Optimization Method for Power Demand Side Response Strategy Based on Feedback Information Extraction

Abstract

The present invention discloses an optimization method for power demand-side response strategies based on feedback information extraction, which relates to the technical field of energy management. The method includes: retrieving the line architecture of a target area, obtaining the set of users on the transmission line, and collecting the power usage data of the users. Decompose and analyze the data in terms of power and power consumption time periods to obtain the power concentration interval of the users and the peak, flat valley power consumption time periods. Formulate an initial power demand-side response strategy. Collect the feedback information of the users through a feedback window. Combine the power interval of the users and the response coefficient to optimize the initial strategy and form the final power demand-side response strategy. It solves the technical problem of the lack of dynamic adaptability to the actual power consumption behavior and response situation of users in the existing power demand-side response strategies, and achieves the technical effect of improving the precise regulation ability of the power load, reducing the impact of power peak-valley fluctuations on the power grid, and thus enhancing the stability of the power grid.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy management, and particularly relates to a method for optimizing a power demand-side response strategy based on feedback information extraction. Background Art

[0002] In the operation scenario of modern power systems, the rapid growth and volatility of power loads pose huge challenges to the stability of the power grid. Especially during peak hours, the contradiction between supply and demand becomes more prominent. Reasonably allocating power resources and enhancing the flexibility and response ability of the power grid have become the key links in solving the dispatching pressure of power systems. Traditional power demand-side response strategies are often relatively single and fixed, mainly relying on historical load data and preset rules, lacking sufficient analysis of real-time user feedback information and the ability of dynamic adjustment, and it is difficult to accurately match the electricity consumption behavior characteristics of users. The limitations of traditional methods make the power system appear passive in dealing with complex load fluctuations and difficult to meet the requirements of modern power systems for real-time and accuracy.

[0003] In the current related technologies, there is a technical problem that the power demand-side response strategy lacks dynamic adaptability to the actual electricity consumption behavior and response situation of users. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for optimizing a power demand-side response strategy based on feedback information extraction. By retrieving the line architecture of the target area, obtaining the set of users on the transmission line, and collecting the power usage data of users. Decompose and analyze the data in terms of power and electricity consumption periods to obtain the power concentration interval and peak, valley, and flat periods of electricity consumption of users. Formulate an initial power demand-side response strategy, including the incentive intensity and response period, and distribute it to each transmission line. Collect the feedback information of users through a feedback window, analyze the response effect and calculate the response coefficient of users. Combine the power interval of users and the response coefficient to optimize the initial strategy to form the final power demand-side response strategy, achieving the technical effect of improving the accurate control ability of power loads, reducing the impact of power peak-valley fluctuations on the power grid, and thus enhancing the stability of the power grid.

[0005] The purpose of the present invention is achieved through the following technical solutions:

[0006] A method for optimizing a power demand-side response strategy based on feedback information extraction, characterized in that the method includes the following steps:

[0007] S100. Retrieve the line architecture of the target area to obtain K sets of users on K transmission lines, where K is an integer greater than or equal to 1;

[0008] S200. Traverse the K user sets to collect power usage data for a preset monitoring window, and obtain K user power usage data sets;

[0009] S300. Perform power and power consumption time period decomposition analysis on the K user power usage data sets to obtain K user power concentration intervals, K peak power consumption concentration time periods, K flat power consumption concentration time periods, and K valley power consumption concentration time periods;

[0010] S400. Obtain an initial demand-side response strategy for electricity, where the initial demand-side response strategy for electricity includes K response strategies, and the K response strategies include K incentive intensities and K response time periods;

[0011] S500. Distribute the K incentive intensities and K response time periods to the K transmission lines, and interact with the K user sets in a preset feedback window to extract feedback information, and obtain K user feedback parameter sets;

[0012] S600. Perform response analysis on the K user feedback parameter sets to obtain K user response coefficients;

[0013] S700. Combine the K user power concentration intervals, K peak power consumption concentration time periods, K flat power consumption concentration time periods, and K valley power consumption concentration time periods, and the K user response coefficients to optimize the initial demand-side response strategy for electricity, and obtain an optimized demand-side response strategy for electricity.

[0014] Furthermore, index by power, extract data from the K user power usage data sets to obtain K user power sets;

[0015] Perform mean processing on the K user power sets to determine K user power means;

[0016] Perform central iteration on the K user power means in the K user power sets according to a preset iteration step size to determine K user power central values;

[0017] Take the K user power central values as the interval centers, and take the preset iteration step size as the distance from both endpoints to the interval center to determine the K user power concentration intervals.

[0018] Pre-construct a central iteration formula, where the central iteration formula is:

[0019] ;

[0020] where is the power central value of the stage user, An iterative neighborhood consists of multiple user powers in each user power set whose distances to the user power mean are the preset iterative step size. For the th user power in the iterative neighborhood, is the user power mean, is the Gaussian weight kernel function;

[0021] Taking the K user power means as matching objects, neighborhood retrieval is performed in the K user power sets respectively according to the preset iterative step size to determine K iterative neighborhoods;

[0022] Using the central iterative formula to perform central iteration on the K user power means and the K iterative neighborhoods respectively to obtain K stage user power central values;

[0023] After multiple iterations, until the difference between the stage user power central values obtained in two adjacent iterations is less than or equal to the preset difference, stop the iteration, and take the K stage user power central values obtained in the last iteration as the K user power central values.

[0024] Further, construct an electricity consumption coordinate system with time as the abscissa and electricity consumption as the ordinate;

[0025] Obtain K user electricity consumption curve sets according to the K user power consumption data sets and the electricity consumption coordinate system;

[0026] Fit the K user electricity consumption curve sets respectively to obtain K fitted user electricity consumption curves;

[0027] Based on the K fitted user electricity consumption curves, perform electricity peak-valley analysis to determine the K peak electricity consumption concentrated periods, the K flat electricity consumption concentrated periods and the K valley electricity consumption concentrated periods.

[0028] Further, distribute the K excitation intensities and the K response periods to the K transmission lines, and interact with the K user sets in the preset feedback window to extract feedback information to obtain K user feedback parameter sets, including:

[0029] Obtain the K distribution time nodes of the K excitation intensities and the K response periods;

[0030] Extract the K receiving time node sets of the K users receiving the K excitation intensities and the K response periods in the K transmission lines;

[0031] Based on the K distribution time nodes and the K receiving time node sets, perform feedback correction factor analysis to determine K user feedback correction factor sets;

[0032] Modify the K user feedback parameter sets based on the K user feedback correction factor sets.

[0033] Furthermore, the K user feedback parameter sets include K response rate sets, K response duration sets, and K participation frequency sets.

[0034] Pre-build a response coefficient identifier;

[0035] Use the response coefficient identifier to analyze the K response rate sets, K response duration sets, and K participation frequency sets to determine the K user feedback parameter sets.

[0036] Calculate the ratios of the K user response coefficients to the sum of the K user response coefficients respectively, and take the reciprocals of the ratios as the K policy optimization coefficients;

[0037] Using the K policy optimization coefficients as the optimization scale, and using the K user power concentration intervals, K peak electricity consumption concentration periods, K flat electricity consumption concentration periods, and K valley electricity consumption concentration periods as the optimization analysis data, optimize the initial power demand side response strategy to obtain an optimized power demand side response strategy.

[0038] The beneficial effects of the present invention are as follows:

[0039] First, retrieve the line architecture of the target area, obtain the set of users on the transmission line, and collect the power usage data of the users. Decompose and analyze the data in terms of power and electricity consumption time periods to obtain the user's power concentration interval and peak, flat, and valley electricity consumption periods. Develop an initial power demand side response strategy, including the incentive intensity and response time periods, and distribute it to each transmission line. Collect the feedback information of users through the feedback window, analyze the response effect and calculate the response coefficients of the users. Combine the user's power interval and response coefficient to optimize the initial strategy to form the final power demand side response strategy, achieving the technical effects of improving the precise control ability of the power load, reducing the impact of power peak-valley fluctuations on the power grid, and thus enhancing the stability of the power grid. Description of the Drawings

[0040] Figure 1 It is a flow schematic diagram of the power demand side response strategy optimization method based on feedback information extraction provided by an embodiment of the present application;

[0041] Figure 2 It is a flow schematic diagram of the feedback correction of the user feedback parameter set of the power demand side response strategy optimization method based on feedback information extraction provided by an embodiment of the present application. Detailed Embodiments

[0042] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific implementation manners of this application are specifically exemplified below.

[0043] A method for optimizing a power demand-side response strategy based on feedback information extraction, as Figure 1 shown, the method includes:

[0044] Step S100, retrieve the line architecture of the target area, and obtain K user sets of K transmission lines, where K is an integer greater than or equal to 1. Specifically, first establish a connection with the power system database management system, and use the power data management software to screen and extract the line architecture information according to conditions such as the geographical coordinate range or administrative region division of the target area, including the physical parameters of the transmission line, the identification code, and the connection points with the substation, etc. Sort and organize K transmission lines according to attributes such as voltage level and commissioning time. Then, with the help of the customer-line association file records in the power marketing system and the information on the installation of smart meters and the connection with the lines, divide the user sets by using the data matching algorithm with the meter code or user account number as the association key, and conduct a combined processing of manual verification and system automatic identification for special user situations such as dual power supplies and temporary electricity use. At the same time, establish a dynamic update mechanism to ensure timely adjustment of the user set information when new users are connected or the power supply lines change due to line transformation to ensure accuracy and real-time.

[0045] Step S200, traverse the K user sets to collect power usage data for a preset monitoring window, and obtain K user power usage data sets. Specifically, analyze the power usage law characteristics of the target area, and comprehensively consider factors such as the business peak period law in the commercial area, the seasonal influence in the residential area, the operation scheduling cycle of the power system, and the time period division of the electricity price policy to determine the preset monitoring window. Install smart meters or data acquisition terminal devices with high-precision power measurement, data storage, and preprocessing capabilities at each user access point, and build a stable communication network of wired (such as power dedicated optical fiber or urban comprehensive wiring system) and wireless (such as 4G / 5G or power wireless private network), and optimize the configuration of the communication network's priority, bandwidth allocation, etc. According to the start time of the preset monitoring window, the acquisition device collects data at a set frequency and conducts a preliminary check, interpolates and fills in the missing data, judges and marks the rationality of the mutant data. After the monitoring window ends, it is sent to the data center for further cleaning and integration to remove duplicates and correct incorrect formats, and finally form K user power usage data sets containing comprehensive and accurate power usage data information.

[0046] Step S300: Conduct power and electricity consumption period decomposition analysis on the K sets of user power consumption data to obtain K user power concentration intervals, K peak electricity consumption concentration periods, K flat electricity consumption concentration periods, and K valley electricity consumption concentration periods. Specifically, first perform data cleaning on the K sets of user power consumption data, handle missing values, correct abnormal data, and sort them in chronological order. Then calculate the frequency distribution of each user's power data, group and count the occurrence frequencies of power values at a certain time interval, draw a power frequency histogram, use a clustering analysis algorithm to cluster similar power values to determine the main groups, calculate the central values and dispersion degrees of the groups, and determine the power concentration intervals according to the thresholds. Then use the moving average method to smooth the electricity consumption data, set an electricity consumption threshold, calculate the average electricity consumption in each time period and compare it with the threshold, combine time characteristics such as weekdays and weekends, seasonal factors, refer to historical data to establish an electricity consumption pattern library and match and correct it, so as to determine the peak, flat, and valley electricity consumption concentration periods. Finally, provide key data support for the formulation and optimization of the power demand side response strategy.

[0047] In a possible implementation manner, when conducting power and electricity consumption period decomposition analysis on the K sets of user power consumption data to obtain K user power concentration intervals, K peak electricity consumption concentration periods, K flat electricity consumption concentration periods, and K valley electricity consumption concentration periods, step S300 further includes:

[0048] Step S310: Extract data from the K sets of user power consumption data with power as the index to obtain K user power sets. Specifically, from the comprehensive database of power consumption data, based on power as the retrieval basis, for each set of user power consumption data, traverse each record therein, and filter out the data fields related to power in the record. For example, if the data record format is [timestamp, electricity consumption, power value, voltage value], then extract the column of power values. Perform the same operation for the K sets of user power consumption data, so as to obtain power data subsets corresponding to K users respectively, and these subsets combined together constitute K user power sets. During the extraction process, ensure the accuracy and integrity of the data, and preprocess some situations with non-standard formats or missing data, such as supplementing missing power data according to certain rules or excluding invalid records.

[0049] Step S320: Perform mean processing on the K user power sets to determine the K user power means. Specifically, for each user power set, sum up all the power values in the set. Then, divide the sum by the number of power values to obtain the average value of the user power set. The calculation process can be automated by writing a data processing program, using array operations and mathematical calculation functions in a programming language. During the calculation process, attention should be paid to the precision issues of data types to avoid inaccurate calculation results caused by data precision loss. For example, in some programming languages, if integer types are used for calculation, the decimal part may be truncated. Therefore, appropriate data types, such as floating-point types, should be selected according to the actual situation for accurate calculation, so as to determine the K accurate user power means.

[0050] Step S330: Perform central iteration on the K user power means in the K user power sets according to a preset iteration step size to determine the K user power center values. Specifically, first determine the value of the preset iteration step size, which is preset according to factors such as the data precision requirements and data distribution characteristics. Starting from the power mean of each user, in its corresponding power set, gradually expand the search range according to the iteration step size. For example, if the initial power mean is P0 and the iteration step size is ΔP, the first iteration searches for power values in the range from P0 - ΔP to P0 + ΔP, calculates the weighted average value of the power values within the range (the weights can be determined according to factors such as the distance from the mean), and uses it as the new center value P1. Then, based on P1, expand the search range again according to the iteration step size for the next iteration until the preset iteration termination condition is met, such as the difference between the center values obtained from two adjacent iterations is less than a certain minimum value or the preset maximum number of iterations is reached. Through the iteration process, finally determine the accurate power center values for each of the K users.

[0051] Step S340: Take the K user power center values as the interval centers and use the preset iteration step size as the distance from the two endpoints to the interval center to determine the K user power concentration intervals. Specifically, for each user, the power center value has been obtained. Taking the center value as the benchmark and using the preset iteration step size as the distance metric, determine an interval range. For example, if the power center value is Pc and the iteration step size is ΔP, then the power concentration interval is [Pc - ΔP, Pc + ΔP]. The interval represents the range where the user's power data is relatively concentrated. After determining the interval, the rationality of the interval can also be verified. For example, count the proportion of the number of power data points falling within this interval to the total number of data points. If the proportion reaches a certain threshold (such as more than 80%), it indicates that the determined power concentration interval is reasonable and effective, so as to determine the accurate power concentration interval for each user.

[0052] In a possible implementation, the K user power center values are determined by performing a central iteration on the K user power means in the K user power sets according to a preset iteration step size. Step S330 further includes:

[0053] Step S331, pre-construct a central iteration formula, where the central iteration formula is: ; where is the stage user power center value, is an iteration neighborhood composed of multiple user powers whose distance to the user power mean in each user power set is the preset iteration step size, is the i-th user power in the iteration neighborhood, is the user power mean, is the Gaussian weight kernel function. Specifically, the central iteration formula is constructed according to mathematical principles and data characteristics. The numerator part in the formula represents that within the iteration neighborhood , each user power is multiplied by the corresponding Gaussian weight kernel function value and then summed. The role of the Gaussian weight kernel function is to assign different weights according to the distance between the power value and the mean . The closer the distance to the mean, the greater the weight; the farther the distance, the smaller the weight. This can more prominently reflect the influence of data points near the center. The denominator is to sum the weights for normalizing the numerator, so that the calculated stage user power center value is more reasonable and accurate, providing a mathematical model basis for subsequent center value calculations.

[0054] Step S332, using the K user power means as matching objects, perform neighborhood retrieval in the K user power sets respectively according to the preset iteration step size to determine K iteration neighborhoods. Specifically, for each user power set, using the already determined user power mean as a reference point, search for power values within the preset iteration step size range from the mean in the power set. These power values form the iteration neighborhood . For example, if the preset iteration step size is Δ and the mean is , then in the power set, find all that satisfy . Combining determines an iteration neighborhood. Perform such operations on the K user power means respectively to obtain K corresponding iteration neighborhoods. During the retrieval process, an efficient data search algorithm should be established to quickly and accurately find the power values that meet the conditions.

[0055] Step S333: Use the central iteration formula to perform central iteration on the K user power means and the K iterative neighborhoods respectively to obtain the user power central values at K stages. Specifically, substitute the power mean of each user and the corresponding iterative neighborhood into the central iteration formula. For each power value in the iterative neighborhood , first calculate the Gaussian weight kernel function value , then calculate the values of the numerator and denominator respectively according to the formula, and finally obtain the user power central value at the stage . Perform such calculations for K users respectively to obtain the user power central values at K stages. During the calculation process, attention should be paid to the precision control of data and the accuracy of function calculation to avoid result deviation caused by calculation errors.

[0056] Step S334: After multiple iterations, stop the iteration until the difference between the user power central values at two adjacent iterations is less than or equal to the preset difference, and use the K user power central values obtained in the last iteration as the K user power central values. Specifically, at the beginning of the next iteration, use the user power central value obtained in the previous iteration as the new mean, repeat the steps of neighborhood retrieval and central iteration calculation. After each iteration, calculate the difference between the user power central value obtained in this iteration and the value obtained in the previous iteration. When the difference is less than or equal to the preset difference (such as 0.01), it means that the iteration has converged and the power central value has tended to be stable. At this time, stop the iteration and determine the K user power central values obtained in the last iteration as the final K user power central values for subsequent operations such as determining the power concentration interval.

[0057] In a possible implementation manner, perform power and power consumption time period decomposition and analysis on the K user power consumption data sets to obtain K user power concentration intervals, K peak power consumption concentration time periods, K flat power consumption concentration time periods, and K valley power consumption concentration time periods. Step S300 further includes:

[0058] Step S350: Construct a power consumption coordinate system with time as the abscissa and power consumption as the ordinate. Specifically, clarify that time is used as an independent variable and marked on the horizontal axis (abscissa), divide the scale at a certain time interval, such as in hours or according to the data acquisition frequency to determine the scale interval. For the ordinate power consumption, set appropriate scale values according to the actual power consumption range to ensure that the numerical changes of different power consumptions can be clearly displayed. At the same time, determine parameters such as the origin position and unit length of the coordinate system to make the entire coordinate system have a unified standard and specification, and use the graph drawing function in the drawing software or data analysis tool to construct this two-dimensional coordinate system to prepare for the subsequent drawing of the power consumption curve.

[0059] Step S360: Obtain a set of electricity consumption curves for K users based on the K sets of user electricity consumption data and the electricity consumption coordinate system. Specifically, for each set of user electricity consumption data, extract the time data and the corresponding electricity consumption data from the set in sequence. Map the extracted time data to the abscissa and the electricity consumption data to the ordinate. In the electricity consumption coordinate system, connect each data point in chronological order to draw the electricity consumption curve of each user. Since there may be some small fluctuations and errors during the data collection process, the drawn curve may have some jagged or non-smooth parts. Performing such operations on K users respectively can obtain a set of electricity consumption curves for K users, intuitively showing the changes in electricity consumption of each user at different times.

[0060] Step S370: Fit the set of electricity consumption curves for K users respectively to obtain a set of fitted electricity consumption curves for K users. Specifically, select a suitable fitting algorithm, such as polynomial fitting, exponential fitting, or curve fitting algorithms based on machine learning, etc. For the electricity consumption curve of each user, input the curve data into the fitting algorithm. The fitting algorithm determines the parameters of the fitting curve by minimizing the error between the actual data points and the fitting curve. For example, in polynomial fitting, select a suitable polynomial degree according to the data characteristics and solve the system of equations to determine the coefficients of the polynomial. After fitting, a smoother fitted electricity consumption curve that can reflect the electricity consumption trend is obtained. Fitting the electricity consumption curves of K users respectively can obtain a set of fitted electricity consumption curves for K users, providing a more accurate data basis for subsequent peak and valley electricity consumption analysis.

[0061] Step S380: Conduct peak and valley electricity consumption analysis based on the set of fitted electricity consumption curves for K users to determine the K peak electricity consumption concentrated periods, the K flat electricity consumption concentrated periods, and the K valley electricity consumption concentrated periods. Specifically, set the threshold criteria for peak and valley judgment. Generally, it can be determined according to methods such as the relative magnitude of electricity consumption or the difference from the average electricity consumption. Analyze the electricity consumption values corresponding to each time point in sequence along the fitted electricity consumption curve from left to right. When the electricity consumption is higher than the peak electricity consumption threshold and lasts for a certain period (such as several consecutive time points), this period is determined as the peak electricity consumption concentrated period; when the electricity consumption is lower than the valley electricity consumption threshold and meets certain duration conditions, it is determined as the valley electricity consumption concentrated period; the period between the peak and valley thresholds is the flat electricity consumption concentrated period. At the same time, make a comprehensive judgment in combination with users' electricity consumption habits, seasonal factors, differences between weekdays and weekends, etc. For example, on a summer weekday, the electricity consumption in the daytime office is high, which may be the peak period; the electricity consumption of residents at night decreases, which is the valley period. Conduct such analysis on the set of fitted electricity consumption curves for K users respectively to finally determine the peak, flat, and valley electricity consumption concentrated periods corresponding to each user.

[0062] Step S400: Obtain the initial power demand-side response strategy. The initial power demand-side response strategy includes K response strategies, where the K response strategies include K incentive intensities and K response time periods. Specifically, collect the records of past demand-side response activities in the power system and evaluate the current supply and demand situation in the power market, analyze the electricity consumption behavior characteristics of users in the target area, and use big data analysis to mine the laws of electricity consumption data. Set different incentive intensities according to the sensitivity differences of users to price and rewards, consider the costs and expected effects of power companies, determine the range through simulation calculation and cost-benefit analysis, set electricity price discounts for price-sensitive users, and set reward plans for users who pay attention to non-monetary incentives. Combine the load peak-valley variation law of the power grid and the distribution characteristics of power generation resources to set the response time periods. Analyze the historical load curve to find out the characteristics of peak-valley time periods, set the response time periods according to the power generation resource situation (such as high wind power at night and low electricity consumption during the low valley period) and consider the living and production rules of users, communicate and consult with relevant parties to solicit opinions and make adjustments, and finally determine the incentive intensity and response time period corresponding to each response strategy to form the initial power demand-side response strategy.

[0063] Step S500: Distribute the K incentive intensities and K response time periods to the K transmission lines, and interact with the K user sets during a preset feedback window to extract feedback information and obtain K user feedback parameter sets. Specifically, use various methods such as publishing notices and announcements on the official website of the power company and setting up a query page, sending mobile phone text messages with links using the marketing system, arranging customer managers to provide on-site services to large and important users and distributing paper materials, and setting pop-up prompts on smart meters to synchronize the data of the K incentive intensities and response time periods from the strategy formulation system to the relevant business systems, ensure the transmission security with encryption technology and perform verification before displaying or notifying to ensure that the information is accurately conveyed to the K user sets. Build an interactive platform that combines online (developing a mobile application or mini-program with a feedback entry and equipped with an online customer service) and offline (setting up a consultation service desk in the power supply business hall) before the preset feedback window, use the smart meters to transmit the changes in electricity consumption data, continuously collect feedback information from various channels and classify and organize it during the feedback window, extract key parameters such as user satisfaction with the incentive intensity, rationality feedback of the response time period, and electricity consumption change data, improve fuzzy or incomplete information, and form K user feedback parameter sets to provide a reliable data basis for response analysis.

[0064] In a possible implementation manner, as Figure 2 shown, distributing the K incentive intensities and K response time periods to the K transmission lines, and interacting with the K user sets during a preset feedback window to extract feedback information and obtain K user feedback parameter sets, step S500 further includes:

[0065] Step S510: Obtain the K distribution time nodes for the K excitation intensities and the K response time periods. Specifically, a monitoring program is set up in the policy distribution system. When starting to distribute the excitation intensity and response time period information to the users corresponding to each transmission line, the exact time points are automatically recorded. The time recording process can utilize the system's log function or a specially developed timestamp recording module. For different distribution channels, such as SMS sending, website announcement publishing, and meter pushing, the respective distribution start times are recorded separately. The data is sorted and classified, and the corresponding distribution time nodes are accurately associated according to the transmission line number or the identifier of the user set, forming clear records of the K distribution time nodes for subsequent time difference analysis.

[0066] Step S520: Extract the K sets of reception time nodes for the K users in the K transmission lines who receive the K excitation intensities and the K response time periods. Specifically, a feedback monitoring mechanism is set up on the user terminal devices (such as mobile phones, computers, smart meters, etc.) to obtain the reception time information. When the user opens an SMS, browses a website announcement, or views the meter prompt information, the device automatically transmits the reception time data back to the system. For some situations with unstable networks or limited device functions, a mechanism of multiple attempts to transmit and data caching is adopted to ensure that the reception time data can be accurately obtained. After collecting the reception time data of each user, it is sorted and classified according to the corresponding transmission line and user set, forming K sets of reception time nodes. The set contains the specific time points when each user receives the information, providing basic data for subsequent analysis.

[0067] Step S530: Conduct feedback correction factor analysis based on the K distribution time nodes and the K sets of reception time nodes to determine the K sets of user feedback correction factors. Specifically, for each corresponding pair of distribution time nodes and reception time nodes, calculate the time difference. The calculation of the time difference can be accurate to the second or even millisecond level to accurately reflect the delay situation of information transmission. According to the pre-set algorithm rules, convert the time difference into a feedback correction factor. Generally speaking, if the time difference is long, it indicates that there may be obstacles in the information transmission process or the user receives the information untimely, and the corresponding feedback correction factor will be larger. For example, a simple linear relationship function can be set. When the time difference is within a certain range, calculate the feedback correction factor according to the proportion. Calculate and convert the time differences of the K users respectively to determine the K sets of user feedback correction factors. The set reflects the delay situation and potential influencing factors of each user in the process of receiving information.

[0068] Step S540: Modify the \(K\) sets of user feedback parameters based on the \(K\) sets of user feedback correction factors. Specifically, associate and match the set of feedback correction factors with the set of feedback parameters. For each parameter in the set of feedback parameters, adjust it according to the corresponding feedback correction factor. If a user's feedback correction factor is relatively large, it indicates that there are certain difficulties or delays in receiving information. Then, a certain degree of tolerance needs to be given when analyzing their feedback parameters. For example, for the response willingness parameter in the user feedback, if it was originally at a low level, but considering that the user received the information late and may not have fully understood the strategy content, the weight of this parameter can be appropriately increased or its value range can be adjusted. In this way, comprehensively modify the \(K\) sets of user feedback parameters, making the subsequent strategy adjustment and analysis based on the feedback parameters more scientific and reasonable, and fully considering the actual situation of users in the information reception link.

[0069] In a possible implementation, distribute the \(K\) incentive intensities and \(K\) response time periods to the \(K\) transmission lines, and interact with the \(K\) user sets in a preset feedback window to extract feedback information, obtaining \(K\) sets of user feedback parameters. Step S500 further includes Step S550. The \(K\) sets of user feedback parameters include \(K\) sets of response rates, \(K\) sets of response durations, and \(K\) sets of participation frequencies. Specifically, during the preset feedback window, collect the electricity consumption change data at short time intervals through smart meters and monitoring systems and perform smoothing processing. Calculate the change rate of electricity consumption at each time point relative to the previous moment starting from the moment of receiving the incentive information. After analyzing and removing unstable data, comprehensively represent it with statistical quantities, and determine the representative value in combination with the actual scenario to form \(K\) sets of response rates. Record the start and end time points of the user's response, compare different data to screen out the effective response duration period, summarize and organize the data sets of each user, and determine the typical range or representative value through clustering analysis, etc., to generate \(K\) sets of response durations. Count the number of times each user participates in the demand response within a certain time period from multiple channels, combine manual review and data analysis to confirm the data, calculate the number of participations per unit time and check its rationality, and organize and form \(K\) sets of participation frequencies to provide data support for subsequent strategy optimization and other work.

[0070] In a possible implementation, the K excitation intensities and K response periods are distributed to the K transmission lines, and feedback information is extracted by interacting with the K user sets within a preset feedback window to obtain K user feedback parameter sets. Step S500 further includes step S560 of pre-constructing a response coefficient recognizer. Specifically, the algorithm core of the response coefficient recognizer is determined based on statistical principles and the expertise of demand-side response in electricity. The mutual relationships between different response rates, durations, and participation frequencies and their influence weights on the overall response effect are studied. For example, through the analysis of a large amount of historical data, it is found that when the response rate is fast and the duration is long, the contribution to the demand-side response in electricity is relatively large, but unstable participation frequencies will also affect the overall effect. Considering these factors comprehensively, the calculation methods and interrelation formulas of various parameters in the algorithm are determined. A method combining classification and regression algorithms in machine learning algorithms is adopted to improve the accuracy and adaptability of recognition. The classification algorithm can classify different response situations of users, such as excellent response, general response, poor response, etc.; the regression algorithm is used to predict the response effect values under different combinations of response parameters. User feedback data in past demand-side response activities in electricity are collected, including response rates, durations, participation frequencies, and corresponding actual response effect data, etc. The data are divided into a training set and a test set. The training set data are used to train the model of the response coefficient recognizer. During the training process, the parameters and model structure in the algorithm are continuously adjusted with the goal of minimizing the prediction error. For example, the parameters of the model are optimized through the gradient descent algorithm to improve the fitting ability of the model. The test set data are used to verify and evaluate the trained model. The model is further optimized according to the evaluation results, such as adjusting the classification threshold, increasing or decreasing the complexity of the model, etc., until the model reaches the predetermined accuracy and stability indicators. After multiple iterations of optimization, a response coefficient recognizer that can accurately recognize the user response coefficient is finally constructed.

[0071] Step S570: Analyze the K response rate sets, K response duration sets, and K participation frequency sets using the response coefficient identifier to determine the K user feedback parameter sets. Specifically, organize and format the data in the K response rate sets, K response duration sets, and K participation frequency sets to meet the input requirements of the response coefficient identifier. For example, standardize the data to convert data with different dimensions into a unified standard scale so that the model can process it accurately, fill in missing values using appropriate methods such as mean filling and interpolation to ensure data integrity, and then sequentially input the processed data into the response coefficient identifier. The response rate, duration, and participation frequency data corresponding to each user are used as a set of input data. The response coefficient identifier analyzes and calculates the input data according to a pre-constructed algorithm model. For each set of input data, through the classification part in the model, determine the category to which the user response belongs; through the regression part, calculate the specific response coefficient value. Combine the classification results and response coefficient values of each user to form K user feedback parameter sets. The sets not only contain the classification information of the user response situation but also accurately quantify the response degree of each user, providing a key basis for subsequent work such as optimizing the power demand side response strategy. By continuously accumulating new data and updating and optimizing the identifier, it can more accurately analyze and process user feedback parameters.

[0072] Step S600: Conduct a response analysis on the K user feedback parameter sets to obtain K user response coefficients. Specifically, first perform Z-score standardization on the response rate, response duration, and participation frequency data in the K user feedback parameter sets to make the data comparable. Then, construct a response analysis model based on the power demand side response principle and objectives, determine the weights of each parameter through a combination of historical data regression analysis and expert experience, and use the weighted summation method to establish a mathematical relationship with the response rate, duration, and participation frequency as input variables. Substitute the standardized data into the model and calculate the response coefficient for each user according to the weights, paying attention to data precision control during the calculation. Finally, evaluate and verify the response coefficients by comparing with the actual power system operation data and using internal verification methods such as cross-validation. If there are deviations, re-check and adjust the data processing, model construction, and weight allocation links until reliable K user response coefficients are obtained.

[0073] Step S700: Optimize the initial demand-side response strategy by combining the K user power concentration intervals, the K peak electricity consumption concentration periods, the K flat electricity consumption concentration periods, the K valley electricity consumption concentration periods, and the K user response coefficients to obtain an optimized demand-side response strategy. Specifically, first summarize and integrate the user power concentration intervals, peak-valley electricity consumption periods, and response coefficient data, classify and organize the power interval data, conduct statistical analysis, and draw a trend chart of electricity consumption periods to compare the electricity consumption differences of different users. Adjust the incentive intensity according to the user electricity consumption behavior, increase the incentive for users with large electricity consumption and concentrated power during peak hours to encourage them to adjust the electricity consumption time, and optimize the cost adjustment incentive for users with low power and high electricity consumption during valley hours; optimize the response period according to the response coefficient, extend the period for users with high response and long flat electricity consumption concentration periods, and evaluate the rationality of the period for users with low response and adjust or guide according to the feedback. Use simulation software to establish a model, input the adjusted parameters to simulate the system operation, compare the results with the optimization goal, if not meeting the expectation, re-analyze and adjust, and simulate multiple times. Finally, determine the strategy parameters, integrate them into an optimized strategy, and establish a dynamic adjustment mechanism to adapt to changes.

[0074] In a possible implementation manner, when optimizing the initial demand-side response strategy by combining the K user power concentration intervals, the K peak electricity consumption concentration periods, the K flat electricity consumption concentration periods, the K valley electricity consumption concentration periods, and the K user response coefficients to obtain an optimized demand-side response strategy, step S700 further includes:

[0075] Step S710: Calculate the ratio of each of the K user response coefficients to the sum of the K user response coefficients respectively, and take the reciprocal of the ratio as the K strategy optimization coefficients. Specifically, for the response coefficient of each user, calculate its ratio to the sum of the K user response coefficients respectively. This step requires accurately calculating the sum of the K user response coefficients first, and then dividing each user's response coefficient by this sum one by one. During the calculation process, pay attention to controlling the data precision, and use appropriate data types and calculation methods to ensure the accuracy of the calculation results. For example, use a high-precision numerical calculation library or software tool for calculation to avoid calculation errors of the ratio caused by data precision problems. After calculating the ratio, take its reciprocal as the strategy optimization coefficient. Since the better the user feedback (the larger the response coefficient), the larger the ratio and the smaller the reciprocal (the strategy optimization coefficient). This means that for users with positive response and good feedback, the adjustment amplitude is relatively small in the subsequent strategy optimization; while for users with a smaller response coefficient and less good feedback, the strategy optimization coefficient is larger, and a larger adjustment is required during the optimization process. Through such a calculation method, a coefficient that can reflect the adjustment weight of each user in the strategy optimization is determined for each user.

[0076] Step S720: Using the K policy optimization coefficients as the optimization scale, and using the K user power concentration intervals, K peak power consumption concentration periods, K flat power consumption concentration periods, and K valley power consumption concentration periods as the optimization analysis data, optimize the initial power demand side response strategy to obtain an optimized power demand side response strategy. Specifically, associate and correspond the K policy optimization coefficients with the optimization analysis data such as user power concentration intervals and peak-valley-flat power consumption concentration periods. According to the number or identifier of each user, ensure the accurate matching of the policy optimization coefficients with the corresponding power consumption data. Further preprocess the optimization analysis data. For example, refine and classify the power concentration interval data, divide different grade intervals according to the power magnitude; statistically analyze the time span of the peak-valley-flat power consumption concentration period data, clarify the typical power consumption characteristics of each period, and adjust the incentive intensity according to the policy optimization coefficients. For users with small policy optimization coefficients, appropriately reduce the adjustment range of the incentive intensity, and make fine-tuning on the basis of maintaining their original power consumption habits and response modes. For users with large coefficients, increase the adjustment intensity of the incentive intensity, and attract users to change their power consumption behaviors by means such as increasing the electricity price discount, increasing the subsidy amount, or providing more value-added services. For example, for users with concentrated power during peak periods and large policy optimization coefficients, a higher peak-valley electricity price difference incentive can be provided to prompt them to transfer their power consumption time to valley periods or flat periods, and optimize the response period in combination with the policy optimization coefficients and user power consumption period data. For users with small policy optimization coefficients and stable power consumption period rules, maintain their original response period settings or make minor optimizations. For users with large coefficients and irregular power consumption periods or poor response effects, re-evaluate their power consumption behavior characteristics, and formulate more reasonable response periods for them in combination with the grid load demand and power generation resource conditions. For example, according to the peak-valley distribution of power generation resources in the area where the user is located and the grid load prediction curve, adjust the response period to a time period that is more conducive to balancing the power grid supply and demand relationship, so as to optimize the initial power demand side response strategy and obtain an optimized power demand side response strategy that better meets the actual situation of users and the operation requirements of the power grid.

[0077] The present invention adopts the method of retrieving the line architecture of the target area, obtaining the user set on the transmission line, and collecting the power consumption data of users. Disassemble and analyze the data in terms of power and power consumption period to obtain the user's power concentration interval and peak, flat power consumption periods. Formulate an initial power demand side response strategy, including the incentive intensity and response period, and distribute it to each transmission line. Collect the feedback information of users through the feedback window, analyze the response effect and calculate the response coefficient of users. Combine the user's power interval and response coefficient to optimize the initial strategy to form a final power demand side response strategy, achieving the technical effects of improving the accurate control ability of power load, reducing the impact of power peak-valley fluctuations on the power grid, and thus enhancing the stability of the power grid.

[0078] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recited in the present application can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for optimizing power demand response strategy based on feedback information extraction, characterized in that: The method comprises the following steps: S100, calling the line architecture of the target area, obtaining K user sets of K transmission lines, where K is an integer greater than or equal to 1; S200, traversing the K user sets to collect power usage data in a preset monitoring window to obtain K user power usage data sets; S300, performing power and power consumption period disassembly analysis on the K user power usage data sets to obtain K user power concentration intervals, K peak power consumption concentration periods, K average power consumption concentration periods, and K valley power consumption concentration periods; S400, obtaining an initial power demand side response strategy, wherein the initial power demand side response strategy includes K response strategies, wherein the K response strategies include K incentive intensities and K response time periods; S500, distributing the K excitation intensities and K response time periods to the K transmission lines, and interacting with the K user sets in a preset feedback window to extract feedback information, and obtaining K user feedback parameter sets; S600, performing response analysis on the K user feedback parameter sets to obtain K user response coefficients; First, the response rate, response duration and participation frequency data in the K user feedback parameter set are Z-score standardized to make the data comparable. Then, a response analysis model is constructed based on the power demand side response principle and objectives. The weights of each parameter are determined by combining historical data regression analysis with expert experience. The weighted summation method is used to establish a mathematical relationship with the response rate, duration and participation frequency as input variables. The standardized data is substituted into the model, and the response coefficient of each user is calculated according to the weight. Finally, the response coefficient is evaluated and verified by comparing it with the actual power system operation data and using the cross-validation method. If there is any deviation, the data processing, model construction and weight distribution links are re-checked and adjusted until reliable K user response coefficients are obtained. Step S700, optimizing the initial power demand side response strategy in combination with the K user power concentration intervals, the K peak power concentration time periods, the K average power concentration time periods and the K valley power concentration time periods, and the K user response coefficients, to obtain an optimized power demand side response strategy; First, summarize and integrate the user power concentration interval, peak, flat and valley power consumption time periods and response coefficient data, classify and organize the power interval data and conduct statistical analysis, draw a power consumption time period trend chart to compare the power consumption differences of different users; adjust the incentive intensity according to the user's power consumption behavior, increase the incentive for users with high power consumption and concentrated power during peak hours to encourage them to adjust their power consumption time, and optimize the cost adjustment incentive for users with low power and high power consumption during valley hours; optimize the response time period according to the response coefficient, extend the time period for users with high response and long flat power concentration period, evaluate the rationality of the time period for users with low response and adjust or guide according to feedback; use simulation software to establish a model to input the adjusted parameters to simulate the system operation, compare the results with the optimization goals, and re-analyze and adjust and simulate multiple times if the expectations are not met, and finally determine the strategy parameters to integrate into the optimization strategy and establish a dynamic adjustment mechanism to adapt to changes.

2. The power demand side response strategy optimization method based on feedback information extraction according to claim 1 is characterized in that: include: Taking power as an index, extracting data from the K user power usage data sets to obtain K user power sets; Performing mean processing on the K user power sets to determine the mean values ​​of the K user powers; Performing center iteration on the K user power means in the K user power sets according to a preset iteration step length to determine the K user power center values; The K user power concentration intervals are determined by taking the K user power center values ​​as the interval center and setting the preset iteration step length as the distance from the two end points to the interval center.

3. The power demand side response strategy optimization method based on feedback information extraction according to claim 2 is characterized in that: include: A central iteration formula is pre-constructed, wherein the central iteration formula is: Where L(x) is the central value of the user power in the stage, N(x) is the iterative neighborhood composed of multiple user powers whose distance to the user power mean in each user power set is the preset iteration step length, and x i is the power of the ith user in the iterative neighborhood, x is the average power of the users, K(x i -x) is the Gaussian weight kernel function; Taking the K user power averages as matching objects, performing neighborhood searches in the K user power sets according to a preset iteration step length, and determining K iteration neighborhoods; Using the center iteration formula, center iteration is performed on the K user power means and the K iteration neighborhoods to obtain K stage user power center values; After multiple iterations, until the difference between the stage user power center values ​​obtained in two adjacent iterations is less than or equal to the preset difference, the iteration is stopped, and the K stage user power center values ​​obtained in the last iteration are used as the K user power center values.

4. The power demand side response strategy optimization method based on feedback information extraction according to claim 1 is characterized in that: include: Construct an electricity consumption coordinate system with time as the horizontal axis and electricity consumption as the vertical axis; Obtaining K user power consumption curve sets according to the K user power consumption data sets and the power consumption coordinate system; Fitting the K user power consumption curve sets respectively to obtain K fitted user power consumption curves; Based on the K fitted user power consumption curves, power consumption peak and valley analysis is performed to determine the K peak power consumption concentrated time periods, K average power consumption concentrated time periods and K valley power consumption concentrated time periods.

5. The power demand side response strategy optimization method based on feedback information extraction according to claim 1 is characterized in that: The K excitation intensities and K response periods are distributed to the K transmission lines, and the K user sets are interacted in a preset feedback window to extract feedback information, and K user feedback parameter sets are obtained, including: Obtaining K distribution time nodes of the K excitation intensities and the K response time periods; Extracting K receiving time node sets at which K users in the K transmission lines receive the K excitation intensities and the K response time periods; Performing feedback correction factor analysis based on the K distribution time nodes and the K receiving time node sets to determine K user feedback correction factor sets; The K user feedback parameter sets are modified based on the K user feedback modification factor sets.

6. The power demand side response strategy optimization method based on feedback information extraction according to claim 1 is characterized in that: The K user feedback parameter sets include K response rate sets, K response duration sets, and K participation frequency sets.

7. The power demand side response strategy optimization method based on feedback information extraction according to claim 6 is characterized in that: include: Pre-built response coefficient identifier; The K response rate sets, the K response duration sets and the K participation frequency sets are analyzed by using the response coefficient identifier to determine the K user feedback parameter sets.

8. The power demand side response strategy optimization method based on feedback information extraction according to claim 1 is characterized in that: include: Calculate the ratio of the K user response coefficients to the sum of the K user response coefficients respectively, and use the reciprocal of the ratio as K strategy optimization coefficients; Taking the K strategy optimization coefficients as the optimization scale, and taking the K user power concentration intervals, K peak power concentration time periods, K flat power concentration time periods and K valley power concentration time periods as the optimization analysis data, the initial power demand side response strategy is optimized to obtain the optimized power demand side response strategy.

Images