Multi-supply coordinated scheduling system and method for regional integrated energy system

Abstract

The present invention relates to the field of energy coordination technology, and in particular to a multi-supply collaborative scheduling system and method for a regional integrated energy system, comprising: a data acquisition module for acquiring, in real time, a data set of equipment operating status and a data set of energy load demand in the regional integrated energy system; a multi-cooperative strategy generation module for calculating the data set of equipment operating status and the data set of energy load demand using a collaborative scheduling model based on multi-agent game to obtain a multi-cooperative scheduling strategy; a strategy update module for acquiring, in real time, external environmental information and inputting it and the multi-cooperative scheduling strategy into a preset strategy update node analysis model to generate the next strategy update time node; and a duration feature extraction module for collecting multiple continuous strategy update time nodes and performing duration feature extraction. The system can achieve collaborative optimization scheduling of multiple energy forms in a complex and changing environment, thereby improving energy utilization efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of energy coordination, and in particular to a multi-supply coordinated scheduling system and method for a regional integrated energy system. Background Art

[0002] With the continuous growth of global energy demand and the transformation of energy structures, regional integrated energy systems (RISs)—complex energy supply and management networks that integrate multiple energy forms (such as electricity, heat, cooling, and gas), multiple energy devices, and multiple energy users—are gaining increasing attention. In RISs, different types of energy supply equipment, such as power generation, heating, and gas supply equipment, must operate in coordination to meet the energy needs of various energy-consuming groups within the region.

[0003] The operation of a regional integrated energy system is influenced not only by the operating status of its own equipment and energy load demand, but also by external environmental constraints such as grid electricity prices, natural gas prices, and meteorological data. These ever-changing external environmental factors impact both energy supply costs and demand characteristics, requiring scheduling strategies to dynamically adjust to these changes. Existing scheduling strategies for regional integrated energy systems mostly utilize fixed update cycles and lack quantitative analysis of update node characteristics, making them difficult to adapt to complex and changing internal and external environments. This fixed update cycle can easily lead to policy lags or frequent adjustments, especially when the external environment fluctuates dramatically. Summary of the Invention

[0004] The present invention provides a multi-supply collaborative scheduling system and method for a regional integrated energy system that can achieve collaborative optimization scheduling of multiple energy forms in a complex and changeable environment and improve energy utilization efficiency, which can effectively solve the problems in the background technology.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a multi-supply coordinated scheduling system for a regional integrated energy system, comprising:

[0006] The data acquisition module is used to obtain the equipment operation status data set and energy load demand data set in the regional integrated energy system in real time;

[0007] A multi-element collaborative strategy generation module uses a built-in multi-element collaborative scheduling model to calculate the equipment operation status data set and the energy load demand data set to obtain a multi-element collaborative scheduling strategy;

[0008] A strategy update module is used to obtain external environment information in real time, and input it and the multi-element collaborative scheduling strategy into a preset strategy update node analysis model to generate the next strategy update time node;

[0009] Duration feature extraction module, used to collect multiple consecutive strategy update time nodes, and perform duration feature extraction to obtain the duration of multiple strategies;

[0010] A stability evaluation module, configured to eliminate environmental external factors for the duration of each of the strategies, and to perform stability evaluation on the durations of the strategies after elimination to obtain a stability index;

[0011] The model optimization and deployment module is used to optimize the multivariate collaborative scheduling model according to the difference between the stability index and the preset stability threshold, and update and deploy the optimized model into the regional integrated energy system.

[0012] In combination with the first aspect, in one possible design, the duration feature extraction module is further configured as follows:

[0013] The multiple consecutive policy update time nodes include at least the current policy update time node, the next policy update time node, and the historical policy update time node that is closest to the current policy update time node in terms of time dimension.

[0014] In a second aspect, the present invention further provides a multi-supply coordinated scheduling method for a regional integrated energy system, comprising:

[0015] Acquire the equipment operation status dataset and energy load demand dataset in the regional integrated energy system in real time, and input them into the multi-element coordinated scheduling model to obtain the multi-element coordinated scheduling strategy;

[0016] Acquire external environment information in real time, and input it and the multi-element collaborative scheduling strategy into the strategy update node analysis model to generate the next strategy update time node;

[0017] Collect multiple consecutive strategy update time nodes and extract duration features to obtain the duration of multiple strategies;

[0018] Eliminating environmental external factors for the duration of each strategy, and performing stability evaluation on the durations of multiple strategies after elimination to obtain a stability index;

[0019] Based on the difference between the stability index and the preset stability threshold, the multi-element collaborative scheduling model is optimized, and the optimized multi-element collaborative scheduling model is updated and deployed in the regional integrated energy system.

[0020] In combination with the second aspect, in one possible design, the external environmental information includes grid electricity prices, natural gas prices, and meteorological data.

[0021] In combination with the second aspect, in a possible design, the equipment operation status data set includes operation status information of various types of energy supply equipment, and the energy load demand data set includes real-time energy demand information of different types of energy load groups.

[0022] In combination with the second aspect, in a possible design, the multiple consecutive policy update time nodes include at least the current policy update time node, the next policy update time node, and the historical policy update time node that is closest to the current policy update time node in the time dimension.

[0023] In conjunction with the second aspect, in a possible design, the policy duration represents the time span between two adjacent policy update time nodes;

[0024] The multiple policy durations include at least the policy duration before the current update and the policy duration after the current update.

[0025] In combination with the second aspect, in a possible design, the multi-element collaborative scheduling model adopts a composite model, including a supply and demand interactive game model, a user group evolution game model and a benefit evaluation model.

[0026] In conjunction with the second aspect, in one possible design, the active update triggering condition of the strategy update node analysis model is: in response to the comprehensive fitness of the current multi-element coordinated scheduling strategy decaying to a set fitness threshold, it is determined that the current multi-element coordinated scheduling strategy is invalid and needs to be actively updated;

[0027] The comprehensive fitness calculation formula is:

[0028] ;

[0029] Where F(t) represents the comprehensive fitness; t represents the duration of the current multi-element collaborative scheduling strategy; F0 represents the normalized initial fitness, indicating that the initial state of the strategy is optimal; -ΔC price t indicates that the price shock decays linearly over time. The larger the shock, the faster the comprehensive fitness decreases; -ΔE weather ·t 2 Indicates that the meteorological impact decays with the square of time, reflecting the nonlinear impact of the emergency; A s +A d It represents the weighted sum of supply-side and demand-side adaptability. The larger the value, the more robust the strategy.

[0030] The duration of the current multi-element collaborative scheduling strategy is reversely solved by setting the fitness threshold, and the next update time node is calculated in combination with the update time node of the current strategy.

[0031] In combination with the second aspect, in a possible design, the ΔC price The impact factor of price fluctuation is calculated as follows:

[0032] ;

[0033] Among them, P e (t) represents the electricity price at time t; P e (t-Δt) represents the electricity price at the previous monitoring time point (t-Δt); P g (t) represents the natural gas price at the current time t, in yuan / m³; P g (t-Δt) represents the natural gas price at the previous monitoring time point (t-Δt); d1 max Indicates the peak upper limit of the electricity price within the floating range of the demand-side time-of-use electricity price; d1 min Indicates the lower limit of the electricity price valley in the floating range of the demand side time-of-use electricity price; P g base It represents the historical benchmark value of natural gas prices and is used to measure the degree to which the current gas price deviates from the historical average.

[0034] Through the technical solution of the present invention, the following technical effects can be achieved: through the closed-loop linkage of multiple modules, an adaptive mechanism of dynamic perception, strategy generation, node optimization, and stability iteration is constructed, breaking through the limitations of static updates and single-target optimization of traditional scheduling systems, and realizing efficient, stable, and sustainable collaborative scheduling in complex and changeable energy supply and demand scenarios; the data acquisition module collaborates with the multi-dimensional collaborative strategy generation module to generate initial strategies based on real-time and accurate equipment and load data, laying the foundation for system operation; the strategy update module determines a new update time node in combination with external environmental information, so that scheduling no longer relies on a fixed cycle and can flexibly adapt to environmental changes; the duration feature extraction module collects the durations of multiple update nodes, and the stability evaluation module eliminates external environmental factors on this basis to evaluate stability, which can accurately reflect the inherent stability characteristics of system strategy adjustment, and finally the model optimization and deployment module optimizes the model according to the stability index and updates the deployment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 This is a structural block diagram of the multi-supply coordinated dispatching system for a regional integrated energy system in the present invention;

[0037] Figure 2 This is a logic flow chart of the multi-supply coordinated dispatching system for a regional integrated energy system in the present invention;

[0038] Figure 3 It is a logical flow chart of the supply and demand interactive game model, user group evolution game model and benefit evaluation model in the present invention. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0040] The present application is described below in conjunction with the accompanying drawings.

[0041] like Figures 1 to 2 As shown, the present invention provides a multi-supply coordinated scheduling system for a regional integrated energy system, specifically comprising: a data acquisition module, a multi-coordinated strategy generation module, a strategy update module, a duration feature extraction module, a stability assessment module, and a model optimization deployment module; the specific implementation is as follows:

[0042] The data acquisition module acquires in real time the equipment operation status dataset and the energy load demand dataset in the regional integrated energy system; wherein the equipment operation status dataset includes the operation status information of various energy supply equipment, and the energy load demand dataset includes the real-time energy demand information of different types of energy load groups; the equipment operation status dataset and the energy load demand dataset correspond one-to-one in the temporal and spatial dimensions;

[0043] The multivariate collaborative strategy generation module uses a built-in multivariate collaborative scheduling model to calculate the equipment operation status dataset and the energy load demand dataset to obtain a multivariate collaborative scheduling strategy; wherein the multivariate collaborative scheduling model adopts a composite model, including a supply and demand interactive game model, a user group evolution game model, and a benefit evaluation model;

[0044] The strategy update module acquires external environmental information in real time and inputs it and the multi-element collaborative scheduling strategy into a preset strategy update node analysis model to generate the next strategy update time node; the external environmental information includes grid electricity prices, natural gas prices and meteorological data;

[0045] The duration feature extraction module collects multiple consecutive policy update time nodes and performs duration feature extraction to obtain multiple policy durations; the multiple consecutive policy update time nodes include at least the current policy update time node, the next policy update time node, and the historical policy update time node closest to the current policy update time node in terms of time dimension; the policy duration represents the time span between two adjacent policy update time nodes; the multiple policy durations include at least the policy duration before the current update and the policy duration after the current update;

[0046] The stability evaluation module eliminates environmental external factors for the duration of each strategy, and performs stability evaluation on the durations of multiple strategies after elimination to obtain a stability index;

[0047] The model optimization and deployment module optimizes the multivariate collaborative scheduling model according to the difference between the stability index and the preset stability threshold, and updates and deploys the optimized model to the regional integrated energy system.

[0048] In this embodiment, through the closed-loop linkage of multiple modules, an adaptive mechanism of dynamic perception, strategy generation, node optimization, and stability iteration is constructed, breaking through the limitations of static updates and single-objective optimization of traditional scheduling systems, and realizing efficient, stable, and sustainable coordinated scheduling in complex and changing energy supply and demand scenarios. The strategy update module adjusts the update time nodes in real time based on external environmental fluctuations (such as electricity prices and weather), while the stability assessment module accurately identifies the system's own stability defects by eliminating external environmental interference. With the combination of the two, the system can not only quickly respond to external mutations (such as extreme weather) but also avoid frequent strategy adjustments caused by environmental noise, achieving a balance between sensitive response and steady-state operation. For example, when electricity prices fluctuate sharply, the system can shorten the update cycle to reduce costs. At the same time, stability assessment can suppress over-optimization caused by short-term fluctuations and prevent frequent equipment startup and shutdown.

[0049] The stability assessment module eliminates external environmental factors and extracts purely internal operating characteristics (such as equipment aging and load evolution patterns), enabling the model optimization and deployment module to specifically strengthen the system's inherent vulnerabilities. For example, after eliminating the impact of meteorological conditions on heating load, if the stability index remains below the threshold, this directly exposes insufficient equipment coordination efficiency. The optimization algorithm can prioritize adjusting the weight parameters of the supply and demand game model rather than blindly expanding the proportion of renewable energy.

[0050] The duration feature extraction module analyzes the historical patterns of the strategy duration cycle (such as seasonality and event-driven characteristics) and combines this with the real-time generated update time nodes to give the system the dual characteristics of short-term agility and long-term robustness. For example, during the winter heating season, the system can autonomously learn the strong correlation between weather and load, automatically extending the strategy update cycle to match thermal inertia characteristics while retaining the ability to respond to sudden cold waves. The above-mentioned multi-time-scale coupling mechanism enables the system to exhibit human-like decision-making adaptability in complex environments.

[0051] In the multi-supply coordinated dispatch system of the regional integrated energy system, the adaptive mechanism of dynamic perception, strategy generation, node optimization, and stability iteration, through the closed-loop linkage of multiple modules, can effectively respond to complex and changing energy supply and demand scenarios. The details are as follows:

[0052] The data acquisition module acquires the equipment operating status data set and energy load demand data set of the regional integrated energy system in real time. At the same time, the strategy update module obtains external environmental information such as grid electricity prices, natural gas prices, and meteorological data in real time to understand the internal and external conditions of the system and provide an accurate basis for subsequent decision-making.

[0053] The multi-factor collaborative strategy generation module uses a built-in multi-factor collaborative scheduling model to calculate equipment operating status and energy load demand data. This model uses a composite model that includes a supply-demand interactive game model, a user group evolution game model, and a benefit evaluation model. It comprehensively considers multiple factors to generate a multi-factor collaborative scheduling strategy to achieve reasonable energy allocation.

[0054] The strategy update module inputs external environmental information and multi-faceted collaborative scheduling strategies into a preset strategy update node analysis model to calculate indicators such as comprehensive fitness. When the comprehensive fitness decays to a set threshold or the external impact factor exceeds a preset value, the next strategy update time node is determined, allowing the scheduling to flexibly adapt to environmental changes and avoid strategy lags.

[0055] The duration feature extraction module collects strategy update time nodes to obtain the strategy duration. The stability assessment module evaluates the stability after eliminating external environmental factors to obtain a stability index. The model optimization and deployment module optimizes and updates the deployment of the multi-element collaborative scheduling model based on the difference between the index and the preset threshold, continuously improving system stability and energy utilization efficiency, and achieving sustainable collaborative scheduling.

[0056] The present invention also provides a multi-supply coordinated scheduling method for a regional integrated energy system, which specifically includes the following steps:

[0057] Step S1: acquiring a device operation status dataset and an energy load demand dataset in a regional integrated energy system in real time, and inputting both into a multivariate collaborative scheduling model to obtain a multivariate collaborative scheduling strategy; the device operation status dataset and the energy load demand dataset have a one-to-one correspondence in the spatiotemporal dimension;

[0058] Step S2: acquiring external environment information in real time, and inputting it and the multi-element collaborative scheduling strategy into the strategy update node analysis model to generate the next strategy update time node;

[0059] Step S3: Collect multiple consecutive strategy update time nodes, and extract duration features to obtain multiple strategy durations;

[0060] Step S4: Eliminate environmental external factors for each duration of the strategy, and perform stability evaluation on the durations of the strategies after elimination to obtain a stability index;

[0061] Step S5: Based on the difference between the stability index and the preset stability threshold, the multi-element collaborative scheduling model is optimized, and the optimized multi-element collaborative scheduling model is updated and deployed into the regional integrated energy system.

[0062] In this embodiment, step S1 generates a strategy by acquiring real-time data sets of equipment operating status and energy load demand and inputting them into the multivariate collaborative scheduling model. This ensures that the underlying data for scheduling decisions is always up-to-date and accurate. Combined with the real-time monitoring and analysis of external environmental information in step S2, this allows for rapid response to external changes, such as electricity price fluctuations or weather changes, enabling immediate adjustments to the scheduling strategy and avoiding the lag issues associated with fixed-cycle scheduling strategies. Steps S3 and S4 eliminate the influence of external environmental factors by extracting duration features and performing stability assessments at multiple consecutive policy update time nodes, thereby obtaining a stability index. This not only improves the ability to cope with complex and changing internal and external environments, but also reduces the frequent policy adjustments caused by drastic external environmental fluctuations, thereby enhancing overall stability and reliability. Step S5 optimizes and redeploys the multivariate collaborative scheduling model based on the stability assessment results to ensure it remains in the optimal configuration. Through closed-loop feedback control, the entire process, from data acquisition, strategy generation, external environment analysis, stability assessment, to model optimization, is managed, forming a complete dynamic control cycle. This not only improves energy efficiency and reduces operating costs, but also enables the efficient integration and coordinated operation of multiple energy sources and equipment within the region.

[0063] In some embodiments of the present invention, a dynamic multi-element collaborative scheduling strategy is generated through real-time data collection and composite model calculation. The data collection is as follows:

[0064] For equipment operating status data sets, IoT sensors are used to collect real-time operating parameters of energy supply equipment such as electricity, heat, cooling, and gas. These parameters include, but are not limited to, generator output, heat pump heating efficiency, gas storage tank pressure, and refrigeration equipment performance coefficient. Discrete events such as equipment start and stop status and fault alarms are also recorded. Data is spatiotemporally labeled using unified timestamps and geographic coordinates, such as GIS grids or equipment codes.

[0065] For the energy load demand data set, the real-time demand baselines of electricity, heat, cooling and gas are collected by terminal devices such as smart meters and heat meters according to user groups such as industry, commerce and residence, and meteorological compensation parameters such as temperature and humidity are introduced to normalize the data; for example, when the temperature drops sharply, the demand for heating will increase significantly, and such correlation needs to be dynamically corrected at the data level; all load data must be strictly aligned with the equipment status data in the time and space dimensions to ensure that the cooling load demand of a building complex in the same time slice can be accurately mapped to the operating parameters of the corresponding refrigeration unit.

[0066] Furthermore, if Figure 3 As shown in the figure, the multi-element collaborative scheduling model adopts a composite model, which is composed of a supply-demand interactive game model, a user group evolution game model, and a benefit evaluation model. It forms a closed loop through the data flow series and feedback mechanism. The specific implementation is as follows:

[0067] The supply-demand interactive game model simulates the game behavior between the energy supply side (power generation, heating, gas equipment and waste heat recovery system) and the demand side (user group) based on equipment operating status and load demand data. The supply-side game is based on the constraints of equipment output cost and carbon emissions to solve the Nash equilibrium solution of the coordinated output of multiple energy equipment. For example, when gas turbines and heat pumps meet electricity and heat demand, they dynamically allocate output ratios through distributed optimization algorithms; the demand-side game introduces real-time electricity price and heat price signals to simulate the elastic response of user load to price changes. For example, when electricity prices rise, users may reduce non-essential electricity consumption, and the system needs to recalculate the supply and demand balance point; the input of the supply-demand interactive game model is the equipment output capacity parameters in the equipment operating status data and the real-time demand baseline in the energy load demand data; the output is a preliminary scheduling strategy, including equipment output plan and demand-side price signals.

[0068] The user group evolutionary game model is used to analyze the dynamic evolution path of the energy consumption behavior of user groups, including the user strategy benefit function, which defines weight parameters such as economic cost and comfort preference. For example, the cost sensitivity weight of industrial users is set to 0.7, and the comfort weight of residential users is set to 0.6. The replication dynamics equation is used to describe the diffusion of user strategies, and the Monte Carlo method is combined to predict the load change trend. For example, in hot weather, the residential air-conditioning load may increase exponentially. The input of the user group evolutionary game model is the real-time demand of users in the energy load demand data and the dynamic price signal output by the supply and demand game model. The output is the revised load demand forecast and user behavior evolution recommendation.

[0069] The core mechanism of the benefit evaluation model is to quantitatively evaluate the comprehensive benefits of the scheduling strategy in multiple dimensions, including:

[0070] Economic indicators: Calculate equipment operating costs and energy procurement costs. For example, the cost of a gas turbine is 200 yuan per megawatt-hour.

[0071] Environmental performance indicators: assess carbon emission intensity, for example, coal-fired units emit 0.8 tons of carbon per megawatt-hour;

[0072] Reliability indicators: Analyze the probability of power outages. For example, the energy storage system must ensure 99.9% power availability.

[0073] User satisfaction index: Based on parameters such as load satisfaction rate and price acceptance, for example, the user satisfaction threshold is set at 90%;

[0074] Its input is the equipment output plan output by the supply and demand game model and the load demand forecast corrected by the user evolution model; the output is the multi-element collaborative scheduling strategy with the highest comprehensive score.

[0075] The above dynamic calculation process can be briefly described as follows: the supply and demand interactive game model generates the initial strategy for equipment output and price incentives; the user evolution model predicts load changes based on price signals and feeds them back to the game model for iterative optimization; and the benefit evaluation model selects the Pareto optimal solution and determines the final scheduling strategy.

[0076] The multi-faceted coordinated scheduling strategy includes supply-side instructions and demand-side instructions. The supply-side instructions include the output information of various energy equipment and the switching temperature thresholds of the waste heat recovery system; the demand-side instructions include user response instruction information, time-of-use electricity price fluctuation range, and interruptible load priority list.

[0077] In this embodiment, the supply and demand interactive game model is used to integrate the equipment output capacity and user demand in real time, and the supply and demand balance is adjusted in combination with the elasticity of price signals; the user group evolution game model quantifies economic costs and comfort preferences, and uses the Monte Carlo method to simulate the surge in air-conditioning load under high temperature weather, thereby improving demand forecast accuracy and reducing supply and demand deviations; the benefit evaluation model integrates multi-dimensional indicators such as economy, environmental protection, and reliability, and screens non-inferior solutions through the Pareto front; the three sub-models form a closed loop of game, evolution, and evaluation to achieve continuous optimization; after the demand-side electricity price is adjusted, the evolution model feeds back the load changes and drives the game model to recalculate the equipment output; the supply-side instructions coordinate the complementary energy of electricity, heat, and gas, for example, the waste heat recovery system automatically shuts down when the heating demand is low, reducing redundant losses; the demand-side time-of-use electricity price guides users to use energy off-peak and improve overall energy efficiency.

[0078] In some embodiments of the present invention, in order to achieve accurate prediction of strategy update nodes for a regional integrated energy system, the external environmental information includes grid electricity prices, natural gas prices, and meteorological data; the data source and collection method of the external environmental information include:

[0079] Grid electricity price data: Obtain current grid time-of-use electricity prices in real time through the power trading system, such as peak, valley, and flat electricity prices, and record electricity price fluctuations, such as the maximum / minimum price difference per hour;

[0080] Natural gas price data: Access the natural gas trading market database to obtain real-time regional pipeline natural gas prices and forecast prices for the next 24 hours;

[0081] Meteorological data: Real-time data such as temperature, humidity, and wind speed in the area are obtained from meteorological websites, and combined with weather forecast information for the next 6 hours, such as sudden temperature changes and rainfall probability.

[0082] Before utilizing this external environmental information, data preprocessing and feature extraction are required. These include: normalizing grid electricity price data to calculate the deviation between the current price and the historical mean, such as using Z-Score normalization to quantify the intensity of price fluctuations; extracting short-term trend features from natural gas price data, such as using linear regression to fit the slope of future price changes; and detecting temperature mutations in meteorological data. For example, if the temperature change rate within a sliding window exceeds 3°C / hour, it is considered a mutation event.

[0083] In this embodiment, the multi-source fusion and dynamic analysis of grid electricity prices, natural gas prices, and meteorological data can perceive the core external factors affecting energy supply and demand in real time. For example, when high temperature weather causes a surge in air conditioning load and grid electricity prices are at their peak, the strategy update node analysis model will immediately shorten the strategy update time node, quickly respond to load changes, and switch to low-cost energy.

[0084] More specifically, the calculation process of the strategy update node analysis model includes:

[0085] First, calculate the impact factor of price fluctuations. The calculation formula is as follows:

[0086] ;

[0087] Where, ΔC price The impact factor representing price fluctuations;

[0088] P e (t) represents the electricity price at the current time t, in yuan / kWh; P e (t-Δt): The electricity price at the previous monitoring time point (t-Δt); calculate the absolute value of the fluctuation of the electricity price within the Δt time window; for example, if the current electricity price is 1.5 yuan / kWh and the previous time point was 1.2 yuan / kWh, then the fluctuation range is 0.3 yuan / kWh; P g (t): natural gas price at the current time t, in yuan / m³; P g (t-Δt): The natural gas price at the previous monitoring time point; reflects the absolute value of the short-term fluctuation of the natural gas price. For example, if the current gas price is 3.0 yuan / m³ and the previous price was 2.8 yuan / m³, the fluctuation range is 0.2 yuan / m³.

[0089] d1 max Indicates the peak price upper limit defined in the demand-side time-of-use electricity price fluctuation range; for example, the peak price upper limit is 1.8 yuan / kWh; d1 min The denominator represents the lower limit of the electricity price valley defined within the demand-side TOU price fluctuation range. For example, the lower limit of the off-peak price is 0.8 yuan / kWh. The denominator is the preset fluctuation range of the electricity price (1.8-0.8=1.0 yuan / kWh), which is used to normalize electricity price fluctuations. If the absolute value of the actual fluctuation (the numerator) exceeds the denominator, the volatility is greater than 1, indicating that the electricity price is outside the allowable fluctuation range and requires emergency intervention.

[0090] P g base Indicates the historical benchmark value of natural gas prices, usually the average price over a certain period of time. For example, if the average gas price over the past 30 days is 2.5 yuan / m³, then P g base =2.5, which is used to measure the degree to which the current gas price deviates from the historical average; if the gas price volatility is greater than 1, such as the current gas price is 5.0 yuan / m³ and the benchmark price is 2.5 yuan / m³, then the volatility is 1.0, indicating that the gas price deviates sharply from the normal level.

[0091] Secondly, calculate the impact factor of the sudden change in weather conditions. The calculation formula is as follows:

[0092] ;

[0093] Where ΔE weather Indicates the impact factor of sudden climate change;

[0094] T(t)-T(t-Δt) represents the absolute value of the temperature difference between the current temperature and the previous time period; for example, if the temperature rises suddenly from 25°C to 30°C, the difference is 5°C;

[0095] s3 represents the temperature threshold for the waste heat recovery system to start and stop. For example, if the waste heat recovery system starts when the temperature is above 80°C, then s3 = 80°C. The denominator is the threshold. When the temperature difference approaches the threshold, the meteorological impact index will be significantly amplified.

[0096] H(t)-H(t-Δt) represents the absolute difference between the current humidity and the humidity in the previous period; for example, if the humidity drops from 60% to 50%, the difference is 10%;

[0097] α T represents the temperature shock weight, reflecting the impact of temperature changes on system load; for example, in heating-dominated areas, the temperature weight is higher; α H Represents the humidity impact weight, which is applicable to humidity-sensitive scenarios such as data center cooling.

[0098] Then, the adaptability factor of the supply side to the multi-coordinated scheduling strategy is calculated as follows:

[0099] ;

[0100] Among them, A s represents the adaptability factor of the supply side to the multi-coordinated scheduling strategy;

[0101] N s Indicates the number of various energy devices;

[0102] s i current Indicates the current output value of the device; for example, the current charging and discharging power of the energy storage system is 50kW;

[0103] s i max Indicates the maximum output capacity of the equipment; for example, the rated power of the energy storage system is 100kW;

[0104] s i flex =s i max -s i currentIndicates the device's adjustable margin; for example, the energy storage system's remaining adjustable power is 50kW. If the device's current output is close to the upper limit, the score for this item is low, indicating that the device's adjustable capacity is insufficient and the strategy needs to be updated as soon as possible. The formula takes the average of multiple devices to measure overall supply-side flexibility.

[0105] Afterwards, the adaptability factor of the demand side to the multi-coordinated scheduling strategy is calculated using the following formula:

[0106] ;

[0107] Among them, A d represents the adaptability factor of the demand side to the multi-coordinated scheduling strategy;

[0108] N d Indicates the number of instructions in the user response instruction information;

[0109] d j actual Indicates the actual response effect of users; for example, during the peak period of time-of-use electricity prices, users actually reduce their load by 15%;

[0110] d j target Indicates the target value of the instruction; for example, the demand-side instruction requires a 20% load reduction during peak hours;

[0111] w j represents the priority weight of the jth instruction, which comes from the interruptible load priority list in the demand-side instruction; for example, the weight of industrial users is 0.8 and that of commercial users is 0.5;

[0112] If the actual response rate is lower than the target and the priority is high, it indicates that the demand-side execution effect is poor; the weighted sum of multiple instructions (Nd is the number of instructions) is taken to comprehensively evaluate the effectiveness of the demand-side strategy.

[0113] Next, calculate the comprehensive fitness. The calculation formula is as follows:

[0114] ;

[0115] Among them, F(t) represents the comprehensive fitness;

[0116] t represents the duration of the strategy;

[0117] F0 represents the normalized initial fitness, indicating that the initial state of the strategy is optimal;

[0118] -ΔC price t indicates that the price shock decays linearly over time; the larger the shock, the faster the fitness decreases;

[0119] -ΔE weather ·t 2It indicates that the meteorological shock decays with the square of time, reflecting the nonlinear impact of sudden events; for example, when high temperature persists, the cumulative effect of meteorological shock accelerates the decline of fitness;

[0120] A s +A d It represents the weighted sum of supply-side and demand-side adaptability. The larger the value, the more robust the strategy.

[0121] Finally, set the trigger condition for active update. When the comprehensive fitness decays to the set fitness threshold, the current strategy is considered invalid and needs to be actively updated. For example, if the fitness threshold is set to 70%, if ΔC price =0.3, ΔE weather =5,A s +A d =0.8, then:

[0122] 0.7=1·e -0.3t-5t^2 0.8;

[0123] Solving the above formula, we obtain t≈0.4 hours; that is, the current strategy can be sustained for 0.4 hours, and an active strategy update will be performed after 0.4 hours.

[0124] On the other hand, you can also set passive update trigger conditions. For example, if any of the impact factors of price fluctuations and weather changes exceeds its corresponding preset trigger value, an update will be forced immediately.

[0125] In this embodiment, the strategy update node analysis model realizes the conversion of abstract system states into computable mathematical indicators through hierarchical calculation, dynamic attenuation, and multi-source fusion; based on time attenuation and threshold triggering, it balances stability and real-time performance; coordinates supply-side equipment capabilities and demand-side user behavior to improve overall energy efficiency; is applicable to scenarios such as power market transactions, microgrid scheduling, and smart city energy management, and provides theoretical support and implementation tools for the active optimization of multi-faceted collaborative scheduling strategies; active updates are made by setting a fitness threshold, and when the comprehensive fitness decays to the threshold, the strategy is judged to be invalid and actively updated, and timely adjustments can be made when the strategy gradually becomes unsuitable for the environment; passive updates are immediately forced to update when the impact factor of price fluctuations or sudden weather changes exceeds the preset trigger value, and can quickly respond to drastic changes in the external environment. The double-insurance update mechanism ensures that the scheduling strategy can adapt to various changes inside and outside the system in a timely manner, thereby improving the stability and reliability of the operation of the regional integrated energy system.

[0126] In some embodiments of the present invention, step S3 extracts the duration characteristics of the policy by analyzing the policy update time node, which is specifically implemented as follows:

[0127] Step S31: Collect multiple consecutive policy update time nodes. There are clear requirements for the collected time nodes, which must at least cover the current policy update time node, the next policy update time node, and the historical policy update time node that is closest to the current policy update time node in terms of time dimension. For example, if a policy update is currently in progress, then the current policy update time node is the current moment; the next policy update time node is a future moment generated by the policy update node analysis model in step S2; and the historical policy update time node that is closest to the current policy update time node in terms of time dimension refers to the time point of the policy update that was closest to the current moment before the current update. By collecting the above time nodes, a continuous, chronologically ordered time node sequence can be constructed, providing a data foundation in terms of time dimension for subsequent analysis.

[0128] Step S32: Define the concept of policy duration, which represents the time span between two adjacent policy update time nodes. For example, if the last policy update time node is t1 and the current policy update time node is t2, then the policy duration before the current update is t2-t1. Similarly, if the next policy update time node is t3, then the policy duration after the current update is t3-t2.

[0129] Step S33: Since multiple continuous strategy update time nodes are collected, multiple strategy durations can be obtained; the duration data at least includes the strategy duration before this update and the strategy duration after this update; by obtaining multiple strategy durations, the changes in the scheduling strategy can be analyzed from the time dimension; for example, by comparing different strategy durations, the stability of the strategy in different time periods can be understood; if the strategy duration is longer within a certain period of time, it means that the scheduling strategy in this period is relatively stable and can better adapt to the internal and external environment at that time; on the contrary, if the strategy duration is shorter, it may mean that the current scheduling strategy is difficult to adapt to environmental changes and needs further optimization and adjustment; at the same time, the data on multiple strategy durations also provide specific analysis objects for the subsequent step S4 to eliminate external environmental factors and evaluate their stability, which helps to understand the performance and characteristics of the regional integrated energy system scheduling strategy more comprehensively and in-depth.

[0130] In some embodiments of the present invention, in order to remove the impact of external shocks such as electricity prices, gas prices, and weather conditions, and accurately evaluate the robustness of the scheduling strategy under the influence of internal equipment and load demand, the specific evaluation is as follows:

[0131] Step S41: Separate the external environmental noise from the strategy duration, retain the pure strategy duration dominated by the system's internal operating characteristics (device status, load demand), and establish a mathematical model for elimination. The input data includes:

[0132] The strategy duration sequence is {t1,t2,...,t n}, where t i represents the duration of the i-th policy update;

[0133] The external shock factor series includes the price shock factor {ΔC price (1) ,ΔC price (2) ,...,ΔC price (n)} and meteorological impact factor {ΔE weather (1) ,ΔE weather (2) ,...,ΔE weather (n)};

[0134] The elimination model uses multiple linear regression to establish a quantitative relationship between the duration of the strategy and external impact factors:

[0135] ;

[0136] β0, β1, and β2 represent regression coefficients, reflecting the linear effect of external shocks on duration;

[0137] represents the residual term, which represents the duration fluctuation that cannot be explained by external shocks in the i-th strategy update, that is, the duration of the pure strategy after eliminating external factors;

[0138] Calculate the duration after elimination:

[0139] ;

[0140] After eliminating the impact of external fluctuations such as electricity prices and weather, the remaining time reflects the effectiveness of the strategy itself.

[0141] Step S42: Based on the strategy duration sequence {t1 adjusted ,t2 adjusted ,...,t n adjusted}Calculate the stability index, the stability of the quantitative strategy, the calculation formula is as follows:

[0142] CV=1-σ(t adjusted ) / μ(t adjusted );

[0143] Where CV represents the stability index, σ(t adjusted ) represents the standard deviation of the duration after elimination; μ(t adjusted) represents the mean of the duration after elimination; the smaller the stability index, that is, the closer the stability index is to 1, the lower the volatility of the strategy duration and the higher the stability; if the duration after elimination is completely constant (σ=0), the stability index is 1, indicating absolute stability.

[0144] In this embodiment, interferences such as electricity prices and weather are eliminated and stripped away through external environmental factors, and the stability of the strategy itself is quantified through the coefficient of variation, providing accurate input for the model optimization of step S5; solving the lag problem of the fixed update cycle strategy, and ensuring that the scheduling strategy maintains efficiency and robustness in the dynamic changes of the internal and external environment.

[0145] In some embodiments of the present invention, how to adjust and optimize the existing scheduling model based on the stability evaluation results of the policy and reapply the improved model to the system is as follows:

[0146] Step S51: Compare the stability index calculated in step S4 with the preset stability threshold. If the stability index is lower than the threshold, it means that the stability of the scheduling strategy generated by the current multi-element collaborative scheduling model is insufficient and needs to be optimized. The greater the difference between the two, the higher the optimization priority. On the contrary, if the stability meets the standard, no adjustment is required for the time being.

[0147] Step S52: When it is necessary to optimize the multi-element collaborative scheduling model, the following optimization strategy is adopted:

[0148] The supply-demand interactive game model is optimized to improve the matching between equipment output flexibility and load demand. A stability penalty term is introduced by updating the cost function in the game strategy: new cost function = original cost function + λ·|ΔS|; where λ is the penalty coefficient, dynamically adjusted using the Lagrange multiplier method; and ΔS represents the difference between the stability index and the preset stability threshold.

[0149] The optimization goal is to enhance the compliance and stability of users in responding to instructions. For example, if a user is required to reduce electricity consumption by 20%, but only achieves a 15% reduction, the system will lower the priority weight of such users and reduce their reliance on them. By introducing a reputation mechanism, users with long-term cooperation are given higher priority. For example, if a factory has responded well in the past, subsequent instructions will be assigned to it first, thereby improving the overall execution rate. The reputation value calculation formula is:

[0150] Reputation value = α·historical response rate + (1-α)·recent response rate;

[0151] Where α is the attenuation factor;

[0152] Optimization is performed on the benefit evaluation model with the goal of balancing economy and stability. An optimal solution is sought through an optimization algorithm, such as a multi-objective genetic algorithm, to achieve a balance between reducing energy costs (such as purchasing electricity during low-price periods) and improving stability. For example, the algorithm may recommend a slight increase in gas procurement costs, but reduce the volatility of the strategy duration by 30%, thereby significantly improving stability.

[0153] Step S53: The optimized model will not be put into use immediately. Instead, it will be simulated and run through historical data to ensure that key indicators such as stability and cost are improved. After verification, the system will adopt a progressive update strategy, as follows:

[0154] Run the new and old models simultaneously and compare the real-time results. For example, run the new model in area A and the old model in area B to see if the stability of area A improves.

[0155] After confirming that the new model is valid, the old model is seamlessly replaced through background technology to avoid service interruption;

[0156] If stability unexpectedly decreases after an update, for example due to data anomalies, the system automatically switches back to the old version to ensure safe operation.

[0157] In this embodiment, the adaptability and reliability of the regional integrated energy system are significantly improved through a dynamic optimization closed-loop mechanism; directional adjustments are triggered based on stability differences to avoid waste of resources and ensure that optimization focuses on key issues; stability penalty items are introduced into the supply and demand model to improve the equipment adjustment capability and load matching efficiency; the user model strengthens the weight of high-response rate users through a credit mechanism to improve the execution rate; the benefit model adopts a multi-objective optimization algorithm to balance economy and stability to avoid neglecting a single goal; through A / B test verification, hot update and automatic rollback mechanism, zero downtime for strategy updates is guaranteed to reduce implementation risks; combined with real-time evaluation and dynamic optimization, a closed loop of perception, analysis, decision-making and verification is formed to continuously adapt to complex environmental changes and achieve long-term stable and efficient operation of the system.

[0158] In some schemes, multiple embodiments of the present application can be combined and the combined scheme can be implemented. Optionally, some operations in the process of each method embodiment are optionally combined, and / or the order of some operations is optionally changed. In addition, the execution order between the steps of each process is only exemplary and does not constitute a limitation on the execution order between the steps. There can also be other execution orders between the steps. It is not intended to indicate that the execution order is the only order in which these operations can be performed. Ordinary technicians in this field will think of many ways to reorder the operations described herein. In addition, it should be noted that the process details involved in a certain embodiment of this article are also applicable to other embodiments in a similar manner, or different embodiments can be used in combination.

[0159] Furthermore, some steps in the method embodiments may be equivalently replaced with other possible steps. Alternatively, some steps in the method embodiments may be optional and may be deleted in certain usage scenarios. Alternatively, other possible steps may be added to the method embodiments. Furthermore, the various method embodiments may be implemented separately or in combination.

[0160] The various variations and specific embodiments of the multi-supply coordinated scheduling method for a regional integrated energy system in the aforementioned embodiments are also applicable to the multi-supply coordinated scheduling system for a regional integrated energy system in this embodiment. Through the aforementioned detailed description of the multi-supply coordinated scheduling method for a regional integrated energy system, those skilled in the art can clearly understand the implementation method of the multi-supply coordinated scheduling system for a regional integrated energy system in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0161] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-supply coordinated dispatching system for a regional integrated energy system, characterized in that: include: The data acquisition module is used to obtain the equipment operation status data set and energy load demand data set in the regional integrated energy system in real time; A multi-element collaborative strategy generation module uses a built-in multi-element collaborative scheduling model to calculate the equipment operation status data set and the energy load demand data set to obtain a multi-element collaborative scheduling strategy; The multi-element collaborative scheduling model adopts a composite model, including a supply-demand interactive game model, a user group evolution game model, and a benefit evaluation model. The input of the supply-demand interactive game model is the equipment output capacity parameters in the equipment operation status data and the real-time demand baseline in the energy load demand data. The output is a preliminary scheduling strategy, including equipment output plans and demand-side price signals. The input of the user group evolution game model is the real-time user demand in the energy load demand data and the demand-side price signal output by the supply and demand game model. The output is the revised load demand forecast; the input of the benefit evaluation model is the equipment output plan output by the supply and demand game model and the load demand forecast revised by the user evolution model; The output is the multi-element collaborative scheduling strategy with the highest comprehensive score; A strategy update module is used to obtain external environment information in real time, and input it and the multi-element collaborative scheduling strategy into a preset strategy update node analysis model to generate the next strategy update time node; Duration feature extraction module, used to collect multiple consecutive strategy update time nodes, and perform duration feature extraction to obtain the duration of multiple strategies; A stability evaluation module, configured to eliminate environmental external factors for the duration of each of the strategies, and to perform stability evaluation on the durations of the strategies after elimination to obtain a stability index; The model optimization and deployment module is used to optimize the multivariate collaborative scheduling model according to the difference between the stability index and the preset stability threshold, and update and deploy the optimized model into the regional integrated energy system.

2. The multi-supply coordinated scheduling system for a regional integrated energy system according to claim 1, characterized in that: The duration feature extraction module is further configured to: The multiple consecutive policy update time nodes include at least the current policy update time node, the next policy update time node, and the historical policy update time node that is closest to the current policy update time node in terms of time dimension.

3. A multi-supply coordinated scheduling method for a regional integrated energy system, characterized in that: include: Acquire the equipment operation status dataset and energy load demand dataset in the regional integrated energy system in real time, and input them into the multi-element coordinated scheduling model to obtain the multi-element coordinated scheduling strategy; Acquire external environment information in real time, and input it and the multi-element collaborative scheduling strategy into the strategy update node analysis model to generate the next strategy update time node; Collect multiple consecutive strategy update time nodes and extract duration features to obtain the duration of multiple strategies; Eliminating environmental external factors for the duration of each strategy, and performing stability evaluation on the durations of multiple strategies after elimination to obtain a stability index; Based on the difference between the stability index and a preset stability threshold, the multi-element coordinated scheduling model is optimized, and the optimized multi-element coordinated scheduling model is updated and deployed in the regional integrated energy system; The multi-element collaborative scheduling model adopts a composite model, including a supply-demand interactive game model, a user group evolution game model, and a benefit evaluation model; The input of the supply-demand interactive game model is the equipment output capacity parameters in the equipment operating status data and the real-time demand baseline in the energy load demand data; The output is a preliminary dispatch strategy, including equipment output plans and demand-side price signals; The input of the user group evolution game model is the real-time user demand in the energy load demand data and the demand-side price signal output by the supply and demand game model; The output is the revised load demand forecast; The input of the benefit evaluation model is the equipment output plan output by the supply and demand game model and the load demand forecast corrected by the user evolution model; The output is the multi-element collaborative scheduling strategy with the highest comprehensive score.

4. The multi-supply coordinated scheduling method for a regional integrated energy system according to claim 3, characterized in that: The equipment operation status data set includes operation status information of various types of energy supply equipment, and the energy load demand data set includes real-time energy demand information of different types of energy load groups.

5. The multi-supply coordinated scheduling method for a regional integrated energy system according to claim 4, characterized in that: The external environmental information includes grid electricity prices, natural gas prices and meteorological data.

6. The multi-supply coordinated scheduling method for a regional integrated energy system according to claim 5, characterized in that: The multiple consecutive policy update time nodes include at least the current policy update time node, the next policy update time node, and the historical policy update time node that is closest to the current policy update time node in terms of time dimension.

7. The multi-supply coordinated scheduling method for a regional integrated energy system according to claim 6, characterized in that: The policy duration represents the time span between two adjacent policy update time nodes; The multiple policy durations include at least the policy duration before the current update and the policy duration after the current update.

8. The multi-supply coordinated scheduling method for a regional integrated energy system according to any one of claims 3 to 7, characterized in that: The active update triggering condition of the strategy update node analysis model is: in response to the comprehensive fitness of the current multi-element coordinated scheduling strategy decaying to a set fitness threshold, it is determined that the current multi-element coordinated scheduling strategy is invalid and needs to be actively updated; The comprehensive fitness calculation formula is: ； Where F(t) represents the comprehensive fitness; t represents the duration of the current multi-element collaborative scheduling strategy; F0 represents the normalized initial fitness, indicating that the initial state of the strategy is optimal; -ΔC price t indicates that the price shock decays linearly over time. The larger the shock, the faster the comprehensive fitness decreases; -ΔE weather ·t 2 Indicates that the meteorological impact decays with the square of time, reflecting the nonlinear impact of the emergency; A s +A d It represents the weighted sum of supply-side and demand-side adaptability. The larger the value, the more robust the strategy. The duration of the current multi-element collaborative scheduling strategy is reversely solved by setting the fitness threshold, and the next update time node is calculated in combination with the update time node of the current strategy.

9. The multi-supply coordinated scheduling method for a regional integrated energy system according to claim 8, characterized in that: The ΔC price The impact factor of price fluctuation is calculated as follows: ； Among them, P e (t) represents the electricity price at time t; P e (t-Δt) represents the electricity price at the previous monitoring time point (t-Δt); P g (t) represents the natural gas price at the current time t, in yuan / m³; P g (t-Δt) represents the natural gas price at the previous monitoring time point (t-Δt); d1 max Indicates the peak upper limit of the electricity price within the floating range of the demand-side time-of-use electricity price; d1 min Indicates the lower limit of the electricity price valley in the floating range of the demand side time-of-use electricity price; P g base It represents the historical benchmark value of natural gas prices and is used to measure the degree to which the current gas price deviates from the historical average.

Images