption data of the power grid marketing within the monitoring period, calculate the rate of change of electricity consumption, calculate the characteristic value of the rate of change of electricity consumption based on the trend of the rate of change of electricity consumption, and evaluate the stability of power grid electricity consumption based on the characteristic value of the rate of change of electricity consumption. The process for obtaining the characteristic value of the electricity consumption change rate is as follows: Obtain a time-series dataset of electricity consumption within a monitoring period using smart meters; Perform a difference operation on the time series data of electricity consumption to calculate the rate of change of electricity consumption between adjacent time points. Specifically, for each time point, calculate the electricity consumption of the next time point minus the electricity consumption of the current time point to obtain the rate of change of electricity consumption within the corresponding time period. The electricity consumption change rate data is decomposed using Haar wavelet transform to extract information from different frequency components. Specifically, the electricity consumption change rate data is first decomposed into approximation coefficients and detail coefficients, and then the approximation coefficients are recursively decomposed further. By using low-pass and high-pass filters, the approximation part reflecting the general outline of the signal and the detail part capturing the subtle changes in the signal are obtained, respectively. By averaging the absolute values ​​of all detail coefficients across all wavelet decomposition layers, a single value representing the degree of fluctuation in the rate of change of electricity consumption is obtained, namely, the characteristic value of the rate of change of electricity consumption.

[0023] Determine whether the characteristic value of the electricity consumption change rate during the power grid marketing process is greater than or equal to a preset threshold. If it is, the power grid electricity consumption is unstable; otherwise, the power grid electricity consumption is stable.

[0024] It should be noted that this invention utilizes edge computing nodes to perform deep processing on the time-series electricity consumption data collected by smart meters. It not only calculates the rate of change in electricity consumption between adjacent time points but also extracts different frequency components of these rates of change through Haar wavelet transform, thereby constructing a feature value for the rate of change in electricity consumption that comprehensively reflects the fluctuation characteristics of the power grid. Specifically, by performing Haar wavelet decomposition on the rate of change in electricity consumption and averaging the absolute values ​​of all detail coefficients as the feature value, we can accurately capture subtle fluctuations and potential instabilities in electricity consumption patterns. Based on this feature value and comparing it with a preset threshold, we can intuitively judge the stability of the power grid: if the feature value exceeds the threshold, it indicates significant fluctuations in the power grid and unstable electricity consumption; otherwise, it indicates stable power grid operation and stable electricity consumption. This method provides a fast and effective means to monitor and evaluate the health status of the power grid in real time, supporting timely measures to optimize power grid operating efficiency and service quality. This fully automated processing approach, from raw data to advanced feature extraction to final decision support, represents an advanced practice in the field of power grid data analysis.

[0025] In S3, edge computing nodes process the received power factor data and assess the stability of the power grid system based on the degree of power factor fluctuation. Specifically, this includes: According to the time series, obtain the power factor data of the power grid marketing within the monitoring period, calculate the power factor characteristic value according to the degree of power factor fluctuation, and evaluate the stability of the power grid power system based on the power factor characteristic value. The process for obtaining the power factor characteristic value is as follows: Use smart meters to obtain a power factor time series dataset for a monitoring period; Applying Fast Fourier Transform to the power factor time series data converts the time-domain signal into a frequency-domain representation, including: calculating the corresponding Fourier coefficients for each frequency component; the Fourier coefficients are obtained by multiplying each data point in the original time series by a complex exponential function and summing the results. Based on the Fourier coefficients, the amplitude square of each frequency component is calculated to obtain the power spectral density, wherein the amplitude square is the modulus of each Fourier coefficient and then squared. Obtain the frequencies corresponding to the maximum and minimum power spectral density values, calculate the difference between the power spectral densities to obtain the power spectral density range, and calculate the ratio of the power spectral density range to the mean of all power spectral densities to obtain the power factor characteristic value. The assessment of the stability of the power grid system specifically includes: Determine whether the power factor characteristic value during the power grid marketing process is greater than or equal to a preset threshold. If it is, the corresponding power grid system is unstable; otherwise, the power grid system is stable.

[0026] It should be noted that edge computing nodes were used to perform in-depth analysis of the power factor time-series data collected by smart meters. The time-domain signal was converted to a frequency-domain representation using a Fast Fourier Transform (FFT), and a unique power factor characteristic value was calculated based on this to assess the stability of the power grid system. Specifically, the process involves calculating the corresponding Fourier coefficients for each frequency component and then solving for the energy or amplitude square of each frequency component to construct the power spectral density. Further, the final power factor characteristic value was obtained by calculating the difference between the maximum and minimum values ​​of the power spectral density and comparing it to the mean of all power spectral densities. This method not only captures subtle fluctuations in the power factor but also effectively identifies potential instability factors. Based on the comparison between this characteristic value and a preset threshold, the stability of the power grid system can be intuitively judged: if the characteristic value exceeds the threshold, it indicates a risk of instability; otherwise, it indicates stable system operation. This process provides a novel and efficient technical means for real-time monitoring and assessment of the power grid health status, supporting timely measures to optimize grid performance, and demonstrating an intelligent processing path from raw data to advanced feature extraction and decision support.

[0027] In S4, a comprehensive analysis of power grid electricity consumption and power factor data is performed. Based on the analysis results, a response speed assessment model is established to evaluate the power grid's marketing response speed. The assessment results then inform power grid operators' adjustments to their marketing strategies, specifically including: The characteristic values ​​of electricity consumption change rate and power factor in the power grid marketing process are obtained. The characteristic values ​​of electricity consumption change rate and power factor are used to construct a comprehensive feature vector as input to the response speed evaluation model. The training objective is to minimize the error between the predicted marketing response speed score and the actual marketing response speed score. Based on the trained model, the marketing response speed score is output. The response speed evaluation model is a support vector machine model. The training process of the response speed evaluation model is as follows: Obtain historical multi-set feature vectors and marketing response speed scores, determine the type of support vector machine (SVM) model as radial basis function (RBF) kernel, and set initial parameters, such as regularization and kernel function parameters. Train the SVM model using the prepared training set. The training process aims to minimize the error between the predicted and actual marketing response speed scores. This typically involves finding an optimal hyperplane that maximizes the margin between different classes of samples while classifying or regressing given data points as accurately as possible.

[0028] Evaluate model performance using validation sets or cross-validation techniques, and adjust model parameters based on the results to improve accuracy. This step may require multiple iterations until the optimal parameter configuration is found.

[0029] Once the model has been trained and fully validated, it can be used to predict new input feature vectors and output corresponding marketing response speed scores.

[0030] The assessment of the power grid marketing response speed specifically includes: Determine whether the marketing response speed score output by the response speed evaluation model in the power grid marketing process is greater than or equal to the preset threshold. If yes, the power grid marketing response speed is normal; otherwise, the power grid marketing response speed is abnormal. The provision of adjusted marketing strategies to grid operators based on assessment results specifically includes: In the event of abnormal response speed in power grid marketing, power grid operators should monitor changes in user demand in real time and develop differentiated electricity price discounts, customized service packages, and instant interactive activities to improve user participation and response speed.

[0031] The working principle of this invention: This invention provides a data processing and analysis method for a power grid marketing-side system platform based on edge computing. It aims to collect users' electricity consumption and power factor data in real time through smart meters, and utilize edge computing nodes close to users for efficient data processing and feature extraction to assess the stability of power grid electricity consumption and the power system. Smart meters automatically read and transmit this key data to edge computing nodes at preset time intervals, ensuring data timeliness and accuracy. In-depth analysis is conducted on the rate of change of electricity consumption and the power factor. For the former, information from different frequency components is extracted using Haar wavelet transform to construct the characteristic value of the rate of change of electricity consumption. For the latter, a fast Fourier transform is used to convert it to a frequency domain representation, and the power spectral density range is calculated as the characteristic value of the power factor, thereby assessing the stability of the power grid. The characteristics of the rate of change of electricity consumption and the characteristic value of the power factor are integrated into a comprehensive feature vector, which is input into a trained support vector machine model. This model aims to minimize the prediction error and outputs a marketing response speed score to determine whether the power grid's marketing response speed is normal. Based on this scoring, grid operators can take measures to address anomalies, such as implementing differentiated pricing strategies, customizing service packages, or launching real-time interactive activities, thereby optimizing marketing strategies and improving user engagement and responsiveness. This approach not only automates the entire process from data collection to advanced feature extraction and decision support, but also provides the ability to flexibly respond to market changes, significantly improving grid operational efficiency and service quality, marking an innovative practice in the field of grid data analytics. Through this intelligent processing path, the grid can more effectively manage and meet user needs while ensuring grid security and stability.

[0032] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0033] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0034] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0035] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply 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 this application.

[0036] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A data processing and analysis method for a power grid marketing-side system platform based on edge computing, characterized in that, Includes the following steps: S1: Collect electricity consumption data and power factor data in real time through smart meters installed at the user end, and transmit these data to edge computing nodes close to the user; S2: Edge computing nodes process the received electricity consumption data, calculate the rate of change of electricity consumption, and assess the stability of the power grid based on the rate of change of electricity consumption. S3: Edge computing nodes process the received power factor data and assess the stability of the power grid system based on the degree of power factor fluctuation. S4: Conduct a comprehensive analysis of the power consumption data and power factor data of the power grid, establish a response speed evaluation model based on the analysis results, use it to evaluate the power grid marketing response speed, and provide power grid operators with guidance on adjusting marketing strategies based on the evaluation results.

2. The data processing and analysis method for a power grid marketing-side system platform based on edge computing according to claim 1, characterized in that, The edge computing node processes the received electricity consumption data, specifically including: According to the time series, obtain the electricity consumption data of the power grid marketing within the monitoring period, calculate the rate of change of electricity consumption, calculate the characteristic value of the rate of change of electricity consumption based on the trend of the rate of change of electricity consumption, and evaluate the stability of power grid electricity consumption based on the characteristic value of the rate of change of electricity consumption.

3. The data processing and analysis method for the power grid marketing side system platform based on edge computing according to claim 2, characterized in that, The process for obtaining the characteristic value of the electricity consumption change rate is as follows: Obtain a time-series dataset of electricity consumption within a monitoring period using smart meters; Perform a difference operation on the time series data of electricity consumption to calculate the rate of change of electricity consumption between adjacent time points. Specifically, for each time point, calculate the electricity consumption of the next time point minus the electricity consumption of the current time point to obtain the rate of change of electricity consumption within the corresponding time period. The electricity consumption change rate data is decomposed using Haar wavelet transform to extract information from different frequency components. Specifically, this involves first decomposing the electricity consumption change rate data into approximation coefficients and detail coefficients, and then recursively decomposing the approximation coefficients further. By averaging the absolute values ​​of all detail coefficients across all wavelet decomposition layers, a single value representing the degree of fluctuation in the rate of change of electricity consumption is obtained, namely, the characteristic value of the rate of change of electricity consumption.

4. The data processing and analysis method for a power grid marketing-side system platform based on edge computing according to claim 2, characterized in that, The assessment of power grid stability specifically includes: Determine whether the characteristic value of the electricity consumption change rate during the power grid marketing process is greater than or equal to a preset threshold. If it is, the power grid electricity consumption is unstable; otherwise, the power grid electricity consumption is stable.

5. The data processing and analysis method for a power grid marketing-side system platform based on edge computing according to claim 1, characterized in that, The edge computing node processes the received power factor data, specifically including: According to the time series, the power factor data of the power grid marketing during the monitoring period is obtained. Based on the fluctuation of the power factor, the characteristic value of the power factor is calculated. Based on the characteristic value of the power factor, the stability of the power grid power system is evaluated.

6. The data processing and analysis method for a power grid marketing-side system platform based on edge computing according to claim 5, characterized in that, The process for obtaining the power factor characteristic value is as follows: Use smart meters to obtain a power factor time series dataset for a monitoring period; Applying Fast Fourier Transform to the power factor time series data converts the time-domain signal into a frequency-domain representation, including: calculating the corresponding Fourier coefficients for each frequency component; the Fourier coefficients are obtained by multiplying each data point in the original time series by a complex exponential function and summing the results. Based on the Fourier coefficients, the amplitude square of each frequency component is calculated to obtain the power spectral density, wherein the amplitude square is the modulus of each Fourier coefficient and then squared. Obtain the frequencies corresponding to the maximum and minimum power spectral density values, calculate the difference between the power spectral densities to obtain the power spectral density range, and calculate the ratio of the power spectral density range to the mean of all power spectral densities to obtain the power factor characteristic value.

7. The data processing and analysis method for a power grid marketing-side system platform based on edge computing according to claim 5, characterized in that, The assessment of the stability of the power grid system specifically includes: Determine whether the power factor characteristic value during the power grid marketing process is greater than or equal to a preset threshold. If it is, the corresponding power grid system is unstable; otherwise, the power grid system is stable.

8. The data processing and analysis method for a power grid marketing-side system platform based on edge computing according to claim 1, characterized in that, The process involves a comprehensive analysis of the power consumption and power factor data of the power grid. Based on the analysis results, a response speed evaluation model is established, specifically including: The characteristic values ​​of electricity consumption change rate and power factor in the power grid marketing process are obtained. The characteristic values ​​of electricity consumption change rate and power factor are used to construct a comprehensive feature vector as input to the response speed evaluation model. The training objective is to minimize the error between the predicted marketing response speed score and the actual marketing response speed score. Based on the trained model, the marketing response speed score is output. The response speed evaluation model is a support vector machine model.

9. The data processing and analysis method for a power grid marketing-side system platform based on edge computing according to claim 1, characterized in that, The assessment of the power grid marketing response speed specifically includes: Determine whether the marketing response speed score output by the response speed evaluation model in the power grid marketing process is greater than or equal to a preset threshold. If yes, the power grid marketing response speed is normal; otherwise, the power grid marketing response speed is abnormal.

Images