Urban energy network intelligent allocation method and system

Abstract

The invention discloses an urban energy network intelligent allocation method and system, and the method comprises the steps: obtaining building energy consumption data and energy supply network topology information, building a supply and demand matching reference, recognizing a load peak value dense time period and a peak clipping and valley filling potential region, and exporting transferable load data to form a regional supply and demand distribution diagram; generating a peak shifting adjustment space in combination with the user response delay duration and the equipment start-stop period; performing gap matching analysis on the regional supply and demand distribution map and the peak shifting adjustment space, creating a hierarchical regulation instruction set, and differentially generating an instant response instruction and a delay response instruction; a regulation and control coordination parameter is formed through coordination configuration of the peak shifting revenue coefficient and the instant response instruction; finally, a regulation and control execution range is determined, cost benefit evaluation is implemented, an urban-level energy scheduling execution scheme is formed, accurate matching and efficient scheduling of urban energy supply and demand are achieved, and comprehensive and efficient scheduling decision support can be provided for application scenes such as an intelligent power grid, regional heat supply and comprehensive energy service.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy management, in particular to a city energy network intelligent deployment method and system. BACKGROUND

[0002] The city energy network undertakes the task of power, heat, gas and other energy transmission and distribution, and is the key infrastructure supporting the normal operation of the city. With the continuous expansion of the city scale and the improvement of the living standards of residents, the total energy consumption continues to rise, and the peak-valley difference of energy consumption is widening. In some areas, there is a shortage of supply during peak periods, while the supply capacity is idle during off-peak periods. Traditional energy deployment mainly relies on dispatchers to arrange supply plans according to historical experience and simple load curves. This method has a relatively slow response to load changes, cannot deeply tap the flexible adjustment capacity of the user side, and cannot accurately grasp the operating characteristics of various energy-using equipment, resulting in low overall operating efficiency of the energy network.

[0003] Some existing technologies attempt to improve the deployment effect through load forecasting, but these methods generally separate energy consumption data analysis from network deployment, lack systematic modeling of the relationship between the two, and have a large deviation between the prediction results and the actual network operating state. In addition, although some studies focus on the value of user-side adjustable load, there is still no clear identification and utilization method for issues such as which areas have peak shaving potential, which time periods are suitable for implementing adjustment, and the response speed differences of different users. More importantly, current control strategies often treat all adjustable resources equally, without classifying and managing resources according to their response speed and economic characteristics, which cannot meet the demand for fast response in emergency situations and cannot fully utilize the economic advantages of delayed adjustment. SUMMARY

[0004] The present application discloses a city energy network intelligent deployment method and system, which aims to accurately identify load fluctuation characteristics and peak shaving potential areas by deeply mining the correlation between building energy consumption data and energy supply network topology information, determine the peak shaving adjustment space in combination with user response delay time and equipment start-stop cycle, generate a set of hierarchical control instructions based on gap matching analysis, realize the collaborative configuration of immediate response instructions and delayed response instructions, and ultimately form a city-level energy scheduling execution scheme covering multiple nodes, time periods and energy types, providing comprehensive technical support for the intelligent and accurate control of city energy systems.

[0005] The present application discloses a city energy network intelligent deployment method and system, which aims to accurately identify load fluctuation characteristics and peak shaving potential areas by deeply mining the correlation between building energy consumption data and energy supply network topology information, determine the peak shaving adjustment space in combination with user response delay time and equipment start-stop cycle, generate a set of hierarchical control instructions based on gap matching analysis, realize the collaborative configuration of immediate response instructions and delayed response instructions, and ultimately form a city-level energy scheduling execution scheme covering multiple nodes, time periods and energy types, providing comprehensive technical support for the intelligent and accurate control of city energy systems. Building energy consumption data and energy supply network topology information are obtained, load fluctuation characteristics are identified based on the energy consumption data, and a supply-demand matching benchmark is established between the load fluctuation characteristics and the energy supply network topology information. Based on the supply and demand matching benchmark, the peak load period is detected, the peak shaving and valley filling potential area is extracted from the peak load period, the transferable load data is exported from the peak shaving and valley filling potential area, and a regional supply and demand distribution map is formed based on the transferable load data; The system acquires user response delay duration and device start-stop cycle, identifies time elasticity intervals through the response delay duration, captures adjustment switching times based on the device start-stop cycle, and performs time-series comparison between the time elasticity interval and the adjustment switching times to generate peak-shaving adjustment space. Gap matching analysis is performed on the regional supply and demand distribution map and the peak-shifting adjustment space to generate gap compensation parameters. The control target node is established through the gap compensation parameters, and a hierarchical control instruction set is created based on the control target node. The hierarchical control instruction set is divided into immediate response instructions and delayed response instructions according to the response time difference. The delayed response instructions are used to identify the fluctuation adjustment benefit and obtain the peak-shaving benefit coefficient. The peak-shaving benefit coefficient and the immediate response instructions are coordinated to form control coordination parameters. Based on the aforementioned regulation coordination parameters and the regional supply and demand distribution map, the scope of regulation implementation is determined, and a cost-benefit assessment is conducted on the scope of regulation implementation to form a city-level energy dispatch implementation plan.

[0006] A second aspect of this invention provides an intelligent dispatching system for urban energy networks, comprising: The energy consumption acquisition module is used to acquire building energy consumption data and energy supply network topology information, identify load fluctuation characteristics based on the energy consumption data, and establish a supply and demand matching benchmark between the load fluctuation characteristics and the energy supply network topology information. The load analysis module is used to detect periods of concentrated load peaks based on the supply and demand matching benchmark, extract potential areas for peak shaving and valley filling from the periods of concentrated load peaks, export transferable load data from the potential areas for peak shaving and valley filling, and form a regional supply and demand distribution map based on the transferable load data. The timing matching module is used to obtain the user response delay duration and the device start-stop cycle, identify the time elasticity interval through the response delay duration, capture the adjustment switching time according to the device start-stop cycle, and perform a timing comparison between the time elasticity interval and the adjustment switching time to generate a peak-shaving adjustment space. The regulation strategy module is used to perform gap matching analysis on the regional supply and demand distribution map and the peak-shifting regulation space to generate gap compensation parameters, establish regulation target nodes through the gap compensation parameters, and create a hierarchical regulation instruction set based on the regulation target nodes; An instruction coordination module is configured to generate instant response instructions and delayed response instructions according to response time differences of the hierarchical regulation instruction set, to obtain a peak shaving benefit coefficient by implementing fluctuation adjustment benefit identification on the delayed response instructions, and to form regulation coordination parameters according to the peak shaving benefit coefficient and the instant response instructions. A scheme generation module is configured to determine a regulation execution range based on the regulation coordination parameters and the regional supply and demand distribution map, to implement cost benefit evaluation on the regulation execution range, and to form a city-level energy scheduling execution scheme.

[0007] The beneficial effects of the present application are as follows: 1. By fusing the building energy consumption behavior characteristics with the network topology structure, the supply and demand balance nodes and unbalance nodes in the network are identified, the capacity of the balance nodes and the gap of the unbalance nodes are analyzed, the supply and demand deviation quantitative indicators are generated, and the supply and demand correlation benchmark is established. On this basis, by detecting the peak value intensive period, the peak value is continuously identified and the peak value starting position is determined, the pre-regulation capacity before the peak is obtained, the peak load cutting and valley filling potential region is divided, and the transferable load data is derived, and the regional supply and demand distribution situation is formed. This technical path of integrating supply and demand correlation modeling and potential tapping makes the allocation decision be made based on the accurate supply and demand state and the clear resource distribution, improves the pertinence of the allocation, and solves the problem that the traditional method separately processes the energy consumption data analysis and the allocation decision, resulting in the disconnection between the allocation instruction and the actual supply and demand state. 2. By obtaining the user response delay time length, the delay tolerance threshold is generated according to the delay time length, the upper limit constraint of the response delay is generated to produce an elastic reserve constraint delay section, and the section is subjected to stability test to determine a stable delay period, and the maximum continuous time length is extracted as a time elasticity interval. At the same time, the regulation switching time is captured from the device start-stop cycle data, the time elasticity interval is compared with the regulation switching time in time sequence, and the peak load cutting and valley filling adjustment space that meets the user response capacity and conforms to the device operation law is generated, which provides a time dimension constraint condition for the accurate issuance of the allocation instruction, and ensures the executability of the regulation and control measures. 3. The gap interaction transmission of the regional supply and demand distribution map is tracked to identify the gap trigger chain, the gap trigger chain is compensated and damaged according to the peak load cutting and valley filling adjustment space, the gap compensation parameters are determined according to the compensation dissipation boundary, and the regulation target node is established, and the hierarchical regulation instruction set is created. The hierarchical regulation instruction set is divided into instant response instructions and delayed response instructions according to the response time difference, the peak valley difference of the load transfer vector is analyzed to determine the peak shaving benefit coefficient of the delayed response instructions, and the instant response instructions are configured according to the peak shaving benefit coefficient. The regulation execution range is determined by spatial superposition of the regulation coordination parameters and the regional supply and demand distribution map, the total regulation cost and benefit are counted, the benefit cost ratio is calculated, the technical feasibility and execution reliability are comprehensively evaluated, the city-level energy scheduling execution scheme is formed, the rapid response capacity is ensured, the economic advantages of the delayed response are fully utilized, and the economicity and feasibility of the scheme are ensured. BRIEF DESCRIPTION OF DRAWINGS

[0008] The drawings hereof are incorporated in and constitute a part of this specification, illustrate embodiments of the technology described herein, and, together with the specification, serve to explain the principles of the technology.

[0009] Unless specifically stated or otherwise dictated, the same reference numerals in different drawings represent the same or similar technical features, and different reference numerals can also be used to represent the same or similar technical features.

[0010] Figure 1 is a flow diagram of a method for intelligent deployment of urban energy networks according to the present application.

[0011] Figure 2 is a block diagram of a system for intelligent deployment of urban energy networks according to the present application. DETAILED DESCRIPTION

[0012] In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular systems, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0013] It should be understood that the term "comprises" when used in this specification and the appended claims, specifies the presence of stated features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0014] Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "in other embodiments" or "in still other embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment, unless otherwise specified. The terms "comprise," "comprises," "comprising," and other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0015] The technical solutions of the embodiments of the present application are described below.

[0016] As Figure 1As shown, this embodiment of the invention provides a method for intelligent dispatching of urban energy networks, including the following steps S110-S160: Step S110: Obtain building energy consumption data and energy supply network topology information, identify load fluctuation characteristics based on energy consumption data, and establish a supply and demand matching benchmark by combining load fluctuation characteristics with energy supply network topology information.

[0017] Specifically, the process involves acquiring building energy consumption data and energy supply network topology information. Building energy consumption data for various building types is collected from the city's energy management platform, including data on electricity consumption, heating demand, gas consumption, and cooling load. The data shows that a commercial complex experiences approximately twice the electricity load during peak weekday hours compared to the same period on weekends, exhibiting a clear temporal pattern. Energy consumption characteristics for different building types are extracted from the data, including residential communities, commercial buildings, industrial plants, and public facilities. The data indicates that heating demand in a residential community exhibits a bi-peak pattern in the morning and evening during winter, while the electricity load of office buildings is mainly concentrated during working hours. The energy supply network topology information is also acquired, including the location of energy supply stations, the connection relationships of transmission and distribution pipelines, pipeline capacity, and transmission distance. The topology information shows that the city's heating network forms a network structure where a central heat source station connects to several heat exchange stations through a main pipeline network, with each heat exchange station covering the surrounding area. Key nodes are identified from the energy supply network topology information, including energy stations, hub heat exchange stations, branch regulating valves, and end-user access points. Topological information indicates that a certain regional power grid consists of multiple high-voltage substations and several medium-voltage substations forming a double-ring power supply structure.

[0018] Identify load fluctuation characteristics based on energy consumption data. Analyze the temporal variation patterns of energy consumption data, extracting daily, weekly, and seasonal load curves. Energy consumption data shows that the daily load curve of a commercial area exhibits three peak characteristics: morning, noon, and evening. Calculate the amplitude and frequency parameters of load fluctuation characteristics, quantifying the degree of fluctuation through the ratio of maximum load, minimum load, and average load in the energy consumption data. Energy consumption data indicates that the peak-to-valley difference in electricity load is large in an industrial park, and the fluctuation amplitude of load fluctuation characteristics is significantly higher than in residential areas. Perform Fourier transform analysis on the energy consumption data to extract the dominant frequency components and amplitude distribution of load fluctuation characteristics. Spectral analysis of the energy consumption data shows that the dominant frequency cycle of the heating load in a residential area is 24 hours, corresponding to diurnal temperature variations, while the secondary frequency cycle is one week, corresponding to weekday and weekend differences. Statistically analyze the frequency and intensity of load abrupt events in the energy consumption data, including load jumps caused by sudden weather changes and load anomalies caused by equipment failures. Energy consumption data records show that the heating load in a certain area increased sharply in a short period of time during a cold wave, forming a load abrupt event. Predicting future load changes based on historical fluctuation characteristics of energy consumption data. Load fluctuation characteristics include multi-dimensional information such as time series patterns, fluctuation parameters, frequency components, and forecast data.

[0019] In some embodiments, establishing a supply-demand matching benchmark by combining the load fluctuation characteristics with the power supply network topology information includes: identifying supply-demand balanced nodes and supply-demand imbalanced nodes based on the matching relationship between the load fluctuation characteristics and the power supply network topology information; generating a supply-demand deviation value by performing capacity matching between the surplus of the supply-demand balanced nodes and the gap of the supply-demand imbalanced nodes; determining a capacity allocation threshold based on the supply-demand deviation value; and applying the capacity allocation threshold to the power supply network topology information to establish a supply-demand matching benchmark.

[0020] Based on the matching relationship between load fluctuation characteristics and energy supply network topology information, nodes with balanced supply and demand and nodes with imbalanced supply and demand are identified. A supply-demand balance index is calculated for each node in the energy supply network topology information. The formula for the balance index is B = 1 - |C_s - C_d| / C_d, where B is the balance index, C_s is the node's supply capacity, and C_d is the node's demand load. A threshold for determining supply-demand balance is set; nodes with a balance index higher than the threshold are identified as balanced nodes, and nodes with a balance index lower than the threshold are identified as imbalanced nodes. A city sets a reasonable balance threshold to classify nodes in the energy supply network topology information into two categories: balanced nodes and imbalanced nodes. Combining the predicted data of load fluctuation characteristics, the balance of each node in the energy supply network topology information is predicted for future time periods. If a node is currently a balanced node, but the predicted load fluctuation characteristics indicate that it will become an imbalanced node during the evening peak period, it is marked as a potential imbalanced node in advance. Balanced and imbalanced nodes are marked with different colors on the network diagram of the energy supply network topology information, forming a supply-demand balance status map. The situation map of a certain region shows that most nodes in the energy supply network topology are in a balanced state, while a few nodes are experiencing supply-demand imbalance. Statistics on the distribution changes of balanced and imbalanced nodes at different times reveal that, based on the temporal patterns of load fluctuations, the number of imbalanced nodes in a certain city peaks during the morning rush hour on weekdays and decreases to its lowest point during the nighttime.

[0021] The capacity allocation between balanced nodes and imbalanced nodes generates a supply-demand deviation value. The adjustable capacity of balanced nodes is calculated, referring to the remaining supply capacity after ensuring their own supply-demand balance. A balanced node, after maintaining necessary safety margins, still has a certain capacity available to support other nodes. The supply gap of imbalanced nodes is calculated, referring to the portion of a node's demand load exceeding its supply capacity. A certain imbalanced node's demand load significantly exceeds its supply capacity, resulting in a large supply gap. The spatial distance and connection paths between balanced and imbalanced nodes are assessed, as spatial distance and path constraints affect the feasibility and losses of energy allocation. A balanced and imbalanced node is connected via a transmission and distribution network with a certain transmission efficiency. A capacity allocation analysis is performed, considering transmission distance, network capacity, and transmission losses. In a region with multiple balanced nodes providing surplus capacity, it needs to be rationally allocated to imbalanced nodes based on transmission efficiency. Based on the capacity allocation analysis, the supply-demand deviation value is calculated. The supply-demand deviation value quantifies the degree of supply-demand imbalance in a region. The calculation formula is D = Σ(Gap_i) - Σ(Surplus_j × Transmission Efficiency_j), where D is the supply-demand deviation value, Gap_i is the gap at the i-th imbalance node, Surplus_j is the surplus at the j-th equilibrium node, and Transmission Efficiency_j is the corresponding transmission efficiency. A positive supply-demand deviation value indicates insufficient supply in the region, while a negative value indicates a surplus.

[0022] Capacity allocation thresholds are determined based on supply-demand deviation values. First, the distribution characteristics of these deviations are analyzed to identify the mean, variance, and extreme values. In a certain urban area, supply-demand deviation values ​​fluctuate within a week, with larger deviations during peak periods. The operational risks at different supply-demand deviation levels are assessed: smaller deviations result in stable operation, while larger deviations may lead to power outages or equipment overload. In a certain region, when the supply-demand deviation exceeds a certain limit, pipeline pressure drops significantly, affecting heating quality. Triggering conditions for capacity allocation are determined, based on the ratio of the supply-demand deviation to the total capacity. In a certain heating network, allocation is triggered when the supply-demand deviation exceeds a certain proportion of the total capacity. Considering the load characteristics of different seasons and time periods, dynamically adjustable capacity allocation thresholds are set. A city uses a higher capacity allocation threshold during the winter heating season, appropriately lowers the threshold during the transition season, and adjusts it according to actual demand during the summer cooling season.

[0023] A capacity allocation threshold is applied to the energy supply network topology to establish a supply-demand matching benchmark. The capacity allocation threshold is marked on each node of the energy supply network topology, forming a node-level allocation triggering mechanism. Each heat exchange station in a certain heating network sets a personalized capacity allocation threshold based on its own supply and demand status; stations with high loads use higher thresholds, and stations with low loads use lower thresholds. A supply-demand matching evaluation system based on the capacity allocation threshold is established, including three dimensions: node matching degree, regional balance degree, and network stability. The supply-demand matching benchmark quantifies the degree of supply-demand matching through the evaluation system. A high node matching degree in a region indicates that most nodes are basically in a balanced supply-demand situation; a good regional balance degree indicates that the overall supply and demand in the region is coordinated; and network stability is at a reasonable level. Dynamic adjustment rules for the supply-demand matching benchmark are defined, and these rules update the benchmark in real time based on load fluctuation forecasts and changes in supply capacity. During seasonal transitions, a city adjusts its supply-demand matching benchmark in advance based on temperature forecasts and load fluctuation forecasts, gradually increasing the capacity allocation threshold before the start of the heating season.

[0024] Step S120: Based on the supply and demand matching benchmark, detect the peak load period, extract the peak shaving and valley filling potential area from the peak load period, export the transferable load data through the peak shaving and valley filling potential area, and form a regional supply and demand distribution map based on the transferable load data.

[0025] Specifically, peak load periods are detected based on supply-demand matching benchmarks. From the ideal supply-demand states defined in the benchmarks, periods where the actual load exceeds the benchmark are identified. In a commercial area, the actual load consistently exceeds the benchmark by more than 20% during two periods on weekdays: 9:00-11:00 AM and 6:00-8:00 PM, which are identified as peak periods. The frequency and distribution patterns of these peak periods are statistically analyzed, and peak load periods are identified based on the degree of deviation from the supply-demand matching benchmark. In a city's heating system, peak loads consistently occur from 6:00-8:00 AM and 5:00-10:00 PM daily during winter, forming peak load periods. The peak density of these peak load periods is calculated using the formula I = N_p / (T × ΔT), where I is the peak density, N_p is the number of peak occurrences, T is the observation period, and ΔT is the total duration of the peak period. In a certain area, 15 peaks occurred within a one-week observation period, indicating a high peak density during peak load periods. Analysis of the peak load periods for different regions and energy types reveals that peak heating demand in residential areas is mainly concentrated in the morning and evening, peak electricity demand in commercial areas is mainly concentrated during working hours, and peak loads in industrial areas are more dispersed.

[0026] In some embodiments, extracting peak shaving and valley filling potential areas from the peak load period includes: identifying peak duration during the peak load period to generate peak duration data; determining the peak start position based on the peak duration data; obtaining the pre-peak adjustable load capacity based on the peak start position; and dividing the peak shaving and valley filling potential areas based on the pre-peak adjustable load capacity.

[0027] Peak duration data is generated by identifying peak load periods. The morphological characteristics of the load curve during peak load periods are analyzed to identify the duration and trend of peak loads. In a commercial area, the evening peak load begins to rise at 18:00, reaches its peak at 19:00, and remains high until 20:30, with a peak duration of approximately 2.5 hours. The peak duration for different dates and regions is statistically analyzed and recorded in the peak duration data. In a residential area, the average duration of the morning peak load on weekdays is 1.5 hours, while on weekends it extends to 2 hours; these data are recorded in the peak duration data. Factors influencing peak duration are identified, including weather conditions, user behavior, and holiday effects. In a city experiencing extremely cold weather, peak duration data shows that the peak duration of heating load is more than 50% longer than in normal weather. A stability index for peak duration is calculated, reflecting the predictability of peak duration. Peak duration data from a certain industrial park shows relatively stable duration and low variance, facilitating the early development of control measures. Key parameters for peak duration are extracted, including peak start time, peak end time, duration, and peak intensity.

[0028] For example, determining the peak start position based on the peak duration data includes: analyzing key points of duration change in the peak duration data; determining a usable peak prediction time at the key points of duration change; evaluating the prediction accuracy of the peak prediction time to generate an accuracy evaluation result; and generating the peak start position based on the peak prediction time and the accuracy evaluation result.

[0029] Analyze key points of duration variation in peak load duration data. Extract the first and second derivatives of the load curve from the peak load duration data to identify abrupt changes in the load change rate. In a certain region, the first derivative of the load curve suddenly increases from near zero to 0.2 MW / hour at 8:00 AM in the peak load duration data, indicating that the load has entered a rapid ramp-up phase; this moment is the key point of duration variation. Analyze the distribution of key points of duration variation across different days in the peak load duration data to identify the temporal regularity of these key points. Peak load duration data for a commercial area shows that the key points of duration variation are concentrated between 8:00 and 9:00 AM on weekdays, while they are delayed to 9:00 and 10:00 AM on weekends. Calculate the time difference between the key points of duration variation and the peak arrival time; this time difference reflects the duration from the start of load ramp-up to the peak. Peak load duration data for a residential area shows that it takes an average of 1.5 hours from the key points of duration variation to the peak arrival time; this time window can be used to implement pre-regulation measures. Identify external factors influencing key moments of duration variation, including temperature changes, solar radiation intensity, and user activity patterns. Peak duration data for a certain city shows that key moments of duration variation occur earlier and load ramp-up accelerates when temperatures drop sharply.

[0030] Determine the available peak prediction time at key points of time-varying changes. Use these key points as trigger signals for peak prediction, initiating load forecasting and pre-regulation preparation at those times. A heating system, upon detecting a key point of time-varying change, immediately initiates load forecasting to predict load changes over the next two hours. Combining historical data and real-time monitoring information, the estimated peak arrival time is calculated at each key point of time-varying change. Forecasts for a certain region indicate that the load will reach its peak in 80-100 minutes from the current key point of time-varying change. Set a lead time for the peak prediction time; this lead time needs to be long enough to implement pre-regulation measures, but not too long to avoid increasing prediction errors. A city sets the peak prediction time to 60 minutes before the estimated peak arrival time to ensure sufficient time to activate energy storage equipment and adjust controllable loads. Considering the response time characteristics of different types of loads, differentiated peak prediction times are set for different regulation methods. A certain energy storage system responds quickly and can be activated 30 minutes before the peak; a building requiring longer pre-cooling needs to be activated 90 minutes before the peak.

[0031] The accuracy of peak arrival time prediction is assessed to generate an accuracy evaluation result. Historical prediction data and actual peak arrival data are collected, and the prediction error is calculated. The prediction error calculation formula is E=|T_predicted - T_actual|, where E is the prediction error, T_predicted is the predicted peak arrival time, and T_actual is the actual peak arrival time. The average prediction error of a certain prediction over the past 30 days is 12 minutes. The distribution characteristics of the prediction error are statistically analyzed, and the statistical results are recorded in the accuracy evaluation result, including the mean, standard deviation, and maximum error. The accuracy evaluation result shows that the standard deviation of a certain prediction error is 8 minutes, and 95% of the prediction errors are within 25 minutes. The differences in prediction accuracy under different weather conditions and load types are analyzed. The accuracy evaluation results show that the prediction error is smaller under clear weather conditions and increases under extreme weather conditions; the prediction accuracy is high for loads with strong regularity and decreases for loads with strong randomness. A prediction accuracy score is calculated, which comprehensively considers the magnitude and stability of the prediction error. The prediction accuracy score in the accuracy evaluation result is 85 points, which is at a relatively high level. Establish a confidence interval for the accuracy of the prediction; the confidence interval reflects the reliability of the prediction result. The accuracy assessment results show that the 95% confidence interval for a certain prediction time is ±20 minutes, indicating that the actual peak has a 95% probability of arriving within 20 minutes before or after the prediction time.

[0032] The peak start position is generated based on the peak prediction time and accuracy assessment results. First, the time range of the peak start position is determined by combining the peak prediction time and accuracy assessment results. For example, a system with a prediction time of 9:00 and a confidence interval of ±15 minutes in the accuracy assessment results determines the peak start position time range to be 8:45-9:15. A dynamic monitoring mechanism is set up within the peak start position time range to track load changes in real time and correct the prediction results. The system starts high-frequency monitoring at the peak start position of 8:45, updating the load forecast every 5 minutes and adjusting the judgment of the peak start position based on the latest data. Different response strategies are set according to the accuracy assessment results: precise control is used when accuracy is high, and a conservative strategy is used when accuracy is low. When the accuracy assessment score is higher than 80 points, the system initiates pre-adjustment precisely according to the peak start position; when the score is lower than 60 points, pre-adjustment is initiated 30 minutes in advance to cope with uncertainty. The peak start position is associated with the pre-adjustment trigger conditions, and corresponding control measures are automatically initiated when the load reaches the peak start position.

[0033] The adjustable load capacity for pre-peak pre-regulation is obtained by identifying the peak start position. During the period before the peak start position, available load resources for pre-regulation are identified. Pre-peak pre-regulation shifts some load from the peak period to the pre-peak period by activating adjustable loads in advance. A commercial building activates its air conditioning pre-cooling one hour before the peak, based on the peak start position, to reduce the cooling load demand during the peak period. The responsiveness of the adjustable load is evaluated, including regulation capacity, response speed, and duration. An energy storage system with a rated power of 1MW can be activated within 5 minutes of receiving a dispatch command and continuously discharge for 2 hours. The adjustable load capacity for pre-peak pre-regulation is calculated, taking into account user acceptance and constraints. A residential area's thermal storage device can pre-charge before the peak, but it must ensure that it does not affect users' normal heating demand; the adjustable load capacity for pre-peak pre-regulation is approximately 70% of the rated capacity. The contribution of pre-peak pre-regulation to peak shaving is analyzed; pre-peak pre-regulation can reduce the magnitude of peak load. The adjustable load capacity for pre-peak pre-regulation in a certain area can reduce peak load by approximately 8%, effectively alleviating supply and demand pressure during peak periods.

[0034] Peak shaving and valley filling potential areas are classified based on pre-peak adjustable load capacity. Areas are divided into different levels of peak shaving and valley filling potential according to the size of the pre-peak adjustable load capacity. Areas with a pre-peak adjustable load capacity greater than 15% of the total load are classified as high-potential areas, areas with a capacity between 5% and 15% are classified as medium-potential areas, and areas with a capacity less than 5% are classified as low-potential areas. A city identified three high-potential areas based on pre-peak adjustable load capacity; these areas are equipped with a large number of energy storage devices and adjustable loads. The spatial distribution characteristics of peak shaving and valley filling potential areas are analyzed to identify clustering patterns. High-potential peak shaving and valley filling potential areas in a certain region are mainly distributed around industrial parks and large commercial complexes, areas with abundant load regulation resources. The regulation priority of different peak shaving and valley filling potential areas is evaluated, taking into account adjustable load capacity, regulation cost, and user acceptance. A certain high-potential peak shaving and valley filling potential area has low regulation cost and high user acceptance, and is therefore designated as a priority regulation area.

[0035] Data on transferable loads is derived from peak-shaving and valley-filling potential areas. Within these areas, the types and scales of transferable loads are identified, including electric vehicle charging, energy storage device charging and discharging, industrial production loads, and building air conditioning loads. For example, a parking lot within a peak-shaving and valley-filling potential area experiences 500kW of electric vehicle charging load during the evening peak hours, which can be transferred to off-peak hours at night through intelligent charging management. The temporal characteristics of the transferable loads are extracted and recorded in the transferable load data, including the start time, end time, and duration of the transfer. For instance, a data center within a peak-shaving and valley-filling potential area can start pre-cooling two hours before peak hours, transferring some of the cooling load away from peak periods; these temporal characteristics are recorded in the transferable load data. The spatial characteristics of the transferable loads are also extracted and recorded in the transferable load data, including the node where the load is located, its connection to the power supply network, and the feasibility of the transfer. In an industrial park, the transferable loads are mainly concentrated in three production workshops; the data shows that these workshops are connected to the same substation, facilitating unified dispatching. Extract the constraints of transferable loads and record them in the transferable load data, including user comfort requirements, production process limitations, and equipment performance constraints. Transferable load data shows that the transfer of air conditioning load in a residential building must ensure that the indoor temperature fluctuates within a set range of no more than 2°C, and the transfer of load from a production facility must not affect the delivery date. Transferable load data includes load type, scale, temporal characteristics, spatial characteristics, and constraints.

[0036] A regional supply and demand distribution map is generated based on transferable load data. The transferable load data is mapped onto the energy supply network topology, and the transferable load resources of each node are marked on the regional supply and demand distribution map. The regional supply and demand distribution map shows that the transferable load in the northern area is mainly industrial production load, while the transferable load in the southern area is mainly commercial air conditioning load and electric vehicle charging load. The changes in supply and demand distribution before and after load transfer are calculated, showing that load transfer alters the original supply and demand matching state. The regional supply and demand distribution map indicates that a node experienced a supply and demand imbalance before load transfer. By transferring some load from the transferable load data to off-peak hours, the supply and demand matching degree of this node improved from 0.75 to 0.92. Regional supply and demand distribution maps for different time periods are drawn to demonstrate the changes in supply and demand trends before and after peak shaving and valley filling. The regional supply and demand distribution map of a certain city shows that after implementing peak shaving and valley filling, the number of nodes with supply and demand imbalance during peak hours decreased from 8 to 3, and the oversupply during off-peak hours was alleviated. The spatial imbalance of the regional supply and demand distribution map is analyzed to identify areas where supply and demand contradictions still exist. The regional supply and demand distribution map shows that even after load shifting, a certain area still has insufficient supply, which needs to be resolved through other means such as cross-regional energy allocation or increasing supply capacity.

[0037] Step S130: Obtain the user response delay duration and the device start-stop cycle; identify the time elasticity interval through the response delay duration; capture the adjustment switching time according to the device start-stop cycle; and perform a time-series comparison between the time elasticity interval and the adjustment switching time to generate a peak-shaving adjustment space.

[0038] Specifically, user response latency and equipment start-up / shutdown cycles are collected. User response latency for various user types is collected from the demand response platform, and the time interval from the issuance of a dispatch command to the actual load change is statistically analyzed. After receiving a peak-shaving command, a factory needs to coordinate the shutdown sequence of its production lines; the user response latency is 18 minutes after the command is issued. Analyzing the response characteristics of different user types, commercial building air conditioning users have shorter response latency, industrial users have longer response latency due to production process constraints, and residential users have more fluctuating response latency due to behavioral habits. A shopping mall can adjust its central air conditioning power within 5 minutes of receiving a dispatch command; the user response latency is 5 minutes. However, a chemical company needs to complete its current batch of production before reducing the load; the user response latency may extend to 40 minutes. Equipment start-up / shutdown cycle characteristics are collected, including equipment start-up time, normal operating period, shutdown time, and restart preparation time. A boiler's equipment start-up / shutdown cycle is as follows: preheating at 6:00 AM, normal operation at 7:00 AM, load reduction starting at 10:00 PM, complete shutdown at 11:00 PM, and low-power standby starting in the early morning of the next day. Extract the regularity characteristics of equipment start-up and shutdown to identify the matching relationship between equipment start-up and shutdown cycles and load demand cycles. The start-up and shutdown cycle of a data center cooling unit adjusts with changes in server load. During off-peak hours at night, some cooling units can be shut down. The equipment start-up and shutdown cycle is highly correlated with the computing load cycle.

[0039] In some embodiments, identifying the time elasticity interval by the response delay duration includes: generating a delay tolerance threshold based on the response delay duration; applying an upper limit constraint to the response delay duration based on the delay tolerance threshold to generate an elastic reserve constraint delay segment; performing a stability test on the elastic reserve constraint delay segment to determine a stable delay period; and extracting the maximum continuous duration from the stable delay period as the time elasticity interval.

[0040] A delay tolerance threshold is generated based on response delay duration. The distribution of user response delay durations in historical scheduling events is statistically analyzed, and the delay duration corresponding to different percentiles is calculated. User response delay duration data for a certain region shows that 50% of responses are completed within 15 minutes, 80% within 25 minutes, and 95% within 40 minutes. Based on the urgency of the scheduling demand, the maximum tolerable response delay is determined from the statistical data of user response delay durations, generating a delay tolerance threshold. For routine peak shaving needs, the delay tolerance threshold can be set relatively long; for load control under emergency conditions, the delay tolerance threshold is set very low. For a certain power grid, the delay tolerance threshold during routine peak shaving is 30 minutes, but the delay tolerance threshold during frequency anomalies is required to be 5 minutes. Differentiated delay tolerance thresholds are set for different categories of users, considering user type and load characteristics. For industrial users, due to complex production processes, the delay tolerance threshold extracted from their user response delay duration data is set at 45 minutes; for commercial users, who have flexible responses, the delay tolerance threshold is set at 20 minutes; and for critical load users, who must respond quickly, the delay tolerance threshold is set at 10 minutes. The latency tolerance threshold integrates statistical analysis of user response latency, urgency assessment, and user classification.

[0041] An upper limit constraint on response latency is applied based on a latency tolerance threshold to generate a resilience reserve constraint latency segment. The actual user response latency is compared with the latency tolerance threshold to identify latency segments that meet the threshold requirements. For example, a user's actual response latency ranges from 10 to 35 minutes, and the latency tolerance threshold is 40 minutes; all of this user's responses are within the tolerance range. Abnormal response data exceeding the latency tolerance threshold is removed; these abnormal data may be caused by equipment failure or communication interruption and should not be included in regular scheduling. In one scheduling event, a user's response latency reached 75 minutes due to equipment failure; this data was marked as abnormal and excluded from resilience reserve calculation. Under the constraint of the latency tolerance threshold, the available resilience reserve constraint latency segment for scheduling is calculated; this segment represents the available time window from instruction issuance to the required response completion. A dispatch instruction requires load reduction to be completed before 18:00. Considering the average user response delay is 20 minutes and the delay tolerance threshold is 30 minutes, the latest time to issue the instruction is 17:30. 17:00-17:30 is the elastic reserve constraint delay period. The elastic reserve constraint delay period for a certain area is 30 minutes, meaning that the time for issuing the dispatch instruction can be flexibly selected within a 30-minute range.

[0042] Conduct stability tests on the elastic reserve constraint delay section to determine the stable delay period. First, analyze the fluctuation characteristics of the elastic reserve constraint delay section under different times and conditions to evaluate its stability. Calculate the stability index of the elastic reserve constraint delay section. The stability index is quantified using the coefficient of variation CV, and the calculation formula is CV = σ / μ, where σ is the standard deviation of the elastic reserve constraint delay section and μ is the mean. Identify the key factors affecting the stability of the elastic reserve constraint delay section, including meteorological conditions, changes in user behavior patterns, and equipment health status. In a certain area, during extreme high-temperature weather, the air-conditioning load surges, resulting in a decline in response ability. The elastic reserve constraint delay section is shortened by 20%, and the coefficient of variation CV rises to 0.28, affecting the stability. Set the stability threshold CV_threshold. When CV < CV_threshold, it is determined as a stable delay period. Eliminate the periods with insufficient stability and retain the periods with satisfactory stability as the stable delay period. A certain dispatching platform requires that the fluctuation range of the elastic reserve constraint delay section be less than 25%. Set the stability threshold CV_threshold = 0.25. The periods when the coefficient of variation CV is higher than 0.25 are marked as unstable and not included in the regular dispatching plan. Perform stability screening on the elastic reserve constraint delay section, and determine the periods passing the stability test as the stable delay period.

[0043] Extract the maximum continuous duration from the stable delay period as the time elasticity interval. First, identify continuous available time segments in the stable delay period. The continuity requires that the delay characteristics in this period remain stable and without interruption. A certain user has stable response delays and no production interference during the period from 14:00 to 16:00, forming a continuous 2-hour stable delay period. Extract the maximum continuous duration in the stable delay period, and this maximum continuous duration is the time elasticity interval. The time elasticity interval reflects the optimal dispatching window. The time elasticity interval extracted from the stable delay period in an industrial park is 3.5 hours, which appears at night from 22:00 to 1:30 the next day. This time elasticity interval can be used as the best window for load regulation in this park. Considering the duration requirements of the dispatching demand, if the extracted time elasticity interval is not sufficient to meet the dispatching demand, then select the sub-optimal continuous period or combine multiple short periods. A certain dispatching task requires 4 hours of continuous adjustment, but the time elasticity interval extracted for this user is only 3 hours. Then, two shorter periods need to be combined, or other users need to be considered to participate.

[0044] Capture adjustment switching moments based on equipment start-up and shutdown cycles. Extract key time nodes for equipment state transitions from the start-up and shutdown cycle data, including start-up time, time to reach stable operation, time to begin load reduction, and time to complete shutdown. For example, the start-up and shutdown cycle of a certain production equipment shows that it starts at 8:00, reaches rated power at 8:30, begins load reduction at 17:00, and completely shuts down at 17:30. These four times are potential adjustment switching moments. Identify adjustment switching moments that match load scheduling needs by comparing the natural start-up and shutdown moments in the equipment start-up and shutdown cycle with the peak shaving and valley filling needs of the power grid. For instance, the air conditioning in a commercial complex starts at 9:00 AM in its equipment start-up and shutdown cycle, which coincides with the morning peak of the power grid. If the start-up time is advanced to 7:30 AM, it can meet comfort requirements while avoiding peak load. Assess the feasibility and cost of implementing load adjustments during adjustment switching moments. Adjustments at some adjustment switching moments have low adjustment costs and are less noticeable to users, while adjustments at others may affect normal business operations. A hotel struggles to adjust its air conditioning load during peak check-out times, but can achieve a 10% load reduction without increasing customer complaints during afternoon tea hours through minor temperature adjustments. By comparing various time points in the equipment start-up and shutdown cycle with load scheduling requirements, the adjustment and switching times that satisfy both equipment operation requirements and scheduling needs are identified.

[0045] A time-series comparison between the time elasticity interval and the adjustment switching time generates a peak-shaving adjustment space. Based on the time elasticity interval and the adjustment switching time, the peak-shaving adjustment space is generated. First, the start and end times of the time elasticity interval and the position of the adjustment switching time are marked on the time axis, identifying the overlapping area between the time elasticity interval and the adjustment switching time. For example, a user's time elasticity interval is 17:00-17:30, and the equipment's adjustment switching time includes the start of load reduction at 17:00 and complete shutdown at 17:30. Both adjustment switching times fall within the time elasticity interval, forming an effective peak-shaving adjustment window. The matching degree between the time elasticity interval and the adjustment switching time is analyzed. Combinations with high matching degree can achieve low-cost load regulation, while combinations with low matching degree require manual intervention or additional incentives. For instance, a manufacturing company's equipment natural shutdown time is 23:00, while the power grid needs to reduce peak loads between 21:00-22:00. The time elasticity interval and the adjustment switching time do not match, requiring early shutdown to achieve peak-shaving, but economic compensation is necessary. A multi-dimensional representation of peak-shifting regulation space is constructed, including the regulation window in the time dimension, the adjustable load distribution in the spatial dimension, and the adjustable load amount in the capacity dimension. The peak-shifting regulation space shows that in a certain area, 12 users can participate in regulation during the period from 18:00 to 19:00, with a total adjustable capacity of 3.5MW, and the spatial distribution is concentrated in the northern part of the industrial park.

[0046] Step S140: Perform gap matching analysis on the regional supply and demand distribution map and peak-shifting adjustment space to generate gap compensation parameters, establish the control target node through the gap compensation parameters, and create a hierarchical control instruction set based on the control target node.

[0047] In some embodiments, the step of performing gap matching analysis on the regional supply and demand distribution map and the peak-shifting adjustment space to generate gap compensation parameters includes: performing gap interaction transmission tracking and identifying gap trigger chains on the regional supply and demand distribution map; performing compensation loss assessment on the gap trigger chains and the peak-shifting adjustment space to generate compensation loss coefficients; identifying compensation dissipation boundaries based on the compensation loss coefficients; and determining gap compensation parameters based on the compensation dissipation boundaries.

[0048] This study uses a regional supply and demand distribution map to track and identify gap triggering chains. It analyzes the energy transfer relationships between nodes in the map and traces the propagation path of gaps within the network. A supply gap at one node can be transmitted to adjacent nodes through the energy network, potentially triggering a chain reaction; this chain reaction is the core characteristic of a gap triggering chain. The study extracts the connections between nodes and the direction of energy flow from the regional supply and demand distribution map. In a heating network, a heat source station supplies heat to a heat exchange station via a main pipeline, which then supplies heat to downstream users. When the heat source station's heating capacity is insufficient, the gap first affects the directly connected heat exchange station. Unable to meet downstream demand, the heat exchange station continues to propagate the gap to the user end, forming a complete gap triggering chain. The study tracks the propagation process of the gap triggering chain, recording the starting position, propagation path, and impact range of the gap. When an energy storage node receives an upstream gap, it compensates for part of the gap by releasing stored energy, slowing the downstream propagation of the gap triggering chain. When a load-intensive node receives a gap, its high demand amplifies the gap at that node, causing the gap triggering chain to exhibit diffusion characteristics. Analyzing the response behavior of each node in the gap trigger chain reveals that some nodes have buffering capabilities that can slow down the propagation of the gap trigger chain, while others, due to insufficient adjustment capabilities, will accelerate the spread of the gap trigger chain.

[0049] The compensation loss coefficient is generated by assessing the compensation loss of the gap trigger chain and the peak shifting adjustment space. The compensation demand of each node in the gap trigger chain is extracted to identify the location and time when peak shifting adjustment resources need to compensate. A gap trigger chain contains several nodes, and the gap size and occurrence time of each node are known. Available compensation resources with certain capacity, response speed, and available time periods are extracted from the peak shifting adjustment space. The process loss of transporting compensation resources from the adjustment point to the gap node is assessed. When compensation resources are transmitted from the adjustment point to the gap node, they experience response delay and transmission loss. A certain compensation resource needs to pass through several intermediate nodes to be transmitted from the adjustment point to the gap node. Each node incurs transmission loss, and response delay also leads to a lag in the compensation time. The compensation loss coefficient is calculated by comparing the theoretical compensation capacity with the actual effective compensation capacity. The calculation formula is η=C_eff / C_theo, where η is the compensation loss coefficient, C_eff is the actual effective compensation capacity considering transmission loss and response delay, and C_theo is the theoretical compensation capacity. A higher compensation loss coefficient indicates better compensation efficiency, while a lower compensation loss coefficient indicates greater losses and lower efficiency during the compensation process.

[0050] The compensation dissipation boundary is identified based on the compensation loss coefficient. The spatial distribution characteristics of the compensation loss coefficient are analyzed to identify areas with significant losses. Some areas have lower compensation loss coefficients due to their distance from regulatory resources or the presence of many intermediate links; these areas are considered difficult to compensate. For example, a remote industrial area has a compensation loss coefficient of 0.55, indicating that peak-shifting resources are insufficient to effectively compensate for the gap in this area. A central urban area, closer to regulatory resources, has a compensation loss coefficient of 0.88, indicating a better peak-shifting effect. A threshold for the compensation loss coefficient is set as a criterion; areas below this threshold are classified outside the compensation dissipation boundary. The gap in these areas cannot be effectively compensated through peak-shifting and requires other regulatory measures, such as increasing local supply capacity or implementing demand-side management. For instance, a city set a compensation loss coefficient threshold of 0.70 and identified several nodes with compensation loss coefficients below 0.70. These nodes are located outside the compensation dissipation boundary, and specific control plans are developed for these nodes. The identification of the compensation dissipation boundary clarifies the effective scope of peak-shifting regulation, enabling the precise allocation of regulatory resources to areas with high compensation efficiency.

[0051] The gap compensation parameters are determined based on the dissipation compensation boundary. Within the area covered by the dissipation compensation boundary, the effective compensation capacity of each node is calculated. Gap data and corresponding compensation loss coefficients are extracted from the nodes included in the gap compensation parameters. The effective compensation capacity is obtained by multiplying the theoretical gap by the compensation loss coefficient. For example, a node has a theoretical gap of 600kW and a compensation loss coefficient of 0.82, resulting in an effective compensation capacity of 492kW, which is included in the gap compensation parameters. The remaining 108kW gap requires other solutions. Determining the compensation start time in the gap compensation parameters requires considering response delay and transmission time. For example, a node's gap occurs at 18:00 in the evening, with a response delay of 15 minutes and a transmission time of 8 minutes. To ensure timely arrival of compensation resources, the gap compensation parameters specify a compensation start time of 17:37. For areas outside the dissipation compensation boundary, the compensation capacity for these areas is marked as zero in the gap compensation parameters, indicating that peak-shaving regulation cannot cover them. A suburban industrial park is located outside the dissipation compensation boundary; its available compensation capacity in the gap compensation parameters is 0, requiring reliance on local energy storage or temporary power generation equipment. The gap compensation parameters cover key information such as effective compensation capacity, compensation start time, compensation efficiency, and compensable area range, quantifying the compensation needs and control timing requirements of each node.

[0052] Target nodes for regulation are established using gap compensation parameters. The distribution of compensation capacity in the gap compensation parameters is analyzed to identify key areas and nodes requiring regulation. The gap compensation parameter data shows that some nodes have large compensation needs, while others have moderate needs. Nodes with large compensation capacities are marked as key regulation nodes, as these target nodes have a significant impact on the overall supply-demand balance. A city identified several key regulation target nodes in industrial, commercial, and residential areas from the gap compensation parameters; the compensation needs of these target nodes account for the majority of the total gap. The temporal characteristics of the gap compensation parameters are analyzed to identify the periods when gaps are concentrated. Morning and evening peak hours are the periods when gaps are concentrated, requiring regulation preparation to be initiated before these periods. The regulation priority of each target node is assessed. Although the gap at a certain substation node is not large, it supplies power to hospitals and data centers, making it extremely important; therefore, its regulation priority is set to the highest in the target node list. An industrial node has a large gap but its users have high flexibility; its regulation priority is set to medium. By comprehensively analyzing the spatial distribution, temporal characteristics, and node importance of the gap compensation parameters, a list of target nodes requiring regulation is established. These target nodes constitute the objects of subsequent regulation instructions.

[0053] A hierarchical control instruction set is created based on the target nodes. The target nodes are categorized according to their response speed. Target nodes with short response times include energy storage devices and interruptible loads, which can quickly respond to control demands; target nodes with long response times include industrial loads and building air conditioning, which require a longer response time. In a certain city, energy storage stations and large shopping mall air conditioning units can respond quickly, while chemical plants and dyeing workshops require a longer time to adjust their production schedules. Corresponding control instructions are created in the hierarchical control instruction set for target nodes with different response levels. Fast-response layer instructions require a short response time, while slow-response layer instructions allow for a longer response time. The hierarchical control instruction set for an industrial park node is scheduled to activate in the evening, using production shift adjustments to reduce load and complete the response before the specified time. The hierarchical control instruction set for an energy storage station node requires immediate discharge upon receiving the instruction to quickly compensate for the shortfall. A priority mechanism for the hierarchical control instruction set is established: when multiple target nodes require control simultaneously, the hierarchical control instruction set prioritizes the execution of instructions from important nodes and fast-response nodes. This layered design allows the layered control instruction set to meet both the needs of rapid response and make full use of slow-response resources.

[0054] Step S150: The hierarchical control instruction set is divided into immediate response instructions and delayed response instructions according to the response time difference. The delayed response instructions are used to identify the fluctuation adjustment benefit to obtain the peak-shaving benefit coefficient. The peak-shaving benefit coefficient and the immediate response instructions are coordinated to form the control coordination parameters.

[0055] In some embodiments, the step of generating immediate response instructions and delayed response instructions by distinguishing the hierarchical control instruction set according to the response time difference includes: establishing a time response axis based on the response time difference; mapping the hierarchical control instruction set to the time response axis to form a response time mark; dividing the hierarchical control instruction set into a fast response segment and a peak-shifting resource slow response segment according to the response time mark; and classifying the fast response segment and the peak-shifting resource slow response segment by time difference to generate immediate response instructions and delayed response instructions.

[0056] A time response axis is established based on response time differences. Response time difference data for all commands in the hierarchical control command set are statistically analyzed, ranging from several minutes to tens of minutes. A certain hierarchical control command set contains several commands; the shortest response time difference is for energy storage discharge, which can be completed within minutes; the longest response time difference is for industrial production adjustments, which require waiting for the current production batch to finish. A time response axis is established as an analytical tool. The horizontal axis represents the response time extending from zero, and the vertical axis represents the number of commands or cumulative control capacity corresponding to the response time. Scales are marked on the horizontal axis at reasonable time intervals, and capacity scales are marked on the vertical axis, forming a complete two-dimensional coordinate system. For a certain city, the horizontal axis range of the time response axis is set to 0-60 minutes, and the vertical axis range is set according to the actual control capacity. The time response axis allows for a visual observation of the command distribution density across different response time periods. Dense commands within short time periods indicate abundant rapid response resources, while scattered commands within long time periods indicate that slow-response resources dominate.

[0057] The hierarchical control command set is mapped onto a time response axis to form response time markers. The response time and control capacity of each command in the hierarchical control command set are extracted, and these commands are mapped one by one to the corresponding positions on the time response axis. A certain energy storage discharge command has a short response time and moderate capacity, and is marked at a short time position on the time response axis; a certain industrial control command has a long response time and large capacity, and is marked at a long time position. As all commands are mapped, a distribution map of response time markers is formed on the time response axis. The density of the markers reflects the degree of command concentration in different response time intervals, and the height of the markers reflects the size of the control capacity. The response time markers of a certain city show that there are dense command markers in short time intervals, while the command markers are relatively dispersed in longer time intervals. Analyzing the clustering characteristics of the response time markers can identify response time clusters in the command set. Response time markers form obvious clusters near certain time points; these clusters correspond to the typical response times of different types of resources.

[0058] Based on the response time markers, the hierarchical control command set is divided into a fast response segment and a peak-shaving resource slow response segment. The distribution pattern of the response time markers on the time response axis is analyzed to find the natural boundary between fast and slow responses. The distribution of the response time markers shows a significant change in command density around a certain time point; commands are densely distributed before this time point and dispersed after it. This density change reflects the transition area where fast response resources are exhausted and slow response resources begin to function. This time point is used as the boundary between the fast and slow response segments; commands within this time point are classified as the fast response segment, and commands outside this time point are classified as the peak-shaving resource slow response segment. The fast response segment mainly includes commands for resources such as energy storage, interruptible loads, and standby units; the peak-shaving resource slow response segment mainly includes commands for resources such as industrial loads, building control, and charging management. Commands in the fast response segment are characterized by fast response speed but short duration, while commands in the peak-shaving resource slow response segment are characterized by slow response speed but large control capacity and long duration.

[0059] For example, the step of classifying the fast response segment and the off-peak resource slow response segment by time difference to generate immediate response instructions and delayed response instructions includes: converting the fast response segment into an immediate execution sequence; superimposing the off-peak resource slow response segment onto the immediate execution sequence to form a response difference distribution; deriving the time difference boundary threshold of the delay benefit window from the response difference distribution; and generating immediate response instructions and delayed response instructions based on the distinguishing significance of the time difference boundary threshold.

[0060] The fast response segment is converted into an instant execution sequence. The execution time and control capacity of all instructions in the fast response segment are extracted and arranged in chronological order. The execution times of the instructions in the fast response segment are concentrated within a short period after the dispatch command is issued. The fast response segment of a certain city includes instructions such as energy storage discharge, interruptible load shedding, and standby unit startup. These instructions are executed rapidly upon receiving the dispatch command. An instant execution sequence is constructed, with time as the horizontal axis and cumulative control capacity as the vertical axis, depicting the release process of control capacity in the fast response segment. An instant execution sequence shows that energy storage begins discharging 2 minutes after the dispatch command is issued, interruptible loads are shedding 5 minutes later, and standby units start 8 minutes later. The cumulative control capacity increases stepwise as time progresses. The slope of the instant execution sequence curve reflects the response speed; a larger slope indicates more control capacity is deployed per unit time. The instant execution sequence of an industrial park has a larger slope in the first few minutes, indicating intensive deployment of fast response resources. The curve then gradually flattens out, indicating that the fast response resources have been largely released.

[0061] The response difference distribution is constructed by superimposing the slow response segment of off-peak resources onto the real-time execution sequence. The execution time and control capacity of all instructions in the slow response segment of off-peak resources are extracted, and the capacity changes of these slow response resources are superimposed onto the real-time execution sequence. The instructions in the slow response segment of off-peak resources take effect successively over a relatively long period. In a certain city, the slow response segment begins to see industrial load transfer take effect after 15 minutes, building pre-cooling control after 25 minutes, and charging transfer control after 40 minutes. Superimposing the capacity change curve of the slow response segment with the real-time execution sequence yields a response difference distribution encompassing the entire process of fast and slow responses. The response difference distribution shows a complete transition from fast to slow response; the curve rises sharply in the initial stage due to fast response resources, the slope gradually slows down in the middle stage, and continues to grow in the later stage due to the continuous input of slow response resources. In a certain region, the response difference distribution is mainly contributed by fast response in the first 10 minutes, the superposition stage of fast and slow responses is from 10 to 30 minutes, and the contribution of slow response is mainly from 30 to 60 minutes.

[0062] The time difference threshold for the delay benefit window is derived from the response difference distribution. The slope variation pattern of the response difference distribution is analyzed to identify moments where the slope changes significantly. In a certain city, the response difference distribution curve shows a clear slope inflection point around 12 minutes; the slope is steeper before 12 minutes and decreases significantly afterward. This slope inflection point corresponds to the transition moment when fast response resources are gradually exhausted and slow response resources begin to play a dominant role. The moment of significant slope change is selected as a candidate point for the time difference threshold. To the left of the candidate point, instructions are mainly fast-response, which, although fast, has a short duration and limited peak-shaving benefits; to the right of the candidate point, instructions are mainly slow-response, which, although slow, can fully utilize the peak-shaving benefits brought by load shifting. The average peak-shaving benefits of instructions on both sides of the candidate point are evaluated, and the benefit difference between the two sides is analyzed. In a certain city, 12 minutes is used as a candidate point. The average peak-shaving benefit coefficient of instructions on the left side of this point is lower, while the average peak-shaving benefit coefficient of instructions on the right side is higher, showing a significant benefit difference. The candidate point with the largest benefit difference is selected as the final time difference threshold.

[0063] Based on the discriminative significance of time difference thresholds, immediate and delayed response commands are generated. The discriminative power of the time difference thresholds is evaluated, and the differences in response characteristics on both sides of the threshold are analyzed. At a certain time difference threshold, commands to the left have shorter average response times, while commands to the right have longer average response times, showing a significant difference in response times. The differences in capacity distribution and peak-shaving benefits between the left and right sides are also analyzed. Commands on the left have smaller individual capacities but faster response speeds, while commands on the right have larger individual capacities and higher peak-shaving benefits. The discriminative significance of the time difference thresholds is evaluated by comprehensively considering the differences in response time and other characteristics. A higher discriminative significance score for a certain threshold indicates that it can effectively distinguish between fast and slow response commands. The hierarchical control command set is classified according to the time difference thresholds, generating immediate and delayed response commands. In a certain city, commands with response times within 12 minutes are generated as immediate response commands, characterized by rapid response and coverage of initial gaps. Commands with response times exceeding 12 minutes are generated as delayed response commands, characterized by larger capacity and higher peak-shaving benefits.

[0064] In some embodiments, the step of identifying the peak-shifting revenue coefficient by performing fluctuation adjustment on the delayed response command includes: converting the delayed response command into a load transfer vector; locating the position with the maximum peak-to-valley difference in the load transfer vector; using the position with the maximum peak-to-valley difference as the revenue conversion benchmark to accumulate revenue and construct a revenue distribution curve; and performing peak extraction on the revenue distribution curve to determine the peak-shifting revenue coefficient.

[0065] Delayed response commands are converted into load transfer vectors. Load transfer data is extracted from the delayed response commands, including transfer capacity, source time, and target time. A certain delayed response command transfers industrial load from the evening peak to the nighttime off-peak, with the source time being the evening peak and the target time being the nighttime off-peak. A load transfer vector is constructed, with the dimension of the vector being a one-day time axis, and the elements representing the load change at each time point. In the load transfer vector, negative values ​​at the source time indicate a load decrease, positive values ​​at the target time indicate a load increase, and elements at other times are zero. For example, the load transfer vector of a certain delayed response command has negative elements at the evening peak of 19:00, indicating a load decrease at that time; and positive elements at the nighttime off-peak of 23:00, indicating a load increase at that time. The load transfer effects of multiple delayed response commands are superimposed to form a comprehensive load transfer vector. The superimposed load transfer vector of all delayed response commands in a certain area shows that a certain amount of load is reduced during the evening peak and a corresponding amount of load is increased during the nighttime off-peak.

[0066] Locate the location of maximum peak-to-valley difference in the load transfer vector. Superimpose the load transfer vector onto the original load curve to obtain the adjusted load curve. The original load curve has a peak value during the evening peak and a trough value during the nighttime trough, resulting in a large peak-to-valley difference. After load transfer, the load during the evening peak decreases, while the load during the nighttime trough increases, reducing the peak-to-valley difference. Analyze the changes in peak-to-valley difference at each time before and after the adjustment to identify the time with the largest change. At a certain time, the peak-shaving effect is significant, and at another time, the valley-filling effect is significant; the reduction in peak-to-valley difference between these two times is the location of maximum peak-to-valley difference. In a certain region, the location of maximum peak-to-valley difference corresponds to the evening peak and the nighttime trough. The original peak-to-valley difference was large, but after load transfer, the peak-to-valley difference decreased significantly, indicating the best peak-shaving and valley-filling effect. Mark the location of maximum peak-to-valley difference as the revenue conversion benchmark point, which corresponds to the maximum peak-shaving adjustment value. In a certain city, the location of maximum peak-to-valley difference is between evening peak reduction and nighttime valley filling; this location becomes the reference benchmark for calculating peak-shaving revenue.

[0067] A revenue distribution curve is constructed by accumulating revenue based on the location of maximum peak-to-valley difference. Starting from the location of maximum peak-to-valley difference, the economic benefits brought by delayed response commands at different times are statistically analyzed. Reducing load during the evening peak avoids starting high-cost gas-fired peak-shaving units, saving fuel costs. Increasing load during the nighttime off-peak improves the utilization rate of base-load units, increasing power generation revenue. In a certain city, reducing load during the evening peak avoids starting expensive gas-fired units, saving operating costs per hour; increasing load during the nighttime off-peak improves the utilization rate of base-load units, increasing revenue per hour. The economic benefits at each time point are accumulated in chronological order to construct a revenue distribution curve. The revenue distribution curve, with time as the horizontal axis and cumulative revenue as the vertical axis, shows the accumulation process of peak-shaving revenue over time. A certain revenue distribution curve shows that peak-shaving revenue begins to accumulate in the evening, reaches a peak at a certain time, then the growth rate slows down, eventually reaching the total cumulative revenue for the whole day. The peak position of the revenue distribution curve reflects the period when peak-shaving revenue is most concentrated, and the slope of the curve reflects the growth rate of revenue.

[0068] Peak value extraction is performed on the revenue distribution curve to determine the peak-shifting revenue coefficient. Peak revenue is extracted from the revenue distribution curve, representing the maximum single-period economic benefit brought by the delayed response command. The peak value of a certain revenue distribution curve occurs at a certain moment, which is the period when the peak-shifting revenue is most concentrated; the size of the peak value reflects the maximum economic value of peak-shifting regulation. The peak-shifting revenue coefficient is obtained by the ratio of peak revenue to execution cost, calculated as: Peak-shifting revenue coefficient = R_peak / C_total, where R_peak is the peak revenue and C_total is the execution cost, including user compensation fees, equipment start-up and shutdown costs, and scheduling and maintenance costs. For a given delayed response command with a fixed execution cost C_total, if the peak revenue R_peak is significantly higher than the cost, the peak-shifting revenue coefficient reaches a high level, indicating that the command has good economic efficiency. The peak-shifting revenue coefficients of multiple delayed response commands are statistically analyzed to examine the revenue characteristics of different command types. The peak-shifting revenue coefficients of industrial load transfer commands are generally high, while those of building pre-cooling commands are moderate, and those of charging transfer commands are also relatively high.

[0069] Control coordination parameters are formed based on the staggered peak return coefficient and the coordinated configuration of immediate response commands. Delayed response commands with higher staggered peak return coefficients are selected as priority control targets. In one city, high-return delayed response commands such as industrial park shift optimization and pre-cooling control of large shopping malls were identified. A coordinated configuration mechanism for immediate and delayed response commands is established, determining the capacity allocation of control coordination parameters. Based on the gap size and response time requirements, the control coordination parameters stipulate that immediate response commands undertake 30-40% of the control tasks for rapid response, while delayed response commands undertake 60-70% of the control tasks for continuous control and staggered peak optimization. For example, if the evening peak gap is expected to be 5MW, the control coordination parameters stipulate that immediate response commands provide 1.8MW of rapid support, and delayed response commands provide 3.2MW of continuous control. The timing configuration of the control coordination parameters is determined: immediate response commands are executed immediately after the gap occurs, while delayed response commands are initiated 15-30 minutes in advance before the gap occurs, ensuring that control capacity is fully released when the peak arrives. The control and coordination parameters clarify the capacity ratio, execution sequence, priority ranking, and expected benefits of immediate and delayed response commands, providing a detailed operational plan for actual control and coordination.

[0070] Step S160: Determine the scope of regulation implementation based on regulation coordination parameters and regional supply and demand distribution map, and conduct cost-benefit assessment on the scope of regulation implementation to form a city-level energy dispatch implementation plan.

[0071] Specifically, the scope of regulatory implementation is determined based on regulatory coordination parameters and regional supply and demand distribution maps. The coverage areas of immediate and delayed response commands are extracted from the regulatory coordination parameters to identify which nodes and time periods require regulatory action. The regulatory coordination parameters show that immediate response commands cover several nodes in the city center business district and industrial parks, while delayed response commands have a wider coverage, encompassing several nodes throughout the city. The spatial and temporal distribution characteristics of the supply-demand gap are extracted from the regional supply-demand distribution map. The map shows significant supply-demand gaps in the northern industrial zone, central business district, and southern residential area during morning and evening peak hours, with the gap locations and times clearly marked. Spatial overlay analysis is performed between the coverage areas of the regulatory coordination parameters and the gap distribution on the regional supply-demand distribution map. Overlay analysis reveals that the regulatory nodes in the regulatory coordination parameters can cover most of the gap areas on the regional supply-demand distribution map, while gaps in some remote areas cannot be covered due to the difficulty in reaching them with regulatory resources. The scope of regulatory implementation is then defined, including areas that can effectively cover the supply-demand gap and have sufficient regulatory resources within the scope of implementation. The scope of regulation in a certain city was ultimately determined to be the central business district, the northern industrial park, and the southern residential area. The regulation nodes in these areas can cover the main supply and demand gaps, the allocation of regulation resources is reasonable, and the conditions for implementation are mature.

[0072] A cost-benefit assessment is conducted on the scope of regulation implementation to formulate a city-level energy dispatch implementation plan. Within the scope of regulation implementation, a cost-benefit framework for the city-level energy dispatch implementation plan is constructed. The total regulation cost C_total within the scope of regulation implementation is calculated, including user compensation fees, equipment start-up and shutdown costs, and dispatch operation and maintenance costs. The total regulation benefit R_total within the scope of regulation implementation is calculated, with benefits derived from reduced fuel costs, reduced equipment investment requirements, and improved energy utilization efficiency. By executing immediate and delayed response commands, the high start-up costs of gas-fired peak-shaving units are avoided, reducing peak load on the power grid and improving the utilization rate of baseload units. The economic feasibility of the city-level energy dispatch implementation plan is assessed using the benefit-cost ratio, calculated as benefit-cost ratio = R_total / C_total, where R_total is the total regulation benefit and C_total is the total regulation cost. In a certain city, the total regulation benefit R_total is significantly higher than the total cost C_total, indicating a high benefit-cost ratio and significant economic benefits of the city-level energy dispatch implementation plan. The technical feasibility, user acceptance, and implementation reliability of the city-level energy dispatch implementation plan are evaluated. The technical feasibility assessment confirmed that the equipment and communication conditions within the control and regulation scope meet the control requirements. User acceptance surveys showed that most users are willing to participate in the control and regulation plan, and the reliability analysis indicated a high success rate in executing control and regulation commands. Based on the combined results of the cost-benefit assessment and feasibility assessment, the city-level energy dispatching execution plan was improved. The city-level energy dispatching execution plan clarifies the control and regulation scope, command configuration, expected costs and benefits, and execution safeguards, providing a complete implementation basis for precise urban energy dispatching.

[0073] To implement the above-described method embodiments, a smart dispatching method for urban energy networks is proposed to achieve the corresponding functions and technical effects. See also... Figure 2 , Figure 2 This diagram illustrates a structural block diagram of an intelligent urban energy network dispatching system 200 according to an embodiment of this application. For ease of explanation, only the parts relevant to this embodiment are shown. The intelligent urban energy network dispatching system 200 provided in this embodiment includes: The energy consumption acquisition module 201 is used to acquire building energy consumption data and energy supply network topology information, identify load fluctuation characteristics based on the energy consumption data, and establish a supply and demand matching benchmark between the load fluctuation characteristics and the energy supply network topology information. The load analysis module 202 is used to detect peak load periods based on the supply and demand matching benchmark, extract peak shaving and valley filling potential areas from the peak load periods, export transferable load data through the peak shaving and valley filling potential areas, and form a regional supply and demand distribution map based on the transferable load data. The timing matching module 203 is used to obtain the user response delay duration and the device start-stop cycle, identify the time elasticity interval through the response delay duration, capture the adjustment switching time according to the device start-stop cycle, and perform a timing comparison between the time elasticity interval and the adjustment switching time to generate a peak-shaving adjustment space. The regulation strategy module 204 is used to perform gap matching analysis on the regional supply and demand distribution map and the peak-shifting regulation space to generate gap compensation parameters, establish regulation target nodes through the gap compensation parameters, and create a hierarchical regulation instruction set based on the regulation target nodes; The instruction coordination module 205 is used to generate immediate response instructions and delayed response instructions according to the response time difference of the hierarchical control instruction set, to identify the fluctuation adjustment benefit of the delayed response instructions to obtain the peak-shaving benefit coefficient, and to form control coordination parameters based on the peak-shaving benefit coefficient and the immediate response instructions. The scheme generation module 206 is used to determine the scope of regulation execution based on the regulation coordination parameters and the regional supply and demand distribution map, and to conduct a cost-benefit assessment on the scope of regulation execution to form a city-level energy dispatch execution scheme.

[0074] The aforementioned intelligent urban energy network dispatching system 200 can implement one of the intelligent urban energy network dispatching methods described in the above-described method embodiments. The options described in the above method embodiments are also applicable to this embodiment and will not be detailed here. The remaining content of this application's embodiments can be referred to the content of the above method embodiments, and will not be repeated in this embodiment.

[0075] The purpose of the above embodiments is to reproduce and derive the technical solution of the present invention by way of example, and to fully describe the technical solution, purpose and effect of the present invention. The purpose is to enable the public to have a more thorough and comprehensive understanding of the disclosure of the present invention, and not to limit the scope of protection of the present invention.

Claims

1. A method for intelligent deployment of urban energy networks, characterized in that, The method comprises the following steps: obtaining building energy consumption data and energy supply network topology information, identifying load fluctuation characteristics based on the energy consumption data, establishing a supply-demand matching benchmark for the load fluctuation characteristics and the energy supply network topology information; detecting a load peak value intensive period based on the supply-demand matching benchmark, extracting a peak load shifting potential region from the load peak value intensive period, deriving transferable load data through the peak load shifting potential region, and forming a regional supply-demand distribution map based on the transferable load data; obtaining user response delay duration and equipment start-stop cycle, identifying a time elasticity interval through the response delay duration, capturing an adjustment switching time according to the equipment start-stop cycle, and performing time sequence comparison between the time elasticity interval and the adjustment switching time to generate a peak shifting adjustment space; performing gap matching analysis on the regional supply-demand distribution map and the peak shifting adjustment space to generate a gap compensation parameter, establishing a target node for regulation and control through the gap compensation parameter, and creating a hierarchical regulation and control instruction set based on the target node for regulation and control; distinguishing between immediate response instructions and delayed response instructions according to the response time difference of the hierarchical regulation and control instruction set, identifying a peak shifting benefit coefficient by performing fluctuation adjustment benefit identification on the delayed response instructions, and forming a regulation and control coordination parameter by cooperatively configuring the peak shifting benefit coefficient and the immediate response instructions; determining a regulation and control execution range based on the regulation and control coordination parameter and the regional supply-demand distribution map, and forming a city-level energy dispatch execution scheme by performing cost-benefit evaluation on the regulation and control execution range.

2. The method of claim 1, wherein, The method further comprises the following steps: identifying supply-demand balance nodes and supply-demand imbalance nodes based on the matching relationship between the load fluctuation characteristics and the energy supply network topology information; performing capacity matching on the surplus of the supply-demand balance nodes and the gap of the supply-demand imbalance nodes to generate a supply-demand deviation value; determining a capacity adjustment threshold value according to the supply-demand deviation value; applying the capacity adjustment threshold value to the energy supply network topology information to establish a supply-demand matching benchmark.

3. The method of claim 1, wherein, The method further comprises the following steps: performing peak value persistence identification on the load peak value intensive period to generate peak value duration data; determining a peak value starting position according to the peak value duration data; obtaining a pre-peak regulation adjustable load capacity through the peak value starting position; dividing a peak load shifting potential region based on the pre-peak regulation adjustable load capacity.

4. The method of claim 1, wherein, The method further comprises the following steps: generating a delay tolerance threshold value based on the response delay duration; performing upper limit constraint on the response delay duration based on the delay tolerance threshold value to generate an elastic reserve constraint delay section; determining a stable delay period by performing stability test on the elastic reserve constraint delay section; extracting a maximum continuous duration from the stable delay period as a time elasticity interval.

5. The method of claim 1, wherein, The method further comprises the following steps: performing gap interaction transfer tracking on the regional supply-demand distribution map to identify a gap trigger chain; The gap trigger chain is compensated for loss evaluation to generate a compensation loss coefficient; A compensation dissipation boundary is identified according to the compensation loss coefficient; A gap compensation parameter is determined according to the compensation dissipation boundary.

6. The method of claim 1, wherein, The layered control instruction set is divided into immediate response instructions and delayed response instructions according to response time differences. A time response axis is established according to the response time differences. The layered control instruction set is mapped to the time response axis to form a response time label. The layered control instruction set is divided into a fast response section and a slow response section of peak shaving resources according to the response time label. Immediate response instructions and delayed response instructions are generated by time difference classification of the fast response section and the slow response section of peak shaving resources.

7. The method of claim 1, wherein, The delayed response instructions are subjected to fluctuation adjustment benefit identification to obtain a peak shaving benefit coefficient. The delayed response instructions are converted into a load transfer vector. The maximum position of the peak-valley difference is located in the load transfer vector. The maximum position of the peak-valley difference is used as a benefit conversion benchmark to accumulate benefits and form a benefit distribution curve. The peak shaving benefit coefficient is determined by peak value extraction of the benefit distribution curve.

8. The method of claim 3, wherein, The peak value start position is determined according to the peak value duration data. The duration change key points in the peak value duration data are analyzed. The available peak value prediction time is determined at the duration change key points. The prediction accuracy of the peak value prediction time is evaluated to generate an accuracy evaluation result. The peak value start position is generated according to the peak value prediction time and the accuracy evaluation result.

9. The method of claim 6, wherein, The fast response section and the slow response section of peak shaving resources are subjected to time difference classification to generate immediate response instructions and delayed response instructions. The fast response section is converted into an immediate execution time sequence. The slow response section of peak shaving resources is superimposed on the immediate execution time sequence to form a response difference distribution. The time difference boundary threshold of the delay benefit window is derived from the response difference distribution. Immediate response instructions and delayed response instructions are generated according to the distinguishing significance of the time difference boundary threshold.

10. An intelligent deployment system for urban energy networks, characterized in that it comprises: It includes: The energy consumption collection module is used to obtain building energy consumption data and energy supply network topology information, identify load fluctuation characteristics according to the energy consumption data, and establish a supply-demand matching benchmark between the load fluctuation characteristics and the energy supply network topology information; The load analysis module is used to detect load peak dense time periods based on the supply-demand matching benchmark, extract peak clipping and valley filling potential areas from the load peak dense time periods, derive transferable load data through the peak clipping and valley filling potential areas, and form a regional supply-demand distribution map according to the transferable load data; The time sequence matching module is used to obtain user response delay duration and device start-stop cycle, identify a time elasticity interval through the response delay duration, capture a regulation switching time according to the device start-stop cycle, and generate a peak shaving regulation space by time sequence comparison between the time elasticity interval and the regulation switching time; The regulation strategy module is configured to perform gap matching analysis on the area supply-demand distribution map and the peak-shaving regulation space to generate gap compensation parameters, determine a regulation target node based on the gap compensation parameters, and create a hierarchical regulation instruction set based on the regulation target node. The instruction coordination module is configured to distinguish instant response instructions and delayed response instructions from the hierarchical regulation instruction set according to response time differences, identify and obtain a peak-shaving benefit coefficient by performing fluctuation regulation benefit identification on the delayed response instructions, and form regulation coordination parameters by coordinating the peak-shaving benefit coefficient and the instant response instructions. The scheme generation module is configured to determine a regulation execution range based on the regulation coordination parameters and the area supply-demand distribution map, perform cost-benefit evaluation on the regulation execution range, and form a city-level energy dispatch execution scheme.

Images