A method and system for quantifying time-shifted load under dynamic incentives for time-of-use pricing

By constructing a dynamic incentive index model and utilizing genetic algorithms and PLO optimization algorithms, the targets of renewable energy consumption and peak-valley difference are coordinated, solving the problem of inaccurate time-shifted load quantification in existing technologies, and achieving the effects of grid load optimization and cost reduction.

CN123121471APending Publication Date: 2026-11-17CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510602663.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-12
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing optimization algorithms have failed to effectively coordinate objectives such as renewable energy consumption and reducing peak-valley differences, resulting in inaccurate time-shifted load quantification results under time-of-use pricing incentives.

Method used

A dynamic incentive index model is constructed based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio, and user demand response willingness. The optimization model is solved using genetic algorithm and PLO optimization algorithm to determine the optimal time-shifted load and establish constraints for reducing load peak-valley difference, improving renewable energy utilization rate, and power grid balance.

Benefits of technology

To optimize electricity consumption for customers who purchase electricity through agents, reduce environmental governance costs and generation costs, decrease the peak-valley load difference in the power grid, and improve power grid stability and customer satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123121471A_ABST
    Figure CN123121471A_ABST
Patent Text Reader

Abstract

A method and system for quantifying time-shifted load under dynamic incentives for time-of-use pricing includes: constructing a dynamic incentive index model based on historical grid operation data, user electricity consumption behavior data, grid reserve capacity ratio, and user demand response willingness; determining the price incentive intensity for different time periods based on the dynamic incentive index model; and solving the pre-constructed optimization model using a genetic algorithm and a PLO optimization algorithm based on the price incentive intensity for different time periods to obtain the optimal time-shifted load. The pre-constructed optimization model includes an objective function that minimizes the electricity consumption cost on the user side and the peak-valley difference of the grid load curve. This invention, based on price incentives, maximizes the optimization of electricity consumption by proxy-purchased users, minimizes environmental governance costs, reduces generation costs on the generation side, and minimizes the peak-valley difference of the grid load, thus resolving the coordination and contradictions involved in the optimization design of the dynamic incentive mechanism for time-of-use pricing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of information technology, specifically to a method and system for quantifying time-shifted load under dynamic incentives for time-of-use electricity pricing. Background Technology

[0002] For users who do not yet purchase electricity directly from the electricity market, power grid companies act as agents for electricity purchase. The scale of this agency-purchase market is expanding, meaning that an increase in the number of users purchasing electricity through agents implies that more load can be aggregated, creating economies of scale and implying significant adjustment potential. The time-of-use pricing dynamic adjustment mechanism is an important incentive mechanism in the electricity market. It plays a crucial role in ensuring stable grid operation and reducing electricity costs. For optimizing the time-of-use pricing dynamic incentive mechanism, different constraints affect the incentive of the demand response model. Under constraints based on renewable energy consumption and generation costs, finding the optimal control scheme for demand response under different constraints is the most important issue.

[0003] Many current optimization algorithms operate separately on objectives such as renewable energy consumption and peak-valley reduction. However, in real-world power system operation scenarios, these objectives are not isolated; they exhibit both consistent synergistic effects and conflicting constraints. More importantly, the achievement of these objectives is closely and complexly linked to time-shifted load and electricity price incentive mechanisms, a crucial connection often overlooked by existing algorithms, leading to inaccurate time-shifted load quantification results under electricity price incentives. Summary of the Invention

[0004] To address the problem that many current optimization algorithms neglect the close and complex intrinsic relationship between the achievement process of renewable energy consumption and peak-valley difference reduction and time-shifted load and electricity price incentive mechanisms, leading to inaccurate time-shifted load quantification results under electricity price incentives, this invention proposes a time-shifted load quantification method under dynamic time-of-use pricing incentives, comprising:

[0005] A dynamic incentive index model is constructed based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio, and user demand response willingness. The intensity of electricity price incentives for different time periods is determined based on the dynamic incentive index model.

[0006] Based on the electricity price incentive intensity for different time periods, a genetic algorithm and a PLO optimization algorithm are used to solve the pre-built optimization model to obtain the optimal time-shifted load.

[0007] The pre-built optimization model includes an objective function that aims to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

[0008] Optionally, the dynamic incentive indicator model constructed based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio, and user demand response willingness includes:

[0009] Based on historical power grid operation data and user electricity consumption behavior data, price sensitivity analysis is conducted to establish dynamic incentive indicators for time-of-use electricity pricing.

[0010] Based on the proportion of grid reserve capacity and users' willingness to respond to demand, the dynamic incentive indicators for time-of-use pricing are optimized to obtain a dynamic incentive indicator model.

[0011] Optionally, the construction of the optimization model includes:

[0012] The optimization objective is to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

[0013] Set constraints for the optimization objective;

[0014] An optimization model is constructed based on the optimization objective and the constraints.

[0015] Optionally, the constraints include at least one of the following: constraints aimed at reducing the load peak-valley difference, constraints aimed at improving the utilization of renewable energy, electricity balance constraints, and constraints aimed at minimizing electricity consumption costs.

[0016] Optionally, the optimization objective is as follows:

[0017] Z1=min(L TOU ·P ToU )

[0018] Z2=min(maxL ToU -minL ToU )

[0019] Among them, L ToU For the load of customers who purchase electricity through agents after the time-of-use pricing incentive; P ToU Z1 represents the time-of-use electricity price; Z2 represents the electricity consumption cost; Z3 represents the peak-to-valley difference in the grid load curve; and maxL represents the peak-to-valley difference. ToU For the largest agent-purchased electricity load after the time-of-use pricing incentive, minL ToU This represents the minimum load of the agent-purchased electricity user after the time-of-use pricing incentive.

[0020] Optionally, the optimal time-shifted load is obtained by solving a pre-built optimization model using a genetic algorithm and a PLO optimization algorithm based on the electricity price incentive intensity for different time periods, including:

[0021] Step 1: Based on the electricity price incentive intensity for different time periods, a genetic algorithm is used to transform the multi-objective function in the pre-built optimization model into a single-objective function;

[0022] Step 2: Use the PLO optimization algorithm to solve the constraints in the single objective function and the pre-built optimization model to generate preliminary time-of-use electricity price optimization results;

[0023] Step 3: Determine whether the preliminary time-of-use pricing optimization results meet the set equilibrium conditions. If they do, proceed to Step 4; otherwise, based on the degree of impact of the preliminary time-of-use pricing optimization results on actual operation, use robustness analysis to adjust the parameters in the optimization model and return to Step 1.

[0024] Step 4: Use the preliminary time-of-use pricing optimization results as the final time-of-use pricing optimization results;

[0025] The time-of-use pricing optimization results include the optimal time-shifted load and the user-side cost of purchasing electricity.

[0026] Optionally, the parameters in the optimization model are adjusted using robustness analysis methods based on the impact of the preliminary time-of-use pricing optimization results on actual operation, including:

[0027] Based on the preliminary time-of-use pricing optimization results, relevant user-side and grid-side response data are extracted, and the impact of the time-of-use pricing optimization results on actual operation is quantified through deviation analysis.

[0028] When the reduction in electricity consumption costs does not reach the set threshold or does not meet the physical constraints of the power grid, the parameters in the optimization model are adjusted using a robustness analysis method based on the impact of the time-of-use pricing optimization results on actual operation.

[0029] Optionally, the electricity price incentive intensity based on different time periods uses a genetic algorithm to transform the multi-objective function in the pre-built optimization model into a single-objective function, including:

[0030] The genetic algorithm is used to calculate the weights of the target total user electricity expenditure and the target peak-valley difference of the power grid load curve in the optimization model;

[0031] Based on the target of total user electricity expenditure and the target of peak-valley difference in grid load curve, a single objective function is obtained by weighting and summing their respective weights.

[0032] Furthermore, this invention also provides a time-shifted load quantization system under dynamic time-of-use pricing incentives, comprising:

[0033] The incentive intensity module is used to build a dynamic incentive index model based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio and user demand response willingness, and to determine the electricity price incentive intensity for different time periods based on the dynamic incentive index model.

[0034] The optimization module is used to solve the pre-built optimization model based on the electricity price incentive intensity for different time periods using genetic algorithms and PLO optimization algorithms to obtain the optimal time-shifted load.

[0035] The pre-built optimization model includes an objective function that aims to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

[0036] Optionally, the excitation intensity module is specifically used for:

[0037] Based on historical power grid operation data and user electricity consumption behavior data, price sensitivity analysis is conducted to establish dynamic incentive indicators for time-of-use electricity pricing.

[0038] Based on the proportion of grid reserve capacity and users' willingness to respond to demand, the dynamic incentive indicators for time-of-use pricing are optimized to obtain a dynamic incentive indicator model.

[0039] Optionally, a model building module is also included for:

[0040] The optimization objective is to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

[0041] Set constraints for the optimization objective;

[0042] An optimization model is constructed based on the optimization objective and the constraints.

[0043] Optionally, the constraints include at least one of the following: constraints aimed at reducing the load peak-valley difference, constraints aimed at improving the utilization of renewable energy, electricity balance constraints, and constraints aimed at minimizing electricity consumption costs.

[0044] Optionally, the optimization objective is as follows:

[0045] Z1=min(L TOU ·P ToU )

[0046] Z2=min(maxL ToU -minL ToU )

[0047] Among them, L ToU For the load of customers who purchase electricity through agents after the time-of-use pricing incentive; P ToU Z1 represents the time-of-use electricity price; Z2 represents the electricity consumption cost; and Z3 represents the peak-to-valley difference in the grid load curve. maxL ToU For the largest agent-purchased electricity load after the time-of-use pricing incentive, minL ToU This represents the minimum load of the agent-purchased electricity user after the time-of-use pricing incentive.

[0048] Optionally, the optimization module is specifically used for:

[0049] Step 1: Based on the electricity price incentive intensity for different time periods, a genetic algorithm is used to transform the multi-objective function in the pre-built optimization model into a single-objective function;

[0050] Step 2: Use the PLO optimization algorithm to solve the constraints in the single objective function and the pre-built optimization model to generate preliminary time-of-use electricity price optimization results;

[0051] Step 3: Determine whether the preliminary time-of-use pricing optimization results meet the set equilibrium conditions. If they do, proceed to Step 4; otherwise, based on the degree of impact of the preliminary time-of-use pricing optimization results on actual operation, use robustness analysis to adjust the parameters in the optimization model and return to Step 1.

[0052] Step 4: Use the preliminary time-of-use pricing optimization results as the final time-of-use pricing optimization results;

[0053] The time-of-use pricing optimization results include the optimal time-shifted load and the user-side cost of purchasing electricity.

[0054] Optionally, the specific steps for adjusting the parameters in the optimization model using robust analysis methods, based on the impact of the preliminary time-of-use pricing optimization results on actual operation, include:

[0055] Based on the preliminary time-of-use pricing optimization results, relevant user-side and grid-side response data are extracted, and the impact of the time-of-use pricing optimization results on actual operation is quantified through deviation analysis.

[0056] When the reduction in electricity consumption costs does not reach the set threshold or does not meet the physical constraints of the power grid, the parameters in the optimization model are adjusted using a robustness analysis method based on the impact of the time-of-use pricing optimization results on actual operation.

[0057] Optionally, the specific steps for transforming the multi-objective function in the pre-built optimization model into a single-objective function using a genetic algorithm to optimize the electricity price incentive intensity based on different time periods include:

[0058] The genetic algorithm is used to calculate the weights of the target total user electricity expenditure and the target peak-valley difference of the power grid load curve in the optimization model;

[0059] Based on the target of total user electricity expenditure and the target of peak-valley difference in grid load curve, a single objective function is obtained by weighting and summing their respective weights.

[0060] In another aspect, this application also provides an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0061] The memory is used to store one or more programs;

[0062] When the one or more programs are executed by the at least one processor, a time-shifted load quantization method under time-of-use pricing dynamic incentives as described above is implemented.

[0063] Furthermore, this application also provides a readable storage medium on which an executable program is stored, which, when executed, implements the time-shifted load quantization method under time-of-use pricing dynamic incentive as described above.

[0064] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0065] This invention provides a method for quantifying time-shifted load under dynamic incentives for time-of-use pricing, comprising: constructing a dynamic incentive index model based on historical grid operation data, user electricity consumption behavior data, grid reserve capacity ratio, and user demand response willingness; determining the price incentive intensity for different time periods based on the dynamic incentive index model; and solving the pre-constructed optimization model using a genetic algorithm and a PLO optimization algorithm based on the price incentive intensity for different time periods to obtain the optimal time-shifted load. The pre-constructed optimization model includes an objective function with the goal of minimizing electricity consumption costs on the user side and the peak-valley difference in the grid load curve. Based on price incentives, this invention maximizes the optimization of electricity consumption by proxy-purchased users, minimizes environmental governance costs, reduces generation costs on the generation side, and minimizes the peak-valley difference in grid load, thus resolving the coordination and contradictions involving multiple technical aspects in the optimization design of dynamic incentive mechanisms for time-of-use pricing in existing technologies. Attached Figure Description

[0066] Figure 1 This is a flowchart of a time-shifted load quantification method under dynamic incentive of time-of-use electricity pricing according to the present invention;

[0067] Figure 2 This is a schematic diagram of the time-shifted load quantization method based on the PLO optimization algorithm under the dynamic incentive of time-of-use electricity pricing according to the present invention;

[0068] Figure 3 This is a schematic diagram of an electronic device structure according to the present invention. Detailed Implementation

[0069] To promote the development of agency-based electricity purchase, the urgent task is to optimize electricity consumption for agency-based electricity purchasers by utilizing the dynamic incentive mechanism of time-of-use pricing. The dynamic adjustment mechanism of time-of-use pricing is an important incentive mechanism in the electricity market. It plays a crucial role in ensuring the stable operation of the power grid and reducing electricity costs. For optimizing the dynamic incentive mechanism of time-of-use pricing, different constraints affect the incentive of the demand response model. Under constraints based on renewable energy consumption and generation costs, the most important issue is to optimize the participation in demand response under different constraints and find the optimal control scheme. Currently, many optimization algorithms operate separately on objectives such as renewable energy consumption and reducing peak-valley differences, without unifying the operation of multiple consistent or conflicting objectives. Therefore, some objectives can be placed under constraints, and then the solution can be executed. The Polar Lights Optimization (PLO) algorithm can then be used to optimize different constraint parameters to obtain the optimal control scheme.

[0070] This invention proposes a time-shifted load quantification method under dynamic incentives for time-of-use pricing. This method aims to maximize the optimization of electricity consumption by proxy buyers, minimize environmental governance costs, reduce generation costs on the generation side, and minimize the peak-valley difference in grid load, while achieving electricity price incentives. The method establishes detailed constraints to reduce peak-valley load, improve the utilization rate of renewable energy, maintain power balance, and prevent increases in generation costs. These constraints encompass multiple optimization objectives incorporated into the control scheme. Simultaneously, the PLO optimization algorithm is used to find the optimal time-shifted load quantification scheme by using the electricity cost of proxy buyers as the objective function. This method demonstrates good applicability, economic efficiency, and social benefits for both enterprise and regional applications.

[0071] To better understand the present invention, the following description, in conjunction with the accompanying drawings and embodiments, will further illustrate the content of the present invention.

[0072] Example 1:

[0073] A method for quantifying time-shifted load under dynamic incentives for time-of-use pricing, such as Figure 1 As shown, it includes:

[0074] Step S1: Construct a dynamic incentive index model based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio, and user demand response willingness; determine the intensity of electricity price incentives for different time periods based on the dynamic incentive index model.

[0075] Step S2: Based on the electricity price incentive intensity for different time periods, the pre-built optimization model is solved using a genetic algorithm and a PLO optimization algorithm to obtain the optimal time-shifted load.

[0076] The pre-built optimization model includes an objective function that aims to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

[0077] The following is a further explanation of each step:

[0078] Step S1: Construct a dynamic incentive index model based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio, and user demand response willingness. Determine the intensity of electricity price incentives for different time periods based on the dynamic incentive index model, including:

[0079] Based on historical power grid operation data and user electricity consumption behavior data, price sensitivity analysis is conducted to establish dynamic incentive indicators for time-of-use electricity pricing.

[0080] Based on the proportion of grid reserve capacity and users' willingness to respond to demand, the dynamic incentive indicators for time-of-use pricing are optimized to obtain a dynamic incentive indicator model.

[0081] Step S1 specifically includes:

[0082] S101. Obtain historical power grid operation data and user electricity consumption behavior data, extract load fluctuation characteristic parameters and user load curve characteristics, and establish a dynamic incentive index for time-of-use pricing through price sensitivity analysis. Obtain historical power grid operation data and user electricity consumption behavior data, and extract load fluctuation characteristic parameters using time series analysis. For the extracted load fluctuation characteristic parameters, use a clustering algorithm to classify user load curves, obtaining load curve characteristics for different user groups. Based on the load curve characteristics, use regression analysis to quantify user price sensitivity, obtaining price sensitivity coefficients for each user group. Combine the price sensitivity coefficients and load curve characteristics to establish a dynamic incentive index for time-of-use pricing, determining the price incentive intensity for different time periods. Combine the dynamic incentive index for time-of-use pricing with power grid operation data, and use an optimization algorithm to calculate the optimal time-of-use pricing scheme. Match the optimal time-of-use pricing scheme with user electricity consumption behavior data to determine the load regulation effect after the scheme is implemented. Based on the load regulation effect, adjust the model parameters of the dynamic incentive index for time-of-use pricing to optimize the implementation effect of the time-of-use pricing scheme.

[0083] Specifically, acquiring historical power grid operation data and user electricity consumption behavior data is fundamental to analyzing load fluctuations and user electricity consumption characteristics. For example, a power grid company collected electricity consumption data for a certain area over the past year through smart meters, including total hourly load and user electricity consumption, totaling 8760 hours of data. Using the K-means clustering algorithm to analyze user load curves, users were divided into three categories: daytime peak, nighttime off-peak, and balanced. For instance, daytime peak users consumed 60% of their total electricity between 10 AM and 4 PM, while nighttime off-peak users consumed 70% between 10 PM and 6 AM the following day. Regarding load fluctuation characteristics, Fast Fourier Transform (FFT) was used to extract the frequency characteristics of the load curves, revealing that the main fluctuation period is 24 hours, with an amplitude range of 5000 kW to 15000 kW. Through price sensitivity analysis, the Logit model was used to calculate user response to electricity prices, finding that for every 1 yuan decrease in electricity price, daytime peak users' electricity consumption increased by 5%, while nighttime off-peak users' electricity consumption increased by 8%. Based on the above analysis, a time-of-use electricity price dynamic incentive index model is established, setting the daytime peak electricity price at 8 yuan and the nighttime off-peak electricity price at 4 yuan. By optimizing the electricity price strategy through linear programming, the peak-valley difference of the power grid load is reduced by 15%, while the user's electricity cost is reduced by 10%.

[0084] S102. Based on the accuracy and practicality parameters in the time-of-use electricity price dynamic incentive index model, and taking into account factors such as the proportion of grid reserve capacity and user demand response willingness, determine the balance point between accuracy and practicality, adjust and optimize the key parameters of the time-of-use electricity price dynamic incentive index, and obtain the dynamic incentive index model.

[0085] Based on the grid value, obtain the current reserve and demand values, and calculate the reserve ratio. Use the reserve ratio and user responsiveness to determine the degree of matching between the grid value and the demand value. If the matching degree is lower than a preset threshold, adjust the accuracy and usability parameters in the incentive value. During the adjustment of accuracy and usability parameters, determine the balance point between them. Based on the balance point, optimize the key parameter values ​​in the incentive value. Recalculate the model value using the optimized parameter values. Obtain the optimized model value to obtain the final dynamic incentive index model.

[0086] Specifically, in determining the balance between accuracy and practicality, a mathematical model is first established through correlation analysis between the grid reserve capacity ratio and user demand response willingness. Assuming a regional grid reserve capacity ratio of 10% and user demand response willingness of 70%, the balance point is calculated using a weighted average algorithm: Balance Point = (Reserve Capacity Ratio × 0.6) + (Demand Response Willingness × 0.4), yielding a balance point of 34%. Next, based on the balance point, key parameters of the dynamic incentive index are adjusted and optimized. A gradient descent algorithm is used to iteratively update the parameters, with a learning rate of 0.01. After 100 iterations, the optimized dynamic incentive index model is obtained. During model optimization, historical data is incorporated, such as a monthly grid load fluctuation range of 5% to 15% and a user response rate of 65% to 75%. Regression analysis is used to verify the model's effectiveness, ensuring that the optimized model achieves the best balance between accuracy and practicality. Finally, the optimized model was applied to actual power grid dispatch. Through simulation tests, the results showed that the error rate of the model in predicting power grid reserve demand was reduced to 3%, and the user response rate was increased to 72%, which significantly improved the stability of power grid operation and user satisfaction.

[0087] The process preceding step S2 includes constructing an optimization model, which comprises:

[0088] The optimization objective is to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

[0089] Set constraints for the optimization objective;

[0090] An optimization model is constructed based on the optimization objective and the constraints.

[0091] The constraints include at least one of the following: constraints aimed at reducing the load peak-valley difference, constraints aimed at improving the utilization of renewable energy, electricity balance constraints, and constraints aimed at minimizing electricity consumption costs.

[0092] Furthermore, the optimization objective is shown in the following formula:

[0093] Z1=min(L TOU ·P ToU )

[0094] Z2=min(maxL ToU -minL ToU )

[0095] Among them, L ToU For the load of customers who purchase electricity through agents after the time-of-use pricing incentive; P ToU Z1 represents the time-of-use electricity price, Z2 represents the peak-to-valley difference in the grid load curve, and maxL represents the peak-to-valley difference in the grid load curve. ToUFor the largest agent-purchased electricity load after the time-of-use pricing incentive, minL ToU This represents the minimum load of the agent-purchased electricity user after the time-of-use pricing incentive.

[0096] The specific steps for constructing the optimization model are as follows:

[0097] With the electricity cost of users purchasing electricity through agents and the peak-valley difference of the power grid load curve as optimization objectives, and considering the impact of the energy efficiency level of users' electrical equipment on electricity expenses, a multi-objective optimization problem is constructed. In order to address the conflict between user costs and power grid stability, weight coefficients are set in the objective function.

[0098] Obtain electricity cost, electricity consumption, and time information from users' historical electricity usage data. Calculate the power grid load curve based on electricity consumption and time information to obtain the peak-valley difference. Extract equipment energy efficiency values ​​from the equipment database and calculate the energy efficiency level in conjunction with electricity consumption. Employ a multi-objective optimization algorithm, using electricity cost and peak-valley difference as objective values ​​and energy efficiency level as constraints. Weight electricity cost and peak-valley difference using preset weight values ​​to obtain the optimization point. If the optimization point satisfies the balance between cost and stability, the final solution is output. Generate an equipment power dispatch plan based on the optimization results and adjust the load distribution.

[0099] Specifically, when constructing a multi-objective optimization problem, it is first necessary to clarify the electricity-side costs, namely, the total electricity expenditure of the user and the peak-to-valley difference of the power grid load curve. Assume a user's monthly electricity expenditure is 1000 yuan, and the peak-to-valley difference of the power grid load curve is 500 kilowatts. To optimize both objectives simultaneously, a weighted summation method can be used to integrate the two objective functions into a single comprehensive objective function. Let the weight coefficient for the total electricity expenditure of the user be α, and the weight coefficient for the peak-to-valley difference of the power grid load curve be β, and α + β = 1. Through historical data analysis, assuming α = 0.7 and β = 0.3, the comprehensive objective function is F = 0.7 × electricity expenditure + 0.3 × peak-to-valley difference. Next, consider the impact of the energy efficiency level of the user's electrical equipment on electricity expenditure. Through energy efficiency level calculations, the contribution ratio of each type of equipment to electricity expenditure can be obtained. Based on these contribution ratios, the electricity consumption strategy for each type of equipment can be further adjusted to reduce the total electricity expenditure. For example, through an intelligent control system, the air conditioner's operating time can be reduced from 12 hours to 10 hours per day, the refrigerator's cooling power from 200 watts to 180 watts, and the lighting brightness adjusted from 100% to 80%. After optimization, the user's total electricity cost is expected to decrease to 900 yuan, and the peak-to-valley difference in the power grid load curve will be reduced to 450 kilowatts. Ultimately, by adjusting weighting coefficients and optimizing electricity consumption strategies, a balance between user costs and power grid stability is achieved, realizing the goal of multi-objective optimization.

[0100] Step 1: Establish dynamic incentive indicators for time-of-use pricing: First, based on the time-of-use pricing mechanism, obtain the objective function and decision variables, which are the user-side cost of purchasing electricity through an agent and the peak, mid-peak, flat, and valley electricity prices for time-of-use pricing.

[0101] Step 2: Define the objective function for the user-side cost of electricity purchase through an agent and the peak-to-valley difference of the grid load curve:

[0102] Z1=min(L TOU ·P ToU (1)

[0103] Z2=min(maxL ToU -minL ToU (2)

[0104] Among them, L ToU For the load of customers who purchase electricity through agents after the time-of-use pricing incentive; P ToU Z1 is the time-of-use electricity price; Z2 is the peak-valley load difference; maxL is the peak-valley load difference. ToU For the largest agent-purchased electricity load after the time-of-use pricing incentive, minL ToU This represents the minimum load of the agent-purchased electricity user after the time-of-use pricing incentive.

[0105] Among them, T s T p T f T v These represent different time periods of load, namely sharp, peak, flat, and valley.

[0106] Electricity price P i Determined by time period:

[0107]

[0108] Among them, P s P p P f P v T represents the electricity price during different time periods: sharp, peak, flat, and valley. i This refers to the i-th time period.

[0109] The decision variable is the time-shifted load L. Time-shifting :

[0110] L Time-shifting =L ToU -L0(4)

[0111] Among them, L ToUL0 represents the load of agent-purchased electricity users in each time period after optimization for time-of-use pricing incentives; L0 represents the load of agent-purchased electricity users in each time period before optimization for time-of-use pricing incentives.

[0112] Step 3: Establish constraints for different optimization objectives

[0113] (1) Establish constraints on the goal of increasing the use of renewable energy:

[0114]

[0115] in, and Let i represent the electricity consumption of the j-th renewable energy source in the i-th time period before and after the implementation of time-of-use pricing incentive optimization, respectively. Let i be the time period number, T be the total number of time periods, j be the renewable energy source number, and R be the total number of renewable energy sources.

[0116] (2) Electrical balance constraints:

[0117]

[0118] in, This refers to the electricity consumption of various users in the i-th time period before the time-of-use pricing incentive optimization. This refers to the electricity consumption of various users in the i-th time period after time-of-use pricing incentive optimization, ensuring energy balance and preventing an increase in total energy consumption.

[0119] (3) Establish constraints with the goal of minimizing electricity consumption costs:

[0120] C T ≤P r Q r +P c Q c (7)

[0121] Among them, C T For electricity consumption costs, Q r and Q c It is the total electricity consumption of renewable energy and thermal power generation after the implementation of time-of-use pricing optimization, P r and P c It is the guiding electricity price for renewable energy and thermal power generation.

[0122] Step S2: Based on the electricity price incentive intensity for different time periods, the pre-built optimization model is solved using a genetic algorithm and a PLO optimization algorithm to obtain the optimal time-shifted load, including:

[0123] Step 1: Based on the electricity price incentive intensity for different time periods, a genetic algorithm is used to transform the multi-objective function in the pre-built optimization model into a single-objective function;

[0124] Step 2: Use the PLO optimization algorithm to solve the constraints in the single objective function and the pre-built optimization model to generate preliminary time-of-use electricity price optimization results;

[0125] Step 3: Determine whether the preliminary time-of-use pricing optimization results meet the set equilibrium conditions. If they do, proceed to Step 4; otherwise, based on the degree of impact of the preliminary time-of-use pricing optimization results on actual operation, use robustness analysis to adjust the parameters in the optimization model and return to Step 1.

[0126] Step 4: Use the preliminary time-of-use pricing optimization results as the final time-of-use pricing optimization results;

[0127] The time-of-use pricing optimization results include the optimal time-shifted load and the user-side cost of purchasing electricity.

[0128] The specific implementation steps of step S2 are as follows:

[0129] The constructed multi-objective optimization problem is solved using genetic algorithms and PLO algorithms to generate preliminary time-of-use pricing optimization results. The results are then used to determine whether the results reduce the electricity costs for users while also reducing grid load volatility, thus meeting the dual objectives of grid stability requirements and user economic needs.

[0130] A multi-objective optimization model is constructed using a genetic algorithm. The model includes two optimization objectives: electricity consumption cost and grid load peak-valley difference, referred to as electricity cost and load fluctuation. Historical grid load data and user electricity consumption data are obtained as input data for the model. The genetic algorithm iteratively solves the problem to obtain preliminary time-of-use pricing optimization results. Based on the optimization results, user electricity costs and grid load fluctuation indices are calculated. If both electricity consumption costs and load fluctuation decrease, the result is considered to satisfy both objectives. If neither is simultaneously satisfied, the parameters of the genetic algorithm are adjusted and the solution is recalculated. The final output is a time-of-use pricing optimization scheme that satisfies both grid stability and user economic requirements.

[0131] Specifically, when using a genetic algorithm to solve a multi-objective optimization problem, the fitness function must first be defined to simultaneously consider user electricity costs and grid load fluctuations. For example, the user electricity cost function is set as Cuser = Σ(Pt × Et), where Pt is the electricity price at time t and Et is the electricity consumption at time t. The grid load fluctuation function is defined as Ffluctuation = Σ|Lt - Laaverage|, where Lt is the grid load at time t and Laaverage is the average load. Through weighted summation, the fitness function is F = α × Cuser + β × Ffluctuation, where α and β are weight coefficients, with values ​​of 0.6 and 0.4, respectively. In the genetic algorithm, the initial population size is set to 100, and each individual represents an electricity price scheme, represented by binary encoding. The crossover probability and mutation probability are set to 0.8 and 0.2, respectively. After 50 generations of iteration, the algorithm converges, obtaining the optimal electricity price scheme. The analysis results show that the user's electricity cost decreased from the initial 1000 yuan to 800 yuan, and the grid load fluctuation decreased from the initial 200MW to 150MW. This indicates that the optimization scheme effectively reduced grid load fluctuation while lowering the user's electricity cost, meeting both grid stability requirements and user economic needs. To further verify the results, Monte Carlo simulation was introduced, randomly generating 1000 sets of electricity consumption data and repeating the above optimization process. The results show that the stability and economy of the optimization scheme were maintained, further demonstrating the effectiveness of the genetic algorithm in solving multi-objective optimization problems.

[0132] like Figure 2 As shown, the PLO algorithm steps are as follows:

[0133] (1): Initialize the PLO algorithm:

[0134] Set parameters and initialize the population: Set the population size to N and the maximum number of iterations to Max_iterations;

[0135] (2): Run the PLO algorithm to optimize the objective function of electricity purchase cost and peak-valley difference of grid load curve, and find the optimal peak-valley electricity price parameters for time-of-use pricing;

[0136] (3): Calculate the optimal time-of-use electricity price dynamic incentive optimization operation scheme under the optimal cost by using the optimized quantities under different constraints;

[0137] The specific steps of the Aurora Optimization Algorithm (PLO) are as follows:

[0138] Step 1. Population Initialization

[0139] The population size is set to N, and each particle represents a set of time-shifting load allocation schemes. The particle dimension is D (corresponding to the time-shifting load in different time periods). The position vector of the i-th particle is represented as X.i =[x i1 ,x i2 ,…,x iD ], where i = 1, 2, ..., N, x i1 x i2 x iD Let represent the positions of the i-th particle in dimensions 1, 2, and D, respectively, where D is a positive integer. The initial positions of the particles are randomly generated within the search space.

[0140]

[0141] Where, x ij Let X be the position of the i-th particle in dimension j. j max and X j min , , are the minimum and maximum values ​​of the j-th dimension variable, respectively, and rand(0,1) is a random number in the interval [0,1].

[0142] Step 2. Speed ​​Initialization

[0143] The initial velocity vector V of the i-th particle i =[v i1 ,v i2 ,…,v iD ],v i1 v i2 v iD These are the velocities of the i-th particle in dimensions 1, 2, and D, respectively, and are also randomly generated. The velocity range can typically be set based on the size of the search space, as shown in the following formula:

[0144]

[0145] Among them, v ij Let V be the velocity of the i-th particle in dimension j. j max and V j min , which are the minimum and maximum values ​​of the velocity in the j-th dimension, respectively.

[0146] Step 3. Fitness Assessment

[0147] Define the fitness function f(X) as the peak and trough of the electricity cost for the agent-purchased electricity user and the grid load curve. For each particle X i Calculate its fitness value F i =f(X) i ), F i Let f(X) be the fitness value of the i-th particle. i Let be the fitness function of the i-th particle, and record the historical best position P of each particle. i(Initial time P) i =X i And the global optimal position G (initially the position of the particle with the smallest fitness value).

[0148] Step 4. Particle Motion Update:

[0149] The formulas for updating the particle's position and velocity from generation t to generation t+1 are as follows:

[0150]

[0151] in, The velocity of the particle in generation t+1. Let t be the velocity of the particle. This represents the historical optimal position of the t-generation particle. Let G be the position of particle t. t Let ω be the global optimal position of the particle in generation t; ω is the inertial weight, used to control the influence of the particle's previous velocity on its current velocity, typically ranging from [0.4, 0.9], and can employ a linear decreasing strategy; c1 and c2 are learning factors, typically ranging from [1.5, 2], representing the particle's ability to learn from its historical optimal position and global optimal position, respectively; r1 and r2 are random numbers, taking values ​​from [0, 1]; β is the time-of-use electricity price influence coefficient, used to adjust the degree of influence of time-of-use electricity prices on particle velocity; ΔE t It is the time-of-use electricity price change vector in generation t.

[0152] The position update formula is as follows:

[0153]

[0154] in, This represents the position of the particle in generation t+1.

[0155] Step 5. Boundary Treatment

[0156] After updating the particle position, it is necessary to check if the particle has exceeded the boundary of the search space. If it has, its position is restricted to within the boundary:

[0157]

[0158] In the formula, Let j be the position of the i-th particle in generation t+1. Let be the minimum value of the position of the j-th dimensional particle. is the maximum value of the position of the j-th dimension particle.

[0159] Step 6. Retrospective assessment

[0160] Evaluation criteria are established as a benchmark for measuring success. The best performance is monitored and selected to identify the most outstanding particles, thereby driving their motion. The selection process is as follows:

[0161]

[0162]

[0163] Among them, X t+1 i Let X be the i-th particle in the (t+1)-th iteration; X i X is the i-th particle; best i For the best individual particle in the collision process, f(X) new(i) Let f(X) be the fitness function of the i-th particle in the new iteration. i Let X be the fitness function of the i-th particle. new(i) For a new generation of particles.

[0164] If the initial optimization results fail to balance user costs and grid stability, the weight coefficients representing the two optimization objectives in the objective function are adjusted, some constraints are relaxed in a targeted manner, and the genetic algorithm is used again to solve the problem until a time-of-use pricing optimization result that balances the dual objectives is generated.

[0165] Obtain the preliminary optimized time-of-use pricing and corresponding user cost and grid stability data to determine if it meets the preset balance criteria. If it does not meet the balance criteria, adjust the weight coefficients of user cost and grid stability indicators in the objective function and record the adjustment values. Based on the adjusted weight coefficients, identify the parts of the constraints that have a significant impact on balance and modify the constraints using a relaxation strategy. Under the modified objective function and constraints, rerun the genetic algorithm to obtain a new time-of-use pricing optimization result. Compare the new optimization result with the preset criteria to determine if user cost and grid stability have reached a balance. If not, repeat the weight coefficient adjustment and constraint relaxation process until the balance criteria are met. Finally, generate a time-of-use pricing optimization scheme that balances user cost and grid stability, completing the solution process.

[0166] Specifically, if the initial optimization results show that user electricity costs and grid stability have not reached an equilibrium, these two optimization objectives can be rebalanced by adjusting the weight coefficients in the objective function. For example, the weight coefficient for user costs can be adjusted from the initial 0.6 to 0.5, while the weight coefficient for grid stability can be increased from 0.4 to 0.5 to ensure that both have equal importance in the optimization process. Subsequently, some constraints are appropriately relaxed, such as widening the allowable range for grid load fluctuations from ±5% to ±8%, to increase the flexibility of the optimization scheme. Based on this, a genetic algorithm is used to solve the problem again, setting the population size to 100, the number of iterations to 500, the crossover probability to 8%, and the mutation probability to 1%. The algorithm gradually approaches the optimal solution by simulating the processes of natural selection, crossover, and mutation. During the algorithm's operation, the changes in the objective function value are monitored in real time. When the comprehensive score of user costs and grid stability tends to be balanced, the final time-of-use pricing optimization result is output. For example, the optimized peak-hour electricity price is 2 yuan / kWh, the average-hour price is 8 yuan / kWh, and the off-peak price is 4 yuan / kWh. This can effectively reduce users' electricity costs, ensure the stability of the power grid load, and avoid the risk to the power grid operation caused by excessive fluctuations in electricity prices.

[0167] By using robustness analysis methods, considering the uncertainties of key factors such as the range of electricity price adjustments and user willingness to respond, the corresponding parameters in the optimization model are adjusted, and the optimization solution is re-solved on the basis of taking into account uncertainties, so as to obtain robust time-of-use electricity price optimization results.

[0168] Historical electricity price data and user electricity consumption data are acquired to establish an electricity price optimization model, defining model variables and constraints. Monte Carlo simulation is used to generate multiple sets of random samples of electricity price adjustments and user response rates, which are then input into the optimization model for solution. The objective function value is calculated based on the optimization results; if the objective function value fluctuates beyond a preset threshold, the model parameters are adjusted and the solution is repeated. Support vector regression is used to fit the optimization results and predict user response rates under different electricity price adjustments. Users are grouped according to their response rates using cluster analysis, and differentiated electricity price adjustment ranges are set for different groups. Based on robust optimization theory, an uncertainty set considering both the electricity price adjustment range and user response willingness is constructed, and a robust optimal solution is obtained. Deep learning algorithms are used to train the electricity price optimization model, yielding robust time-of-use electricity price optimization results that take into account uncertainties.

[0169] Specifically, in the robustness analysis method, the uncertainty of the electricity price adjustment range needs to be determined first. Assuming the price adjustment range is between 2 and 8 yuan, 1000 sets of random electricity price data are generated using Monte Carlo simulation. Next, considering the uncertainty of user response intentions, a fuzzy logic method is used to model user response intentions, setting the fuzzy membership function of response intentions as a triangular distribution with parameters of 3, 5, and 7. Based on these uncertainties, a robust optimization model is constructed, with the objective function being to minimize the total cost. Constraints include the electricity price adjustment range, user response intentions, and the balance of electricity supply and demand. A genetic algorithm is used for optimization, setting the population size to 100, the number of iterations to 200, the crossover probability to 8%, and the mutation probability to 1%. Through multiple iterations, robust time-of-use electricity price optimization results are obtained, for example, an electricity price of 75 yuan during peak hours and 25 yuan during off-peak hours. Finally, the stability of the optimization results was verified through sensitivity analysis. The results showed that even with a 10% fluctuation in the range of electricity price adjustments and user willingness to respond, the optimization results still maintained high robustness, with the total cost fluctuation within ±5%.

[0170] Extract the final time-of-use pricing scheme and response load data from the robust optimization results, evaluate the overall effectiveness of the scheme in balancing user costs and grid stability, and determine the optimal dynamic incentive implementation strategy for time-of-use pricing.

[0171] Using time-of-use pricing and response load data from the robust optimization results, time-of-use pricing schemes and response load data are extracted. The overall effectiveness of the time-of-use pricing scheme is evaluated using user-side costs and grid stability indicators. The balance between user-side costs and grid stability is determined based on the overall effectiveness. The optimal implementation method of the dynamic incentive strategy is determined using the dynamism in the optimization results. The matching relationship between the time-of-use pricing scheme and response load data is obtained through extraction and evaluation methods. The dynamic incentive strategy of the time-of-use pricing scheme is adjusted based on the matching relationship. The optimization effect of the dynamic incentive strategy on user costs and grid stability is verified using the overall effectiveness and balance.

[0172] Specifically, firstly, a robust optimization algorithm is used to solve the time-of-use pricing scheme. The objective function of the optimization model is assumed to be minimizing the total grid cost, with constraints including user load fluctuation range and grid stability indicators. A genetic algorithm is used, with a population size of 100, 500 iterations, a crossover probability of 8%, and a mutation probability of 2%. The optimization results in a set of time-of-use pricing schemes, for example, a peak-hour price of 2 yuan / kWh, an off-peak price of 8 yuan / kWh, and a low-peak price of 5 yuan / kWh. Next, response load data is extracted, assuming a 10% reduction in user load during peak hours, a 5% reduction during off-peak hours, and a 15% increase during low-peak hours. Then, the overall effect of the scheme in balancing user costs and grid stability is evaluated using a multi-objective evaluation method, calculating a user cost saving rate of 8% and a grid stability indicator improvement of 12%. Finally, the optimal dynamic incentive implementation strategy for time-of-use pricing is determined. Based on a fuzzy logic control method, the price adjustment frequency is set to once per hour, with an adjustment range not exceeding 1 yuan / kWh, ensuring the stability and effectiveness of the scheme in actual operation.

[0173] This invention belongs to the field of time-shifted load quantification technology under dynamic time-of-use pricing incentives. It provides a method for quantifying time-shifted load under time-of-use pricing incentives in a multi-objective optimization context. Since multiple objectives exhibit both consistency and conflict, unified constraints are needed to address these issues. For complex constraints, the PLO optimization algorithm is employed, achieving good optimization results and yielding the optimal operating scheme. This invention not only encourages the adoption of renewable energy but also reduces generation costs while optimizing electricity consumption for purchasing agents. Furthermore, it helps stabilize grid load, thus bringing mutually beneficial results to all stakeholders within the power system.

[0174] This invention provides a method for time-shifted load quantization under dynamic time-of-use pricing based on the PLO optimization algorithm, mainly comprising:

[0175] Acquire historical power grid operation data and user electricity consumption behavior data, extract load fluctuation characteristic parameters and user load curve characteristics, and establish dynamic incentive indicators for time-of-use electricity prices through price sensitivity analysis;

[0176] With the user-side cost of purchasing electricity through agents and the peak-valley difference of the power grid load curve as optimization objectives, and taking into account the impact of electricity price incentives, a multi-objective optimization problem is constructed to address issues such as optimizing electricity consumption for users purchasing electricity through agents and reducing environmental governance costs.

[0177] We extract parametric equations to improve the utilization rate of renewable energy, balance the power supply, and prevent the increase in power generation costs. These equations are used as constraints for the optimization problem to ensure that the optimization results meet the actual power grid operation requirements and user electricity demand.

[0178] The constructed multi-objective optimization problem is solved using genetic algorithms and PLO optimization algorithms to generate preliminary time-of-use pricing optimization results. The results are then used to determine whether the results reduce the electricity costs for users while also reducing grid load volatility, thus meeting the dual objectives of grid stability requirements and user economic needs.

[0179] If the initial optimization results fail to balance the electricity consumption cost and grid stability, the weight coefficients representing the two optimization objectives in the objective function are adjusted, some constraints are relaxed in a targeted manner, and the genetic algorithm is used again to solve the problem until a time-of-use electricity price optimization result that balances the dual objectives is generated.

[0180] Based on the optimized time-of-use pricing scheme, the corresponding user-side and grid-side response data are extracted. The impact of the optimization results on actual operation is quantified through deviation analysis. If the reduction in user electricity costs and grid operating costs does not meet expectations, or the risk of violating grid physical constraints increases, it is determined that robustness analysis needs to be further introduced.

[0181] By using robustness analysis methods, considering the uncertainties of key factors such as the range of electricity price adjustments and users' willingness to respond, the corresponding parameters in the optimization model are adjusted, and the optimization solution is re-solved on the basis of taking into account the uncertainties, so as to obtain robust time-of-use electricity price optimization results.

[0182] Extract the final time-of-use pricing scheme and response load data from the robust optimization results, evaluate the overall effectiveness of the scheme in balancing user costs and grid stability, and determine the optimal dynamic incentive implementation strategy for time-of-use pricing.

[0183] Example 2:

[0184] Based on the same inventive concept, this invention also provides a time-shifted load quantization system under dynamic time-of-use pricing incentives, comprising:

[0185] The incentive intensity module is used to build a dynamic incentive index model based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio and user demand response willingness, and to determine the electricity price incentive intensity for different time periods based on the dynamic incentive index model.

[0186] The optimization module is used to solve the pre-built optimization model based on the electricity price incentive intensity for different time periods using genetic algorithms and PLO optimization algorithms to obtain the optimal time-shifted load.

[0187] The pre-built optimization model includes an objective function that aims to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

[0188] Optionally, the excitation intensity module is specifically used for:

[0189] Based on historical power grid operation data and user electricity consumption behavior data, price sensitivity analysis is conducted to establish dynamic incentive indicators for time-of-use electricity pricing.

[0190] Based on the proportion of grid reserve capacity and users' willingness to respond to demand, the dynamic incentive indicators for time-of-use pricing are optimized to obtain a dynamic incentive indicator model.

[0191] Optionally, a model building module is also included for:

[0192] The optimization objective is to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

[0193] Set constraints for the optimization objective;

[0194] An optimization model is constructed based on the optimization objective and the constraints.

[0195] The constraints include: constraints aimed at reducing the load peak-valley difference, constraints aimed at improving the utilization of renewable energy, electricity balance constraints, and constraints aimed at minimizing electricity consumption costs.

[0196] Optionally, the optimization objective is as follows:

[0197] Z1=min(L TOU ·P ToU )

[0198] Z2=min(maxL ToU -minL ToU )

[0199] Among them, L ToU For the load of customers who purchase electricity through agents after the time-of-use pricing incentive; P ToU Z1 is the time-of-use electricity price; Z2 is the peak-valley load difference; maxL is the peak-valley load difference. ToU For the largest agent-purchased electricity load after the time-of-use pricing incentive, minL ToU This represents the minimum load of the agent-purchased electricity user after the time-of-use pricing incentive.

[0200] Optionally, the optimization module is specifically used for:

[0201] Step 1: Based on the electricity price incentive intensity for different time periods, a genetic algorithm is used to transform the multi-objective function in the pre-built optimization model into a single-objective function;

[0202] Step 2: Use the PLO optimization algorithm to solve the constraints in the single objective function and the pre-built optimization model to generate preliminary time-of-use electricity price optimization results;

[0203] Step 3: Determine whether the preliminary time-of-use pricing optimization results meet the set equilibrium conditions. If they do, proceed to Step 4; otherwise, based on the degree of impact of the preliminary time-of-use pricing optimization results on actual operation, use robustness analysis to adjust the parameters in the optimization model and return to Step 1.

[0204] Step 4: Use the preliminary time-of-use pricing optimization results as the final time-of-use pricing optimization results;

[0205] The time-of-use pricing optimization results include the optimal time-shifted load and the user-side cost of purchasing electricity.

[0206] Optionally, the specific steps for adjusting the parameters in the optimization model using robust analysis methods, based on the impact of the preliminary time-of-use pricing optimization results on actual operation, include:

[0207] Based on the preliminary time-of-use pricing optimization results, relevant user-side and grid-side response data are extracted, and the impact of the time-of-use pricing optimization results on actual operation is quantified through deviation analysis.

[0208] When the reduction in electricity consumption costs does not reach the set threshold or does not meet the physical constraints of the power grid, the parameters in the optimization model are adjusted using a robustness analysis method based on the impact of the time-of-use pricing optimization results on actual operation.

[0209] Optionally, the optimization module uses a genetic algorithm to transform the multi-objective function in the pre-built optimization model into a single-objective function based on the electricity price incentive intensity for different time periods. Specific implementation steps include:

[0210] The genetic algorithm is used to calculate the weights of the target total user electricity expenditure and the target peak-valley difference of the power grid load curve in the optimization model;

[0211] Based on the target of total user electricity expenditure and the target of peak-valley difference in grid load curve, a single objective function is obtained by weighting and summing their respective weights.

[0212] Example 3

[0213] like Figure 3 As shown, the present invention also provides an electronic device, which may be a computer device, a microcontroller device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, processor, and transceiver component are connected via a bus; the memory can be used to store executable programs, and an exemplary executable program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, which can be accessed and / or modified when instructions are executed.

[0214] The processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and it is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the storage medium to implement the corresponding method flow or corresponding function, so as to realize the steps of the time-shifted load quantization method under the time-sharing electricity price dynamic incentive in the above embodiments.

[0215] Example 4

[0216] Based on the same inventive concept, this invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory). This readable storage medium is a memory device within an electronic device used to store programs and data. It is understood that the storage medium here can include both built-in storage media within the electronic device and extended storage media supported by the electronic device. The storage medium provides storage space, which stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more executable programs (including program code). It should be noted that the storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. Loading and executing one or more instructions stored in the storage medium by the processor can implement the steps of the time-shifted load quantization method under dynamic time-of-use pricing in the above embodiments.

[0217] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0218] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0219] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0220] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0221] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of the claims of the present invention pending approval.

Claims

1. A method for quantifying time-shifted load under dynamic incentives for time-of-use pricing, characterized in that, include: A dynamic incentive index model is constructed based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio, and user demand response willingness. The intensity of electricity price incentives for different time periods is determined based on the dynamic incentive index model. Based on the electricity price incentive intensity for different time periods, a genetic algorithm and a PLO optimization algorithm are used to solve the pre-built optimization model to obtain the optimal time-shifted load. The pre-built optimization model includes an objective function that aims to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

2. The method as described in claim 1, characterized in that, The dynamic incentive indicator model, constructed based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio, and user demand response willingness, includes: Based on historical power grid operation data and user electricity consumption behavior data, price sensitivity analysis is conducted to establish dynamic incentive indicators for time-of-use electricity pricing. Based on the proportion of grid reserve capacity and users' willingness to respond to demand, the dynamic incentive indicators for time-of-use pricing are optimized to obtain a dynamic incentive indicator model.

3. The method as described in claim 1, characterized in that, The construction of the optimization model includes: The optimization objective is to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve. Set constraints for the optimization objective; An optimization model is constructed based on the optimization objective and the constraints.

4. The method as described in claim 3, characterized in that, The constraints include at least one of the following: constraints aimed at reducing the peak-valley load difference, constraints aimed at improving the utilization of renewable energy, electricity balance constraints, and constraints aimed at minimizing electricity consumption costs.

5. The method as described in claim 4, characterized in that, The optimization objective is shown in the following formula: Z1=min(L TOU ·P ToU ) Z2=min(maxL ToU -minL ToU ) Among them, L ToU For the load of customers who purchase electricity through agents after the time-of-use pricing incentive; P ToU Z1 represents the time-of-use electricity price; Z2 represents the electricity consumption cost; Z3 represents the peak-to-valley difference in the grid load curve; and maxL represents the peak-to-valley difference. ToU For the largest agent-purchased electricity load after the time-of-use pricing incentive, minL ToU This represents the minimum load of the agent-purchased electricity user after the time-of-use pricing incentive.

6. The method as described in claim 3, characterized in that, The electricity price incentive intensity based on different time periods is solved using a genetic algorithm and a PLO optimization algorithm on a pre-built optimization model to obtain the optimal time-shifted load, including: Step 1: Based on the electricity price incentive intensity for different time periods, a genetic algorithm is used to transform the multi-objective function in the pre-built optimization model into a single-objective function; Step 2: Use the PLO optimization algorithm to solve the constraints in the single objective function and the pre-built optimization model to generate preliminary time-of-use electricity price optimization results; Step 3: Determine whether the preliminary time-of-use pricing optimization results meet the set equilibrium conditions. If they do, proceed to Step 4; otherwise, based on the degree of impact of the preliminary time-of-use pricing optimization results on actual operation, use robustness analysis to adjust the parameters in the optimization model and return to Step 1. Step 4: Use the preliminary time-of-use pricing optimization results as the final time-of-use pricing optimization results; The time-of-use pricing optimization results include the optimal time-shifted load and the user-side cost of purchasing electricity.

7. The method as described in claim 6, characterized in that, The impact of the preliminary time-of-use pricing optimization results on actual operation is assessed using robustness analysis to adjust the parameters in the optimization model, including: Based on the preliminary time-of-use pricing optimization results, relevant user-side and grid-side response data are extracted, and the impact of the time-of-use pricing optimization results on actual operation is quantified through deviation analysis. When the reduction in electricity consumption costs does not reach the set threshold or does not meet the physical constraints of the power grid, the parameters in the optimization model are adjusted using a robustness analysis method based on the impact of the time-of-use pricing optimization results on actual operation.

8. The method as described in claim 6, characterized in that, The electricity price incentive intensity based on different time periods uses a genetic algorithm to transform the multi-objective function in the pre-built optimization model into a single-objective function, including: The genetic algorithm is used to calculate the weights of the target total user electricity expenditure and the target peak-valley difference of the power grid load curve in the optimization model; Based on the target of total user electricity expenditure and the target of peak-valley difference in grid load curve, a single objective function is obtained by weighting and summing their respective weights.

9. A time-shifted load quantization system under dynamic time-of-use pricing incentives, characterized in that, include: The incentive intensity module is used to build a dynamic incentive index model based on historical power grid operation data, user electricity consumption behavior data, power grid reserve capacity ratio and user demand response willingness, and to determine the electricity price incentive intensity for different time periods based on the dynamic incentive index model. The optimization module is used to solve the pre-built optimization model based on the electricity price incentive intensity for different time periods using genetic algorithms and PLO optimization algorithms to obtain the optimal time-shifted load. The pre-built optimization model includes an objective function that aims to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve.

10. The system as described in claim 9, characterized in that, The excitation intensity module is specifically used for: Based on historical power grid operation data and user electricity consumption behavior data, price sensitivity analysis is conducted to establish dynamic incentive indicators for time-of-use electricity pricing. Based on the proportion of grid reserve capacity and users' willingness to respond to demand, the dynamic incentive indicators for time-of-use pricing are optimized to obtain a dynamic incentive indicator model.

11. The system as described in claim 9, characterized in that, It also includes a model building module for: The optimization objective is to minimize electricity consumption costs and the peak-to-valley difference in the grid load curve. Set constraints for the optimization objective; An optimization model is constructed based on the optimization objective and the constraints.

12. The system as claimed in claim 11, characterized in that, The constraints include at least one of the following: constraints aimed at reducing the peak-valley load difference, constraints aimed at improving the utilization of renewable energy, electricity balance constraints, and constraints aimed at minimizing electricity consumption costs.

13. The system as described in claim 11, characterized in that, The optimization objective is shown in the following formula: Z1=min(L TOU ·P ToU ) Z2=min(maxL ToU -minL ToU ) Among them, L ToU For the load of customers who purchase electricity through agents after the time-of-use pricing incentive; P ToU Z1 represents the time-of-use electricity price; Z2 represents the electricity consumption cost; Z3 represents the peak-to-valley difference in the grid load curve; and maxL represents the peak-to-valley difference. ToU For the largest agent-purchased electricity load after the time-of-use pricing incentive, minL ToU This represents the minimum load of the agent-purchased electricity user after the time-of-use pricing incentive.

14. The system as described in claim 9, characterized in that, The optimization module is specifically used for: Step 1: Based on the electricity price incentive intensity for different time periods, a genetic algorithm is used to transform the multi-objective function in the pre-built optimization model into a single-objective function; Step 2: Use the PLO optimization algorithm to solve the constraints in the single objective function and the pre-built optimization model to generate preliminary time-of-use electricity price optimization results; Step 3: Determine whether the preliminary time-of-use pricing optimization results meet the set equilibrium conditions. If they do, proceed to Step 4; otherwise, based on the degree of impact of the preliminary time-of-use pricing optimization results on actual operation, use robustness analysis to adjust the parameters in the optimization model and return to Step 1. Step 4: Use the preliminary time-of-use pricing optimization results as the final time-of-use pricing optimization results; The time-of-use pricing optimization results include the optimal time-shifted load and the user-side cost of purchasing electricity.

15. The system as described in claim 14, characterized in that, The optimization module, based on the impact of preliminary time-of-use pricing optimization results on actual operation, employs robust analysis methods to adjust the parameters in the optimization model. Specific implementation steps include: Based on the preliminary time-of-use pricing optimization results, relevant user-side and grid-side response data are extracted, and the impact of the time-of-use pricing optimization results on actual operation is quantified through deviation analysis. When the reduction in electricity consumption costs does not reach the set threshold or does not meet the physical constraints of the power grid, the parameters in the optimization model are adjusted using a robustness analysis method based on the impact of the time-of-use pricing optimization results on actual operation.

16. The system as described in claim 14, characterized in that, The optimization module uses a genetic algorithm to transform the multi-objective function in the pre-built optimization model into a single-objective function based on the electricity price incentive intensity for different time periods. The specific implementation steps include: The genetic algorithm is used to calculate the weights of the target total user electricity expenditure and the target peak-valley difference of the power grid load curve in the optimization model; Based on the target of total user electricity expenditure and the target of peak-valley difference in grid load curve, a single objective function is obtained by weighting and summing their respective weights.

17. An electronic device, characterized in that, include: At least one processor and memory; The memory and processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, a time-shifted load quantization method under time-of-use pricing dynamic incentive as described in any one of claims 1 to 8 is implemented.

18. A readable storage medium, characterized in that, It contains an execution program, which, when executed, implements a time-shifted load quantization method under dynamic incentive of time-of-use electricity pricing as described in any one of claims 1 to 8.