Comprehensive energy demand response scheduling method and platform for smart grid

Abstract

The present invention discloses a comprehensive energy demand response scheduling method and platform for smart grids, which relates to the field of energy management technology. The method includes: predicting user load demand through a future time zone window, and establishing a comprehensive energy demand scheduling space based on multi-energy collaborative scheduling; forming a better scheduling space by modeling K energy supply units and combining the power grid energy scheduling evaluation channel for initial optimization and variation expansion optimization; introducing an energy scheduling optimization operator, deeply optimizing the scheduling space, obtaining a comprehensive energy demand scheduling strategy, and performing dynamic response scheduling. The present invention solves the technical problems in the prior art of lacking efficient collaborative scheduling of multiple energy types and accurate adaptation capabilities to dynamic user load demands, resulting in low energy utilization efficiency and insufficient scheduling flexibility, and achieves the technical effect of improving energy utilization efficiency and scheduling flexibility through multi-energy collaborative optimization and dynamic response scheduling.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to a comprehensive energy demand response scheduling method and platform for smart grids. Background Art

[0002] With the rapid development of energy diversification and smart grid technology, traditional single-energy dispatch methods are no longer able to meet the increasingly complex user load demands and the requirements for coordinated multi-energy supply. Existing technologies often lack a unified optimization mechanism for dispatching multiple energy supply units (such as thermal power, photovoltaic power, wind power, and energy storage), making it difficult to balance energy efficiency, dispatch flexibility, and carbon emission targets. Furthermore, the volatility of load demand and the instability of renewable energy further complicate dispatching, leading to imbalanced energy distribution and delayed dispatch response. Summary of the Invention

[0003] This application provides a comprehensive energy demand response scheduling method and platform for smart grids, which is used to solve the technical problems in the existing technology that lack efficient coordinated scheduling of multiple energy types and precise adaptation to dynamic user load demands, resulting in low energy utilization efficiency and insufficient scheduling flexibility.

[0004] The first aspect of the present application provides a comprehensive energy demand response scheduling method for smart grids, the method comprising: performing load forecasting on the user side of the power grid according to a future time zone window to determine the user load demand, wherein the power grid includes K energy supply units, the energy types of the K energy supply units are different, and K is a positive integer greater than 1; performing multi-energy collaborative scheduling on the K energy supply units according to the user load demand to establish a first space for comprehensive energy demand scheduling; modeling the K energy supply units to generate a multi-energy supply integrated model, and combining the power grid energy scheduling evaluation channel An initial optimization search is performed on the first space of the comprehensive energy demand scheduling to obtain a second space of the comprehensive energy demand scheduling; based on the power grid energy scheduling evaluation channel, the second space of the comprehensive energy demand scheduling is mutated and expanded for optimization according to the power grid energy scheduling variation function to generate a third space of the comprehensive energy demand scheduling; the first optimization operator of the power grid energy scheduling and the second optimization operator of the power grid energy scheduling are introduced to perform a deep optimization search on the third space of the comprehensive energy demand scheduling to obtain a comprehensive energy demand scheduling strategy; based on the user load demand, the K energy supply units are response-scheduled according to the comprehensive energy demand scheduling strategy.

[0005] The second aspect of the present application provides an integrated energy demand response scheduling platform for smart grids, the platform comprising: a user-side load prediction module, the user-side load prediction module is used to perform load prediction on the user side of the power grid according to the future time zone window, and determine the user load demand, wherein the power grid includes K energy supply units, the energy types of the K energy supply units are different, and K is a positive integer greater than 1; a scheduling first space generation module, the scheduling first space generation module is used to perform multi-energy coordinated scheduling of the K energy supply units according to the user load demand, and establish a comprehensive energy demand scheduling first space; a scheduling second space generation module, the scheduling second space generation module is used to model according to the K energy supply units, generate a multi-energy supply integration model, and combine the power grid energy scheduling The degree evaluation channel performs initial optimization on the first space of the comprehensive energy demand scheduling to obtain the second space of the comprehensive energy demand scheduling; the scheduling third space generation module is used to perform mutation, expansion and optimization on the second space of the comprehensive energy demand scheduling based on the power grid energy scheduling evaluation channel and the power grid energy scheduling variation function to generate the third space of the comprehensive energy demand scheduling; the scheduling strategy optimization module is used to introduce the first optimization operator of the power grid energy scheduling and the second optimization operator of the power grid energy scheduling to perform deep optimization on the third space of the comprehensive energy demand scheduling to obtain the comprehensive energy demand scheduling strategy; the response scheduling module is used to perform response scheduling on the K energy supply units according to the comprehensive energy demand scheduling strategy based on the user load demand.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The integrated energy demand response scheduling method and platform for smart grids provided in this application relate to the field of energy management technology. Through user load forecasting and multi-energy coordinated scheduling, an integrated energy scheduling space is constructed, and initial optimization and variation expansion optimization are performed in combination with multi-energy supply modeling and power grid evaluation channels. By introducing deep optimization of the optimization operator, an integrated energy demand scheduling strategy is generated, and ultimately efficient response scheduling of K energy supply units is achieved. This solves the technical problems in the existing technology of lacking efficient coordinated scheduling of multiple energy types and accurate adaptation to dynamic user load demands, resulting in low energy utilization efficiency and insufficient scheduling flexibility. It achieves the technical effect of improving energy utilization efficiency and scheduling flexibility through multi-energy coordinated optimization and dynamic response scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A flow chart of a comprehensive energy demand response scheduling method for smart grids provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of the structure of an integrated energy demand response scheduling platform for smart grids provided in an embodiment of the present application.

[0011] Explanation of the accompanying drawings: user-side load prediction module 11, scheduling first space generation module 12, scheduling second space generation module 13, scheduling third space generation module 14, scheduling strategy optimization module 15, response scheduling module 16. DETAILED DESCRIPTION

[0012] This application provides a comprehensive energy demand response scheduling method and platform for smart grids, which is used to solve the technical problems in the existing technology that lack efficient coordinated scheduling of multiple energy types and precise adaptation to dynamic user load demands, resulting in low energy utilization efficiency and insufficient scheduling flexibility.

[0013] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0014] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0015] Example 1, as Figure 1As shown, the present application provides a comprehensive energy demand response scheduling method for smart grids, the method comprising:

[0016] P10: Perform load forecasting on the user side of the power grid based on a future time zone window to determine the user load demand, wherein the power grid includes K energy supply units, the K energy supply units have different energy types, and K is a positive integer greater than 1.

[0017] Specifically, load forecasting is performed on the grid user side of electricity demand based on a future time window, ultimately determining the user's load demand. The future time window is a pre-defined future time range (such as hours, days, or weeks) used to predict user electricity demand trends within that timeframe. This load forecast for future time zones allows for a pre-defined understanding of user energy demand characteristics, providing data support and decision-making for subsequent multi-energy coordinated scheduling.

[0018] The power grid consists of K energy supply units, each of which uses a different type of energy. These units may include, for example, traditional thermal power generation units, wind power generation units, photovoltaic power generation units, and energy storage units. K is a positive integer greater than 1, indicating the diversity of energy types and the number of supply units in the power grid. This diversified energy supply system enables the power grid to coordinate the dispatch of multiple energy sources and lays the foundation for the subsequent optimization of energy resource allocation.

[0019] For example, to accurately forecast user load demand, historical user electricity usage data must first be analyzed to identify patterns in load demand, such as peak and off-peak periods, and consumption patterns during special holidays. These patterns can be extracted using time series analysis models such as ARIMA and Prophet models, or deep learning models such as LSTM (Long Short-Term Memory) networks. These methods can capture complex load trends and potential seasonal fluctuations. Furthermore, to further improve forecast accuracy, external factors can be incorporated, such as weather conditions (e.g., the impact of temperature on heating and cooling demand), policy adjustments (e.g., the impact of energy-saving and emission-reduction policies on industrial electricity consumption), and social events (e.g., short-term surges in electricity demand caused by large-scale events). Furthermore, through mathematical statistical analysis of user behavior, such as residential users' daily electricity usage habits or industrial users' production patterns, load forecasts can be further refined to meet the demand forecasting requirements of different user types.

[0020] The results of the load forecast are presented in numerical form, covering user load demand in various time periods within the future time zone, and may be further broken down into the demand for different energy types, thereby providing accurate user demand information for the integrated energy scheduling of the power grid, supporting the multi-energy coordinated optimization in subsequent steps, and improving the efficiency and reliability of energy distribution.

[0021] P20: Perform multi-energy coordinated scheduling on the K energy supply units according to the user load demand, and establish a first space for comprehensive energy demand scheduling.

[0022] Optionally, multi-energy coordinated scheduling can be performed on the K energy supply units in the power grid based on user load demand, thereby constructing the first space for comprehensive energy demand scheduling. The K energy supply units here refer to the various energy supply devices or systems in the power grid, such as thermal power generation, photovoltaic power generation, wind power generation, and energy storage units. These units have different energy types and provide the power grid with diverse energy supply capabilities.

[0023] The core goal of multi-energy coordinated scheduling is to optimize the scheduling strategy for each energy source based on user load demand, taking into account factors such as the power generation characteristics, energy efficiency, operating costs, and environmental impact of different energy supply units. During the scheduling process, it is necessary to maximize user satisfaction, reduce scheduling costs, and achieve efficient energy utilization.

[0024] For example, scheduling begins with establishing an accurate user load demand forecast model to provide detailed energy demand distribution data. Next, K energy supply units are modeled, defining each unit's output capacity, response speed, operating constraints (such as upper and lower load limits), and economic and environmental costs. All units are then jointly optimized using a scheduling algorithm (such as linear programming, nonlinear programming, genetic algorithms, or reinforcement learning-based methods) to ensure that the multi-energy system works collaboratively to meet demand.

[0025] During this process, the first space for comprehensive energy demand scheduling is constructed as a multidimensional solution space encompassing multiple parameters, including user load demand, energy supply unit status, power generation costs, and energy type ratios. This solution space can be defined through mathematical modeling (such as constrained optimization models) to identify the optimal scheduling solution while satisfying constraints (such as user demand, equipment capacity limitations, and environmental requirements). Furthermore, to improve scheduling efficiency and accuracy, real-time data feedback is required, such as the current operating status of each energy unit, weather information, and load trends. By incorporating this real-time information into the scheduling model, energy allocation strategies can be dynamically adjusted to further optimize operational performance.

[0026] By implementing this step, the power grid can construct a preliminary dispatch solution space (i.e., the first space for integrated energy demand dispatch), providing foundational data for optimization and expansion in subsequent steps. The establishment of this space marks the official launch of multi-energy coordinated dispatch, a crucial step in integrated energy management.

[0027] P30: Modeling is performed based on the K energy supply units to generate a multi-energy supply integration model, and initial optimization is performed on the first space of comprehensive energy demand scheduling in combination with the power grid energy scheduling evaluation channel to obtain the second space of comprehensive energy demand scheduling.

[0028] Furthermore, step P30 in the embodiment of the present application further includes:

[0029] P31: According to the first space of the comprehensive energy demand scheduling, extract the first decision of the comprehensive energy demand scheduling; P32: Based on the multi-energy energy supply integration model and the power grid energy dispatching evaluation channel, evaluate the first decision of the comprehensive energy demand scheduling to obtain the first energy dispatching evaluation result; P33: Determine whether the first energy dispatching evaluation result meets the energy dispatching evaluation constraints, wherein the energy dispatching evaluation constraints include power supply quality evaluation constraints, power supply efficiency evaluation constraints, energy dispatching loss evaluation constraints and power grid dispatching safety evaluation constraints; P34: If the first energy dispatching evaluation result meets the energy dispatching evaluation constraints, add the first decision of the comprehensive energy demand scheduling to the second space of the comprehensive energy demand scheduling; P35: If the first energy dispatching evaluation result does not meet the second space of the comprehensive energy demand scheduling, eliminate the first decision of the comprehensive energy demand scheduling; P36: Based on the multi-energy energy supply integration model and the power grid energy dispatching evaluation channel, continue to search and select the first space of the comprehensive energy demand scheduling according to the energy dispatching evaluation constraints to obtain the second space of the comprehensive energy demand scheduling.

[0030] It should be understood that by modeling K energy supply units, a multi-energy supply integration model is generated. This model is a mathematical framework that uniformly expresses the characteristics of multiple energy types (such as thermal power, photovoltaic power, wind power, and energy storage), covering key parameters such as the output capacity, operating cost, response speed, and environmental impact of energy units. Simultaneously, the first-phase integrated energy demand scheduling plan is analyzed in conjunction with the grid energy scheduling evaluation channel to ensure that the scheduling plan strikes a balance between performance and constraints.

[0031] For example, based on the first space of comprehensive energy demand scheduling, initial scheduling solutions are extracted as the first batch of candidate decisions. These candidate solutions are generated based on user load requirements and preliminary energy unit allocation rules and represent direct applications of the solutions in the first space. The goal of this step is to narrow the decision space and provide a relatively high-quality decision set for subsequent accurate evaluation.

[0032] Next, using the multi-energy supply integration model and the grid energy dispatch evaluation channel, a comprehensive evaluation is conducted on each extracted first decision, generating a first energy dispatch evaluation result. Evaluation criteria include power supply quality (such as voltage and frequency stability), power supply efficiency (such as energy utilization), dispatch losses (such as energy loss during transmission), and grid dispatch security (such as operational stability). This process ensures that the actual effectiveness of the dispatch plan meets the comprehensive goals of the grid.

[0033] Next, each dispatch plan is evaluated based on energy dispatch evaluation constraints to determine if it meets the requirements. These constraints include: power supply quality evaluation constraints, which ensure the stability of user power demand in terms of voltage, frequency, and other aspects; power supply efficiency evaluation constraints, which can be used to optimize energy efficiency; energy dispatch loss evaluation constraints, which can be used to reduce energy losses during transmission and dispatch; and grid dispatch security evaluation constraints, which ensure that the dispatch plan does not affect the overall security of the grid.

[0034] Furthermore, the first decision that satisfies all constraints is directly added to the second space of integrated energy demand scheduling as the optimized, high-quality scheduling solution. This ensures that the solutions in the second space have been screened and meet multi-dimensional performance requirements. If a scheduling solution fails to meet the evaluation constraints, it is eliminated from the candidate set. This decision screening process eliminates solutions that may lead to reduced power quality or inefficient scheduling, thereby further improving overall scheduling quality.

[0035] Finally, based on the multi-energy supply integration model and dispatch evaluation channel, the remaining solutions in the first space are further optimized and screened according to the energy dispatch evaluation constraints to generate a second space for comprehensive energy demand dispatch. This means that through in-depth analysis and dynamic adjustments, the solutions in the second space are ensured to optimally meet user load demands and grid performance objectives.

[0036] Through the above steps, the second space of integrated energy demand scheduling is finally formed, marking the transition from initial scheduling to optimized scheduling, and laying a solid foundation for subsequent in-depth optimization.

[0037] Furthermore, step P32 of the embodiment of the present application further includes:

[0038] P32-1: According to the first decision of the comprehensive energy demand scheduling, the multi-energy supply integration model is simulated and scheduled to obtain the first simulated energy scheduling data set; P32-2: The power grid energy scheduling evaluation channel includes a power supply quality evaluation model, a power supply efficiency evaluation model, an energy scheduling loss evaluation model and a power grid scheduling safety evaluation model; P32-3: According to the first simulated energy scheduling data set, feature recognition is performed to obtain the first power supply quality related data, the first power supply efficiency related data, the first energy scheduling loss related data and the first power grid scheduling safety related data; P32-4: The first power supply quality related data is input into the power supply quality evaluation model to obtain the first power supply quality related data. Quality evaluation coefficient; P32-5: Input the first power supply efficiency related data into the power supply efficiency evaluation model to obtain the first power supply efficiency evaluation coefficient; P32-6: Input the first energy dispatching loss related data into the energy dispatching loss evaluation model to obtain the first energy dispatching loss evaluation coefficient; P32-7: Input the first power grid dispatching safety related data into the power grid dispatching safety evaluation model to obtain the first power grid dispatching safety evaluation coefficient; P32-8: Output the first power supply quality evaluation coefficient, the first power supply efficiency evaluation coefficient, the first energy dispatching loss evaluation coefficient and the first power grid dispatching safety evaluation coefficient as the first energy dispatching evaluation result.

[0039] Optionally, the process of generating the first energy dispatch evaluation result can be further refined, and the multi-energy supply integration model can be used to simulate the dispatch, and the dispatch data can be feature identified and quantitatively evaluated through multiple evaluation models of the power grid energy dispatch evaluation channel, thereby generating a set of comprehensive evaluation coefficients to constitute a complete dispatch evaluation result.

[0040] First, a multi-energy supply integrated model is simulated based on the first decision for comprehensive energy demand scheduling, generating the first simulated energy scheduling dataset. This step uses simulation to convert the allocation of different energy units in the first decision into specific data on energy supply status, scheduling paths, and operating characteristics. These simulation results form the basis for subsequent evaluation processes.

[0041] Next, the composition of the power grid energy dispatch evaluation channel is clarified, including four core evaluation models: the power supply quality evaluation model, which is used to evaluate indicators such as voltage stability, frequency control and fluctuation range during the power supply process; the power supply efficiency evaluation model, which is used to measure energy utilization, power factor of the power grid system and the degree of optimization of resource allocation; the energy dispatch loss evaluation model, which is used to evaluate the transmission loss and system internal consumption generated by energy during the dispatch process; and the power grid dispatch safety evaluation model, which is used to analyze the reliability of the dispatch process and its impact on the overall stability of the power grid.

[0042] Next, feature identification is performed on the first simulated energy dispatch dataset to extract feature data relevant to the four evaluation models, generating first power supply quality-related data, first power supply efficiency-related data, first energy dispatch loss-related data, and first power grid dispatch security-related data. This feature data identification process can utilize feature extraction algorithms, such as principal component analysis (PCA)-based dimensionality reduction methods or deep learning feature extraction networks, to ensure that the extracted data accurately reflects the core characteristics of the simulated dispatch.

[0043] Subsequently, each type of associated data is input into the corresponding evaluation model, including inputting the first power supply quality associated data into the power supply quality evaluation model, inputting the first power supply efficiency associated data into the power supply efficiency evaluation model, inputting the first energy dispatch loss associated data into the energy dispatch loss evaluation model, and inputting the first grid dispatch safety associated data into the grid dispatch safety evaluation model, to obtain the first power supply quality evaluation coefficient, the first power supply efficiency evaluation coefficient, the first energy dispatch loss evaluation coefficient, and the first grid dispatch safety evaluation coefficient, respectively. These evaluation coefficients quantify the performance of the dispatch scheme in terms of power supply quality, efficiency, loss, and safety through the calculation results of the model. For example, the power supply quality evaluation coefficient can be calculated using a fluctuation analysis function to score the voltage stability, while the power supply efficiency evaluation coefficient is obtained through a comprehensive analysis of energy conversion efficiency and load matching.

[0044] Finally, all evaluation coefficients are aggregated and output as the primary energy dispatch evaluation results. This result is a comprehensive quantitative assessment of the dispatch plan, providing solid data support for selecting high-quality plans and optimizing dispatch strategies in subsequent steps.

[0045] P40: Based on the power grid energy dispatch evaluation channel, the second space of the comprehensive energy demand dispatch is mutated, expanded and optimized according to the power grid energy dispatch variation function to generate a third space of the comprehensive energy demand dispatch.

[0046] Furthermore, step P40 in this embodiment of the present application further includes:

[0047] P41: According to the power grid energy dispatch variation function, the variation quantity characteristics of each integrated energy demand scheduling decision in the second space of the integrated energy demand scheduling are analyzed to obtain the variation quantity of each scheduling decision; P42: Based on the user load demand, the second space of the integrated energy demand scheduling is mutated according to the variation quantity of each scheduling decision to obtain the first space of energy scheduling decision variation; P43: According to the multi-energy supply integration model and the power grid energy dispatch evaluation channel, the first space of energy scheduling decision variation is optimized and selected to establish the second space of energy scheduling decision variation; P44: According to the second space of energy dispatch decision variation, the second space of integrated energy demand scheduling is expanded to obtain the third space of integrated energy demand scheduling.

[0048] It should be understood that, based on the grid energy dispatch evaluation channel and utilizing the grid energy dispatch variation function, scheduling decisions within the second space of integrated energy demand dispatch are mutated, expanded, and optimized, thereby generating the third space of integrated energy demand dispatch. This process, by introducing appropriate mutation operations, explores more possible scheduling solutions while retaining the best solutions in the second space, thereby improving overall optimization capabilities.

[0049] First, based on the grid energy dispatch variation function, the variation characteristics of each dispatch decision within the second space of integrated energy demand dispatch are analyzed, and the number of variations for each dispatch decision is calculated. The grid energy dispatch variation function is a mathematical function that quantifies the range and frequency of changes in the energy supply characteristics of dispatch decisions. This process analyzes the adaptability and sensitivity of each dispatch plan when it is mutated by dynamically responding to user load demand, providing a basis for subsequent mutation operations.

[0050] Next, based on user load demands and the number of variations in each scheduling decision, the second space of comprehensive energy demand scheduling is mutated to generate the first space of energy scheduling decision variations. Mutations include adjusting the allocation ratio of energy units, changing scheduling paths, and modifying switching parameters between energy types. These operations can be implemented using heuristic algorithms (such as mutation operations in genetic algorithms) or rule-based dynamic adjustment strategies. By introducing mutations, potential high-quality scheduling solutions can be explored while enhancing the diversity of scheduling models.

[0051] Furthermore, after the mutation operation is complete, the multi-energy supply integrated model and the grid energy dispatch evaluation channel are used to comprehensively evaluate and optimize the first energy dispatch decision variation space, screen out high-quality solutions that meet energy dispatch objectives, and establish the second energy dispatch decision variation space. This process is similar to the initial screening of the first space, but because the mutation introduces new dispatch characteristics, the evaluation results may show higher optimization potential. Feature identification and evaluation rely on the model's efficient computing capabilities to ensure the scientific and practical nature of the variation solutions.

[0052] Finally, the high-quality solutions from the second energy scheduling decision-making variation space are integrated into the second space of comprehensive energy demand scheduling, completing the expansion of the space and forming a new third space for comprehensive energy demand scheduling. This expanded third space incorporates the excellent solutions from the original second space as well as the high-potential solutions obtained through variation, laying a broader foundation for subsequent deep optimization.

[0053] Through this step, the grid dispatching scheme is further improved in terms of stability, efficiency and flexibility, while providing rich decision-making support for the generation of the final comprehensive energy dispatching strategy.

[0054] Furthermore, step P41 of the embodiment of the present application further includes:

[0055] P41-1: According to the power grid energy dispatch evaluation channel, multiple energy dispatch evaluation results corresponding to each comprehensive energy demand dispatch decision are retrieved; P41-2: Based on the multiple energy dispatch evaluation results, a variation value evaluation is performed on each comprehensive energy demand dispatch decision to obtain a variation value coefficient of each dispatch decision; P41-3: The variation value coefficient of each dispatch decision is input into the power grid energy dispatch variation function to obtain the variation quantity of each dispatch decision, wherein the power grid energy dispatch variation function is:

[0056] ; Among them, SDN represents the number of scheduling decision variations, FLOOR refers to rounding down, SDK represents the number of scheduled variations, SXC represents the scheduling decision variation value coefficient, and SXO represents the scheduled scheduling decision variation value coefficient.

[0057] In one possible embodiment of the present application, the specific process for obtaining the number of scheduling decision variations through the grid energy scheduling evaluation channel can be further clarified. By combining the variation value assessment with the grid energy scheduling variation function, the number of variations for each scheduling decision can be determined to support subsequent variation expansion optimization.

[0058] First, according to the power grid energy dispatch evaluation channel, retrieve multiple energy dispatch evaluation results corresponding to each integrated energy demand dispatch decision. The energy dispatch evaluation results include multiple dimensions such as power supply quality, power supply efficiency, energy dispatch loss, and power grid dispatch safety, comprehensively reflecting the comprehensive performance of the current dispatch decision in energy distribution and operation efficiency. These evaluation results provide the necessary input data for the mutation value evaluation.

[0059] Next, through the analysis of multiple energy dispatch evaluation results, conduct a mutation value evaluation for each dispatch decision to generate the corresponding mutation value coefficient. The mutation value coefficient is an important indicator for quantifying the potential benefits and risks of each decision's mutation. Specifically, if a certain dispatch decision performs mediocrely in the current evaluation, its optimization potential may be improved through mutation, and the mutation value coefficient may be relatively high; conversely, for a decision with excellent performance, its mutation value coefficient may be relatively low. This evaluation process relies on weighted analysis or multi-objective optimization algorithms to convert the evaluation results of multiple dimensions into a single mutation value quantification index.

[0060] Furthermore, input the mutation value coefficient of each dispatch decision into the power grid energy dispatch mutation function to calculate its specific mutation quantity. The definition of the mutation function is as follows:

[0061] ; where SDN represents the mutation quantity of the dispatch decision, which is the output result of the function, FLOOR means rounding down, SDK represents the predetermined mutation quantity, which is the set benchmark value, SXC represents the mutation value coefficient of the dispatch decision, which is the result of the mutation value evaluation, and SXO represents the predetermined dispatch decision mutation value coefficient, which is the dispatch value standard as the benchmark.

[0062] This function dynamically adjusts the mutation quantity according to the relationship between SXC and SXO (i.e., the relative size of the current mutation value and the predetermined benchmark). When SXC < SXO, the mutation quantity decreases; when SXC = SXO, the mutation quantity remains unchanged; when SXC > SXO, the mutation quantity increases. This dynamic adjustment mechanism ensures the accuracy of the mutation operation and preferentially mutates the decisions with higher optimization potential.

[0063] Through the above steps, based on the evaluation results and mutation values of the dispatch decisions, it is possible to reasonably allocate mutation resources, avoid unnecessary computational overhead, and at the same time explore more potential high-quality dispatch schemes. This process utilizes the comprehensiveness of the evaluation channel and the flexibility of the mutation function, providing sufficient expansion space for subsequent dispatch optimization.

[0064] P50: Introduce the first optimization operator for power grid energy dispatch and the second optimization operator for power grid energy dispatch to conduct in-depth optimization of the third space of integrated energy demand dispatch, and obtain the integrated energy demand dispatch strategy.

[0065] Furthermore, step P50 in the embodiment of the present application further includes:

[0066] P51: The first optimization operator of the power grid energy dispatching includes an energy dispatching optimality threshold, and the second optimization operator of the power grid energy dispatching is carbon emission minimization; P52: According to the first optimization operator of the power grid energy dispatching, the third space of the comprehensive energy demand dispatching is optimized and selected to obtain the fourth space of the comprehensive energy demand dispatching; P53: According to the second optimization operator of the power grid energy dispatching, the fourth space of the comprehensive energy demand dispatching is optimized and analyzed to generate the comprehensive energy demand dispatching strategy.

[0067] Optionally, by introducing the first and second optimization operators for grid energy dispatch, the third space of comprehensive energy demand dispatch is deeply optimized to ultimately obtain a comprehensive energy demand dispatch strategy. This process, through the combined action of multi-dimensional optimization operators, ensures that the final dispatch strategy achieves the optimal balance between energy efficiency and environmental protection goals.

[0068] The first optimization operator for grid energy dispatch, centered around an energy dispatch optimality threshold, sets basic adaptability criteria that each dispatch solution must meet. This operator evaluates each solution's performance across multiple dimensions, including power quality, efficiency, energy loss, and grid security, to select solutions with overall adaptability exceeding the threshold, ensuring the optimized solution's high feasibility and practical value.

[0069] The second optimization operator for grid energy dispatch focuses on minimizing carbon emissions and optimizes the environmental performance of energy dispatch solutions. This operator calculates the carbon emissions of each solution and uses this as the primary objective function for optimization, ensuring that the final dispatch strategy meets load demand while minimizing carbon emissions and supporting sustainable development.

[0070] First, based on the third dimension of integrated energy demand scheduling, a preliminary optimization is performed using the first optimization operator for grid energy scheduling. This identifies solutions that meet the optimal energy scheduling threshold, generating the fourth dimension of integrated energy demand scheduling. The key to this step is ensuring that the optimized solutions meet basic requirements in terms of performance, efficiency, and safety, thereby laying a solid foundation for further optimization. The specific optimization process can be implemented using multi-objective linear programming or heuristic algorithms, where solutions that do not meet the requirements are screened and eliminated based on set thresholds.

[0071] Next, building on the fourth dimension, a second optimization operator for grid energy dispatch is introduced to conduct in-depth analysis and optimization of the carbon emissions of each option, ultimately generating a comprehensive energy demand dispatch strategy. By quantifying the carbon emission characteristics of each option and employing objective function minimization methods (such as those based on genetic algorithms or particle swarm optimization), the option with the lowest carbon emissions is identified and prioritized, ensuring that the dispatch strategy achieves both efficient energy allocation and high environmental performance.

[0072] Through the above steps, the optimized integrated energy demand scheduling strategy can effectively cope with complex and changing load demands, while minimizing the impact of energy scheduling on the environment, and achieving the dual goals of smart grid in terms of economy and sustainability.

[0073] Furthermore, step P52 of the embodiment of the present application further includes:

[0074] P52-1: Construct an energy scheduling optimal analytical function, wherein the energy scheduling optimal analytical function is:

[0075] ; Among them, ECF represents the energy scheduling optimality, exp represents the exponential function with the natural constant e as the base, WC represents the power supply quality weight, K (PQC) represents the normalized power supply quality evaluation coefficient, WE represents the power supply efficiency weight, K (PQE) represents the normalized power supply efficiency evaluation coefficient, WS represents the power grid scheduling safety weight, K (PQS) represents the normalized power grid scheduling safety evaluation coefficient, WL represents the energy scheduling loss weight, and K (PQL) represents the normalized energy scheduling loss evaluation coefficient; P52-2: Based on the energy scheduling optimality analytical function, the energy scheduling optimality of the third space of the comprehensive energy demand scheduling is calculated to obtain multiple energy scheduling optimalities; P52-3: Determine whether the multiple energy scheduling optimalities meet the first optimization operator of the power grid energy scheduling to obtain multiple decision optimality judgment results; P52-4: Based on the multiple decision optimality judgment results, screen the third space of the comprehensive energy demand scheduling to obtain the fourth space of the comprehensive energy demand scheduling.

[0076] Specifically, by constructing and utilizing an energy dispatch optimality analytical function, we can calculate and screen the optimality of the third space for comprehensive energy demand dispatch, thereby generating the fourth space for comprehensive energy demand dispatch. This process quantitatively evaluates the comprehensive performance of dispatch plans across multiple evaluation dimensions to ensure that the selected plans meet the requirements of the first optimization operator for power grid energy dispatch.

[0077] First, an analytical function for energy scheduling optimization is constructed, and its mathematical expression is: Among them, ECF represents the energy dispatching quality and is a quantitative indicator for evaluating the overall quality of each dispatching scheme. exp represents the exponential function with the natural constant e as the base, which is used to enhance the nonlinear distribution characteristics of the score. WC represents the power supply quality weight, K(PQC) represents the normalized power supply quality evaluation coefficient, WE represents the power supply efficiency weight, K(PQE) represents the normalized power supply efficiency evaluation coefficient, WS represents the grid dispatching safety weight, K(PQS) represents the normalized grid dispatching safety evaluation coefficient, WL represents the energy dispatching loss weight, and K(PQL) represents the normalized energy dispatching loss evaluation coefficient, which is used to standardize indicators of different dimensions to ensure comparability.

[0078] The construction of this function aims to balance multiple key factors and comprehensively evaluate the adaptability and optimization potential of each scheduling scheme.

[0079] Next, based on the aforementioned optimality analytical function, the optimality of each scheduling scheme in the integrated energy demand scheduling third space is calculated to obtain multiple energy scheduling optimalities. This calculation process substitutes the evaluation indicators of each scheme into the optimality function to generate the corresponding optimality value. The calculation results directly reflect the overall performance and efficiency of the scheduling scheme. The higher the optimality value, the better the overall performance of the scheme.

[0080] Furthermore, the optimality threshold set in the first optimization operator for grid energy dispatch is used to evaluate the multiple optimality values calculated, screening out dispatch solutions that meet the threshold conditions. The optimality evaluation results categorize the solutions into two categories: high-quality solutions that meet the conditions and eliminated solutions that do not. The core goal of this step is to eliminate solutions that do not meet basic adaptability requirements, providing a high-quality decision-making foundation for subsequent optimization.

[0081] Finally, based on the optimality judgment results, the third space of integrated energy demand scheduling is screened, and low-optimality solutions are eliminated, ultimately forming the fourth space of integrated energy demand scheduling. The set of solutions in the fourth space consists of solutions that meet the optimality threshold. This represents the set of scheduling strategies with outstanding performance in the current optimization stage, providing a solid foundation for deep optimization.

[0082] P60: Based on the user load demand, the K energy supply units are responsively scheduled according to the comprehensive energy demand scheduling strategy.

[0083] Optionally, based on user load demand and the optimized comprehensive energy demand scheduling strategy, K energy supply units are dispatched to ensure efficient, safe, and economical energy distribution and use while meeting user energy needs. This step is the concrete implementation of the scheduling strategy, transforming the optimization model into actual operational execution.

[0084] First, user load demand is the core basis for responsive dispatch. User load demand reflects energy requirements for a specific future time period, including load curves, peak loads, and special electricity demands. Energy resources are precisely allocated based on these demands, taking into account the intensity and distribution of demand over different time periods. The dispatch process must not only meet user energy demands but also strike a balance between energy efficiency and grid system stability.

[0085] Secondly, combined with a comprehensive energy demand scheduling strategy, K energy supply units are allocated and scheduled. The K energy supply units here refer to the various energy types within the power grid, including but not limited to thermal power, wind power, photovoltaic power generation, and energy storage units. These energy supply units have their own characteristics, such as output power, response speed, operating costs, and environmental impact. The scheduling strategy comprehensively optimizes these characteristics to set specific operating plans and output targets for each energy unit. For example, during periods of low electricity consumption, low-cost, high-efficiency energy units are prioritized for output; during peak periods, energy storage units are mobilized to participate in energy supply to alleviate load pressure.

[0086] To achieve efficient scheduling, real-time monitoring of user loads and the operating status of energy units is also required, allowing for dynamic adjustments to the scheduling plan. This real-time feedback mechanism allows for rapid adjustments to energy supply unit output based on sudden changes in load demand, such as unexpected load increases or fluctuations in renewable energy due to weather changes. For example, if photovoltaic power generation output decreases due to weather changes, energy storage units can be immediately deployed to supplement it, ensuring a balanced supply and demand.

[0087] Multi-energy synergy is a key technical support for responsive dispatch. Through coordinated dispatch, different energy units can be organically combined to leverage their respective strengths. For example, on sunny days, photovoltaic power generation is prioritized, with excess energy stored in energy storage units. At night or during peak hours, energy storage units release power to supplement power demand. Furthermore, the synergy of thermal power and renewable energy can not only meet long-term stable energy supply needs, but also reduce carbon emissions and improve the environmental friendliness of the power grid system.

[0088] Through the implementation of the comprehensive energy demand scheduling strategy, K energy supply units are responded to and scheduled, which can optimize energy utilization efficiency while meeting user load demands, ensuring the economy, safety and sustainability of power grid operation.

[0089] In summary, the embodiments of the present application have at least the following technical effects:

[0090] This application predicts user load demand through future time zone windows and establishes a comprehensive energy demand scheduling space based on multi-energy collaborative scheduling. By modeling K energy supply units, a multi-energy supply integration model is generated, and initial optimization and variation expansion optimization are performed in combination with the power grid energy scheduling evaluation channel to form a better scheduling space. Further introducing the energy scheduling optimization operator, the scheduling space is deeply optimized to obtain a comprehensive energy demand scheduling strategy, and finally the K energy supply units are dynamically responded to and scheduled according to the user load demand, so as to achieve improved energy utilization efficiency and enhanced scheduling flexibility.

[0091] The technical effect of improving energy utilization efficiency and scheduling flexibility has been achieved through multi-energy collaborative optimization and dynamic response scheduling.

[0092] Embodiment 2 is based on the same inventive concept as the integrated energy demand response scheduling method for smart grids in the above embodiment. Figure 2 As shown, this application provides a comprehensive energy demand response scheduling platform for smart grids. The platform and method embodiments in this application are based on the same inventive concept. The platform includes:

[0093] The user-side load prediction module 11 is used to perform load prediction on the user side of the power grid according to the future time zone window to determine the user load demand, wherein the power grid includes K energy supply units, the energy types of the K energy supply units are different, and K is a positive integer greater than 1.

[0094] The scheduling first space generation module 12 is used to perform multi-energy coordinated scheduling on the K energy supply units according to the user load demand, and establish a comprehensive energy demand scheduling first space.

[0095] The scheduling second space generation module 13 is used to model the K energy supply units, generate a multi-energy supply integration model, and perform initial optimization on the comprehensive energy demand scheduling first space in combination with the power grid energy scheduling evaluation channel to obtain the comprehensive energy demand scheduling second space.

[0096] The scheduling third space generation module 14 is used to mutate, expand and optimize the second space of comprehensive energy demand scheduling based on the power grid energy scheduling evaluation channel and the power grid energy scheduling variation function to generate the third space of comprehensive energy demand scheduling.

[0097] The scheduling strategy optimization module 15 is used to introduce the first optimization operator of power grid energy scheduling and the second optimization operator of power grid energy scheduling to perform deep optimization on the third space of comprehensive energy demand scheduling to obtain a comprehensive energy demand scheduling strategy.

[0098] The response scheduling module 16 is used to perform response scheduling on the K energy supply units based on the user load demand and the comprehensive energy demand scheduling strategy.

[0099] Furthermore, the scheduling second space generation module 13 is further configured to perform the following steps:

[0100] According to the first space of comprehensive energy demand scheduling, the first decision of comprehensive energy demand scheduling is extracted; based on the multi-energy energy supply integration model and the power grid energy dispatching evaluation channel, the first decision of comprehensive energy demand scheduling is evaluated to obtain a first energy dispatching evaluation result; it is judged whether the first energy dispatching evaluation result meets the energy dispatching evaluation constraints, wherein the energy dispatching evaluation constraints include power supply quality evaluation constraints, power supply efficiency evaluation constraints, energy dispatching loss evaluation constraints and power grid dispatching safety evaluation constraints; if the first energy dispatching evaluation result meets the energy dispatching evaluation constraints, the first decision of comprehensive energy demand scheduling is added to the second space of comprehensive energy demand scheduling; if the first energy dispatching evaluation result does not meet the second space of comprehensive energy demand scheduling, the first decision of comprehensive energy demand scheduling is eliminated; based on the multi-energy energy supply integration model and the power grid energy dispatching evaluation channel, the first space of comprehensive energy demand scheduling is continued to be optimized and selected according to the energy dispatching evaluation constraints to obtain the second space of comprehensive energy demand scheduling.

[0101] Furthermore, the scheduling second space generation module 13 is further configured to perform the following steps:

[0102] According to the first decision of the comprehensive energy demand scheduling, the multi-energy supply integration model is simulated and scheduled to obtain a first simulated energy scheduling data set; the power grid energy scheduling evaluation channel includes a power supply quality evaluation model, a power supply efficiency evaluation model, an energy scheduling loss evaluation model and a power grid scheduling safety evaluation model; feature recognition is performed based on the first simulated energy scheduling data set to obtain first power supply quality related data, first power supply efficiency related data, first energy scheduling loss related data and first power grid scheduling safety related data; the first power supply quality related data is input into the power supply quality evaluation model to obtain a first power supply quality evaluation coefficient; the first power supply efficiency related data is input into the power supply efficiency evaluation model to obtain a first power supply efficiency evaluation coefficient; the first energy scheduling loss related data is input into the energy scheduling loss evaluation model to obtain a first energy scheduling loss evaluation coefficient; the first power grid scheduling safety related data is input into the power grid scheduling safety evaluation model to obtain a first power grid scheduling safety evaluation coefficient; the first power supply quality evaluation coefficient, the first power supply efficiency evaluation coefficient, the first energy scheduling loss evaluation coefficient and the first power grid scheduling safety evaluation coefficient are output as the first energy scheduling evaluation result.

[0103] Furthermore, the scheduling third space generation module 14 is further configured to perform the following steps:

[0104] According to the power grid energy dispatch variation function, the variation quantity characteristics of each integrated energy demand dispatching decision in the second integrated energy demand dispatching space are analyzed to obtain the variation quantity of each dispatching decision; based on the user load demand, the second integrated energy demand dispatching space is mutated according to the variation quantity of each dispatching decision to obtain the first energy dispatching decision variation space; according to the multi-energy supply integration model and the power grid energy dispatching evaluation channel, the first energy dispatching decision variation space is optimized and selected to establish the second energy dispatching decision variation space; according to the second energy dispatching decision variation space, the second integrated energy demand dispatching space is expanded to obtain the third integrated energy demand dispatching space.

[0105] Furthermore, the scheduling third space generation module 14 is further configured to perform the following steps:

[0106] According to the power grid energy dispatch evaluation channel, multiple energy dispatch evaluation results corresponding to each comprehensive energy demand dispatch decision are retrieved; according to the multiple energy dispatch evaluation results, a variation value evaluation is performed on each comprehensive energy demand dispatch decision to obtain a variation value coefficient of each dispatch decision; the variation value coefficient of each dispatch decision is input into the power grid energy dispatch variation function to obtain the variation quantity of each dispatch decision, wherein the power grid energy dispatch variation function is: ; Among them, SDN represents the number of scheduling decision variations, FLOOR refers to rounding down, SDK represents the number of scheduled variations, SXC represents the scheduling decision variation value coefficient, and SXO represents the scheduled scheduling decision variation value coefficient.

[0107] Furthermore, the scheduling strategy optimization module 15 is further configured to perform the following steps:

[0108] The first optimization operator of the power grid energy dispatching includes an energy dispatching optimality threshold, and the second optimization operator of the power grid energy dispatching is to minimize carbon emissions; according to the first optimization operator of the power grid energy dispatching, the third space of the comprehensive energy demand dispatching is optimized and selected to obtain the fourth space of the comprehensive energy demand dispatching; according to the second optimization operator of the power grid energy dispatching, the fourth space of the comprehensive energy demand dispatching is optimized and analyzed to generate the comprehensive energy demand dispatching strategy.

[0109] Furthermore, the scheduling strategy optimization module 15 is further configured to perform the following steps:

[0110] Construct an energy scheduling optimal analytical function, wherein the energy scheduling optimal analytical function is: ; Among them, ECF represents the energy scheduling optimality, exp represents the exponential function with the natural constant e as the base, WC represents the power supply quality weight, K(PQC) represents the normalized power supply quality evaluation coefficient, WE represents the power supply efficiency weight, K(PQE) represents the normalized power supply efficiency evaluation coefficient, WS represents the power grid scheduling safety weight, K(PQS) represents the normalized power grid scheduling safety evaluation coefficient, WL represents the energy scheduling loss weight, and K(PQL) represents the normalized energy scheduling loss evaluation coefficient; based on the energy scheduling optimality analytical function, the energy scheduling optimality of the third space of the comprehensive energy demand scheduling is calculated to obtain multiple energy scheduling optimalities; it is judged whether the multiple energy scheduling optimalities meet the first optimization operator of the power grid energy scheduling to obtain multiple decision optimality judgment results; based on the multiple decision optimality judgment results, the third space of the comprehensive energy demand scheduling is screened to obtain the fourth space of the comprehensive energy demand scheduling.

[0111] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0112] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0113] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, to the extent such modifications and variations fall within the scope of the present application and its equivalents, the present application is intended to include such modifications and variations.

Claims

1. A comprehensive energy demand response scheduling method for smart grids, characterized by: The method comprises: Performing load forecasting on a user side of a power grid according to a future time zone window to determine user load demand, wherein the power grid includes K energy supply units, the K energy supply units each have a different energy type, and K is a positive integer greater than 1; Perform multi-energy coordinated scheduling on the K energy supply units according to the user load demand, and establish a first space for comprehensive energy demand scheduling; Modeling is performed based on the K energy supply units to generate a multi-energy supply integration model, and initial optimization is performed on the first space of comprehensive energy demand scheduling in combination with the power grid energy scheduling evaluation channel to obtain a second space of comprehensive energy demand scheduling; Based on the power grid energy dispatch evaluation channel, the second space of comprehensive energy demand dispatch is mutated, expanded and optimized according to the power grid energy dispatch variation function to generate a third space of comprehensive energy demand dispatch; Introducing a first optimization operator for power grid energy dispatch and a second optimization operator for power grid energy dispatch to perform deep optimization on the third space of comprehensive energy demand dispatch to obtain a comprehensive energy demand dispatch strategy; Based on the user load demand, the K energy supply units are responsively scheduled according to the comprehensive energy demand scheduling strategy; The method comprises the following steps: based on the power grid energy dispatch evaluation channel, performing mutation expansion and optimization on the second space of comprehensive energy demand dispatch according to the power grid energy dispatch variation function to generate a third space of comprehensive energy demand dispatch, including: According to the power grid energy dispatch variation function, performing a variation quantity feature analysis on each integrated energy demand dispatch decision in the second integrated energy demand dispatch space to obtain the variation quantity of each dispatch decision; Based on the user load demand, mutate the second space of comprehensive energy demand scheduling according to the number of each scheduling decision variation to obtain a first space of energy scheduling decision variation; According to the multi-energy energy supply integration model and the power grid energy dispatch evaluation channel, the first energy dispatch decision variation space is optimized and selected to establish a second energy dispatch decision variation space; Expanding the second space of comprehensive energy demand scheduling according to the second space of energy scheduling decision variation to obtain the third space of comprehensive energy demand scheduling; According to the grid energy dispatch variation function, the variation quantity characteristics of each integrated energy demand dispatch decision in the second integrated energy demand dispatch space are analyzed to obtain the variation quantity of each dispatch decision, including: Retrieving, according to the power grid energy dispatch evaluation channel, multiple energy dispatch evaluation results corresponding to each comprehensive energy demand dispatch decision; Performing a variation value evaluation on each of the comprehensive energy demand scheduling decisions based on the multiple energy scheduling evaluation results to obtain a variation value coefficient for each scheduling decision; Input the variation value coefficients of each scheduling decision into the grid energy scheduling variation function to obtain the variation quantity of each scheduling decision, wherein the grid energy scheduling variation function is: ； Among them, SDN represents the number of scheduling decision variations, FLOOR refers to rounding down, SDK represents the number of scheduled variations, SXC represents the scheduling decision variation value coefficient, and SXO represents the scheduled scheduling decision variation value coefficient.

2. The method according to claim 1, wherein Modeling is performed based on the K energy supply units to generate a multi-energy supply integration model, and initial optimization is performed on the first space of comprehensive energy demand scheduling in combination with the grid energy scheduling evaluation channel to obtain the second space of comprehensive energy demand scheduling, including: Extracting a first comprehensive energy demand scheduling decision according to the first comprehensive energy demand scheduling space; Based on the multi-energy supply integration model and the power grid energy dispatch evaluation channel, the first comprehensive energy demand dispatch decision is evaluated to obtain a first energy dispatch evaluation result; Determining whether the first energy dispatch evaluation result satisfies energy dispatch evaluation constraints, wherein the energy dispatch evaluation constraints include power supply quality evaluation constraints, power supply efficiency evaluation constraints, energy dispatch loss evaluation constraints, and power grid dispatch security evaluation constraints; If the first energy scheduling evaluation result satisfies the energy scheduling evaluation constraint, adding the first comprehensive energy demand scheduling decision to the second comprehensive energy demand scheduling space; If the first energy scheduling evaluation result does not meet the second space of the comprehensive energy demand scheduling, eliminating the first decision of the comprehensive energy demand scheduling; Based on the multi-energy supply integration model and the power grid energy dispatch evaluation channel, the first space of the comprehensive energy demand dispatch is continuously optimized and selected according to the energy dispatch evaluation constraints to obtain the second space of the comprehensive energy demand dispatch.

3. The method according to claim 2, wherein Based on the multi-energy supply integration model and the power grid energy dispatch evaluation channel, the first comprehensive energy demand dispatch decision is evaluated to obtain a first energy dispatch evaluation result, including: Performing simulation scheduling on the multi-energy supply integration model according to the first comprehensive energy demand scheduling decision to obtain a first simulated energy scheduling data set; The power grid energy dispatch evaluation channel includes a power supply quality evaluation model, a power supply efficiency evaluation model, an energy dispatch loss evaluation model and a power grid dispatch security evaluation model; Perform feature recognition based on the first simulated energy scheduling data set to obtain first power supply quality-related data, first power supply efficiency-related data, first energy scheduling loss-related data, and first power grid scheduling security-related data; Inputting the first power supply quality associated data into the power supply quality evaluation model to obtain a first power supply quality evaluation coefficient; inputting the first power supply efficiency associated data into the power supply efficiency evaluation model to obtain a first power supply efficiency evaluation coefficient; Inputting the first energy scheduling loss associated data into the energy scheduling loss evaluation model to obtain a first energy scheduling loss evaluation coefficient; Inputting the first power grid dispatching safety-related data into the power grid dispatching safety evaluation model to obtain a first power grid dispatching safety evaluation coefficient; The first power supply quality evaluation coefficient, the first power supply efficiency evaluation coefficient, the first energy scheduling loss evaluation coefficient and the first power grid scheduling safety evaluation coefficient are output as the first energy scheduling evaluation result.

4. The method according to claim 1, wherein Introducing the first optimization operator for power grid energy dispatch and the second optimization operator for power grid energy dispatch to perform deep optimization on the third space of comprehensive energy demand dispatch to obtain a comprehensive energy demand dispatch strategy, including: The first optimization operator for grid energy dispatching includes an energy dispatching optimality threshold, and the second optimization operator for grid energy dispatching is carbon emission minimization; Performing optimization selection on the third space of comprehensive energy demand scheduling according to the first optimization operator of the power grid energy scheduling to obtain a fourth space of comprehensive energy demand scheduling; An optimization analysis is performed on the fourth space of the comprehensive energy demand scheduling according to the second optimization operator of the power grid energy scheduling to generate the comprehensive energy demand scheduling strategy.

5. The method according to claim 4, wherein The third space of comprehensive energy demand scheduling is optimized and selected according to the first optimization operator of the power grid energy scheduling to obtain a fourth space of comprehensive energy demand scheduling, including: Construct an energy scheduling optimal analytical function, wherein the energy scheduling optimal analytical function is: ； Among them, ECF represents the energy dispatching optimality, exp represents the exponential function with the natural constant e as the base, WC represents the power supply quality weight, K(PQC) represents the normalized power supply quality evaluation coefficient, WE represents the power supply efficiency weight, K(PQE) represents the normalized power supply efficiency evaluation coefficient, WS represents the grid dispatching security weight, K(PQS) represents the normalized grid dispatching security evaluation coefficient, WL represents the energy dispatching loss weight, and K(PQL) represents the normalized energy dispatching loss evaluation coefficient. Based on the energy scheduling optimality analytical function, the energy scheduling optimality is calculated for the third space of the comprehensive energy demand scheduling to obtain multiple energy scheduling optimalities; Determine whether the plurality of energy scheduling optima satisfy the first optimization operator of the power grid energy scheduling, and obtain a plurality of decision optima determination results; Based on the multiple decision-making priority judgment results, the third space of the comprehensive energy demand scheduling is screened to obtain the fourth space of the comprehensive energy demand scheduling.

6. The integrated energy demand response and dispatching platform for smart grid is characterized by: The platform is used to execute the integrated energy demand response scheduling method for smart grids according to any one of claims 1 to 5, the platform comprising: A user-side load prediction module, configured to perform load prediction on the user side of the power grid based on a future time zone window to determine user load demand, wherein the power grid includes K energy supply units, each of the K energy supply units has a different energy type, and K is a positive integer greater than 1; a scheduling first space generation module, wherein the scheduling first space generation module is used to perform multi-energy coordinated scheduling on the K energy supply units according to the user load demand, and establish a comprehensive energy demand scheduling first space; a second scheduling space generation module, the second scheduling space generation module being used to model the K energy supply units, generate a multi-energy supply integrated model, and perform initial optimization on the first comprehensive energy demand scheduling space in combination with the power grid energy scheduling evaluation channel to obtain a second comprehensive energy demand scheduling space; a scheduling third space generation module, the scheduling third space generation module being configured to perform mutation, expansion, and optimization on the second space of comprehensive energy demand scheduling based on the grid energy scheduling evaluation channel and the grid energy scheduling variation function to generate a third space of comprehensive energy demand scheduling; A scheduling strategy optimization module, wherein the scheduling strategy optimization module is used to introduce a first optimization operator for power grid energy scheduling and a second optimization operator for power grid energy scheduling to perform deep optimization on the third space of comprehensive energy demand scheduling to obtain a comprehensive energy demand scheduling strategy; A response scheduling module is used to perform response scheduling on the K energy supply units based on the user load demand and the comprehensive energy demand scheduling strategy.

Images