Method for determining load regulation strategy based on multi-objective optimization and electronic equipment

Abstract

The invention discloses a method for determining a load regulation strategy based on multi-objective optimization and electronic equipment. The method relates to the field of intelligent power grids, and comprises the steps: constructing a first objective function enabling the cost consumption corresponding to load adjustment to be minimum according to the industry kilowatt-hour output value, the adjustment confidence coefficient, the continuous participation adjustment coefficient, the response characteristic coefficient, the declaration adjustment amount and the continuous adjustment duration of a target power user in a target time period; constructing a second objective function which enables the number of participations of the users to be minimum; based on the first objective function and the second objective function, the initial load adjustment strategy is optimized, a target load adjustment strategy of the target time period is obtained, and the target load adjustment strategy comprises the target power user, the adjustment participation time period of the target power user and the load adjustment amount. According to the method and the device, the technical problems of inaccurate formulation of the load regulation strategy and low efficiency of user participation in coincidence regulation caused by incomplete consideration factors during formulation of the load regulation strategy in related technologies are solved.

Description

Technical Field

[0001] This invention relates to the field of smart grids, and more specifically, to a method and electronic device for determining a load regulation strategy based on multi-objective optimization. Background Technology

[0002] In the operation and management of power systems, the formulation of load regulation strategies is a crucial step in ensuring power supply and demand balance and improving grid stability and efficiency. However, the methods for formulating load regulation strategies in related technologies have several limitations, mainly reflected in the incompleteness of the factors considered. This leads to inaccurate load regulation strategies and low efficiency in user participation in load regulation. Currently, most load regulation strategies rely on users' fixed regulation declarations and are usually prioritized according to the principle of "scale priority, time priority" to form the final load regulation plan. This approach ignores the real-time changes in market dynamics and user behavior, which can cause deviations between the load regulation plan and the actual situation, reducing the effectiveness and accuracy of regulation. In addition, the lack of impact assessment on continuous user participation in load regulation during the scheme formulation process may lead to some users suffering cost losses or production interruptions due to excessively frequent participation in regulation, thereby affecting user participation enthusiasm and the overall efficiency of the regulation strategy execution. In summary, the incomplete consideration of factors in the formulation of load regulation strategies in related technologies leads to inaccurate load regulation strategies and low efficiency in user participation in load regulation.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method and electronic device for determining a load regulation strategy based on multi-objective optimization, which at least solves the technical problem in the related art that the load regulation strategy is not fully considered when formulating the strategy, resulting in inaccurate load regulation strategy formulation and low user participation in regulation efficiency.

[0005] According to one aspect of the present invention, a method for determining a load regulation strategy based on multi-objective optimization is provided, comprising: constructing a first objective function based on the industry-specific electricity output value, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration of a target power user within a target time period, wherein the target power user is a power user participating in load regulation within the target time period, the regulation confidence level refers to the degree of confidence of the user in participating in load regulation, the response characteristic coefficient is used to indicate whether the user performs load transfer, and the first objective function is used to minimize the cost consumption corresponding to load regulation; constructing a second objective function based on the number of users participating within the target time period, wherein the second objective function is used to minimize the number of users participating; and optimizing the initial load regulation strategy based on the first objective function and the second objective function to obtain a target load regulation strategy for the target time period, wherein the target load regulation strategy includes the target power user, and the target power user's participation regulation period and load regulation amount.

[0006] According to another aspect of the present invention, a non-volatile storage medium is also provided, which stores a plurality of instructions, any one of which is adapted to be loaded by a processor to determine a multi-objective optimization-based load balancing strategy.

[0007] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the methods for determining a load regulation strategy based on multi-objective optimization.

[0008] According to another aspect of the present invention, a computer program product is also provided, including a computer program, wherein when the computer program is executed by a processor, the steps of a method for determining a load regulation strategy based on multi-objective optimization are implemented.

[0009] In this embodiment of the invention, a first objective function is constructed based on the industry-specific electricity output value, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration of target power users within a target time period. Here, the target power users are those participating in load regulation within the target time period; the regulation confidence level refers to the user's confidence in participating in load regulation; and the response characteristic coefficient indicates whether the user will perform load transfer. The first objective function aims to minimize the cost of load regulation. A second objective function is constructed based on the number of participating users within the target time period, aiming to minimize the number of participating users. Based on the first and second objective functions, the initial load regulation strategy is optimized to obtain the target load regulation strategy for the target time period. The target load... The regulation strategy includes target power users, their participation periods, and load regulation amounts. It achieves the goal of constructing a first objective function that considers industry output per kilowatt-hour, regulation confidence level, continuous participation regulation coefficient, and response characteristic coefficient to minimize load regulation costs, and a second objective function that minimizes the number of participating users. This results in a load regulation strategy that satisfies both the dual objectives of minimizing load regulation costs and minimizing the number of participating users, thus achieving an optimal balance between minimizing cost losses and maximizing operational efficiency. This improves the accuracy of power supply and demand coordination and the rationality of user participation, thereby solving the technical problems in related technologies where incomplete consideration of factors leads to inaccurate load regulation strategy formulation and low efficiency in user participation regulation. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0011] Figure 1 This is a flowchart of a method for determining a load regulation strategy based on multi-objective optimization according to an embodiment of the present invention;

[0012] Figure 2 This is a schematic diagram of a device for determining a load regulation strategy based on multi-objective optimization according to an embodiment of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] According to an embodiment of the present invention, a method embodiment for determining a load regulation strategy based on multi-objective optimization is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0016] Figure 1 This is a flowchart of a method for determining a load regulation strategy based on multi-objective optimization according to an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes the following steps:

[0017] Step S102: Based on the industry-specific electricity output value, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration of the target power users within the target time period, a first objective function is constructed. Here, the target power users are the power users participating in load regulation within the target time period, the regulation confidence level refers to the degree of confidence of the user in participating in load regulation, the response characteristic coefficient is used to indicate whether the user performs load transfer, and the first objective function is used to minimize the cost consumption corresponding to load regulation.

[0018] Optionally, the target period is a time within a cycle (e.g., a full day) during which power supply and demand are strained, requiring adjustment of demand-side resources; the target power user is a user whose load can be adjusted during the target period. Industry output per kilowatt-hour represents the output per kilowatt-hour of the user's industry (which can be represented by the quotient of the industry's annual GDP and total annual electricity consumption), reflecting the output per unit of electricity in the target power user's industry and used to assess the impact of adjusted electricity on cost losses. Adjustment confidence represents the reliability of the user in load adjustment, calculated based on historical participation, used to ensure the reliability of the scheme. The continuous participation adjustment coefficient considers the potential impact of frequent load adjustment on the user's production activities, avoiding excessive participation by the same user to reduce their burden. This coefficient increases with the number of times the user participates in adjustment within the current cycle; by considering this coefficient, fairness issues arising from frequent participation by the same user can be effectively reduced. The response characteristic coefficient distinguishes between user load adjustment methods, i.e., load reduction or load transfer. Simply reducing load means that participation in adjustment leads to a decrease in user capacity, significantly impacting user production; transferring load means shifting capacity to other time periods, with relatively less impact on user production and operations. The declared adjustment volume represents the amount of load adjustment a user can contribute within the target time period, and is the basis for plan formulation. The continuous adjustment duration represents the time during which a user can continuously adjust the load within the target time period, ensuring the feasibility of the adjustment plan. Taking all these factors into account, the first objective function aims to minimize the cost incurred during the load adjustment process.

[0019] In one optional embodiment, there are multiple target electricity users. A first objective function is constructed based on the industry-specific electricity output, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration of each target electricity user within a target time period. This includes constructing the first objective function in the following manner, based on the industry-specific electricity output, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration of each target electricity user within the target time period: ;in, This represents the function value of the first objective function; This represents the industry output value per kilowatt-hour for any one of multiple target electricity users; This represents the adjustment confidence level for any target electricity user. This represents the continuous participation regulation coefficient for any target electricity user; Represents the response characteristic coefficients of any target electricity user; This represents the declared regulation amount for any target electricity user during any regulation period within the target time period. This represents the duration of continuous adjustment for any target power user during any adjustment period. For example, the t-th adjustment period is from 7 pm to 9 pm, which is the overall adjustment period. The 7-8 pm and 8-9 pm periods are two separate adjustment periods that need to be optimized and scheduled separately. Let N represent any target electricity user, and let N represent the total number of multiple target electricity users. M represents any adjustment period, and M represents the total number of adjustment periods within the target period.

[0020] Optionally, the load regulation strategy can be applied to multiple different users simultaneously. Each user has its own industry-specific electricity output value, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration. This embodiment extends the optimization of the load regulation strategy to scenarios involving multiple users. By introducing parameters such as industry-specific electricity output value, regulation confidence level, continuous participation regulation coefficient, and response characteristic coefficient, a complex multi-objective function is constructed. This function aims to minimize overall cost losses while fairly and reasonably allocating load regulation tasks, ensuring the efficiency of the load regulation strategy and fairness among users.

[0021] In one optional embodiment, the adjustment confidence of any target power user is obtained by: acquiring the number of times the target power user reaches a predetermined adjustment standard within a predetermined historical period, and the actual number of times the target power user participates in adjustment within the predetermined historical period; and determining the adjustment confidence of any target power user based on the number of times the predetermined adjustment standard is reached and the actual number of times the user participates in adjustment.

[0022] Optionally, the adjustment confidence level can be obtained from historical data. The number of times the predetermined adjustment standard is met refers to the number of times the account has successfully completed load adjustment tasks within a predetermined historical period. The predetermined adjustment standard can be a specific target for load reduction or transfer defined by the power grid platform. For example, when a user is required to reduce load by 10% within a specific period, if the user accurately executes this instruction, it will be recorded as a successful adjustment. The actual number of adjustments participated in refers to the total number of times the account has been required to participate in adjustments within the same predetermined historical period, regardless of whether the adjustments were successful. This data reflects the frequency of user participation in load adjustment and is an important basis for assessing the user's adjustment capabilities. The quotient of the number of times the predetermined adjustment standard is met and the actual number of adjustments participated in can be used as the adjustment confidence level to quantify the reliability of its execution of load adjustment instructions. For example, if a user has been required to participate in 10 load adjustments in the past week, and successfully met the predetermined adjustment standard 8 times, then the user's adjustment confidence level is 8 / 10 = 0.8. Users with high confidence are more likely to be prioritized because their past performance indicates they can effectively respond to load regulation commands, while users with low confidence may require more monitoring or be assigned fewer regulation tasks to reduce the risk of grid instability due to frequent regulation failures. Regulation confidence is considered an important variable in the primary objective function (minimizing cost losses). By assigning higher weight to high-confidence users, it is possible to favor those who have historically proven their effectiveness in load regulation, thereby improving the overall effectiveness of load regulation.

[0023] In one alternative embodiment, the continuous participation regulation coefficient for any target electricity user is obtained as follows: ;in, This represents the continuous participation regulation coefficient for any target electricity user; This refers to the actual number of times a target electricity user participates in load regulation within a target time period. For example, if a user has participated in load regulation 5 times this month, then... ; It is the natural logarithm; A preset adjustment coefficient is used to determine the overall rate of increase, and it is adjusted according to the needs of the power grid operator and the objectives of the load regulation strategy. For example, it can be set... The value of is 1. The value of x determines the continuous participation adjustment coefficient as x increases. The rate of change. If If it is relatively large, then even if x increases, Decreasing speed can be done relatively slowly, and conversely, if Smaller, then It decreases rapidly as x increases.

[0024] The continuous participation regulation coefficient is defined as the continuous participation regulation coefficient of the target power user. This coefficient measures the frequency with which a user participates in load regulation within a given period, aiming to prevent individual users from participating in regulation activities too frequently, thus avoiding impacting their normal production activities or causing unnecessary cost losses. The continuous participation regulation coefficient in this form indicates that the more times a user participates in load regulation, the smaller the coefficient becomes. Consequently, its weight in the first objective function (minimizing cost losses) decreases accordingly, automatically favoring users with fewer participation times to balance the load regulation task, preventing some users from being harmed by excessive regulation, and reducing the complexity of communication and monitoring. The continuous participation regulation coefficient is a key component of the first objective function, ensuring the long-term feasibility of the load regulation strategy and fairness among users. By introducing this coefficient, while minimizing cost losses, the historical frequency of user participation in regulation can be considered, avoiding over-reliance on a few users for load regulation, thereby improving the robustness of the overall load regulation strategy and user satisfaction.

[0025] In an optional embodiment, the response characteristic coefficients of any target power user are obtained as follows: The response characteristic evaluation index of any target power user is obtained as follows: ;in, This represents the response characteristics evaluation index for any target power user. Its value can be set according to the needs of the scenario, for example, it can be set to 3 or 5. Q1 represents the regulated electricity volume corresponding to any target power user participating in regulation once within the target time period; Q2 represents the electricity volume that changes during a cycle (the whole day) excluding the corresponding regulation time period when participating in regulation once; based on the comparison results between the response characteristic evaluation index of any target power user and the preset threshold, the response characteristic coefficient of any target power user is determined.

[0026] Optionally, Q1 can be obtained, but is not limited to, in the following ways: ;in, Let be the regulated load at the i-th time point during the m-th regulation period; The step size is the data acquisition step size; multiplying the two gives the adjusted power. n represents the total adjustment time T1 and the data acquisition step size. The quotient. Q2 can be obtained, but is not limited to, through the following methods: ;in, The non-adjustment period and data collection step size are calculated after subtracting the total adjustment duration T1 from 24 hours. For example, if the adjustment is made between 7-9 pm, then the non-adjustment period is from 12 am to 7 pm and from 9 pm to 12 am, totaling 22 hours. If one collection point is taken every 15 minutes, then there are 88 collection points. Let i be the load level at the i-th time point during the period when the load participates in the m-th adjustment but does not participate in the adjustment. This represents the load level at the point in time corresponding to the nearest non-regulation day before the m-th regulation participation (e.g., if regulation was participated on September 9th but not on September 8th, then September 8th is used). Multiplying the differences represents the change in electricity consumption during the non-regulation period when regulation was participated in. If the adjusted power consumption exceeds a certain threshold (e.g., 2), it indicates that the user's overall power consumption has been reduced, and this is considered to be a response characteristic of load transfer not being implemented, meaning that the power transfer during the adjustment period has not reached the unadjusted period. The value of (A smaller value can be taken, such as 1). If it is less than a certain coefficient, it is considered that the load level in other time periods is higher and has been transferred, that is, the response characteristic is load reduction. Take a smaller value, such as 0.2.

[0027] Step S104: Based on the number of user participations within the target time period, construct a second objective function, wherein the second objective function is used to minimize the number of user participations;

[0028] Optionally, the second objective function aims to reduce the number of users participating in load regulation, optimize scheduling efficiency, and minimize interference with users' normal production and operation. This function calculates the total number of users participating in load regulation within a target time period, aiming to minimize this number to optimize resource allocation and improve user satisfaction. The formula for this second objective function is as follows: ,in, This represents the function value of the second objective function. Let M represent the number of users adjusted during the t-th adjustment period, and M represent the total number of adjustment periods within the target period.

[0029] Step S106: Based on the first objective function and the second objective function, optimize the initial load regulation strategy to obtain the target load regulation strategy for the target time period. The target load regulation strategy includes the target power users, the target power users' participation period and load regulation amount.

[0030] Optionally, the initial load regulation strategy can be optimized by combining the two objectives of minimizing cost losses and minimizing the number of participating users. This can be achieved, but is not limited to, using a multi-objective optimization algorithm (such as the Nondominated Sorting Genetic Algorithm III, NSGA-III) based on the first and second objective functions to find the optimal load regulation strategy. This strategy not only balances power supply and demand but also minimizes cost losses and reduces the number of users directly involved in regulation as much as possible. Through the above steps, the method in this embodiment aims to achieve accurate, efficient, and fair power load regulation, effectively responding to changes in supply and demand while minimizing the adverse impact on user and load transfer costs.

[0031] As an optional implementation, a multi-objective optimization algorithm (such as NSGA-III) is used to solve the problem based on the first objective function, the second objective function, and the constraints to find the optimal load regulation strategy, including:

[0032] S1061 generates an initial set of solutions, i.e., a population. Each solution (individual) in the population represents a set of parameter configurations for a load adjustment strategy.

[0033] S1062, Evaluation Function Calculation: Evaluate each solution in the population, calculating its performance under the first and second objective functions. For example, calculate the specific values ​​for load balancing costs and the number of participating users.

[0034] S1063, Fast Non-Dominated Sort: Using the fast non-dominated sorting method of NSGA-III, the solutions in the population are classified according to their non-dominated relations in the target space, resulting in multiple non-dominated layers.

[0035] S1064, Calculate crowding distance: For solutions in the same non-dominated layer, calculate their crowding distance in the target space as a means of maintaining population diversity.

[0036] S1065, Selection, Crossover, and Mutation: Based on the fast non-dominated sorting results and crowding distance, select solutions for genetic operations, including crossover and mutation, to generate the next generation population. Crossover creates new solutions by exchanging partial information between two parent solutions, while mutation explores the solution space by randomly changing certain parameters of the solutions.

[0037] S1066, Repeated Iteration: The newly generated population is evaluated again, fast non-dominated sorting and crowding distance calculation are performed, and steps S1063 to S1065 are repeated until the predetermined number of iterations is reached or other stopping conditions are met.

[0038] S1067, Solution Preservation and Analysis: In each iteration, the optimal solution in the non-dominated layer is preserved. Finally, from the optimal solutions selected in all iterations, a solution selection strategy based on reference points is used to determine one or more optimal load adjustment strategies. The obtained optimal strategies are analyzed to ensure that they satisfy all constraints and effectively balance load transfer costs and the number of users.

[0039] S1068, Strategy Output: The final determined optimal load regulation strategy is output as the basis for implementing the power system demand response.

[0040] In one optional embodiment, the initial load regulation strategy is optimized based on a first objective function and a second objective function to obtain a target load regulation strategy for a target time period. This includes: determining constraints including: the load regulation capacity of all target power users is greater than or equal to the load shortage amount of the corresponding regulation period; the continuous regulation duration of any target power user is greater than or equal to the corresponding declared regulation duration; and the actual regulation amount of any target power user is less than or equal to the corresponding target load regulation capacity. Based on the constraints, the first objective function, and the second objective function, the initial load regulation strategy is optimized to obtain the target load regulation strategy.

[0041] In this embodiment, the overall boundary conditions (i.e., constraints) are as follows: First, the user's load regulation capacity is greater than the supply-demand gap to ensure the overall effectiveness of the load regulation strategy; second, the duration of user regulation is longer than the period of the currently declared regulation capacity, because the user has committed to a certain regulation duration when declaring, and the optimization strategy should not violate this commitment; third, the actual regulation amount of the user during the regulation period does not exceed the corresponding target load regulation capacity. This constraint avoids overload regulation and ensures the user's equipment safety and production stability. If the overall user representation of the scheme formed according to the above method is V, the three boundary conditions (i.e., constraints) are as follows: ; ; Among them, there are two characteristics. This represents the declared capacity of the i-th user (i.e., the target power user) within the adjustment period t; This represents the adjusted confidence level for the i-th user; This indicates the amount of load shortage during the corresponding adjustment period; This represents the longest duration that the i-th user can sustain during this adjustment period; This indicates the corresponding application adjustment period; This represents the actual adjustment amount for the i-th user; This represents the target load regulation capacity of the i-th user.

[0042] After clarifying the constraints, the optimization process combines the first and second objective functions to improve the initial load regulation strategy. Here, the objective functions are minimizing the impact of load transfer costs and minimizing the number of participating users within a multi-objective optimization framework. By solving this constrained multi-objective optimization problem, a set of regulation strategies can be found. These strategies, while satisfying all constraints, minimize the impact of load transfer costs and limit the number of participants, thus ensuring the optimality of the load regulation strategy in terms of load transfer cost losses, technology, and fairness. Ultimately, the optimization process generates a target load regulation strategy. This strategy not only considers the real-time demand of the power system but also fully evaluates the load regulation capabilities and confidence levels of each power user, while balancing load transfer cost losses and the fair burden on participants. In other words, the target load regulation strategy is the optimal solution derived by considering the interests of all participants and system requirements.

[0043] In one optional embodiment, the target load regulation capacity of any target power user is obtained as follows: The actual load curve and verification load curve of any target power user during a predetermined time period are obtained, wherein the verification load curve is the load curve of the power user determined during a verification phase prior to the predetermined time period; Based on the actual load curve of any target power user, the predicted average load level of any target power user during the predetermined time period is determined; and based on the verification load curve of any target power user, the verification average load level of any target power user during the predetermined time period is determined, wherein the verification average load level is obtained by averaging multiple load points corresponding to the target time period in the verification load curve; Based on the predicted average load level and the verification average load level, it is determined whether the load regulation capacity of any target power user needs to be dynamically adjusted; If it is determined that the load regulation capacity of any target power user needs to be dynamically adjusted, the load regulation capacity of any target power user is adjusted based on the verification load curves corresponding to multiple power users, thereby obtaining the target load regulation capacity, wherein the multiple power users are power users in the same industry as any target power user.

[0044] Optionally, firstly, for each target electricity user, it is necessary to collect their actual load curve and verification load curve for the predetermined period. The verification load curve is determined based on the load level established during the capacity verification phase prior to the predetermined period, reflecting the electricity user's expectations for load regulation. Next, based on the actual load curve, the predicted average load level for the target electricity user during the predetermined period is calculated; similarly, based on the verification load curve, its verification average load level is calculated. The purpose of this step is to compare the user's actual load with the expected load to assess whether there is a deviation. By comparing the predicted average load level and the verification average load level, it is determined whether the target electricity user's load regulation capacity needs dynamic adjustment. If there is a significant difference between the two, it indicates that the user's regulation capacity may change due to external factors (such as changes in production plans, equipment maintenance status, etc.), and its regulation capacity needs to be reassessed. Select multiple power users within the same industry whose verified load curves are similar to those of the target power user. Based on these selected power users' verified load curves, calculate an average regulation capacity or determine a more accurate load regulation capacity index through statistical analysis. Use the calculated average or adjusted regulation capacity to update the target power user's load regulation capacity, making it closer to the current actual load level and regulation potential. The dynamically adjusted load regulation capacity will be used as an important parameter in subsequent optimization processes to ensure that the load regulation strategy can more accurately reflect the user's current regulation capacity and avoid deviations in scheme formulation.

[0045] This embodiment provides a method for dynamically verifying and adjusting user load regulation capabilities. It overcomes the limitations of related technologies that rely solely on periodic verification data, enabling load regulation strategies to more flexibly respond to real-time changes in electricity demand and dynamic fluctuations in user regulation capabilities, thereby improving the efficiency and reliability of electricity supply and demand coordination. This method is particularly suitable for rapidly changing electricity market environments, ensuring the real-time nature and adaptability of strategies and reducing the risk of supply-demand mismatch.

[0046] In one optional embodiment, determining whether dynamic adjustment of the load regulation capacity of any target power user is needed based on the predicted average load level and the verification average load level includes: determining whether dynamic adjustment of the load regulation capacity of any target power user is needed based on the predicted average load level and the verification average load level in the following manner: ;in, Indicates the predicted average load level. This indicates the average load level being checked. The preset deviation threshold can be set according to the actual needs of the scenario, for example, it can be set to 10%.

[0047] Optionally, the load regulation capacity of the target power user can be determined to need updating by calculating the relative deviation between the predicted average load level and the verification average load level. If, then, a significant difference exists between the predicted average load level and the verification average load level, it is considered that the load regulation capacity of the target electricity users needs to be dynamically adjusted to reflect their latest regulation potential. Conversely, if If the difference is within an acceptable range, no dynamic adjustment is required, and the existing load regulation capacity data can be used. This approach allows for timely identification and response to changes in user load levels, ensuring the accuracy and effectiveness of load regulation strategies.

[0048] In one optional embodiment, when it is determined that the load regulation capacity of any target power user needs to be dynamically adjusted, the load regulation capacity of any target power user is adjusted based on the verification load curves of multiple power users in the same industry as the target power user to obtain the target load regulation capacity. This includes: determining a first number of candidate power users from multiple power users based on the curve similarity between the verification load curves of each of the multiple power users and the actual load curve of the target power user; determining a second number of candidate power users from the first number of candidate power users based on the amplitude similarity between the verification load curves of each of the first number of candidate power users and the actual load curve of the target power user, wherein the second number is less than the first number; and obtaining the target load regulation capacity based on the expected load regulation capacity of each of the second number of candidate power users.

[0049] Optionally, firstly, curve similarity can be used as a screening mechanism to initially select a certain number (i.e., the first batch) of candidate power users from multiple power users within the same industry. Curve similarity refers to the similarity in shape between two sets of data points, which can be evaluated using metrics such as Euclidean distance, Pearson correlation coefficient, or Dynamic Time Warping (DTW). The goal is to identify a group of users whose actual load curves are most similar to those of the target power user, as these load patterns and response modes are likely to be more similar. From the initially selected first batch of candidate power users, a smaller number (i.e., the second batch) of candidate power users can be further selected based on the amplitude similarity between their respective verification load curves and the actual load curve of the target power user. Amplitude similarity focuses on the absolute value or amplitude of the curve, which can help identify users who are similar to the target power user not only in terms of load fluctuation trends but also in terms of load magnitude, thereby more accurately estimating the load regulation capacity of the target power user. Finally, based on the expected load regulation capacity of the second number of candidate power users, a comprehensive calculation is performed to determine the target load regulation capacity of the target power users. The purpose is to integrate the regulation data of these highly similar users to obtain a regulation capacity estimate that is more in line with the current actual load conditions.

[0050] The method in this embodiment considers not only the shape characteristics of the load curve but also the amplitude information of the curve when dynamically adjusting the load regulation capacity. This allows for a more comprehensive assessment of changes in the user's load regulation capacity, ensuring that the regulation strategy is both effective and fair during execution.

[0051] Optionally, if the regulation capacity of the target power user deviates, its regulation capacity can be dynamically adjusted. First, the recent load curve of the target power user is calculated, and its similarity to the load curve of other users in the same industry within the scheme during periodic capacity checks is determined. To minimize the impact of abnormal fluctuations, this step first requires smoothing the 96-point load curve (one metering point every 15 minutes, totaling 96 metering points over 24 hours) using a median filtering method to eliminate abnormally fluctuating load points. ; ;in, , Let k be the smoothed load curves of the target electricity user and the r-th electricity user in the same industry within the scheme, respectively. The calculation method for k is as follows: ,in, The window size can be an odd number, such as 3 or 5, depending on the situation. The smoothed curve is then standardized. For power users in the same industry within the same project, the average value is: ;variance Based on the obtained mean and variance, each load point is standardized in the following way: For the target electricity user: mean ;variance Based on the obtained mean and variance, each load point is standardized in the following manner. The curve similarity between the target electricity user and other users in the same industry within the plan is calculated, using Euclidean distance as the representation. The calculation formula is as follows: ,in, The smaller the value, the more similar the load curves. (Take...) The smallest pool of 20 users (which can be represented numerically later, but we'll tentatively use 20) constitutes the candidate electricity user pool. Since the standardization process described above only represents the similarity of load curves, this step requires further selection of users with similar load levels and load curves. Within the 20 users in the candidate pool, the load level during the adjustment period T is calculated for each user. Where n represents the number of data collection points within the adjustment period T, which can be taken as T / data collection step size (i.e., 15 minutes). The five smallest number of users (i.e., the first number of candidate electricity users) form the final selection pool.

[0052] In one optional embodiment, obtaining the target load regulation capacity based on the expected load regulation capacity corresponding to each of the second number of candidate power users includes: taking the average value of the expected load regulation capacity corresponding to each of the second number of candidate power users as the target load regulation capacity; or determining the weight value corresponding to each of the second number of candidate power users; and performing a weighted calculation based on the expected load regulation capacity corresponding to each of the second number of candidate power users and the corresponding weight value to obtain the target load regulation capacity.

[0053] Optionally, the average of the expected load regulation capabilities of a second number of candidate power users can be calculated and used as the target load regulation capability for the target power user, for updating the target power user's regulation capability. The corresponding formula can be expressed as: ,in, The dynamic adjustment capability (i.e., target load adjustment capability) for the target power users within the scheme. This refers to the adjustment capability during the periodic verification of relevant users in the final candidate pool. D represents the number of users in the final candidate pool, which can be set to 5.

[0054] Optionally, a weighted average can be calculated first for each of the second number of candidate power users, and then the target load regulation capacity of the target power user can be obtained by weighted averaging based on these expected load regulation capacities and their corresponding weights. The weights can be set based on various factors, such as the user's historical load regulation behavior, industry characteristics, equipment efficiency, and geographical location, so that the calculation results more closely reflect the actual load regulation potential of the target power user. This method is more flexible and accurate, taking into account the differences in load regulation contributions from different users, and is suitable for scenarios where regulation capacities vary significantly. By using an average or weighted average calculation method, it can be ensured that the updated load regulation capacity of the target power user reflects both industry commonalities and individual user characteristics, providing a more scientific and reasonable basis for power system scheduling and optimization in demand response. This strategy, based on a comprehensive calculation of industry data and user characteristics, helps improve the overall performance of load regulation strategies, reduce supply-demand matching errors, and better meet users' personalized needs, increasing user participation and satisfaction.

[0055] Through the above steps S102 to S106, the goal of constructing a first objective function that considers industry electricity output value, regulation confidence, continuous participation regulation coefficient, and response characteristic coefficient to minimize load regulation cost, and constructing a second objective function to minimize the number of users participating, can be achieved. This allows for the formulation of a load regulation strategy that satisfies both the dual objectives of minimizing load regulation cost and minimizing the number of users participating. This achieves an optimal balance between minimizing cost loss and maximizing operational efficiency, thereby improving the accuracy of power supply and demand coordination and the rationality of user participation. Furthermore, it addresses the technical problems in related technologies where incomplete consideration of factors leads to inaccurate load regulation strategy formulation and low efficiency in user participation regulation.

[0056] Based on the above embodiments and optional embodiments, the present invention proposes an implementation method for determining a load regulation strategy based on multi-objective optimization, the method comprising:

[0057] S1, Recent Load Curve Comparison: Compare the recent load curve of the target power user with the load curve during the periodic verification of its regulation capacity to determine whether there are significant changes.

[0058] S2, Load curve smoothing: The load curve is smoothed using the median filtering method to eliminate abnormal load fluctuations.

[0059] S3, Curve Standardization: The smoothed load curve is standardized to facilitate curve similarity comparison.

[0060] S4, Curve Similarity Calculation: Calculate the curve similarity between the target power user and users in the same industry within the scheme, and select the user with the highest similarity to enter the candidate pool.

[0061] S5, Load level difference calculation: Calculate the load level difference between the user adjustment period in the candidate pool and the target power user adjustment period, and further filter out the most similar users.

[0062] S6, Dynamic Adjustment and Regulation Capacity Calculation: Based on the periodic verification regulation capacity of the most similar user, calculate the dynamic adjustment regulation capacity of the target power user.

[0063] S7, Construction of multi-objective function: Construct a first objective function that minimizes the impact of load transfer cost loss and a second objective function that minimizes the number of participating users. The specific construction methods of the first and second objective functions are the same as those in the previous embodiments, and will not be repeated here.

[0064] S8, Load transfer response characteristic calculation: The load transfer response characteristic is calculated based on historical participation in regulation, which is used to distinguish whether users have transferred load.

[0065] S9, Application of NSGA-III Optimization Algorithm: The NSGA-III algorithm is used to optimize and solve the objective function and constraints to generate the optimal scheduling strategy. The specific form of the constraints is the same as in the previous embodiment, and will not be repeated here.

[0066] This embodiment of the method achieves the goal of constructing a first objective function that considers industry electricity output, regulation confidence, continuous participation regulation coefficient, and response characteristic coefficient to minimize load regulation costs, and a second objective function to minimize the number of users participating. This allows for the formulation of load regulation strategies that satisfy both the dual objectives of minimizing load regulation costs and minimizing the number of users participating, thereby achieving an optimal balance between minimizing cost losses and maximizing operational efficiency. This improves the accuracy of power supply and demand coordination and the rationality of user participation, thus addressing the technical problems in related technologies where incomplete consideration of factors leads to inaccurate load regulation strategies and low efficiency in user participation regulation.

[0067] This embodiment also provides a device for determining a load regulation strategy based on multi-objective optimization. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0068] According to an embodiment of the present invention, an apparatus embodiment for implementing the above-described method for determining a load regulation strategy based on multi-objective optimization is also provided. Figure 2 This is a schematic diagram of a device for determining a load regulation strategy based on multi-objective optimization according to an embodiment of the present invention, as shown below. Figure 2 As shown, the above-mentioned device for determining load regulation strategies based on multi-objective optimization includes: a first objective function construction module 200, a second objective function construction module 202, and a strategy optimization module 204, wherein:

[0069] The first objective function construction module 200 is used to construct a first objective function based on the industry electricity output value per unit area of ​​the target power user within the target time period, the adjustment confidence level, the continuous participation adjustment coefficient, the response characteristic coefficient, the declared adjustment amount, and the continuous adjustment duration. The target power user is the power user participating in load adjustment within the target time period, the adjustment confidence level refers to the degree of confidence of the user in participating in load adjustment, the response characteristic coefficient is used to indicate whether the user should transfer the load, and the first objective function is used to minimize the cost consumption corresponding to load adjustment.

[0070] The second objective function construction module 202 is connected to the first objective function construction module 200 and is used to construct a second objective function based on the number of user participations within a target time period. The second objective function is used to minimize the number of user participations.

[0071] The strategy optimization module 204 is connected to the second objective function construction module 202. It is used to optimize the initial load regulation strategy based on the first objective function and the second objective function to obtain the target load regulation strategy for the target time period. The target load regulation strategy includes the target power users, as well as the participation period and load regulation amount of the target power users.

[0072] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0073] It should be noted that the first objective function construction module 200, the second objective function construction module 202, and the strategy optimization module 204 mentioned above correspond to steps S102 to S106 in the embodiments. The instances and application scenarios implemented by the above modules and their corresponding steps are the same, but they are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run on a computer terminal.

[0074] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0075] The aforementioned device for determining load regulation strategies based on multi-objective optimization may further include a processor and a memory. The first objective function construction module 200, the second objective function construction module 202, the strategy optimization module 204, etc., are all stored in the memory as program modules, and the processor executes the aforementioned program modules stored in the memory to implement the corresponding functions.

[0076] The processor contains a core that retrieves the corresponding program modules from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0077] According to an embodiment of this application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein, when the program runs, it controls the device where the non-volatile storage medium is located to execute any of the above-mentioned methods for determining a load regulation strategy based on multi-objective optimization.

[0078] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals, and the non-volatile storage medium includes stored programs.

[0079] Optionally, a program that controls the device containing the non-volatile storage medium to execute any of the above-mentioned steps of the method for determining a load regulation strategy based on multi-objective optimization during program execution.

[0080] According to an embodiment of this application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein the program executes any of the above-described methods for determining a load regulation strategy based on multi-objective optimization.

[0081] According to an embodiment of this application, an embodiment of a computer program product is also provided, which, when executed on a data processing device, is adapted to execute a program that initializes the determination method steps of a multi-objective optimization-based load regulation strategy, which includes any of the above-described steps.

[0082] Optionally, when the above-mentioned computer program product is executed on a data processing device, it is suitable for executing a program that initializes the determination method steps of the load regulation strategy based on multi-objective optimization, which includes any of the above-mentioned steps.

[0083] This invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the method for determining a load regulation strategy based on multi-objective optimization as described above.

[0084] The order of the above embodiments of the present invention is merely for description and does not represent the superiority or inferiority of the embodiments.

[0085] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of modules described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between modules, and may be electrical or other forms.

[0087] The modules described above as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0088] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0089] If the aforementioned integrated modules are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0090] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining a load regulation strategy based on multi-objective optimization, characterized in that, include: Based on the industry-specific electricity output per unit area, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration of target power users within the target time period, a first objective function is constructed. The target power users are power users participating in load regulation within the target time period. The regulation confidence level refers to the degree of confidence of the user in participating in load regulation. The response characteristic coefficient is used to indicate whether the user performs load transfer. The first objective function is used to minimize the cost of load regulation. Based on the number of user participations within the target time period, a second objective function is constructed, wherein the second objective function is used to minimize the number of user participations; Based on the first objective function and the second objective function, the initial load adjustment strategy is optimized to obtain the target load adjustment strategy for the target time period. The target load adjustment strategy includes the target power user, the target power user's participation period and load adjustment amount.

2. The method according to claim 1, characterized in that, The target power users are multiple. The first objective function is constructed based on the target power users' industry-specific electricity output, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration within the target time period. This includes: Based on the industry-specific electricity output, regulation confidence level, continuous participation regulation coefficient, response characteristic coefficient, declared regulation amount, and continuous regulation duration of each of the multiple target electricity users within the target time period, the first objective function is constructed as follows: ； in, This represents the function value of the first objective function; This represents the industry-specific electricity output value of any one of the plurality of target electricity users; This represents the adjustment confidence level of any of the target power users. This represents the continuous participation regulation coefficient for any of the target power users; Represents the response characteristic coefficient of any of the target power users; This represents the declared adjustment amount for any target electricity user during any adjustment period within the target time period. This indicates the duration of continuous adjustment for any target electricity user during any adjustment period; N represents any one of the target electricity users, and N represents the total number of the multiple target electricity users; M represents any one of the adjustment periods, and M represents the total number of adjustment periods within the target period.

3. The method according to claim 2, characterized in that, The adjustment confidence level of any target power user is obtained in the following manner: The number of times the target power user reaches the predetermined adjustment standard within a predetermined historical period is obtained, as well as the number of times the target power user actually participates in adjustment within the predetermined historical period. The adjustment confidence level of any target power user is determined based on the number of times the predetermined adjustment standard is reached and the number of times the adjustment is actually participated in.

4. The method according to claim 2, characterized in that, The continuous participation regulation coefficient for any target electricity user is obtained as follows: ； in, This represents the continuous participation regulation coefficient for any of the target power users; The actual number of times the target power user participated in regulation during the target time period; It is the natural logarithm; This is the preset adjustment coefficient.

5. The method according to claim 2, characterized in that, The response characteristic coefficients of any target electricity user are obtained in the following manner: The response characteristic evaluation index for any target power user is obtained through the following method: ;in, This represents the response characteristic evaluation index for any of the target power users; Q1 represents the adjusted electricity amount corresponding to any one time the target power user participates in the adjustment within the target time period; Q2 represents the electricity amount that changes in a cycle, excluding the corresponding adjustment period, during any one time the user participates in the adjustment. Based on the comparison results between the response characteristic evaluation index of any target power user and the preset threshold, the response characteristic coefficient of any target power user is determined.

6. The method according to any one of claims 1 to 5, characterized in that, The optimization of the initial load adjustment strategy based on the first objective function and the second objective function to obtain the target load adjustment strategy for the target time period includes: The constraints include: the load regulation capacity of all target power users is greater than or equal to the load shortage during the corresponding regulation period; the continuous regulation duration of any target power user is greater than or equal to the corresponding declared regulation duration; and the actual regulation amount of any target power user is less than or equal to the corresponding target load regulation capacity. Based on the constraints, the first objective function and the second objective function are used to optimize the initial load adjustment strategy to obtain the target load adjustment strategy.

7. The method according to claim 6, characterized in that, The target load regulation capacity of any target power user is obtained in the following manner: Obtain the actual load curve and verification load curve of any target power user during a predetermined period, wherein the verification load curve is the load curve of the power user determined in the verification phase before the predetermined period; Based on the actual load curve of any target power user, determine the predicted average load level of any target power user in the predetermined period; and based on the verification load curve of any target power user, determine the verification average load level of any target power user in the predetermined period, wherein the verification average load level is obtained by averaging multiple load points corresponding to the target period in the verification load curve; Based on the predicted average load level and the verified average load level, determine whether it is necessary to dynamically adjust the load regulation capacity of any target power user. If it is determined that the load regulation capacity of any target power user needs to be dynamically adjusted, the load regulation capacity of any target power user is adjusted based on the verification load curves corresponding to each of the multiple power users to obtain the target load regulation capacity, wherein the multiple power users are power users in the same industry as the target power user.

8. The method according to claim 7, characterized in that, The step of determining whether dynamic adjustment of the load regulation capacity of any target power user is needed based on the predicted average load level and the verification average load level includes: Based on the predicted average load level and the verified average load level, the determination of whether dynamic adjustment of the load regulation capacity of any target power user is required is made in the following manner: ； in, This represents the predicted average load level. This indicates the average load level being checked. This is the preset deviation threshold.

9. The method according to claim 7, characterized in that, When it is determined that the load regulation capacity of any target power user needs to be dynamically adjusted, the load regulation capacity of any target power user is adjusted based on the verification load curves of multiple power users in the same industry as the target power user to obtain the target load regulation capacity, including: If it is determined that the load regulation capacity of any target power user needs to be dynamically adjusted, a first number of candidate power users are determined from the plurality of power users based on the curve similarity between the verification load curves corresponding to each of the plurality of power users and the actual load curve of any target power user. Based on the amplitude similarity between the verification load curves corresponding to the first number of candidate power users and the actual load curves of any target power user, a second number of candidate power users is determined from the first number of candidate power users, wherein the second number is less than the first number; The target load regulation capacity is obtained based on the expected load regulation capacity of each of the second number of candidate power users.

10. The method according to claim 9, characterized in that, The process of obtaining the target load regulation capacity based on the expected load regulation capacity corresponding to each of the second number of candidate power users includes: The average of the expected load regulation capabilities corresponding to each of the second number of candidate power users is taken as the target load regulation capability; or Determine the weight value corresponding to each of the second number of candidate power users; perform a weighted calculation based on the expected load regulation capacity corresponding to each of the second number of candidate power users and the corresponding weight value to obtain the target load regulation capacity.

11. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method for determining a load regulation strategy based on multi-objective optimization as described in any one of claims 1 to 10.

Images