Smart power grid multi-time scale resource scheduling optimization method and system

Abstract

The invention discloses a smart power grid multi-time scale resource scheduling optimization method and system, and relates to the technical field of multi-time scale resource scheduling, and the method comprises the following steps: obtaining a first constraint condition of a rolling update compliance rate, and determining an initial rolling update compliance rate; obtaining a second constraint condition of a scheduling margin configuration ratio, and quantifying an initial scheduling margin configuration ratio; performing multi-sample simulation on the initial parameters to generate a plurality of configuration arrays to be adjusted; mapping the configuration array to be adjusted to multi-time scale resource scheduling through scheduling arrangement and optimization driving, and performing collaborative evaluation; fitting a high-order collaborative response display curved surface based on the evaluation result and the configuration array to be adjusted; according to the method, the scheduling sensitive area of the curved surface is selected according to the actual demand, the optimal configuration array is screened, and the multi-time-scale resource scheduling is driven, so that the problem of cooperative imbalance of multi-time-scale scheduling is solved by analyzing, screening and regulating the scheduling margin configuration ratio and the rolling updating compliance rate.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-time scale resource scheduling, and more specifically, to a multi-time scale resource scheduling optimization method and system for a smart grid. Background Art

[0002] The resource scheduling optimization technology of smart grid aims to solve the problems of renewable energy output fluctuation, load demand uncertainty and multi-agent coordinated scheduling, and improve the economy, reliability and energy efficiency of power grid operation. The current technical solution mainly adopts multi-time scale optimization strategy, combined with short-term (seconds-hours), medium-term (hours-days) and long-term (days-months) scheduling framework, and builds distributed energy generation prediction model through deep learning algorithm to improve power prediction accuracy. In addition, adjustable resources such as energy storage system, demand-side response, electric vehicles are introduced, and dynamic scheduling decisions are made using algorithms such as reinforcement learning and multi-objective optimization to achieve flexible and optimal allocation of resources and improve the overall stability and sustainability of the power grid.

[0003] The existing smart grid multi-time scale resource dispatching process is mainly divided into day-ahead dispatching, intraday dispatching and real-time dispatching, corresponding to long-term, medium-term and short-term optimization, respectively, to ensure the economy, stability and new energy absorption capacity of the power grid. In the day-ahead dispatching stage, based on load forecasting and renewable energy output forecasting, optimization algorithms (such as mixed integer linear programming and reinforcement learning) are used to formulate unit combination plans and optimize the charging and discharging strategies of energy storage systems. In the intraday dispatching stage, combined with the latest meteorological and market data, through short-term load forecasting, economic dispatching and demand-side response technology, the unit output and spare capacity are optimized to cope with new energy fluctuations and load changes. In the real-time dispatching stage, the SCADA system and synchronized phasor measurement (PMU) are used to monitor the power grid status, and millisecond-level response is achieved through automatic generation control (AGC), event-driven dispatching and power electronic equipment regulation to maintain the stability of power grid frequency and voltage and ensure safe and efficient operation.

[0004] For example, the invention patent announcement with the announcement number of CN109765787B discloses a method for fast tracking of distribution network sources and loads based on intraday-real-time rolling control, including the invention relating to distribution network control technology, specifically relating to a method for fast tracking of distribution network sources and loads based on intraday-real-time rolling control, establishing a static load model with time-varying parameters for the load in the distribution network, and using the least square method with constraints to identify the parameters of the load model online, and using the established load model to derive the load state space equation; with the lowest dispatching cost, perform global optimization within a 15-minute time scale to obtain the economically optimal downstream power; establish the state space equation of the distribution network system based on the established load model and the photovoltaic and energy storage output models; use multivariable generalized predictive control to control the output on both sides of the source and load, use the economically optimal downstream power as the reference sequence, obtain the control instructions at the next moment, and form a rolling optimization process; evaluate the results after control with volatility index and economic index. This method can improve the accuracy of control and suppress the influence of source-load fluctuations.

[0005] For example, the invention patent announcement with announcement number: CN119024705A discloses a load control method based on model prediction and multi-time scale robustness, which belongs to the field of load control technology. The method predicts the load of each load device in the control system based on the multi-time scale load prediction model stored in the database to obtain the total load prediction result; establishes a system dynamic model to be controlled; based on the system dynamic model and the load prediction result, constructs a minimization cost function to determine the load control input, and the load control input is the load adjustment amount required for the control system to be controlled. The present invention can accurately adjust the load demand in the system, thereby optimizing energy distribution, reducing energy waste, and coping with the uncertainty and dynamic changes in energy demand, ensuring the economy and reliability of system operation, and can effectively solve the problem of load fluctuation in energy management, and improve energy utilization efficiency and system stability.

[0006] The above disclosed technical solutions have at least the following technical problems: In smart grids, short-term scheduling (such as minute-level), medium-term scheduling (such as intraday), and long-term scheduling (such as monthly / annual) are often driven by different mechanisms and models. Due to the different focus targets, data accuracy, and response speeds at each scale, scheduling strategy conflicts, resource allocation fragmentation, and incoherent feedback are prone to occur, resulting in a decline in the overall performance of the system.

[0007] There is a lack of effective coordination and feedback mechanisms between different time scales. Short-term scheduling cannot fully utilize the expected trends of long-term planning, and long-term planning cannot respond quickly to short-term disturbances. This is especially true in scenarios where multiple adjustable resources (such as renewable energy, energy storage, and load-side response) coexist.

[0008] When the rolling update compliance rate is high, it can improve the responsiveness to short-term load changes, but it is easy to frequently disturb the medium- and long-term plans, increase system instability and adjustment costs; When the compliance rate is low, the coordination burden is reduced, but short-term scheduling deviations may accumulate due to untimely adjustments, affecting the immediacy and accuracy of system operation; When the scheduling margin configuration ratio is set higher, the system's ability to handle forecast errors and emergencies can be enhanced, but it will reduce resource utilization and bring higher operating costs; When the configuration is relatively low, resource utilization efficiency and scheduling economy are improved, but the robustness of the system in the face of uncertainty and load fluctuations will decrease.

[0009] The scheduling margin configuration ratio and the rolling update compliance rate jointly affect the dynamic response capability and system robustness of multi-time scale scheduling; however, the existing technology lacks a dynamic optimization and adaptive adjustment mechanism between the rolling update compliance rate and the scheduling margin configuration ratio, resulting in an imbalance in the coordination of multi-time scale scheduling.

[0010] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0011] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a smart grid multi-time scale resource scheduling optimization method and system, which solves the problem of imbalance in multi-time scale scheduling coordination by analyzing, screening and regulating the scheduling margin configuration ratio and the rolling update compliance rate.

[0012] To achieve the above object, the present invention provides the following technical solutions: The method for optimizing multi-time-scale resource scheduling of a smart grid includes the following steps: obtaining a first constraint condition of a rolling update compliance rate and determining an initial rolling update compliance rate; obtaining a second constraint condition of a scheduling margin configuration ratio and quantifying the initial scheduling margin configuration ratio; performing multi-sample simulation on initial parameters and generating a number of configuration arrays to be adjusted; mapping the configuration arrays to be adjusted to multi-time-scale resource scheduling through scheduling orchestration and optimization drive, and performing collaborative evaluation; fitting a high-order collaborative response display surface based on the evaluation results and the configuration arrays to be adjusted; selecting a scheduling sensitive area of ​​the surface according to actual needs, screening the best configuration array, and driving multi-time-scale resource scheduling.

[0013] In a preferred embodiment, the first constraint condition for obtaining the rolling update compliance rate determines the initial rolling update compliance rate, specifically: the first constraint condition includes the maximum offset frequency of the rolling adjustment of the scheduling plan and the response coupling capability of each time scale scheduling model; the planned offset frequency and amplitude of the multi-time scale models within the cycle are obtained to construct a scheduling offset sample set; the impact of the response delay of each scheduling model after the rolling adjustment is triggered on the scheduling consistency is analyzed in combination with the response coupling capability of the time scale scheduling model; according to the maximum acceptable offset frequency, the coordination stability of the system at different frequencies is evaluated; the historical rolling update compliance rate data set and its stability and consistency loss function are obtained, and the compliance rate is screened in combination with the first constraint condition; from the screened historical rolling update compliance rates, based on the minimum deviation matching, the rolling update compliance rate with the smallest deviation from the current system is selected as the initial rolling update compliance rate.

[0014] In a preferred embodiment, the second constraint condition for obtaining the scheduling margin configuration ratio quantifies the initial scheduling margin configuration ratio, specifically: the second constraint condition includes the load forecast error distribution, the fluctuation range of renewable energy output and the minimum guarantee capacity of scheduling resources; the scheduling margin configuration ratio is the ratio of resource redundancy rate to accident response demand under a typical operating scenario, and the accident response demand is quantitatively obtained by analyzing load surge and renewable energy fluctuation; the scheduling margin configuration ratios of several multi-scale scheduling systems within a historical preset period are constrained by the second constraint condition, and the initial scheduling margin configuration ratio is obtained by averaging.

[0015] In a preferred embodiment, the initial parameters are subjected to multi-sample simulation to generate a number of configuration arrays to be adjusted, specifically: the initial parameters include an initial rolling update compliance rate and an initial scheduling margin configuration ratio; the value range of the rolling update compliance rate and the scheduling margin configuration ratio is determined based on the first constraint and the second constraint; based on Latin hypercube sampling, a number of configuration arrays to be adjusted are generated within the value range, and the configuration arrays contain different combinations of rolling update compliance rates and scheduling margin configuration ratios.

[0016] In a preferred embodiment, the collaborative evaluation is specifically as follows: the collaborative evaluation performs feature analysis on a multi-time scale scheduling system to obtain feature data for evaluating the degree of adaptation of configuration data; and performs training based on the feature data obtained for evaluating the degree of adaptation of configuration data combined with historical data to obtain a driving effect evaluation model, wherein the feature data includes cross-time scale scheduling fluctuation characteristics and resource utilization dynamic matching characteristics.

[0017] In a preferred embodiment, the high-order collaborative response display surface is fitted based on the evaluation results and the configuration array to be adjusted, specifically: based on the cross-time scale scheduling fluctuation characteristics and the dynamic matching characteristics of resource utilization, a multidimensional feature mapping space is constructed to characterize the response law of the multi-time scale scheduling system; the dimensions of the multidimensional feature mapping space include cross-time scale scheduling fluctuation characteristics, resource utilization dynamic matching characteristics and driving effect evaluation values; the characteristic parameters of each group of configuration arrays to be adjusted are associated and mapped with their corresponding driving effect evaluation values ​​to form a group of mapping sample points; based on the mapping sample points, a high-order collaborative response surface covering the entire feature mapping domain is fitted and constructed to reflect the scheduling coordination performance change trend of the system under different configuration combinations.

[0018] In a preferred embodiment, the scheduling sensitive area of ​​the surface is selected according to actual needs, the optimal configuration array is screened, and multi-time scale resource scheduling is driven, specifically: several peak areas of the high-order collaborative response display surface are determined, and according to the preset dynamic control amplitude, the range is expanded based on several peak values ​​to construct several candidate areas for configuration array adjustment; according to the actual needs of the scheduling target, several candidate areas are screened; if the short-term response capability requirement is high, the area with a higher rolling update compliance rate in the candidate area is selected as the scheduling sensitive area; if the system stability requirement is stronger, the area with a high scheduling margin configuration in the candidate area is selected as the scheduling sensitive area; if resource utilization efficiency is the current priority goal, the area with the highest peak in the candidate area is selected as the scheduling sensitive area; the configuration array corresponding to the peak in the scheduling sensitive area is used as the optimal configuration array to drive multi-time scale resource scheduling.

[0019] In a preferred embodiment, the specific method for obtaining the cross-time scale scheduling fluctuation characteristics is as follows: at different scheduling time scales, the processing time from request to execution completion is obtained as the response time; for the same time scale, the average of several response times is calculated; the resource scheduling amount and total duration at different time scales are obtained, and the scheduling efficiency is calculated; an initial cross-time scale fluctuation model is set according to the average response time and scheduling efficiency; response time points are set for performance testing, and scheduling fluctuation amplitude data at each point is collected; according to the fluctuation amplitude data, the initial fluctuation model parameters are optimized based on the nonlinear least squares method to obtain a scheduling fluctuation characteristic calculation model, and the initial fluctuation model parameters include the maximum fluctuation amplitude, the change speed and the sensitivity characteristics.

[0020] In a preferred embodiment, the specific method for obtaining the dynamic matching characteristics of resource utilization is as follows: obtain the resource utilization changes and scheduling fluctuations under different scheduling strategies and resource allocations, and build a matching evaluation model through a scheduling algorithm; cluster the matching evaluation model; based on the evaluation model characteristics after extracting the clusters, calculate the matching accuracy evaluation characteristics based on resource fluctuations, scheduling errors and contention; simulate the resource utilization under different scheduling strategies through the evaluation model, establish a timeliness model and obtain the resource allocation timeliness evaluation characteristics, and combine the matching accuracy evaluation characteristics to sum up to obtain the dynamic matching characteristics of resource utilization.

[0021] The multi-time-scale resource scheduling optimization system of a smart grid includes an initial parameter acquisition module, a configuration array acquisition module, a drive evaluation module and a configuration array adjustment module; the initial parameter acquisition module is used to acquire the first constraint condition of the rolling update compliance rate and determine the initial rolling update compliance rate; the second constraint condition of the scheduling margin configuration ratio is acquired and the initial scheduling margin configuration ratio is quantified; the configuration array acquisition module is used to perform multi-sample simulation on the initial parameters and generate a number of configuration arrays to be adjusted; the drive evaluation module is used to map the configuration array to be adjusted to the multi-time-scale resource scheduling through scheduling arrangement and optimization drive, and perform collaborative evaluation; the configuration array adjustment module is used to fit a high-order collaborative response display surface based on the evaluation results and the configuration array to be adjusted; the scheduling sensitive area of ​​the surface is selected according to actual needs, the best configuration array is screened, and the multi-time-scale resource scheduling is driven.

[0022] Technical effects and advantages of the multi-time scale resource scheduling optimization method for smart grids of the present invention: 1. The present invention constructs a refined rolling update compliance rate initial calculation mechanism, combines historical scheduling offset data with multi-level scheduling response coupling characteristics, and can effectively identify the most adaptable rolling adjustment strategy for the current system, thereby improving scheduling consistency and system stability. At the same time, combined with factors such as load forecast error, renewable energy fluctuations and minimum guarantee capabilities, a quantitative model of the scheduling margin configuration ratio is established to achieve a dynamic balance between scheduling resource redundancy and risk response. The use of Latin hypercube sampling to generate diversified parameter configurations further enhances the simulation coverage of the solution and the integrity of the optimization space. The overall solution has both real-time adaptability and interpretability, which improves the coordination and control capabilities of the multi-time scale scheduling system in a complex operating environment, and provides effective support for building a new power system with strong resilience, fast response and reasonable resource allocation.

[0023] 2. The present invention maps the configuration array to be adjusted to a multi-time scale resource scheduling model, combines the scheduling goals and characteristics of short-term, medium-term and long-term cycles, and performs refined management from the perspectives of real-time, resource buffering and global balance, significantly enhancing the coordination and flexibility of the scheduling system at different time scales. On this basis, the system introduces a collaborative evaluation mechanism, focusing on the two key indicators of cross-time scale scheduling fluctuation characteristics and resource utilization dynamic matching characteristics, to quantitatively analyze the impact of each configuration array on the system scheduling behavior and resource efficiency, effectively solving the problems of inconsistent scheduling between cycles and imbalanced resource allocation in traditional scheduling systems. On the one hand, the introduction of cross-time scale scheduling fluctuation characteristics helps to accurately capture the degree of interference of configuration arrays in short-term decisions on long-term scheduling goals, and achieve stability optimization of scheduling behavior; on the other hand, the dynamic matching characteristics of resource utilization focus on the supply and demand adaptation in the resource allocation process, improving the responsiveness and utilization efficiency of the scheduling system to changes in resource status. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of the multi-time scale resource scheduling optimization method for smart grid of the present invention; Figure 2 It is a structural schematic diagram of the multi-time scale resource scheduling optimization system of the smart grid of the present invention; Figure 3 A display diagram of the multi-dimensional feature mapping space based on the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Embodiment 1, Figure 1 The present invention provides a smart grid multi-time scale resource scheduling optimization method, which includes the following steps: S1, obtaining the first constraint condition of the rolling update compliance rate, and determining the initial rolling update compliance rate in combination with the historical scheduling execution results.

[0027] In this embodiment, the first constraint condition includes the maximum offset frequency of the rolling adjustment of the scheduling plan and the response coupling capability of the scheduling models at each time scale; In this embodiment, the initial rolling update compliance rate is determined in combination with the historical scheduling execution results, specifically: Obtain the frequency and amplitude changes of the planned deviations of the multi-time-scale scheduling model in the rolling adjustment process within a preset period, and construct a scheduling deviation sample set; Combined with the response coupling capabilities of scheduling models at each time scale, the impact of the response delay of each scheduling model on scheduling consistency after the rolling adjustment is triggered is calculated; According to the maximum acceptable deviation frequency of rolling adjustment, the coordination stability of the dispatching system under different rolling frequencies is evaluated; Based on the scheduling stability and historical deviation sample data, the initial rolling update compliance rate adapted to the current scheduling system is determined through the minimum deviation matching method.

[0028] Furthermore, the response coupling ability between each time scale is quantified as: , In the formula, is the response coupling capability from time scale i to j, is the average response delay from time scale i to j, is the response intensity amplitude, It is the response direction consistency feature.

[0029] Furthermore, the impact of scheduling consistency is quantified by defining a consistency loss function, specifically: , In the formula, is the consistency loss function, is the weight of the scheduling task in scale i→j, and is the offset difference and response delay in scale i→j, To prevent decimals with zero denominator (such as 1e-6); , is the weight feature; Furthermore, the specific method for obtaining the coordination stability of the scheduling system at different rolling frequencies is as follows: , In the formula, For the scroll frequency The coordination stability under is the scheduling offset variance under rolling frequency, are the conflict and failure probabilities, , is the weight factor; Furthermore, based on the scheduling stability and historical deviation sample data, the initial rolling update compliance rate adapted to the current scheduling system is determined by the minimum deviation matching method, specifically: Obtain a historical rolling update compliance rate data set, obtain the coordination stability and consistency loss function of each rolling update compliance rate, and filter the historical rolling update compliance rate in combination with the preset first constraint condition; Based on the minimum deviation matching, the rolling update compliance rate with the minimum deviation from the current system is selected from the filtered historical rolling update compliance rates as the initial rolling update compliance rate.

[0030] In this embodiment, the historical rolling update compliance rate dataset is defined as: , where R is the historical rolling update compliance rate dataset, is the rolling update compliance rate in the Nth scheduling period.

[0031] In this embodiment, the first constraint condition is specifically: ; In the formula, Rolling update of compliance rate dataset for the selected history, Historical rolling update compliance rates for screening, is the coordination stability of the i-th historical rolling update compliance rate, is the minimum threshold of coordination stability, is the consistency loss function of the i-th historical rolling update compliance rate, is the highest threshold of consistency loss; In this embodiment, the initial rolling update compliance rate is specifically:

[0032]

[0033] In the formula, is the initial rolling update compliance rate, is the deviation matching degree, Coordinate stability for the current system's goals, is the target consistency loss of the current system, A control factor for adjusting the consistency loss impact weight.

[0034] It should be noted that the minimum threshold for coordinated stability and the maximum threshold for consistency loss are obtained by statistically analyzing historical rolling update execution data and combining the empirical threshold settings required for system stability and consistency, and can be set according to actual needs.

[0035] It should be noted that the control factor for adjusting the consistency loss influence weight is obtained by fitting the historical scheduling data, and is optimized and adjusted in combination with the scheduling offset sample and the target consistency loss threshold.

[0036] It should be noted that the target coordination stability and target consistency loss of the current system are obtained based on the statistical characteristics of historical scheduling data and the thresholds set in combination with the scheduling strategy requirements.

[0037] It should be noted that the rolling update compliance rate with the smallest deviation is the rolling update compliance rate that is closest to the current scheduling system state among the screened historical rolling update compliance rates.

[0038] It should be noted that the larger the scheduling offset variance, the more unstable it is. The larger the value, the stronger the coordination.

[0039] It should be noted that the response intensity amplitude is the ratio of the response layer to the upper layer instruction amplitude, and the response direction consistency feature quantization result is 1 for the same direction, -1 for the opposite direction, and 0 for partial misalignment.

[0040] It should be noted that the plan deviation frequency refers to the statistical frequency of the number of rolling adjustments (i.e., modification of the original plan) that occur for each scheduling plan in the multi-time-scale scheduling model within a given time window (such as 1 day, 1 week, 1 month); for example: the original plan of the intraday scheduling model is updated once an hour. If there are 6 re-rolling plans due to external disturbances on a certain day, the "intraday scheduling deviation frequency" of that day is deemed to be 6 times / day; if the annual scheduling model has 2 plan reconstructions within a month, the deviation frequency is 2 times / month; the plan deviation frequency is used to reflect the activity of the rolling mechanism in actual operation.

[0041] It should be noted that the amplitude change refers to the degree of change in key resource scheduling variables between the rolling plan and the original plan; it can be further quantified into: load difference amplitude (such as: the variation amplitude of the planned power output or load curve); time window offset (such as: how much the scheduling start or end time is advanced forward / backward); resource call change rate (such as: the original plan to call device A, which is replaced by device B or a combination of multiple devices after rolling); for example: the original plan was to supply 50MW of power from 9:00 to 10:00, and after the rolling adjustment, it was changed to 60MW of power from 9:30 to 10:30. The offset amplitude includes a time offset of 30 minutes and a power increase of 10MW; the amplitude change constitutes a quantitative indicator of the rolling offset, reflecting the intensity of the scheduling response and the flexibility boundary of resource allocation.

[0042] It should be noted that the response coupling capability between the time scales refers to the degree of response linkage and its timeliness between different scheduling levels (such as annual / seasonal / monthly scheduling, daily scheduling, intraday scheduling, and real-time scheduling) to the same rolling adjustment event in the multi-time scale scheduling system, and the measurement indicator of "multi-level scheduling linkage feedback efficiency", which reflects: after the upper layer (such as daily scheduling) changes the plan, whether it can be quickly transmitted to the lower layer (such as real-time scheduling) and adapted in time; whether the lower layer feedback can reversely correct the upper layer plan; whether the intermediate layer (such as intraday scheduling) is "mismatched" or "reacted too late".

[0043] It should be noted that the rolling update compliance rate refers to the degree to which the scheduling system maintains the previous scheduling plan under continuous rolling adjustments, which can be understood as the "inheritance of the old plan"; The maximum acceptable deviation frequency refers to the maximum rolling adjustment frequency allowed by the system to maintain scheduling coordination; The historical deviation sample data set refers to the paired data of planned deviation frequency and planned deviation amplitude extracted from actual operation.

[0044] S2, obtains the second constraint condition of the scheduling margin configuration ratio, and quantifies the initial scheduling margin configuration ratio based on the resource redundancy rate and accident response requirements under typical operation scenarios.

[0045] The second constraint condition of the scheduling margin configuration ratio includes load forecast error distribution, renewable energy output fluctuation range and minimum guarantee capacity of scheduling resources; In this embodiment, the second constraint condition for obtaining the scheduling margin configuration ratio is specifically: The second constraint condition of the scheduling margin configuration ratio is specifically: ,Right now

[0046] In the formula, is the scheduling margin configuration ratio, is the standard deviation of load forecast error, is the mean value of load forecast error, is the standard deviation of renewable energy output fluctuations, is the mean value of renewable energy output fluctuation, To ensure the minimum dispatch power for the system; In this embodiment, based on the resource redundancy rate and accident response requirements in typical operation scenarios, the initial scheduling margin configuration ratio is quantified, specifically: The scheduling margin configuration ratio is the ratio of the resource redundancy rate to the accident response demand in a typical operation scenario; the accident response demand is quantitatively obtained by analyzing the sudden increase in load and the fluctuation of renewable energy.

[0047] The scheduling margin configuration ratios of a plurality of multi-scale scheduling systems within a preset historical period are constrained by the second constraint condition of the scheduling margin configuration ratio, and the initial scheduling margin configuration ratio is obtained by averaging; The resource redundancy rate in the typical operation scenario is specifically:

[0048] The incident response requirements are specifically:

[0049] The scheduling margin configuration ratio is specifically:

[0050] In the formula, is the resource redundancy rate, is the total available power that can be called by the current system, Forecast load demand in a typical scenario, is the maximum load disturbance range, It is the fluctuation range of renewable energy output.

[0051] S3, performs multi-sample simulation on the initial parameters to generate several configuration arrays to be adjusted.

[0052] The initial parameters include an initial rolling update compliance rate and an initial scheduling margin configuration ratio; Determine a value range of a rolling update compliance rate and a scheduling margin configuration ratio based on the first constraint and the second constraint; Based on Latin hypercube sampling, a number of configuration arrays to be adjusted are generated within a value range, each of which contains a different combination of rolling update compliance rate and scheduling margin configuration ratio.

[0053] It should be noted that the first constraint condition limits the range of the rolling update compliance rate based on the historical rolling adjustment offset samples and the scheduling consistency impact, so as to avoid scheduling instability or resource waste caused by too high or too low adjustment frequency.

[0054] The second constraint condition combines the resource redundancy rate and accident response requirements under typical operating scenarios to ensure that the scheduling margin configuration ratio fluctuates within a reasonable range and avoid insufficient or excessive redundancy in scheduling resources.

[0055] The Latin hypercube sampling method is used to uniformly sample within the range of values ​​that satisfy the above constraints to ensure the representativeness of the configuration array and improve the coverage of simulation samples, so that subsequent optimization analysis can fully reflect the possible impact of different scheduling strategies.

[0056] This embodiment constructs a refined rolling update compliance rate initial calculation mechanism, combines historical dispatch offset data with multi-level dispatch response coupling characteristics, and can effectively identify the most adaptable rolling adjustment strategy for the current system, thereby improving dispatch consistency and system stability. At the same time, combined with factors such as load forecast error, renewable energy fluctuations and minimum guarantee capabilities, a quantitative model of the dispatch margin configuration ratio is established to achieve a dynamic balance between dispatch resource redundancy and risk response. The use of Latin hypercube sampling to generate diversified parameter configurations further enhances the simulation coverage of the solution and the integrity of the optimization space. The overall solution has both real-time adaptability and interpretability, which improves the coordination and control capabilities of the multi-time scale dispatch system in a complex operating environment, and provides effective support for building a new power system with strong resilience, fast response and reasonable resource allocation.

[0057] S4, through scheduling and optimization driving, maps the configuration array to be adjusted to multi-time scale resource scheduling and performs collaborative evaluation; In this embodiment, the configuration array to be adjusted is mapped to multi-time scale resource scheduling through scheduling arrangement and optimization driving, specifically: According to the rolling update compliance rate and scheduling margin configuration ratio in the configuration array, combined with the multi-time scale structure of the scheduling system, the parameter setting scheme of the scheduling model at each time scale is determined.

[0058] Based on the scheduling and orchestration strategy, different configuration arrays are mapped to short-cycle scheduling, medium-cycle scheduling, and long-cycle scheduling models to ensure that the scheduling schemes of each time scale can operate in a coordinated manner; Among them, the short-cycle scheduling model focuses on real-time adjustment and is mainly dynamically optimized based on the rolling update compliance rate; The mid-cycle scheduling model combines the scheduling margin configuration ratio to optimize the resource allocation strategy; The long-cycle scheduling model comprehensively considers the rolling update compliance rate and the scheduling margin configuration ratio to jointly drive the scheduling model.

[0059] It should be noted that the existing technology has mature applications for mapping the configuration array to be adjusted to multi-time scale resource scheduling through scheduling orchestration and optimization driving, which will not be described here.

[0060] In this implementation, collaborative assessment is conducted, specifically: The collaborative evaluation performs feature analysis on the multi-time scale scheduling system to obtain feature data for evaluating the degree of adaptation of the configuration data, and performs training based on the feature data for evaluating the degree of adaptation of the configuration data combined with historical data to obtain a driving effect evaluation model.

[0061] The characteristic data includes cross-time scale scheduling fluctuation characteristics and resource utilization dynamic matching characteristics.

[0062] The cross-timescale scheduling fluctuation feature is an indicator used to measure the fluctuation amplitude of scheduling decisions between different time scales, reflecting the impact of short-term scheduling changes on long-term scheduling goals. Specifically, this feature describes the coordination between short-term and long-term scheduling decisions of different configuration arrays. If the rolling update compliance rate or scheduling margin configuration ratio in the configuration array is not properly selected, it may lead to frequent fluctuations in short-term scheduling, thereby affecting the stability of long-term scheduling goals. By evaluating scheduling fluctuations across time scales, the impact of these fluctuations on the overall performance of the system can be quantified, helping to select configuration arrays that are more stable and adaptable at different time scales.

[0063] In practical applications, different configuration arrays (including rolling update compliance rate and scheduling margin configuration ratio) will directly affect the scheduling fluctuation across time scales. For example, a higher rolling update compliance rate may lead to frequent adjustments in the short term, thereby increasing the scheduling fluctuation characteristics; while a scheduling margin configuration ratio that is too high or too low may also cause incoordination between scheduling at different time scales and increase system fluctuations. By simulating the application of different configuration arrays, its impact on scheduling fluctuations across time scales can be evaluated, so as to select the most appropriate configuration array and optimize the stability and adaptability of the scheduling system.

[0064] Analyzing the fluctuation characteristics of scheduling across time scales has the following advantages for analyzing the application effects of different configuration arrays and solving the problem of coordinated imbalance in multi-time scale scheduling: Improve scheduling efficiency: By identifying the characteristics of scheduling fluctuations at different time scales, the configuration array can be adjusted in a targeted manner to reduce the volatility of resource scheduling, thereby optimizing the scheduling efficiency of multi-time scale systems. Relatively stable scheduling fluctuations help improve the overall efficiency of the system and reduce the frequency and cost of over-adjustment of the system.

[0065] Balanced resource allocation: Analysis of scheduling fluctuation characteristics across time scales can reveal the impact of different configuration arrays on resource allocation during the scheduling process, help optimize resource allocation, avoid excessive or insufficient resource scheduling on certain time scales, and thus achieve reasonable and efficient use of resources.

[0066] Improve scheduling consistency: By analyzing the scheduling fluctuation characteristics across time scales, the synergy relationship and potential imbalance points between scheduling strategies at different time scales can be identified, and then the configuration array can be optimized to reduce scheduling imbalance problems between different time scales. Controlling scheduling fluctuations helps improve scheduling consistency and reduce unnecessary adjustments.

[0067] Enhance system stability: Analysis of scheduling fluctuation characteristics across time scales helps the system better adapt to changes in the external environment, adjust the configuration array in a timely manner, reduce system instability caused by fluctuations, and ensure continuous and stable operation in a multi-time scale scheduling environment.

[0068] Optimizing multi-time scale scheduling coordination: In a multi-time scale scheduling system, coordination between time scales is crucial. By analyzing the fluctuation characteristics of scheduling across time scales, the coordination imbalance problem between scheduling at different time scales can be identified and solved, thereby achieving optimized coordination between time scales, allowing the system to flexibly respond to complex scheduling needs.

[0069] The specific method for obtaining the cross-time scale scheduling fluctuation characteristics is as follows: Under different scheduling time scales, the processing time required from initiating a scheduling request to completing the scheduling execution and generating the scheduling result is obtained as the scheduling response time; For the same scheduling time scale, perform several response time calculations and calculate the average response time; Obtain the resource scheduling amount and total duration of the system at different scheduling time scales, and calculate the system scheduling efficiency; An initial cross-time scale scheduling fluctuation model is set according to the average response time and system scheduling efficiency; Set several response time points to perform system performance testing, and collect the fluctuation data of scheduling execution results at each response time point; According to the fluctuation amplitude data, the undetermined parameters of the initial cross-time scale scheduling fluctuation model are optimized based on the nonlinear least squares method to obtain a calculation model of the cross-time scale scheduling fluctuation characteristics. The undetermined parameters include the maximum value of the fluctuation amplitude, the speed of change of the fluctuation amplitude with the increase of response time, and the sensitivity characteristics of the response time to the change of the fluctuation amplitude.

[0070] Through these steps, we can effectively quantify the scheduling fluctuation characteristics across time scales and provide a basis for further scheduling optimization.

[0071] The specific calculation formula of the average response time is as follows:

[0072] The specific calculation formula of the adjustment step size of the cross-time scale scheduling fluctuation model is as follows:

[0073] The specific calculation formula of the cross-time scale scheduling fluctuation characteristics is as follows:

[0074] In the formula, is the average response time, is the response time of the ith scheduling, To measure the number of dispatch response times at the same time scale, is the adjustment step size of the cross-time scale scheduling fluctuation model, is the number of fluctuation characteristic data of the data processing results used for optimization, is the label of the fluctuation characteristic data of the data processing results used for optimization, Scheduling fluctuating data values ​​across time scales for data processing results, To schedule volatility characteristics across time scales.

[0075] The resource utilization dynamic matching feature is an indicator used to measure the impact of different configuration arrays on resource utilization efficiency during resource allocation, reflecting the degree of resource utilization matching of the scheduling system at different time scales. Specifically, the resource utilization dynamic matching feature can reveal the optimization effect of different values ​​of the rolling update compliance rate and the scheduling margin configuration ratio on resource allocation. This feature quantifies whether the configuration array can effectively balance resource demand and available resources during dynamic resource scheduling by comparing the difference between actual resource utilization and predetermined resource demand, thereby ensuring maximum and efficient resource utilization.

[0076] In practical applications, different configuration arrays will directly affect the dynamic matching characteristics of resource utilization. For example, a high rolling update compliance rate may lead to frequent resource reconfiguration and adjustment, resulting in short-term over-scheduling or idleness of resources, thus affecting the overall resource utilization. Changes in the scheduling margin configuration ratio may also affect the over- or under-allocation of resources, especially when load demand changes dramatically. By simulating the application of different configuration arrays, we can evaluate their impact on resource utilization and select the configuration array that can best dynamically match resource demand and supply, thereby optimizing resource utilization efficiency.

[0077] Analyzing the dynamic matching characteristics of resource utilization has the following advantages for analyzing the application effects of different configuration arrays and solving the problem of imbalance in multi-time scale scheduling coordination: Improve resource utilization efficiency: By dynamically matching resource utilization, we can accurately grasp the resource requirements of each configuration array at different time scales, optimize resource allocation, and avoid resource waste or over-scheduling. This helps improve the overall resource utilization of the system and ensure that resources are optimally configured.

[0078] Optimize multi-timescale scheduling coordination: The dynamic matching feature of resource utilization can reveal the changing trend of resource demand at different time scales, thus providing an accurate basis for adjusting the configuration array and reducing conflicts and coordination imbalances between time scales. Dynamic matching can be flexibly adjusted within different scheduling cycles to optimize scheduling coordination.

[0079] Reduced scheduling delays and fluctuations: The dynamic matching feature helps identify and adjust for fluctuations in resource utilization, reducing system fluctuations caused by uneven resource allocation or scheduling delays. This helps improve the responsiveness of the scheduling system and reduce unnecessary fluctuations caused by mismatched configuration arrays.

[0080] Enhance the adaptability and flexibility of the system: With the application of scheduling models at different time scales, the system can quickly adjust to the fluctuations in resource demand through dynamic matching features when facing various external changes. Ensure the adaptability and flexibility of different configuration arrays in resource utilization in actual applications.

[0081] Improve system stability and reliability: By accurately matching resource utilization, over-scheduling or resource shortage can be avoided, thereby reducing the instability of the system in complex scheduling scenarios. By dynamically adjusting the configuration array, the system can maintain high stability and reliability at different time scales.

[0082] Reduce system operating costs: Dynamic matching of resource utilization can reduce over-scheduling caused by unreasonable resource allocation, thereby saving energy and scheduling costs. By optimizing the configuration array and scheduling strategy, the system can allocate resources more effectively and reduce operating costs.

[0083] The cross-timescale scheduling fluctuation characteristics and resource utilization dynamic matching characteristics are selected as the directions for analyzing the application effects of different configuration arrays, mainly because these two aspects directly affect the stability and resource efficiency of the multi-timescale scheduling system. First, the cross-timescale scheduling fluctuation characteristics can reveal the fluctuation behavior and resource demand changes of the system at different time scales, help evaluate the impact of the configuration array on the stability of the system, and especially solve the scheduling imbalance problem between multiple time scales. This is very important for ensuring the coordination of resource demands in different scheduling cycles. The dynamic matching characteristics of resource utilization can accurately optimize the allocation of resources, avoid resource waste or shortage, thereby improving the overall resource utilization efficiency of the system and reducing unnecessary delays and costs. Compared with other possible analysis directions, such as scheduling fluctuations at a single time scale or simple resource utilization analysis, these two directions can more comprehensively capture the dynamic changes and resource utilization efficiency in multi-timescale scheduling coordination, directly affecting the optimization effect and long-term stable operation of the system. Therefore, focusing on these two characteristics is more practical and targeted.

[0084] The specific method for obtaining the resource utilization dynamic matching feature is as follows: Obtain changes in system resource utilization under different scheduling strategies and resource allocation methods, and the distribution of scheduling fluctuations. Through the resource scheduling algorithm, a resource utilization matching evaluation model is constructed; Clustering the resource utilization matching evaluation model; Extract features from the processed resource utilization matching evaluation model, and calculate matching accuracy evaluation features based on resource utilization fluctuations, scheduling errors, and resource contention; The resource utilization rate under different scheduling strategies and resource allocation modes is simulated through the resource utilization rate matching evaluation model, and the resource allocation timeliness model is established to obtain the resource allocation timeliness evaluation characteristics; The resource utilization dynamic matching feature is calculated by combining the matching accuracy evaluation feature.

[0085] The specific calculation formula of the matching accuracy evaluation feature is as follows:

[0086] The specific calculation formula of the resource allocation timeliness evaluation feature is as follows:

[0087] The specific calculation formula of the resource utilization dynamic matching feature is as follows:

[0088] In the formula, To evaluate features for matching accuracy, Assessing the timeliness of resource allocation features, Dynamically matching features for resource utilization, is the deviation value, The energy consumption fluctuations under different load distribution and resource scheduling strategies, The resource utilization coverage under different load distributions, is the scheduling feedback rate, is the scheduling error, is the resource scheduling model, is the resource scheduling efficiency loss, For the stability of the resource scheduling system, It is the resource response time adjustment item.

[0089] In this embodiment, the driving effect evaluation model is specifically: Establish an initial driving effect evaluation model. Based on the cross-time scale scheduling fluctuation characteristics and resource utilization dynamic matching characteristics of historical data, use a multi-layer perceptron (MLP) to supervise the proportional coefficient of the initial driving effect evaluation model and obtain the driving effect evaluation model. The initial driving effect evaluation model is specifically:

[0090] In the formula, is the driving effect evaluation value, that is, the evaluation result, is the scale factor to be trained for scheduling fluctuation characteristics across time scales, The scale factor to be trained for the dynamic matching feature of resource utilization.

[0091] It should be noted that the multilayer perceptron is only one method used in this application. Any supervised training method with strong interpretability or high prediction accuracy can be applied to this application, such as gradient boosting tree (GBDT).

[0092] S5, based on the evaluation results and the configuration array to be adjusted, fit the high-order collaborative response display surface.

[0093] In this embodiment, based on the evaluation results and the configuration array to be adjusted, a high-order coordinated response display surface is fitted, specifically: Based on the cross-time scale scheduling fluctuation characteristics and the dynamic matching characteristics of resource utilization, a multi-dimensional feature mapping space is constructed to characterize the response law of the multi-time scale scheduling system. The dimensions of the multidimensional feature mapping space include cross-time scale scheduling fluctuation characteristics, resource utilization dynamic matching characteristics, and driving effect evaluation values; Associatively mapping the characteristic parameters of each group of configuration arrays to be adjusted and their corresponding driving effect evaluation values ​​to form a group of mapping sample points; Based on the mapping sample points, a high-order collaborative response surface covering the entire feature mapping domain is fitted and constructed to reflect the changing trend of the scheduling collaborative performance of the system under different configuration combinations.

[0094] S6, selects the scheduling sensitive area of ​​the surface according to actual needs, screens the optimal configuration array, and drives multi-time scale resource scheduling.

[0095] In this embodiment, the scheduling sensitive area of ​​the surface is selected according to actual needs, the optimal configuration array is screened, and multi-time scale resource scheduling is driven, specifically: Determine several peak areas of the high-order synergistic response display surface, and expand the range based on several peaks according to the preset dynamic control amplitude, so as to construct several candidate areas for configuration array adjustment; Screen several candidate areas according to the actual needs of the scheduling target; If the short-term response capability requirement is high, the area with a high rolling update compliance rate among the candidate areas is selected as the scheduling sensitive area; If the system stability requirement is stronger, the area with high scheduling margin configuration in the candidate area is selected as the scheduling sensitive area; If resource utilization efficiency is the current priority goal, the area with the highest peak value among the candidate areas is selected as the scheduling sensitive area; The configuration array corresponding to the peak value in the scheduling sensitive area is taken as the optimal configuration array to drive multi-time scale resource scheduling.

[0096] This embodiment maps the configuration array to be adjusted to a multi-time scale resource scheduling model, combines the scheduling goals and characteristics of short-term, medium-term and long-term cycles, and performs refined management from the perspectives of real-time, resource buffering and global balance, significantly enhancing the coordination and flexibility of the scheduling system at different time scales. On this basis, the system introduces a collaborative evaluation mechanism, focusing on the two key indicators of cross-time scale scheduling fluctuation characteristics and resource utilization dynamic matching characteristics, to quantitatively analyze the impact of each configuration array on the system scheduling behavior and resource efficiency, effectively solving the problems of inconsistent scheduling between cycles and imbalanced resource allocation in traditional scheduling systems. On the one hand, the introduction of cross-time scale scheduling fluctuation characteristics helps to accurately capture the degree of interference of configuration arrays in short-term decisions on long-term scheduling goals, and achieve stability optimization of scheduling behavior; on the other hand, the dynamic matching characteristics of resource utilization focus on the supply and demand adaptation in the resource allocation process, improving the responsiveness and utilization efficiency of the scheduling system to changes in resource status.

[0097] Figure 2 It is a multi-time scale resource scheduling optimization system for smart grid, including an initial parameter acquisition module, a configuration array acquisition module, a drive evaluation module and a configuration array adjustment module; An initial parameter acquisition module is used to acquire a first constraint condition of a rolling update compliance rate and determine an initial rolling update compliance rate; acquire a second constraint condition of a scheduling margin configuration ratio and quantify the initial scheduling margin configuration ratio; The configuration array acquisition module is used to perform multi-sample simulation on the initial parameters and generate several configuration arrays to be adjusted; The driver evaluation module is used to map the configuration array to be adjusted to the multi-time scale resource scheduling through scheduling orchestration and optimization driving, and perform collaborative evaluation; The configuration array adjustment module is used to fit the high-order collaborative response display surface based on the evaluation results and the configuration array to be adjusted; select the scheduling sensitive area of ​​the surface according to actual needs, screen the best configuration array, and drive multi-time scale resource scheduling.

[0098] Figure 3 The display diagram of the multi-dimensional feature mapping space based on is shown in FIG. 1 , and the vertical axis is the dimension of the driving effect evaluation value. Figure 3 The points in are the mapping sample points of the display.

[0099] The above embodiments may be implemented in whole or in part through software, hardware, firmware or any other combination.

[0100] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0101] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-time scale resource scheduling optimization method for smart grid, characterized in that: The steps include: Obtaining a first constraint condition of a rolling update compliance rate, and determining an initial rolling update compliance rate; Obtaining a second constraint condition of the scheduling margin configuration ratio, and quantifying the initial scheduling margin configuration ratio; Perform multiple sample simulations on the initial parameters to generate several configuration arrays to be adjusted; Through scheduling and optimization driving, the configuration array to be adjusted is mapped to multi-time scale resource scheduling and collaborative evaluation is performed; Based on the evaluation results and the configuration array to be adjusted, a high-order coordinated response display surface is fitted; Select the scheduling-sensitive area of ​​the surface according to actual needs, screen the optimal configuration array, and drive multi-time scale resource scheduling.

2. The smart grid multi-time scale resource scheduling optimization method according to claim 1 is characterized in that: The first constraint condition for obtaining the rolling update compliance rate is used to determine the initial rolling update compliance rate, specifically: The first constraint condition includes the maximum offset frequency of the rolling adjustment of the scheduling plan and the response coupling capability of the scheduling models at each time scale; Obtain the frequency and amplitude of scheduling deviations of multi-time scale models within a period and construct a scheduling deviation sample set; Combined with the response coupling capability of the time-scale scheduling model, the impact of the response delay of each scheduling model on scheduling consistency after the rolling adjustment is triggered is analyzed; According to the maximum acceptable offset frequency, the coordination stability of the system at different frequencies is evaluated; Obtain the historical rolling update compliance rate data set and its stability and consistency loss functions, and filter the compliance rate based on the first constraint condition; Based on the minimum deviation matching, the rolling update compliance rate with the minimum deviation from the current system is selected from the filtered historical rolling update compliance rates as the initial rolling update compliance rate.

3. The smart grid multi-time scale resource scheduling optimization method according to claim 2 is characterized in that: The second constraint condition for obtaining the scheduling margin configuration ratio quantifies the initial scheduling margin configuration ratio, specifically: The second constraint condition includes the load forecast error distribution, the fluctuation range of renewable energy output and the minimum guarantee capacity of the dispatching resources; The scheduling margin configuration ratio is the ratio of the resource redundancy rate to the accident response demand in a typical operation scenario, and the accident response demand is quantitatively obtained by analyzing the sudden increase in load and the fluctuation of renewable energy; The second constraint condition is used to constrain the scheduling margin configuration ratios of several multi-scale scheduling systems within a historical preset period, and the initial scheduling margin configuration ratio is obtained by averaging.

4. The smart grid multi-time scale resource scheduling optimization method according to claim 3 is characterized in that: The initial parameters are simulated by multiple samples to generate several configuration arrays to be adjusted, specifically: The initial parameters include an initial rolling update compliance rate and an initial scheduling margin configuration ratio; Determine a value range of a rolling update compliance rate and a scheduling margin configuration ratio based on the first constraint and the second constraint; Based on Latin hypercube sampling, a number of configuration arrays to be adjusted are generated within a value range, wherein the configuration arrays include different combinations of rolling update compliance rates and scheduling margin configuration ratios.

5. The smart grid multi-time scale resource scheduling optimization method according to claim 4 is characterized in that: The collaborative assessment is specifically: The collaborative evaluation obtains characteristic data for evaluating the degree of adaptation of the configuration data by performing characteristic analysis on the multi-time scale scheduling system; The driving effect evaluation model is obtained by combining the characteristic data obtained for evaluating the degree of adaptation of the configuration data with historical data for training, wherein the characteristic data includes the characteristics of scheduling fluctuations across time scales and the characteristics of dynamic matching of resource utilization.

6. The smart grid multi-time scale resource scheduling optimization method according to claim 5 is characterized in that: The high-order coordinated response display surface is fitted based on the evaluation results and the configuration array to be adjusted, specifically: Based on the cross-time scale scheduling fluctuation characteristics and the dynamic matching characteristics of resource utilization, a multi-dimensional feature mapping space is constructed to characterize the response law of the multi-time scale scheduling system. The dimensions of the multidimensional feature mapping space include cross-time scale scheduling fluctuation characteristics, resource utilization dynamic matching characteristics, and driving effect evaluation values; Associatively mapping the characteristic parameters of each group of configuration arrays to be adjusted and their corresponding driving effect evaluation values ​​to form a group of mapping sample points; Based on the mapping sample points, a high-order collaborative response surface covering the entire feature mapping domain is fitted and constructed to reflect the changing trend of the scheduling collaborative performance of the system under different configuration combinations.

7. The smart grid multi-time scale resource scheduling optimization method according to claim 6 is characterized in that: The scheduling sensitive area of ​​the surface is selected according to actual needs, the optimal configuration array is screened, and multi-time scale resource scheduling is driven, specifically: Determine several peak areas of the high-order synergistic response display surface, and expand the range based on several peaks according to the preset dynamic control amplitude, so as to construct several candidate areas for configuration array adjustment; Screen several candidate areas according to the actual needs of the scheduling target; If the actual demand is short-term response capability, the area with the highest rolling update compliance rate among the candidate areas is selected as the scheduling sensitive area; If the actual demand is system stability, the area with the highest scheduling margin configuration among the candidate areas is selected as the scheduling sensitive area; If the actual demand is resource utilization efficiency, the area with the highest peak value among the candidate areas is selected as the scheduling sensitive area; The configuration array corresponding to the peak value in the scheduling sensitive area is taken as the optimal configuration array to drive multi-time scale resource scheduling.

8. The smart grid multi-time scale resource scheduling optimization method according to claim 7 is characterized in that: The specific method for obtaining the cross-time scale scheduling fluctuation characteristics is as follows: Under different scheduling time scales, the processing time from request to execution completion is obtained as the response time; For the same time scale, calculate the average of several response times; Obtain resource scheduling amounts and total durations at different time scales, and calculate scheduling efficiency; Set up an initial cross-time scale fluctuation model based on average response time and dispatch efficiency; Set response time points for performance testing and collect scheduling fluctuation data at each point; According to the fluctuation amplitude data, the initial fluctuation model parameters are optimized based on the nonlinear least squares method to obtain a scheduling fluctuation characteristic calculation model, wherein the initial fluctuation model parameters include the maximum fluctuation amplitude, the change speed and the sensitivity characteristics.

9. The smart grid multi-time scale resource scheduling optimization method according to claim 8, characterized in that: The specific method for obtaining the resource utilization dynamic matching feature is as follows: Obtain resource utilization changes and scheduling fluctuations under different scheduling strategies and resource allocations, and build a matching evaluation model through the scheduling algorithm; Perform clustering on the matching evaluation model; Based on the evaluation model features after clustering, the matching accuracy evaluation features based on resource fluctuation, scheduling error and contention are calculated; The resource utilization under different scheduling strategies is simulated by the evaluation model, and the timeliness model is established to obtain the resource allocation timeliness evaluation characteristics, which are then combined with the matching accuracy evaluation characteristics to obtain the dynamic matching characteristics of resource utilization.

10. A system using the smart grid multi-time scale resource scheduling optimization method according to any one of claims 1 to 9, characterized in that: It includes an initial parameter acquisition module, a configuration array acquisition module, a drive evaluation module and a configuration array adjustment module; An initial parameter acquisition module is used to acquire a first constraint condition of a rolling update compliance rate and determine an initial rolling update compliance rate; acquire a second constraint condition of a scheduling margin configuration ratio and quantify the initial scheduling margin configuration ratio; The configuration array acquisition module is used to perform multi-sample simulation on the initial parameters and generate several configuration arrays to be adjusted; The driver evaluation module is used to map the configuration array to be adjusted to the multi-time scale resource scheduling through scheduling orchestration and optimization driving, and perform collaborative evaluation; The configuration array adjustment module is used to fit the high-order collaborative response display surface based on the evaluation results and the configuration array to be adjusted; select the scheduling sensitive area of ​​the surface according to actual needs, screen the best configuration array, and drive multi-time scale resource scheduling.

Images