Distributed resource control system and method based on cross-domain dynamic coupling

Abstract

The invention discloses a distributed resource control system and method based on cross-domain dynamic coupling, and the system comprises a space-time dynamic coupling analysis module which is used for analyzing collected distributed resource operation data to obtain a distributed resource space-time distribution condition, constructing an adjustable resource scheduling optimization model, and carrying out the optimization of the adjustable resource scheduling optimization model; inputting actual to-be-analyzed resource data into the adjustable resource scheduling optimization model to generate a resource optimization scheduling scheme; the multi-level differential regulation and control module is used for generating a multi-level differential regulation and control model according to the resource optimization scheduling scheme and the layered and clustered architecture so as to adopt different regulation and control strategies for a regional power grid, a power distribution network and a micro-grid in the layered and clustered architecture; and the cloud edge collaborative synchronization module is used for issuing regulation and control indexes generated according to the regulation and control strategy to edge side equipment, and adjusting the multi-level differential regulation and control model according to feedback data collected by the edge side equipment. By implementing the method and the system, effective regulation and control of massive distributed resources are realized, and the regulation and control efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed resource control, and more specifically to a distributed resource control system and method based on cross-domain dynamic coupling. Background Art

[0002] The large-scale access of distributed new energy and the shift of fossil energy consumption to electricity consumption have led to huge changes in both the supply and demand sides of the power grid. On the supply side, the access capacity and large-scale perception capacity of new energy are insufficient, the power quality is poor, and there is a lack of local collaborative control measures; on the demand side, the power load shows the characteristics of continuous rigid growth in total demand and irregular power consumption, and faces problems such as insufficient capacity to absorb distributed new energy and lack of local autonomy.

[0003] Therefore, how to help the power grid eliminate the uncertainty and contradictions on both the supply and demand sides and solve the problems faced by the supply and demand balance has become the focus of long-term research in the industry. At this stage, according to the overall idea of ​​multi-source secure access and hierarchical aggregation control, key technologies such as new energy access, carbon tracking, carbon verification, and local balance of source, grid and load are studied to promote the transformation of the power grid from the traditional "passive" one-way radiation network to the "active" two-way interactive system, and from a single power supply and distribution service entity to an efficient configuration platform for source, grid, load and storage resources, to support the construction of a new power system with green, low-carbon, flexible, digital and intelligent characteristics, and to help fully utilize distributed new energy and develop in a low-carbon manner. In response to the problems faced by the integration of source, grid, load and storage, the existing control system mainly adopts a centralized control mode, which is regulated by average decomposition and indicators to households through the cloud. It is impossible to effectively regulate massive distributed resources, and the regulation strategy is slow to generate and the regulation efficiency is low. Summary of the invention

[0004] The purpose of the present invention is to provide a distributed resource control system and method based on cross-domain dynamic coupling to solve the problem that the existing control system cannot effectively regulate massive distributed resources and the regulation efficiency is low.

[0005] In order to achieve the above-mentioned objectives, on the one hand, the present invention provides a distributed resource control system based on cross-domain dynamic coupling, including: a spatiotemporal dynamic coupling analysis module, which is used to analyze the change laws and distribution characteristics of the collected distributed resource operation data in the spatiotemporal dimensions to obtain the spatiotemporal distribution of distributed resources, and to construct an adjustable resource scheduling optimization model based on the spatiotemporal distribution of the distributed resources, and to input the actual resource data to be analyzed into the adjustable resource scheduling optimization model to generate a resource optimization scheduling plan; a multi-level differentiated control module, which is used to generate a multi-level differentiated control model according to the resource optimization scheduling plan and the hierarchical clustering architecture, so as to adopt different control strategies for the regional power grid, distribution network and microgrid in the hierarchical clustering architecture; a cloud-edge collaborative synchronization module, which is used to generate control indicators according to the control strategy, and send the control indicators to the edge devices, and adjust the multi-level differentiated control model according to the feedback data collected by the edge devices.

[0006] Its further technical solution is: the time-space dynamic coupling analysis module includes: an acquisition preprocessing module, which is used to collect distributed resource operation data, and clean and classify the distributed resource operation data to obtain distributed resource classification data; a time-space analysis module, which is used to perform time-space feature analysis on the distributed resource classification data to obtain the time-space distribution of the distributed resources; a construction module, which is used to solve the optimization model based on the time-space distribution of the distributed resources, the designed optimization objective function and the established multi-dimensional constraints using the particle swarm optimization method to construct the adjustable resource scheduling optimization model; a model verification optimization module, which is used to verify the adjustable resource scheduling optimization model to obtain a verification result, and adjust the model parameters of the adjustable resource scheduling optimization model according to the verification result to optimize the adjustable resource scheduling optimization model; a scheduling generation module, which is used to input the actual resource data to be analyzed into the adjusted resource scheduling optimization model after verification and optimization for scheduling analysis to generate the resource optimization scheduling plan.

[0007] Its further technical solution is: the multi-level differentiated control module includes: a regional power grid control module, which is used to generate an economic and low-carbon operation control strategy based on the resource optimization scheduling plan and the deep neural network model; a distribution network control module, which is used to establish a task indicator decomposition system based on the resource optimization scheduling plan, and adopt a multi-round response mechanism within the day before to roll out the tasks in the task indicator decomposition system, monitor the accuracy of task execution to generate an intensive management strategy; a microgrid control module, which is used to carry out line flow monitoring and line operation condition analysis, and when the mutual assistance conditions are met, generate mutual assistance and partitioned autonomy strategies according to the resource optimization scheduling plan.

[0008] Its further technical solution is: the regional power grid control module includes: a conditional input determination module, which is used to take the green electricity consumption, energy storage configuration and typical daily load curve in the regional power grid as regional input data, and the power generation capacity, electricity demand and carbon emissions in the regional power grid as regional constraints; a regional strategy generation module, which is used to input the regional input data and the regional constraints into the deep neural network model to output the economic low-carbon operation control strategy, and optimize and adjust the economic low-carbon operation control strategy according to the resource optimization scheduling plan, wherein the economic low-carbon operation control strategy includes annual power generation and consumption indicators, quarterly power generation and consumption indicators, monthly power generation and consumption indicators, annual carbon emissions indicators, quarterly carbon emissions indicators and monthly carbon emissions indicators.

[0009] Its further technical solution is: the distribution network control module includes: a task indicator establishment module, which is used to establish the task indicator decomposition system of the day-ahead source-load forecast information and the day-intraday source-load forecast information based on the spatiotemporal distribution of the distributed resources in the resource optimization scheduling scheme, and put the tasks in the task indicator decomposition system into a multi-load resource pool; a task execution monitoring module, which is used to control the daily execution tasks using a multi-round response mechanism within the day-ahead, and to execute the tasks in the multi-load resource pool in a rolling manner, monitor the accuracy of the execution of the tasks, and when the accuracy is lower than the threshold, start the next round of control, thereby generating the intensive management strategy.

[0010] Its further technical solution is: the microgrid control module includes: a detection module, which is used to perform line overload detection to determine whether the mutual assistance conditions are met; a microgrid strategy generation module, which is used to calculate the capacity required for line overload when the mutual assistance conditions are met, and weight the factors according to the degree of influence of each substation load on the line overload, the adjustable load amount and the load type to obtain a priority weighted value, and prioritize the overload capacity required according to the priority weighted value to obtain a multi-level priority adjustable capacity, and use the i-th priority adjustable capacity as the allocated capacity, where i=1; determine whether the allocated capacity is greater than the remaining adjustment capacity; if the allocated capacity is greater than the remaining adjustment capacity, then decompose the remaining adjustment capacity to each substation in proportion according to the capacity size of each substation, and output the priority adjustment instructions corresponding to each substation to generate the mutual assistance and partitioned autonomous strategy.

[0011] Its further technical solution is: the microgrid control module also includes: an update execution module, which is used to, if the allocated capacity is not greater than the remaining adjustment capacity, involve all the allocated capacity in the adjustment, update the remaining adjustment capacity, and make i=i+1, use the i-th priority adjustable capacity as the allocated capacity, and return to execute the step of determining whether the allocated capacity is greater than the remaining adjustment capacity, until all the multi-level priority adjustable capacities are involved in the adjustment.

[0012] Its further technical solution is: the cloud-edge collaborative synchronization module includes: a sending module, used to send the control instructions corresponding to the control indicators to the edge device; a control evaluation module, used to evaluate the control effect according to the feedback data uploaded by the edge device to generate an effect evaluation result, and adjust the hierarchical differentiated control model according to the effect evaluation result.

[0013] Its further technical solution is: the cloud-edge collaborative synchronization module also includes: a source load prediction module, which is used to predict the source load based on environmental data, weather data and historical data; a positioning and push module, which is used to locate fault information and push the fault information in real time.

[0014] In order to achieve the above-mentioned purpose, on another aspect, the present invention also provides a distributed resource control method based on cross-domain dynamic coupling, including: using a spatiotemporal dynamic coupling analysis module to analyze the change law and distribution characteristics of the collected distributed resource operation data in the spatiotemporal dimension to obtain the spatiotemporal distribution of distributed resources, constructing an adjustable resource scheduling optimization model based on the spatiotemporal distribution of the distributed resources, and inputting the actual resource data to be analyzed into the adjustable resource scheduling optimization model to generate a resource optimization scheduling plan; using a multi-level differentiated control module to generate a multi-level differentiated control model according to the resource optimization scheduling plan and the hierarchical clustering architecture, so as to adopt different control strategies for the regional power grid, distribution network and microgrid in the hierarchical clustering architecture; using a cloud-edge collaborative synchronization module to generate control indicators according to the control strategy, and sending the control indicators to the edge devices.

[0015] The embodiment of the present invention provides a distributed resource control system and method based on cross-domain dynamic coupling, wherein the system first generates a resource optimization scheduling scheme based on a constructed adjustable resource scheduling optimization model through a spatiotemporal dynamic coupling analysis module; then, according to the resource optimization scheduling scheme and the hierarchical and clustered architecture, different control strategies are quickly generated through a multi-level differentiated control module to regulate the regional power grid, distribution network and microgrid; finally, the control indicators are issued through a cloud-edge collaborative synchronization module, and the multi-level differentiated control model is adjusted according to the feedback data to make the generated control strategy more accurate, thereby realizing effective control of massive distributed resources and improving the control efficiency.

[0016] The present invention will become more apparent from the following description taken in conjunction with the accompanying drawings, which are used to illustrate embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A block diagram of a distributed resource control system based on cross-domain dynamic coupling according to the present invention; Figure 2 A schematic diagram of a hierarchical clustering architecture in a distributed resource control system based on cross-domain dynamic coupling according to the present invention; Figure 3 A block diagram of a spatiotemporal dynamic coupling analysis module in a distributed resource control system based on cross-domain dynamic coupling according to the present invention; Figure 4 It is a block diagram of a multi-level differentiated control module in a distributed resource control system based on cross-domain dynamic coupling of the present invention; Figure 5 A block diagram of a regional power grid control module in a distributed resource control system based on cross-domain dynamic coupling according to the present invention; Figure 6 A block diagram of a distribution network control module in a distributed resource control system based on cross-domain dynamic coupling according to the present invention; Figure 7 A block diagram of a microgrid control module in a distributed resource control system based on cross-domain dynamic coupling according to the present invention; Figure 8 It is a block diagram of a cloud-edge collaborative synchronization module in a distributed resource control system based on cross-domain dynamic coupling of the present invention; Fig. 9 A schematic diagram of a flow chart of a distributed resource control method based on cross-domain dynamic coupling according to an embodiment of the present invention; Reference numerals: 10. Distributed resource control system based on cross-domain dynamic coupling; 11. Spatiotemporal dynamic coupling analysis module; 111. Acquisition preprocessing module; 112. Spatiotemporal analysis module; 113. Construction module; 114. Model verification and optimization module; 115. Dispatch generation module; 12. Multi-level differentiated control module; 121. Regional power grid control module; 1211. Conditional input determination module; 1212. Regional strategy generation module; 122. Distribution network control module; 1221. Task indicator establishment module; 1222. Task execution monitoring module; 123. Microgrid control module; 1231. Detection module; 1232. Microgrid strategy generation module; 1233. Update execution module; 13. Cloud-edge collaborative synchronization module; 131. Issuance module; 132. Control and evaluation module; 133. Source and load prediction module; 134. Positioning push module. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Similar component numbers in the drawings represent similar components. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Reference Figures 1 to 8 The distributed resource control system 10 based on cross-domain dynamic coupling provided by the embodiment of the present invention includes a spatiotemporal dynamic coupling analysis module 11, a multi-level differentiated regulation module 12 and a cloud-edge collaborative synchronization module 13, wherein the spatiotemporal dynamic coupling analysis module 11 is used to analyze the change law and distribution characteristics of the collected distributed resource operation data in the spatiotemporal dimension to obtain the spatiotemporal distribution of distributed resources, and to construct an adjustable resource scheduling optimization model based on the spatiotemporal distribution of the distributed resources, and to input the actual resource data to be analyzed into the adjustable resource scheduling optimization model to generate a resource optimization scheduling plan; the multi-level differentiated regulation module 12 is used to generate a multi-level differentiated regulation model according to the resource optimization scheduling plan and the hierarchical clustering architecture, so as to adopt different regulation strategies for the regional power grid, distribution network and microgrid in the hierarchical clustering architecture; the cloud-edge collaborative synchronization module 13 is used to generate a regulation indicator according to the regulation strategy, and send the regulation indicator to the edge device, and adjust the multi-level differentiated regulation model according to the feedback data collected by the edge device. It should be noted that, in this embodiment, the distributed resource control system 10 based on cross-domain dynamic coupling is configured in a computer device in the cloud, and the functions of the distributed resource control system 10 based on cross-domain dynamic coupling are realized by executing corresponding software programs in the computer device. It should also be noted that, in this embodiment, the resource optimization scheduling scheme is first generated by the spatiotemporal dynamic coupling analysis module 11 based on the constructed adjustable resource scheduling optimization model; then, different control strategies are quickly generated by the multi-level differentiated control module 12 according to the resource optimization scheduling scheme and the hierarchical and clustered architecture to control the regional power grid, distribution network and microgrid; finally, the control index is issued by the cloud-edge collaborative synchronization module 13, and the multi-level differentiated control model is adjusted according to the feedback data to make the generated control strategy more accurate, thereby realizing the effective control of massive distributed resources and improving the control efficiency.

[0020] In some embodiments, such as the present embodiment, Figure 2As shown in the figure, the hierarchical clustering architecture realizes the responsibility sharing of the regional power distribution network by dividing the power balance areas at different levels. Specifically, the regional power distribution network includes the regional power grid, the distribution network and the microgrid, among which the regional power grid is composed of a cluster of several interconnected distribution networks, and the distribution network is composed of a cluster of several interconnected microgrids. Each microgrid has power generation, load, intelligent control and communication capabilities, and can realize local power generation / load scheduling and feedback control to maintain net power balance and optimize operation. In the event of a fault, the microgrid can also alleviate the fault problem by reducing power generation or load.

[0021] In some embodiments, such as the present embodiment, Figure 3As shown, the spatiotemporal dynamic coupling analysis module 11 includes an acquisition preprocessing module 111, a spatiotemporal analysis module 112, a construction module 113, a model verification optimization module 114 and a scheduling generation module 115, wherein the acquisition preprocessing module 111 is used to collect distributed resource operation data, and clean and classify the distributed resource operation data to obtain distributed resource classification data; the spatiotemporal analysis module 112 is used to perform spatiotemporal feature analysis on the distributed resource classification data to obtain the spatiotemporal distribution of the distributed resources; the construction module 113 is used to perform spatiotemporal feature analysis on the distributed resource classification data to obtain the spatiotemporal distribution of the distributed resources; the construction module 113 is used to perform spatiotemporal distribution analysis on the distributed resource classification data based on the spatiotemporal distribution of the distributed resources. , the designed optimization objective function and the established multi-dimensional constraints are solved by the particle swarm optimization method to construct the adjustable resource scheduling optimization model; the model verification optimization module 114 is used to verify the adjustable resource scheduling optimization model to obtain a verification result, and adjust the model parameters of the adjustable resource scheduling optimization model according to the verification result to optimize the adjustable resource scheduling optimization model; the scheduling generation module 115 is used to input the actual resource data to be analyzed into the verified and optimized adjustable resource scheduling optimization model for scheduling analysis to generate the resource optimization scheduling plan. It should be noted that in this embodiment, the distributed resource operation data includes photovoltaic output data, load data, geographic location, timestamp and other data of the distributed resources; the distributed resource operation data is cleaned to eliminate outliers and ensure the accuracy of the data; according to urban and rural differences, such as load density, resource type, power grid structure, etc., the cleaned distributed resource operation data is classified to obtain the distributed resource classification data. It should also be noted that, in this embodiment, the temporal and spatial characteristics of the distributed resource classification data are analyzed to obtain the temporal and spatial distribution of the distributed resources. Specifically, in terms of the time dimension, the change rules of the distributed resource classification data at the hourly and minute levels are analyzed, such as the intraday fluctuation of photovoltaic output and the peak and valley characteristics of load, and the change trend of the distributed resource classification data at the seasonal and annual scales is studied, such as seasonal load changes and interannual fluctuations of photovoltaic output; in terms of the spatial dimension, based on the geographic information system, a spatial distribution map of distributed resources is drawn to analyze the density and concentration of distributed resources in urban and rural areas, compare the differences in resource types, capacity, adjustable potential, etc. between urban and rural areas, and identify key influencing factors. Further, in this embodiment, the designed optimization objective function is a function designed based on resource utilization, supply and demand matching, etc., and the multi-dimensional constraints include physical constraints of the power grid, operation constraints, and resource characteristic constraints. The physical constraints of the power grid include line capacity and voltage limit; the operation constraints include power balance and regulation response time, and the resource characteristic constraints include energy storage charging and discharging rate and photovoltaic output fluctuation.Furthermore, in this embodiment, the adjustable resource scheduling optimization model is verified to evaluate its performance under different conditions, and the model parameters of the adjustable resource scheduling optimization model are adjusted to optimize the adjustable resource scheduling optimization model, thereby optimizing the generated resource optimization scheduling scheme.

[0022] In some embodiments, such as the present embodiment, Figure 4 As shown, the multi-level differentiated control module 12 includes a regional power grid control module 121, a distribution network control module 122 and a microgrid control module 123, wherein the regional power grid control module 121 is used to generate an economic and low-carbon operation control strategy based on the resource optimization scheduling scheme and the deep neural network model; the distribution network control module 122 is used to establish a task indicator decomposition system based on the resource optimization scheduling scheme, and adopt a multi-round response mechanism within the day before to roll out the tasks in the task indicator decomposition system, monitor the accuracy of task execution to generate an intensive management strategy; the microgrid control module 123 is used to carry out line flow monitoring, analyze line operating conditions, and when the mutual assistance conditions are met, generate mutual assistance and partition autonomy strategies according to the resource optimization scheduling scheme. It should be noted that, in this embodiment, the low-carbon economic operation and control strategy aims at low-carbon economic development, fully considers regional power generation, power balance and carbon emissions information, and issues annual, quarterly and monthly execution indicators layer by layer; the intensive management strategy constructs a multi-load resource pool to support efficient resource scheduling of distributed photovoltaic stations, charging stations, energy storage stations, etc. in the distribution network; the mutual assistance and regional autonomy strategy aims at safe operation, power load fluctuation suppression, and power quality optimization, realizes cross-domain energy mutual assistance and autonomous operation of microgrids, and supports microgrid fault alarm recovery and power balance.

[0023] In some embodiments, such as the present embodiment, Figure 5As shown, the regional power grid control module 121 includes a condition input determination module 1211 and a regional strategy generation module 1212, wherein the condition input determination module 1211 is used to take the green electricity consumption situation, energy storage configuration and typical daily load curve in the regional power grid as regional input data, and the power generation capacity, electricity demand and carbon emissions in the regional power grid as regional constraints; the regional strategy generation module 1212 is used to input the regional input data and the regional constraints into the deep neural network model to output the economic low-carbon operation control strategy, and optimize and adjust the economic low-carbon operation control strategy according to the resource optimization scheduling plan, wherein the economic low-carbon operation control strategy includes annual power generation and consumption indicators, quarterly power generation and consumption indicators, monthly power generation and consumption indicators, annual carbon emissions indicators, quarterly carbon emissions indicators and monthly carbon emissions indicators. It should be noted that in this embodiment, the economic and low-carbon operation control strategy generated is aimed at medium- and long-term economic (for example, minimizing the operating costs of the regional power grid), low-carbon (for example, maximizing the proportion of green electricity consumption and minimizing carbon emissions), and reliable (for example, ensuring the stability of the power grid and improving the reliability of power supply) operation, taking into account the production and living energy consumption in the regional power grid. It should also be noted that in this embodiment, medium- and long-term indicators, such as annual power generation and consumption indicators, are decomposed into power grids at all levels, and the indicators are regularly adjusted and optimized according to the actual operating conditions and changes in the external environment to ensure that power grids at all levels can achieve efficient operation under the premise of meeting economic and low-carbon constraints.

[0024] In some embodiments, such as the present embodiment, Figure 6 As shown, the distribution network control module 122 includes a task indicator establishment module 1221 and a task execution monitoring module 1222, wherein the task indicator establishment module 1221 is used to establish the task indicator decomposition system of the source load forecast information and the source load forecast information within the day based on the spatiotemporal distribution of the distributed resources in the resource optimization scheduling scheme, and put the tasks in the task indicator decomposition system into a multi-load resource pool; the task execution monitoring module 1222 is used to control the daily execution task by adopting a multi-round response mechanism within the day before, and rollingly execute the tasks in the multi-load resource pool, monitor the accuracy of the execution task, and start the next round of regulation when the accuracy is lower than the threshold, thereby generating the intensive management strategy. It should be noted that in this embodiment, considering the application scenarios such as peak regulation, frequency regulation, voltage regulation and demand-side response, a multi-load resource pool is constructed with a microgrid as an intelligent body, and aggregation-layered cross-domain regulation is realized in the medium and short time scale. It should also be noted that in this embodiment, when the accuracy is not lower than the threshold, the regulation continues.

[0025] In some embodiments, such as the present embodiment, Figure 7As shown, the microgrid control module 123 includes a detection module 1231, a microgrid strategy generation module 1232 and an update execution module 1233, wherein the detection module 1231 is used to perform line overload detection to determine whether the mutual assistance condition is met; the microgrid strategy generation module 1232 is used to calculate the line overload required capacity when the mutual assistance condition is met, and weight the factors according to the influence of each substation load on the line overload, the adjustable load amount and the load type to obtain a priority weighted value, and prioritize the overload required capacity according to the priority weighted value to obtain a multi-level priority adjustable capacity, and use the i-th priority adjustable capacity as the allocated capacity, wherein i=1; judge the distribution Whether the allocated capacity is greater than the remaining adjustment capacity; if the allocated capacity is greater than the remaining adjustment capacity, the remaining adjustment capacity is proportionally decomposed to each substation according to the capacity size of each substation, and the priority adjustment instructions corresponding to each substation are output to generate the mutual assistance and partition autonomy strategy; the update execution module 1233 is used to participate in the regulation of all the allocated capacity if the allocated capacity is not greater than the remaining adjustment capacity, and update the remaining adjustment capacity, and make i=i+1, take the i-th priority adjustable capacity as the allocated capacity, and return to execute the step of judging whether the allocated capacity is greater than the remaining adjustment capacity, until the multi-level priority adjustable capacity is all involved in the regulation. It should be noted that in this embodiment, in view of the problems of close spatiotemporal coupling of distributed resources in the distribution network and difficulty in mutual assistance across substations, a mutual assistance and partition autonomy strategy is established with a preset kilovolt line as the management unit to carry out line power fluctuation suppression and power reverse transmission management. It should also be noted that in other embodiments, the detection module 1231 can also perform overvoltage, undervoltage, three-phase imbalance and other detections, and then determine whether the mutual assistance conditions are met to ensure safe and stable operation of the line.

[0026] In some embodiments, such as the present embodiment, Figure 8As shown, the cloud-edge collaborative synchronization module 13 includes a sending module 131, a control evaluation module 132, a source load prediction module 133 and a positioning push module 134, wherein the sending module 131 is used to send the control instructions corresponding to the control indicators to the edge device; the control evaluation module 132 is used to evaluate the control effect according to the feedback data uploaded by the edge device to generate an effect evaluation result, and adjust the hierarchical differentiated control model according to the effect evaluation result; the source load prediction module 133 is used to predict the source load according to environmental data, weather data and historical data; the positioning push module 134 is used to locate fault information and push the fault information in real time. It should be noted that in this embodiment, the cloud-edge collaborative synchronization module 13 can solve the problems of insufficient cloud computing power and low timeliness in massive distributed resource control scenarios. Specifically, first, the cloud quickly generates control indicators that fit the actual constraints according to the control strategy to ensure the rationality and feasibility of the control target; secondly, the edge device realizes second-level / minute-level load monitoring, and the control indicators issued by the cloud are decomposed to households according to the principles of fairness and rationality, and refined control instructions are generated and issued for execution, so as to improve the real-time and accuracy of the control. It should be noted that in this embodiment, the cloud-edge collaborative communication network is used to achieve data synchronization between the cloud and edge devices to ensure data consistency and real-time; the control indicators generated by the cloud and the control strategy generated by the edge are synchronized to ensure the consistency of the control target; the edge device perceives the operating status of the microgrid in real time, collects feedback data and uploads it to the cloud, and the cloud evaluates the control effect based on the feedback data, identifies the difference between the control strategy and the actual demand, and optimizes the hierarchical differentiated control model according to the effect evaluation results to improve the accuracy and adaptability of the control. It should also be noted that in this embodiment, the cloud-edge collaborative synchronization module 13 empowers functional modules such as energy and load prediction, control evaluation, and positioning push to improve the intelligence level of the distributed control system.

[0027] Reference Fig. 9 , Fig. 9 The flow chart of an embodiment of a distributed resource control method based on cross-domain dynamic coupling of the present invention is shown. The distributed resource control method based on cross-domain dynamic coupling is applied to the above-mentioned distributed resource control system based on cross-domain dynamic coupling. The specific implementation steps of the distributed resource control system based on cross-domain dynamic coupling of the present invention are further described in detail below. Fig. 9 As shown, the method includes steps S110-S130: S110, analyzing the change rules and distribution characteristics of the collected distributed resource operation data in the time and space dimensions through the time and space dynamic coupling analysis module to obtain the time and space distribution of the distributed resources, building an adjustable resource scheduling optimization model based on the time and space distribution of the distributed resources, and inputting the actual resource data to be analyzed into the adjustable resource scheduling optimization model to generate a resource optimization scheduling plan; S120, generating a multi-level differentiated control model according to the resource optimization scheduling scheme and the hierarchical clustering architecture through a multi-level differentiated control module, so as to adopt different control strategies for the regional power grid, distribution network and microgrid in the hierarchical clustering architecture; S130. Generate control indicators according to the control strategy through the cloud-edge collaborative synchronization module, and send the control indicators to the edge device.

[0028] In an embodiment of the present invention, a spatiotemporal dynamic coupling analysis module is used to analyze the change patterns and distribution characteristics of the collected distributed resource operation data in the spatiotemporal dimensions to obtain the spatiotemporal distribution of distributed resources, so as to construct an adjustable resource scheduling optimization model, and the actual resource data to be analyzed is input into the adjustable resource scheduling optimization model to generate a resource optimization scheduling plan; different control strategies are quickly generated through a multi-level differentiated control module according to the resource optimization scheduling plan and the hierarchical and clustered architecture to control the regional power grid, distribution network and microgrid; control indicators are issued through a cloud-edge collaborative synchronization module, and the multi-level differentiated control model is adjusted according to feedback data to make the generated control strategy more accurate, thereby realizing effective control of massive distributed resources and improving control efficiency. Further, the spatiotemporal dynamic coupling analysis module includes an acquisition preprocessing module, a spatiotemporal analysis module, a construction module, a model verification and optimization module, and a scheduling generation module; the multi-level differentiated control module includes: a regional power grid control module, a distribution network control module, and a microgrid control module; the regional power grid control module includes a conditional input determination module and a regional strategy generation module; the distribution network control module includes a task indicator establishment module and a task execution monitoring module; the microgrid control module includes a detection module, a microgrid strategy generation module, and an update execution module; the cloud-edge collaborative synchronization module includes a sending module, a control evaluation module, a source-load prediction module, and a positioning push module. It should be noted that in this embodiment, the specific implementations of the acquisition preprocessing module, the spatiotemporal analysis module, the construction module, the model verification and optimization module, the scheduling generation module, the regional power grid control module, the distribution network control module, the microgrid control module, the conditional input determination module, the regional strategy generation module, the task indicator establishment module, the task execution monitoring module, the detection module, the microgrid strategy generation module, the update execution module, the sending module, the control evaluation module, the source-load prediction module, and the positioning push module are as described above, and for the sake of simplicity, they will not be repeated here.

[0029] The present invention has been described above in conjunction with the best embodiments, but the present invention is not limited to the embodiments disclosed above, but should cover various modifications and equivalent combinations based on the essence of the present invention.

Claims

1. A distributed resource control system based on cross-domain dynamic coupling, characterized in that: include: The spatiotemporal dynamic coupling analysis module is used to analyze the change rules and distribution characteristics of the collected distributed resource operation data in the spatiotemporal dimension to obtain the spatiotemporal distribution of distributed resources, build an adjustable resource scheduling optimization model based on the spatiotemporal distribution of distributed resources, and input the actual resource data to be analyzed into the adjustable resource scheduling optimization model to generate a resource optimization scheduling plan; A multi-level differentiated control module, used to generate a multi-level differentiated control model according to the resource optimization scheduling scheme and the hierarchical clustering architecture, so as to adopt different control strategies for the regional power grid, distribution network and microgrid in the hierarchical clustering architecture; The cloud-edge collaborative synchronization module is used to generate control indicators according to the control strategy, send the control indicators to the edge devices, and adjust the multi-level differentiated control model according to the feedback data collected by the edge devices.

2. The distributed resource control system based on cross-domain dynamic coupling according to claim 1, characterized in that: The spatiotemporal dynamic coupling analysis module includes: The collection and preprocessing module is used to collect distributed resource operation data, and clean and classify the distributed resource operation data to obtain distributed resource classification data; A spatiotemporal analysis module, used to perform spatiotemporal feature analysis on the distributed resource classification data to obtain the spatiotemporal distribution of the distributed resources; A construction module is used to solve the optimization model by using a particle swarm optimization method based on the spatiotemporal distribution of the distributed resources, the designed optimization objective function, and the established multi-dimensional constraints, so as to construct the adjustable resource scheduling optimization model; A model verification and optimization module, used to verify the adjustable resource scheduling optimization model to obtain a verification result, and adjust the model parameters of the adjustable resource scheduling optimization model according to the verification result to optimize the adjustable resource scheduling optimization model; The scheduling generation module is used to input the actual resource data to be analyzed into the adjustable resource scheduling optimization model after verification and optimization to perform scheduling analysis to generate the resource optimization scheduling plan.

3. The distributed resource control system based on cross-domain dynamic coupling according to claim 1, characterized in that: The multi-level differentiated control module includes: A regional power grid control module, used to generate an economical and low-carbon operation control strategy based on the resource optimization scheduling scheme and the deep neural network model; A distribution network control module is used to establish a task index decomposition system based on the resource optimization scheduling scheme, and to use a multi-round response mechanism within the previous day to roll over the tasks in the task index decomposition system, and to monitor the accuracy of task execution to generate an intensive management strategy; The microgrid control module is used to carry out line flow monitoring and line operation condition analysis. When the mutual assistance conditions are met, a mutual assistance and partition autonomy strategy is generated according to the resource optimization scheduling plan.

4. The distributed resource control system based on cross-domain dynamic coupling as claimed in claim 3, characterized in that: The regional power grid control module includes: A condition input determination module is used to use the green power consumption situation, energy storage configuration and typical daily load curve in the regional power grid as regional input data, and the power generation capacity, power demand and carbon emissions in the regional power grid as regional constraint conditions; A regional strategy generation module is used to input the regional input data and the regional constraints into the deep neural network model to output the economic low-carbon operation regulation strategy, and optimize and adjust the economic low-carbon operation regulation strategy according to the resource optimization scheduling plan, wherein the economic low-carbon operation regulation strategy includes annual power generation and consumption indicators, quarterly power generation and consumption indicators, monthly power generation and consumption indicators, annual carbon emissions indicators, quarterly carbon emissions indicators and monthly carbon emissions indicators.

5. The distributed resource control system based on cross-domain dynamic coupling as claimed in claim 3, characterized in that: The distribution network control module includes: A task indicator establishment module, used to establish the task indicator decomposition system of the day-ahead source load forecast information and the intraday source load forecast information based on the spatiotemporal distribution of the distributed resources in the resource optimization scheduling scheme, and put the tasks in the task indicator decomposition system into a multi-load resource pool; The task execution monitoring module is used to control the daily execution tasks by adopting a multi-round response mechanism within the previous day, and to execute the tasks in the multi-load resource pool in a rolling manner, monitor the accuracy of the execution tasks, and when the accuracy is lower than a threshold, start the next round of regulation to generate the intensive management strategy.

6. The distributed resource control system based on cross-domain dynamic coupling as claimed in claim 3, characterized in that: The microgrid control module includes: A detection module, used to perform line overload detection to determine whether the mutual assistance conditions are met; The microgrid strategy generation module is used to calculate the capacity required for line overload when the mutual assistance conditions are met, weight the factors according to the degree of influence of the load of each substation on the line overload, the adjustable load amount and the load type to obtain a priority weighted value, prioritize the overload capacity required for adjustment according to the priority weighted value to obtain a multi-level priority adjustable capacity, and use the i-th priority adjustable capacity as the allocated capacity, where i=1; determine whether the allocated capacity is greater than the remaining adjustment capacity; if the allocated capacity is greater than the remaining adjustment capacity, then decompose the remaining adjustment capacity to each substation in proportion according to the capacity size of each substation, and output the priority adjustment instruction corresponding to each substation to generate the mutual assistance and partition autonomy strategy.

7. The distributed resource control system based on cross-domain dynamic coupling as claimed in claim 6, characterized in that: The microgrid control module also includes: An update execution module is used to, if the allocated capacity is not greater than the remaining adjustment capacity, involve all the allocated capacity in the adjustment, update the remaining adjustment capacity, and make i=i+1, use the i-th priority adjustable capacity as the allocated capacity, and return to execute the step of determining whether the allocated capacity is greater than the remaining adjustment capacity, until all the multi-level priority adjustable capacities are involved in the adjustment.

8. The distributed resource control system based on cross-domain dynamic coupling according to any one of claims 1 to 7, characterized in that: The cloud-edge collaborative synchronization module includes: A sending module, used for sending a control instruction corresponding to the control index to the edge device; The control evaluation module is used to evaluate the control effect according to the feedback data uploaded by the edge device to generate an effect evaluation result, and adjust the hierarchical differentiated control model according to the effect evaluation result.

9. The distributed resource control system based on cross-domain dynamic coupling according to any one of claims 1 to 7, characterized in that: The cloud-edge collaborative synchronization module also includes: The source load prediction module is used to predict the source load based on environmental data, weather data and historical data; The positioning and pushing module is used to locate fault information and push the fault information in real time.

10. A distributed resource control method based on cross-domain dynamic coupling, characterized in that: include: The distributed resource operation data collected is analyzed through the time-space dynamic coupling analysis module to obtain the change law and distribution characteristics in the time-space dimension to obtain the distributed resource time-space distribution situation, and an adjustable resource scheduling optimization model is constructed based on the distributed resource time-space distribution situation, and the actual resource data to be analyzed is input into the adjustable resource scheduling optimization model to generate a resource optimization scheduling plan; A multi-level differentiated control model is generated according to the resource optimization scheduling scheme and the hierarchical clustering architecture through a multi-level differentiated control module, so as to adopt different control strategies for the regional power grid, distribution network and microgrid in the hierarchical clustering architecture; The cloud-edge collaborative synchronization module is used to generate control indicators according to the control strategy, and the control indicators are sent to the edge devices.

Images