Energy management and control method and system for intelligent park

Abstract

The invention provides an intelligent park-oriented energy management and control method and system, and the method comprises the steps: receiving multi-source heterogeneous extreme weather early warning information, analyzing the relation between the coverage range of a geographic information system and the geographic position of an intelligent park through the combination of the geographic information system, and evaluating the influence of extreme weather on different functional regions and energy consumption nodes. A distributed reinforcement learning algorithm is utilized to adaptively adjust an energy supply strategy, an optimal comprehensive adjustment scheme is selected, a multi-level real-time optimization model is constructed based on the scheme, optimization levels are automatically switched according to changes of internal and external environments, an optimized energy distribution plan is generated, and energy distribution is regulated and controlled in real time through Internet of Things equipment. Unmanned aerial vehicle and robot technologies are utilized to inspect key facilities, a feedback data continuous optimization model is collected, and an intelligent park energy management and control mechanism is formed; the energy supply stability, the operation efficiency and the emergency response capability of the intelligent park under the extreme weather condition are improved, and the energy cost and the operation risk are reduced at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of smart parks, and in particular to an energy control method for smart parks. Background Art

[0002] With the rapid development of smart parks, energy management has become a key link to ensure the efficient and stable operation of the parks. Smart parks usually include multiple functional areas, such as office areas, production areas, living areas, etc. The energy demands and consumption patterns of each area are different. However, the frequent occurrence of extreme weather events has brought huge challenges to the energy supply and consumption in the parks. For example, extreme weather such as heavy rain, typhoon, and high temperature may lead to a sharp increase in energy demand or supply interruption;

[0003] Currently, the energy management of smart parks mainly adopts some relatively advanced technical solutions, such as data-driven prediction models and centralized optimization algorithms. These solutions generate energy distribution plans by integrating historical energy consumption data, weather forecast information, and the operation status of the parks, using machine learning and optimization algorithms. However, these technologies still have obvious defects when dealing with extreme weather. For example, data-driven prediction models rely on historical data and are difficult to accurately predict sudden changes in energy demand brought about by extreme weather; while the centralized optimization algorithm can perform energy scheduling at the macro level, but lacks refined control of key energy consumption nodes at the micro level, resulting in low energy distribution efficiency under extreme weather conditions;

[0004] In addition, the existing solutions are insufficient in real-time and adaptability when dealing with extreme weather. For example, existing systems usually adopt a data update and strategy adjustment mechanism at fixed time intervals and cannot respond in real time to the rapid changes brought about by extreme weather. At the same time, these solutions lack in-depth fusion analysis of multi-source heterogeneous extreme weather warning information and are difficult to comprehensively evaluate the specific impacts of extreme weather on different functional areas and energy consumption nodes in the parks. Summary of the Invention

[0005] Embodiments of the present invention provide an energy control method and system for smart parks to solve the problems in the prior art that when facing extreme weather, data-driven prediction models rely on historical data and are difficult to accurately predict sudden changes in energy demand brought about by extreme weather, lack refined control of key energy consumption nodes at the micro level, resulting in low energy distribution efficiency under extreme weather conditions, adopt a data update and strategy adjustment mechanism at fixed time intervals, and cannot respond in real time to the rapid changes brought about by extreme weather, resulting in delays in fault discovery and handling under extreme weather conditions.

[0006] In a first aspect, embodiments of the present invention provide an energy control method for smart parks, including:

[0007] According to the received multi-source heterogeneous extreme weather warning information, combine with the geographical information system to analyze the relationship between the coverage scope of each multi-source heterogeneous extreme weather warning information and the geographical location of the intelligent park, and evaluate the influence level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the intelligent park;

[0008] For the key energy consumption nodes whose influence level by extreme weather is greater than the preset value, use the distributed reinforcement learning algorithm to adaptively adjust the preset energy supply strategy, and simulate and predict the changes in the operating states of the key energy consumption nodes under different energy supply strategies and the mutual influence of the changes in the operating states, so as to select the best comprehensive adjustment plan;

[0009] Based on the comprehensive adjustment plan, as well as the uncertain factors brought by extreme weather and the impact on energy price fluctuations, construct a multi-level real-time optimization model, automatically switch different optimization levels for the multi-level real-time optimization model according to the changes in the internal and external environments of the intelligent park, and perform intelligent scheduling and cost control processing from the micro level of individual key energy consumption nodes to the macro level of the entire intelligent park, and generate an optimized energy distribution plan;

[0010] According to the optimized energy distribution plan, immediately adjust and control the energy distribution in the intelligent park through Internet of Things devices, and use drone and robot technologies to inspect key facilities, collect on-site feedback data to optimize the multi-level real-time optimization model in real time, so as to obtain the energy management and control mechanism of the intelligent park.

[0011] Optionally, for the key energy consumption nodes whose influence level by extreme weather is greater than the preset value, use the distributed reinforcement learning algorithm to adaptively adjust the preset energy supply strategy, and simulate and predict the changes in the operating states of the key energy consumption nodes under different energy supply strategies and the mutual influence of the changes in the operating states, so as to select the best comprehensive adjustment plan, including:

[0012] Use the data integration platform to analyze the energy consumption patterns, environmental parameters and operating modes of key energy consumption nodes under current and historical extreme weather conditions to obtain a dynamically updated basic database;

[0013] According to the dynamically updated basic database, define the state space, action space, reward function and constraint conditions of each key energy consumption node to generate a definition result, and configure each key energy consumption node based on the definition result;

[0014] Based on the defined state space, action space, reward function and constraint conditions, adopt an enhanced distributed reinforcement learning algorithm combined with the federated learning mechanism to independently train each key energy consumption node and share the learning results while protecting data privacy, and generate an initial energy supply strategy;

[0015] For the initial energy supply strategy, conduct multi-round and multi-level simulation tests in the simulation environment. In each round, based on different extreme weather scenario assumptions and combined with actual market information, simulate and predict the changes in the operating states of each key energy consumption node and the complex interactive effects among the key energy consumption nodes, and generate a series of initial adjustment plans;

[0016] Introduce an evaluation framework to comprehensively evaluate the system performance after the execution of each initial adjustment plan, and generate the effectiveness evaluation results of each initial adjustment plan;

[0017] Combined with the overall goals preset for the smart park and the requirements for emergency response capabilities in extreme situations, based on the effectiveness evaluation results of each initial adjustment plan, select the best comprehensive adjustment plan.

[0018] Optionally, for the initial energy supply strategy, conduct multi-round and multi-level simulation tests in the simulation environment. In each round, based on different extreme weather scenario assumptions and combined with actual market information, simulate and predict the changes in the operating states of each key energy consumption node and the complex interactive effects among the key energy consumption nodes, and generate a series of initial adjustment plans, including:

[0019] Use the simulation environment construction module to build a virtual smart park model based on the dynamically updated basic database and definition results;

[0020] According to different types of extreme weather scenarios encountered by the smart park, combined with extreme weather cases in historical data and meteorological forecast information, set multiple hypothetical conditions for each extreme weather scenario to generate a set of extreme weather scenario assumption sets;

[0021] Based on the set of extreme weather scenario assumptions and the actual market information obtained in real time, conduct multi-round simulation tests on the initial energy supply strategy. In each round, for each extreme weather scenario assumption, use the virtual smart park model to simulate and predict the changes in the operating states of each key energy consumption node, analyze how the changes in the operating states affect the operation modes and energy efficiency performances of other nodes, and during the simulation process, collect the complex interactive effects among different key energy consumption nodes, identify potential risk points and optimization opportunities to generate simulation results;

[0022] According to each simulation result, record and quantify the performance indicators of each key energy consumption node under different extreme weather scenarios, evaluate the effects of the initial energy supply strategy under each simulation condition, and obtain the total sum of multiple simulation initial results;

[0023] Based on the sum of the multiple simulation initial results, comprehensively evaluate the performance of each key energy consumption node under various extreme weather scenarios, and generate a series of initial adjustment plans for specific extreme weather scenarios.

[0024] Optionally, based on the comprehensive adjustment plan, as well as the uncertainty factors brought by extreme weather and the impact on energy price fluctuations, construct a multi-level real-time optimization model, automatically switch different optimization levels of the multi-level real-time optimization model according to the changes in the internal and external environments of the smart park, and perform intelligent scheduling and cost control processing from the micro level of individual key energy consumption nodes to the macro level of the entire smart park, and generate an optimized energy distribution plan, including:

[0025] Based on the comprehensive adjustment plan, combine the uncertainty factors of extreme weather and the impact of extreme weather on energy price fluctuations to construct a multi-level real-time optimization model integrating predictive analysis and real-time feedback mechanisms;

[0026] Use the multi-level real-time optimization model to perform micro-level optimization processing on each key energy consumption node, use a high-precision sensor network to monitor the energy consumption pattern of each node in real time, predict the energy consumption trend through machine learning algorithms, and formulate personalized energy supply strategies for potential risks under different extreme weather scenarios to obtain micro-level optimization results;

[0027] According to the real-time changes in the internal and external environments of the smart park, automatically adjust and switch different optimization levels of the multi-level real-time optimization model using an adaptive algorithm. At the meso level, adopt distributed collaborative optimization technology to analyze the energy flow and interaction between subsystems, identify key paths and bottleneck points, and use them to optimize the operating efficiency of the subsystems to obtain meso-level optimization results, where the subsystem is a system composed of multiple related nodes;

[0028] At the macro level, integrate the preliminary optimization results at the micro level and the optimization results at the meso level, and introduce an advanced economic model and a social responsibility assessment framework to comprehensively optimize the overall energy management strategy of the entire smart park to generate macro-level optimization results;

[0029] Construct a secure transaction record system based on blockchain technology, use the secure transaction record system to track and verify the actual implementation of all energy transactions and control measures, and generate secure transaction records;

[0030] Combine the micro-level optimization results, the meso-level optimization results, the macro-level optimization results and the secure transaction records to generate an optimized energy distribution plan.

[0031] Optionally, according to the real-time changes in the internal and external environments of the smart park, an adaptive algorithm is used to automatically adjust and switch different optimization levels of the multi-level real-time optimization model. At the meso level, distributed collaborative optimization technology is adopted to analyze the energy flow and interaction between subsystems, identify key paths and bottleneck points, and optimize the operation efficiency of the subsystems to obtain the optimization results at the meso level. Among them, the subsystem is a system composed of multiple related nodes, including:

[0032] Utilize the intelligent sensor network and external data sources to conduct real-time monitoring and processing of the real-time changes in the internal and external environments of the smart park, and obtain real-time environmental status data;

[0033] Apply an adaptive algorithm to dynamically adjust and switch different optimization levels of the multi-level real-time optimization model. Based on the changes in the real-time environmental status data, select the best optimization level and accordingly adjust the parameters of the multi-level real-time optimization model to obtain the multi-level real-time optimization model after optimizing the level;

[0034] At the meso level, for the subsystems composed of multiple related key energy consumption nodes, adopt distributed collaborative optimization technology, utilize the multi-level real-time optimization model after optimizing the level, deeply analyze the energy flow and interaction between the subsystems, establish an energy flow model between subsystems, simulate the operation status of each subsystem and the mutual influence of each subsystem under different extreme weather scenarios, identify the key paths and bottleneck points that lead to the reduction of overall energy efficiency, and obtain the identification results of key paths and bottleneck points;

[0035] Based on the identification results of the key paths and bottleneck points, optimize the operation strategies of each subsystem, adjust the energy input-output ratio of the key energy consumption nodes, and obtain the optimized operation strategies of the subsystems;

[0036] According to the optimized operation strategies of the subsystems, use simulation tools to conduct multi-round simulation test processing on the subsystems. In each round of testing, based on different hypothetical scenarios, evaluate the performance indicators of the subsystems, adjust the preset optimization measures, obtain the verification results of the optimization measures, and combine the verification results of the optimization measures of all subsystems.

[0037] Optionally, it is characterized in that, according to the received multi-source heterogeneous extreme weather warning information, combined with the geographical information system, analyze the relationship between the coverage range of each multi-source heterogeneous extreme weather warning information and the geographical location of the smart park, and evaluate the influence level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park, including:

[0038] Utilize the data integration platform to integrate and process the multi-source heterogeneous extreme weather warning information received from multiple sources to form an extreme weather warning database in a unified format;

[0039] Based on the extreme weather warning database in the unified format, combined with the geographic information system, conduct spatial analysis and processing on the coverage scope of each extreme weather warning information, compare the geographical coordinates of the extreme weather warning information with the geographical coordinates of the intelligent park, determine the spatial relationship between each extreme weather warning information and the intelligent park, and obtain the spatial coverage analysis result of the extreme weather warning information;

[0040] Based on the spatial coverage analysis result of the extreme weather warning information, use the historical data analysis tool to review and analyze the response modes of different functional areas and energy consumption nodes in the intelligent park under extreme weather conditions, and generate a preliminary impact assessment report;

[0041] According to the preliminary impact assessment report, apply the preset impact level standard to classify each functional area and key energy consumption node in the intelligent park, determine the specific level of impact of each key energy consumption node by extreme weather, and obtain the impact level assessment result.

[0042] Optionally, according to the optimized energy distribution plan, conduct immediate regulation and control on the energy distribution in the intelligent park through Internet of Things devices, and use drone and robot technologies to inspect key facilities, collect on-site feedback data, and optimize the multi-level real-time optimization model in real time to obtain the intelligent park energy management and control mechanism, including:

[0043] Use the optimized energy distribution plan to send control instructions, configure the initial energy supply strategies of each key energy consumption node in the intelligent park, and conduct immediate regulation and control on the received control instructions through Internet of Things devices, so that each key energy consumption node operates according to the optimized energy distribution plan to obtain the immediate regulation result;

[0044] According to the immediate regulation result, start the drone and robot technologies to conduct inspections on the key facilities in the intelligent park for a preset period of time to generate an inspection report. Among them, the drone is used for aerial monitoring and coverage inspection, and the robot is used for ground facility and detection in complex environments to ensure the safety and normal operation status of all key facilities;

[0045] During the inspection process, use high-precision sensors and cameras to comprehensively monitor the status of key facilities and collect on-site feedback data to generate on-site feedback data;

[0046] Transmit the on-site feedback data to the central control system in real time, and comprehensively analyze and process the on-site feedback data in combination with historical data and preset safety standards, identify potential problems, and evaluate the impact degree of the potential problems on the optimized energy distribution plan to generate an analysis report;

[0047] Based on the analysis report, an adaptive algorithm is applied to dynamically adjust the multi-level real-time optimization model, optimizing the energy allocation and scheduling strategies at different levels, so that the multi-level real-time optimization model is consistent with the actual situation, and a real-time updated enhanced multi-level real-time optimization model is obtained;

[0048] According to the real-time updated enhanced multi-level real-time optimization model, the optimized energy allocation plan is adjusted again, and control instructions other than the existing control instructions are executed again through Internet of Things devices, and drones and robots are used again for inspection to generate an intelligent park energy management and control mechanism.

[0049] In a second aspect, an embodiment of the present invention provides an energy management and control system for an intelligent park, including:

[0050] A receiving module, configured to, according to the received multi-source heterogeneous extreme weather warning information, analyze the relationship between the coverage range of each multi-source heterogeneous extreme weather warning information and the geographical location of the intelligent park in combination with a geographic information system, and evaluate the influence level evaluation result of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the intelligent park;

[0051] A simulation module, configured to, for key energy consumption nodes whose influence level by extreme weather is greater than a preset value, adaptively adjust a preset energy supply strategy by using a distributed reinforcement learning algorithm, and simulate and predict the changes in the operating states of key energy consumption nodes and the mutual influence of the changes in the operating states under different energy supply strategies, so as to select an optimal comprehensive adjustment plan;

[0052] A construction module, configured to construct a multi-level real-time optimization model based on the comprehensive adjustment plan, the uncertainty factors brought by extreme weather, and the impact on energy price fluctuations, automatically switch different optimization levels for the multi-level real-time optimization model according to the changes in the internal and external environments of the intelligent park, and perform intelligent scheduling and cost control processing from the microscopic individual key energy consumption nodes to the macroscopic entire intelligent park level to generate an optimized energy allocation plan;

[0053] A regulation module, configured to, according to the optimized energy allocation plan, perform immediate regulation processing on the energy allocation in the intelligent park through Internet of Things devices, and use drone and robot technologies to inspect key facilities, collect on-site feedback data, and optimize the multi-level real-time optimization model in real time to obtain an intelligent park energy management and control mechanism.

[0054] In a third aspect, an embodiment of the present invention provides a computing device, including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method according to any one of the first aspect.

[0055] Fourthly, an embodiment of the present invention provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in any one of the first aspects is implemented.

[0056] In the embodiment of the present invention, according to the received multi-source heterogeneous extreme weather warning information, the relationship between the coverage range of each multi-source heterogeneous extreme weather warning information and the geographical location of the intelligent park is analyzed in combination with the geographical information system, and the influence level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the intelligent park are evaluated; for the key energy consumption nodes whose influence level by extreme weather is greater than a preset value, the distributed reinforcement learning algorithm is used to adaptively adjust the preset energy supply strategy, and the changes in the operating states of the key energy consumption nodes and the mutual influence of the changes in the operating states under different energy supply strategies are simulated and predicted to select the best comprehensive adjustment plan; based on the comprehensive adjustment plan and the uncertainty factors brought by extreme weather and the impact on energy price fluctuations, a multi-level real-time optimization model is constructed, and different optimization levels of the multi-level real-time optimization model are automatically switched according to the changes in the internal and external environments of the intelligent park, and intelligent scheduling and cost control processing are carried out from the micro single key energy consumption node to the macro entire intelligent park level to generate an optimized energy distribution plan; according to the optimized energy distribution plan, the energy distribution in the intelligent park is immediately regulated through Internet of Things devices, and drones and robot technologies are used to inspect key facilities, and on-site feedback data is collected to optimize the multi-level real-time optimization model in real time to obtain an energy management and control mechanism for the intelligent park;

[0057] The technical solution of the present application has the following beneficial effects:

[0058] Through dynamically evaluating the impact of extreme weather, adaptively adjusting the energy supply strategy, constructing a multi-level optimization model, and real-time regulation and inspection, the high-efficiency, intelligent and refined management of the energy in the intelligent park is realized. The beneficial effects include: improving the stability and reliability of energy supply under extreme weather, optimizing the energy distribution efficiency, reducing the operating cost, enhancing the emergency response ability, and further improving the overall energy management and control level of the park through data-driven continuous optimization;

[0059] Furthermore, by constructing a data integration platform, in-depth analysis is carried out on the energy consumption patterns, environmental parameters, and operation modes of key energy consumption nodes under current and historical extreme weather conditions to form a dynamically updated basic database. Based on this database, the state space, action space, reward function, and constraint conditions of each key energy consumption node are defined, and an enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism is used to independently train each node and share the learning results while protecting data privacy, generating an initial energy supply strategy. Subsequently, in a simulation environment, based on different extreme weather scenarios and market information, multiple rounds and multiple levels of simulation tests are carried out on the initial strategy to predict the changes in the operating states of each node and their mutual influences, generating a series of initial adjustment plans. Finally, through an evaluation framework, the system performance of each plan is comprehensively evaluated, and combined with the overall goals of the park and the requirements of emergency response, the best comprehensive adjustment plan is selected;

[0060] In summary, through the dynamically updated basic database and the enhanced distributed reinforcement learning algorithm, refined modeling and strategy optimization of energy consumption nodes under extreme weather conditions are achieved. Combining the federated learning mechanism, the collaborative learning ability of each node is improved while protecting data privacy, and the generated initial energy supply strategy has high adaptability and robustness. Through multiple rounds and multiple levels of simulation tests and evaluations, the plan can effectively predict the complex impacts of extreme weather on each node and generate the optimal comprehensive adjustment plan, significantly improving the energy supply stability, operation efficiency, and emergency response ability of the smart park under extreme weather conditions, while reducing energy costs and operation risks.

[0061] These aspects or other aspects of the present invention will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0063] Figure 1 It is a flowchart of an energy management and control method for a smart park provided by an embodiment of the present invention;

[0064] Figure 2 It is a schematic structural diagram of an energy management and control system for a smart park provided by an embodiment of the present invention;

[0065] Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of the present invention. Detailed implementation manners

[0066] In order to enable those skilled in the art of the present technology to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0067] In some processes described in the specification and claims of the present invention and the above-mentioned accompanying drawings, a plurality of operations that appear in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent the sequence, and do not limit that "first" and "second" are different types.

[0068] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0069] Figure 1 A flowchart of an energy management and control method for an intelligent park provided for an embodiment of the present invention is as Figure 1 shown, and the method includes:

[0070] Step 101: According to the received multi-source heterogeneous extreme weather warning information, combine with the geographic information system to analyze the relationship between the coverage range of each multi-source heterogeneous extreme weather warning information and the geographical location of the intelligent park, and evaluate the influence level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the intelligent park;

[0071] In this step, the multi-source heterogeneous extreme weather warning information includes data from multiple sources such as weather stations, satellite remote sensing, and the Internet. These data cover parameters such as temperature, precipitation, and wind speed, and are used to evaluate the impact of extreme weather on the intelligent park. The geographic information system (GIS) is a technology that combines geographic spatial data with attribute data and is used to analyze the relationship between geographical locations;

[0072] In step 101, first, the data integration platform is used to integrate and process the multi-source heterogeneous extreme weather warning information received, forming an extreme weather warning database in a unified format. Then, using GIS technology, the relationship between the geographical location of the intelligent park and the coverage range of each extreme weather warning is compared to evaluate the specific impact level of each extreme weather warning on different functional areas and energy consumption nodes within the intelligent park. This process not only considers the weather type and intensity but also combines historical data analysis tools to review the performance patterns in previous similar events to more accurately predict potential impacts;

[0073] Suppose an intelligent park receives a heavy rain warning message. Through GIS analysis, it is found that some areas of the park are located within the high-risk zone. According to historical data analysis, in previous similar heavy rain events, some key facilities were severely damaged. Therefore, key energy consumption nodes within these areas are focused on, and their impact level is set to a high level.

[0074] Step 102: For the key energy consumption nodes whose impact level by extreme weather is greater than the preset value, use the distributed reinforcement learning algorithm to adaptively adjust the preset energy supply strategy, and simulate and predict the changes in the operating state of the key energy consumption nodes and the mutual influence of the changes in the operating state under different energy supply strategies to select the best comprehensive adjustment plan;

[0075] In this step, the distributed reinforcement learning algorithm is a machine learning method that can work collaboratively without sharing data and is used to adaptively adjust the preset energy supply strategy. The comprehensive adjustment plan refers to the best energy management strategy for coping with extreme weather selected based on the simulation results;

[0076] In step 102, for the key energy consumption nodes marked with a high impact level, the distributed reinforcement learning algorithm is used to optimize their energy supply strategy. By simulating the changes in the operating state under different strategies and their mutual influence, the best comprehensive adjustment plan is identified. This process not only improves the efficiency of individual nodes but also enhances the stability and response speed of the entire system;

[0077] Continuing with the previous example, after determining the high-risk zone, the distributed reinforcement learning algorithm is used to adjust the energy supply strategy of those key facilities, such as increasing the supply of backup power or optimizing the load distribution. After multiple simulation tests, the best plan that can ensure the safety of the facilities and minimize energy consumption is finally selected.

[0078] Step 103: Based on the comprehensive adjustment plan, as well as the uncertainty factors brought by extreme weather and the impact on energy price fluctuations, construct a multi-level real-time optimization model. Automatically switch different optimization levels for the multi-level real-time optimization model according to the changes in the internal and external environment of the smart park, and conduct intelligent scheduling and cost control processing from the microscopic single key energy consumption node to the macroscopic entire smart park level to generate an optimized energy distribution plan;

[0079] In this step, the multi-level real-time optimization model is a dynamic system that can automatically adjust the optimization level according to the changes in the internal and external environment, and achieve intelligent scheduling and cost control from the microscopic to the macroscopic level. This model integrates short-term prediction and long-term planning to ensure the effective allocation of resources;

[0080] Step 103 is based on the best comprehensive adjustment plan obtained in the previous step, combined with the uncertainty factors brought by extreme weather and energy price fluctuations, to establish a multi-level real-time optimization model. This model can automatically switch different optimization levels according to the changes in the internal and external environment of the smart park, conduct intelligent scheduling and cost control from the microscopic single node to the macroscopic entire park level, and generate an optimized energy distribution plan;

[0081] Based on the best plan selected in the previous stage, further construct a multi-level real-time optimization model. Considering the weather forecast and market price fluctuations in the next few days, a detailed energy distribution plan is formulated. This includes how to reasonably arrange the energy supply of each key node and how to quickly respond in case of emergencies.

[0082] Step 104: According to the optimized energy distribution plan, instantaneously regulate and control the energy distribution in the smart park through Internet of Things devices, and use drone and robot technologies to inspect key facilities, collect on-site feedback data, and optimize the multi-level real-time optimization model in real time to obtain an energy management and control mechanism for the smart park;

[0083] In this step, Internet of Things devices refer to various sensors and controllers used to monitor and control energy distribution; drone and robot technologies are used for remote monitoring and maintenance of facilities. On-site feedback data is information collected from the actual operation environment and is used to optimize the energy management system in real time;

[0084] In Step 104, according to the optimized energy distribution plan, instantaneously regulate the energy distribution in the smart park through Internet of Things devices, and use drone and robot technologies to inspect key facilities and collect on-site feedback data. These data are used to optimize the multi-level real-time optimization model in real time, thus forming a closed-loop feedback system to continuously improve the energy management mechanism;

[0085] During the execution of the optimized energy distribution plan, the IoT devices regulate the energy supply of each node according to the plan, while the drones and robots regularly inspect the facility status. When an abnormality is detected in a certain area, the energy distribution strategy of the relevant nodes is immediately adjusted to ensure the safe and stable operation of the entire park.

[0086] Through the above four steps, a complete process is achieved, from the reception and analysis of extreme weather warning information, to the targeted adjustment of the energy supply strategy, to the construction of a multi-level real-time optimization model, and finally to the real-time regulation and feedback optimization through IoT devices and drone / robot technology. This method not only improves the emergency response ability of the smart park in the face of extreme weather, but also ensures the efficiency and safety of energy use, promoting the intelligent upgrade of energy management and operation in the park. Each step is closely linked, forming a continuous and efficient energy control mechanism.

[0087] To address the challenges posed by extreme weather to the key energy consumption nodes in the smart park and further improve the stability and energy efficiency performance of these nodes under extreme conditions, in some embodiments, according to what is described in step 102, for the key energy consumption nodes whose level of influence by extreme weather is greater than a preset value, the preset energy supply strategy is adaptively adjusted using a distributed reinforcement learning algorithm, and the changes in the operating states of the key energy consumption nodes and the mutual influence of the changes in the operating states under different energy supply strategies are simulated and predicted to select the best comprehensive adjustment plan, specifically including:

[0088] Using a data integration platform, analyze the energy consumption patterns, environmental parameters, and operating modes of key energy consumption nodes under current and historical extreme weather conditions to obtain a dynamically updated basic database; define the state space, action space, reward function, and constraint conditions for each key energy consumption node based on the dynamically updated basic database to generate a definition result, and configure each key energy consumption node based on the definition result; based on the defined state space, action space, reward function, and constraint conditions, use an enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism to independently train each key energy consumption node and share the learning results while protecting data privacy to generate an initial energy supply strategy; perform multi-round and multi-level simulation test processing on the initial energy supply strategy in a simulation environment. In each round, based on different extreme weather scenario assumptions and combined with actual market information, simulate and predict the changes in the operating states of each key energy consumption node and the complex interaction effects among the key energy consumption nodes to generate a series of initial adjustment plans; introduce an evaluation framework to comprehensively evaluate the system performance after each initial adjustment plan is executed to generate an effectiveness evaluation result for each initial adjustment plan; combine the preset overall goals of the intelligent park and the requirements for emergency response capabilities in extreme situations, and select the best comprehensive adjustment plan based on the effectiveness evaluation results of each initial adjustment plan;

[0089] The data integration platform refers to a data platform that integrates data from multiple sources such as weather stations, historical energy consumption records, and real-time sensor feedback, and is used to analyze the energy consumption patterns, environmental parameters, and operating modes of key energy consumption nodes under various extreme weather conditions. It provides a dynamically updated basic database; the state space, action space, reward function, and constraint conditions refer to the core elements that define the behavior of each key energy consumption node. The state space describes the various states that a node may be in; the action space lists all possible actions that can be taken; the reward function evaluates the quality of each action; the constraint conditions ensure that all actions comply with safety standards and operating rules; the enhanced distributed reinforcement learning algorithm combined with the federated learning mechanism refers to an advanced machine learning technology that can enhance the synergy of the entire system by sharing partial learning results while protecting the data privacy of each node;

[0090] In the embodiments of the present application, first, a data integration platform is used to deeply analyze key energy consumption nodes to obtain a dynamically updated basic database. Then, based on this database, the state space, action space, reward function, and constraint conditions of each node are defined, thereby generating a configuration result. Subsequently, an enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism is adopted to independently train each key node and share the learning results to form a preliminary energy supply strategy. Then, these strategies are subjected to multi-round and multi-level simulation tests in a simulation environment. In each round, based on different extreme weather scenario assumptions and actual market information, the changes in the operating states of each node and their interactive effects are simulated and predicted to generate a series of initial adjustment plans. Finally, an evaluation framework is introduced to comprehensively evaluate each plan, and the best comprehensive adjustment plan is selected based on the overall goals of the intelligent park and the requirements for emergency response capabilities;

[0091] For example, in a certain intelligent park, considering the upcoming strong storm warning, the data integration platform analyzed the performance of each key energy consumption node in past similar events to form a basic database. Based on this database, the state space of each node (such as the current load level), action space (such as reducing the load or switching to a backup power supply), reward function (such as reducing energy consumption costs), and constraint conditions (such as not exceeding the maximum load) were defined. An enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism was used to optimize and train the key nodes to generate a preliminary energy supply strategy. Next, in a high-fidelity simulation environment, these strategies were subjected to multiple simulation tests, considering different intensities of storm scenarios and their impact on energy prices. After analyzing the effects of each plan through the evaluation framework, an optimal comprehensive adjustment plan that can not only ensure the safety of the nodes but also minimize the operating costs was finally selected. This not only improves the ability to respond to extreme weather but also ensures the efficiency and safety of energy use within the park.

[0092] To address the impact of extreme weather on the key energy consumption nodes of an intelligent park and further improve the operating stability and energy efficiency performance of these nodes under various extreme conditions, as described in the previous embodiment, the initial energy supply strategy is subjected to multi-round and multi-level simulation test processing in a simulation environment. In each round, based on different extreme weather scenario assumptions, combined with actual market information, the changes in the operating states of each key energy consumption node and the complex interactive effects among the key energy consumption nodes are simulated and predicted to generate a series of initial adjustment plans, specifically including:

[0093] Use the simulation environment construction module to build a virtual intelligent park model based on the dynamically updated basic database and definition results; according to different types of extreme weather scenarios encountered by the intelligent park, combined with extreme weather cases in historical data and meteorological forecast information, set multiple hypothetical conditions for each extreme weather scenario to generate a set of extreme weather scenario hypotheses; based on the set of extreme weather scenario hypotheses and the actual market information obtained in real time, conduct multiple rounds of simulation tests on the initial energy supply strategy. In each round, for each extreme weather scenario hypothesis, use the virtual intelligent park model to simulate and predict the changes in the operating states of each key energy consumption node, analyze how the changes in the operating states affect the operation modes and energy efficiency performances of other nodes, and during the simulation process, collect the complex interaction effects between different key energy consumption nodes, identify potential risk points and optimization opportunities to generate simulation results; according to each simulation result, record and quantify the performance indicators of each key energy consumption node under different extreme weather scenarios, evaluate the effectiveness of the initial energy supply strategy under each simulation condition, and obtain the total sum of multiple simulation initial results; based on the total sum of multiple simulation initial results, comprehensively evaluate the performances of each key energy consumption node under various extreme weather scenarios to generate a series of initial adjustment plans for specific extreme weather scenarios.

[0094] In this embodiment, the simulation environment construction module refers to a tool for building a virtual intelligent park model. It provides a high-fidelity simulation platform based on the dynamically updated basic database and definition results (such as state space, action space, etc.); the set of extreme weather scenario hypotheses refers to a set composed of different types of extreme weather scenarios, and each scenario contains multiple hypothetical conditions (such as intensity, duration, etc.), and these scenarios are generated based on extreme weather cases in historical data and the latest meteorological forecast information; the performance indicators refer to the parameter values that quantify the performances of each key energy consumption node under different extreme weather scenarios, such as total energy consumption, operating cost, emergency response efficiency, etc. These indicators are used to evaluate the effectiveness of the initial energy supply strategy under each simulation condition.

[0095] In the embodiments of the present application, first, a high-fidelity virtual intelligent park model is constructed by using a simulation environment building module based on a dynamically updated basic database and definition results. Then, according to different types of extreme weather scenarios that the intelligent park may encounter (such as heavy rain, heavy snow, strong wind, etc.), combined with historical extreme weather cases in historical data and meteorological forecast information, a variety of hypothetical conditions are set to form a set of extreme weather scenario hypotheses. Next, based on this set of hypotheses and the actual market information obtained in real time (such as energy price fluctuations, policy changes, etc.), multiple rounds of simulation tests are carried out on the initial energy supply strategy. In each round, for each extreme weather scenario hypothesis, the virtual intelligent park model is used to simulate and predict the changes in the operating states of key energy consumption nodes, and analyze how these changes affect the operation modes and energy efficiency performances of other nodes. Through this process, potential risk points and optimization opportunities are identified, and detailed simulation results are generated. Finally, according to the results of each simulation, the performance indicators of key energy consumption nodes under different extreme weather scenarios are recorded and quantified, and the effects of the initial energy supply strategy under each simulation condition are comprehensively evaluated to generate a series of initial adjustment plans for specific extreme weather scenarios;

[0096] For example, in a certain intelligent park, considering the upcoming winter snowstorm warning, a virtual intelligent park model was first constructed using a simulation environment building module, which was based on historical data of past similar snowstorm events and current meteorological forecast information. Next, multiple extreme weather scenario hypotheses were set, including different intensities (light, moderate, heavy) and durations (short-term, long-term) of the snowstorm. Based on these hypothetical conditions and the real-time obtained energy market price fluctuation information, multiple simulation tests were carried out on the preliminarily formulated energy supply strategy. In one simulation, assuming a large snowstorm intensity and a long duration, it was found that some key facilities faced the risk of power outage due to overloading. By adjusting the standby power usage strategy of these facilities and optimizing the load distribution plan, the power outage risk was significantly reduced. After each simulation, the performance indicators such as the energy consumption level and operation cost of each node were recorded and comprehensively evaluated. Finally, an optimal adjustment plan that could ensure the safety of the park and minimize the operation cost was selected. This not only improved the ability to cope with extreme weather but also ensured the efficiency and safety of energy use within the park. In this way, an effective transformation from theory to practice was achieved, enhancing the disaster resistance ability and energy management efficiency of the entire intelligent park.

[0097] To address the complex challenges posed by extreme weather to smart campuses and further improve the flexibility and efficiency of energy distribution, as another embodiment, according to step 103, based on the comprehensive adjustment plan, the uncertainty factors brought by extreme weather, and the impact on energy price fluctuations, a multi-level real-time optimization model is constructed. The multi-level real-time optimization model automatically switches different optimization levels according to the changes in the internal and external environments of the smart campus, and conducts intelligent scheduling and cost control processing from the micro level of individual key energy consumption nodes to the macro level of the entire smart campus, generating an optimized energy distribution plan, specifically including:

[0098] Based on the comprehensive adjustment plan, combined with the uncertainty factors of extreme weather and the impact of extreme weather on energy price fluctuations, a multi-level real-time optimization model integrating predictive analysis and real-time feedback mechanism is constructed; using the multi-level real-time optimization model, micro-level optimization processing is carried out on each key energy consumption node, the energy consumption patterns of each node are monitored in real time using a high-precision sensor network, the energy consumption trends are predicted through machine learning algorithms, and personalized energy supply strategies are formulated for potential risks under different extreme weather scenarios to obtain the micro-level optimization results; according to the real-time changes in the internal and external environments of the smart campus, the different optimization levels of the multi-level real-time optimization model are automatically adjusted and switched using an adaptive algorithm. At the meso level, distributed collaborative optimization technology is adopted to analyze the energy flow and interaction between subsystems, identify key paths and bottleneck points, and optimize the operation efficiency of the subsystems to obtain the meso-level optimization results, where the subsystem is a system composed of multiple related nodes; at the macro level, the preliminary optimization results at the micro level and the optimization results at the meso level are integrated, and an advanced economic model and a social responsibility assessment framework are introduced to comprehensively optimize the overall energy management strategy of the entire smart campus to generate the macro-level optimization results; a secure transaction record system based on blockchain technology is constructed, and the secure transaction record system is used to track and verify the actual implementation of all energy transactions and regulation measures to generate secure transaction records; combining the micro-level optimization results, the meso-level optimization results, the macro-level optimization results, and the secure transaction records, an optimized energy distribution plan is generated;

[0099] In this embodiment, the multi-level real-time optimization model refers to a dynamic system that can automatically adjust the optimization level according to the changes in the internal and external environments of the smart park. This model integrates short-term prediction and long-term planning functions, covering different levels from the micro single node to the macro entire park; the high-precision sensor network refers to a network used to monitor the energy consumption patterns of each key energy consumption node in real time. These sensors can accurately collect data such as current, voltage, temperature, etc., for machine learning algorithms to predict future energy consumption trends; the distributed collaborative optimization technology refers to a technology for optimizing between subsystems composed of multiple related nodes, identifying critical paths and bottleneck points by analyzing energy flow and interactions to improve the overall operating efficiency; the advanced economic model and social responsibility assessment framework refer to a set of tools for comprehensively evaluating the overall energy management strategy of the smart park, considering not only economic benefits but also social responsibility indicators such as carbon emissions and social impact assessment;

[0100] In the embodiment of the present application, first, based on the comprehensive adjustment plan, combined with the uncertainty factors of extreme weather and the impact of extreme weather on energy price fluctuations, a multi-level real-time optimization model integrating prediction analysis and real-time feedback mechanism is constructed. Then, this model is used to perform micro-level optimization processing on each key energy consumption node, monitor the energy consumption patterns of each node in real time through a high-precision sensor network, and use machine learning algorithms to predict energy consumption trends. Personalized energy supply strategies are formulated for potential risks under different extreme weather scenarios to obtain preliminary optimization results at the micro level. Then, according to the real-time changes in the internal and external environments of the smart park, an adaptive algorithm is used to automatically adjust and switch different optimization levels of the multi-level real-time optimization model. At the meso level, the distributed collaborative optimization technology is adopted to analyze the energy flow and interactions between subsystems composed of multiple related nodes, identify critical paths and bottleneck points, and optimize the operating efficiency of the subsystems to obtain optimization results at the meso level. Next, at the macro level, all optimization results at the micro and meso levels are integrated, and an advanced economic model and social responsibility assessment framework are introduced for comprehensive optimization processing to ensure both high efficiency and sustainability, generating final optimization results at the macro level. In addition, a secure transaction record system based on blockchain technology is constructed to track and verify the actual implementation of all energy transactions and control measures, enhancing transparency and trust. Finally, combining the optimization results at the micro, meso, and macro levels and the secure transaction records, a highly customized and flexible adjustable optimized energy distribution plan is generated;

[0101] For example, when a certain intelligent park faces an upcoming rainstorm warning, a multi-level real-time optimization model is first constructed based on a comprehensive adjustment plan. This model takes into account the uncertainty of extreme weather and the fluctuations in energy market prices. Using a high-precision sensor network, the energy consumption patterns of each key energy consumption node (such as data centers, manufacturing workshops, etc.) are monitored in real time, and the energy consumption trends in the next few hours are predicted through machine learning algorithms. In response to the flood risk that may be caused by the rainstorm, personalized energy supply strategies are formulated, such as increasing the supply of backup power or reducing the power load in non-critical areas. As the intensity and duration of the rainstorm change, the adaptive algorithm automatically adjusts the different optimization levels of the multi-level real-time optimization model. At the meso level, distributed collaborative optimization is carried out on the subsystems composed of multiple related nodes, identifying certain key paths and bottleneck points (such as the overload risk of the power distribution system), and taking measures to optimize their operating efficiency. At the macro level, the optimization results at all micro and meso levels are integrated, and advanced economic models and social responsibility assessment frameworks are introduced to comprehensively evaluate the energy management strategy of the entire park, ensuring both high efficiency and compliance with social responsibility standards. At the same time, a secure transaction recording system based on blockchain technology records the actual implementation of all energy transactions and regulatory measures, enhancing transparency and trust. Finally, a detailed optimized energy distribution plan is generated, which not only ensures the safe and stable operation of the park during the rainstorm but also minimizes the operating costs. In this way, comprehensive coverage from micro to macro is achieved, enhancing the ability of the entire intelligent park to respond to extreme weather and the efficiency of energy management.

[0102] To address the complex challenges brought by extreme weather to the energy flow and interaction among the subsystems of an intelligent park, and to further improve the operating efficiency of each subsystem and the overall energy efficiency performance, as described in the previous embodiment, according to the real-time changes in the internal and external environment of the intelligent park, the adaptive algorithm is used to automatically adjust and switch the different optimization levels of the multi-level real-time optimization model. At the meso level, distributed collaborative optimization technology is adopted to analyze the energy flow and interaction among the subsystems, identify the key paths and bottleneck points, and use them to optimize the operating efficiency of the subsystems to obtain the meso-level optimization results. Among them, the subsystem is a system composed of multiple related nodes, specifically including:

[0103] Utilize an intelligent sensor network and external data sources to monitor and process the real-time changes in the internal and external environments of the smart campus in real time, obtaining real-time environmental status data; apply an adaptive algorithm to dynamically adjust and switch different optimization levels of the multi-level real-time optimization model, select the optimal optimization level based on the changes in the real-time environmental status data, and accordingly adjust the parameters of the multi-level real-time optimization model to obtain a multi-level real-time optimization model with adjusted optimization levels; at the meso level, for a subsystem composed of multiple related key energy consumption nodes, adopt distributed collaborative optimization technology, use the multi-level real-time optimization model with adjusted optimization levels to deeply analyze the energy flow and interaction between the subsystems, establish an energy flow model between the subsystems, simulate the operating states of each subsystem and the mutual influence of each subsystem under different extreme weather scenarios, identify the key paths and bottleneck points that lead to the reduction of overall energy efficiency, and obtain the identification results of key paths and bottleneck points; based on the identification results of key paths and bottleneck points, optimize the operating strategies of each subsystem, adjust the energy input-output ratio of key energy consumption nodes to obtain optimized subsystem operating strategies; according to the optimized subsystem operating strategies, use a simulation tool to conduct multiple rounds of simulation tests on the subsystems. In each round of testing, evaluate the performance indicators of the subsystems based on different assumed scenarios, adjust the preset optimization measures, obtain the verification results of the optimization measures, and combine the verification results of the optimization measures of all subsystems.

[0104] In this embodiment, the intelligent sensor network and external data sources include high-precision sensors, weather stations, energy market price information, etc. distributed in various corners of the smart campus. These data are collected and processed in real time for monitoring the changes in the internal and external environments of the smart campus. The adaptive algorithm is a technology that can dynamically adjust the parameters of the multi-level real-time optimization model according to the real-time environmental status data, ensuring that the model always remains consistent with the actual situation. The distributed collaborative optimization technology is a technology for optimizing between subsystems composed of multiple related key energy consumption nodes, identifying key paths and bottleneck points by analyzing energy flow and interaction.

[0105] In the embodiments of the present application, first, a smart sensor network and external data sources are used to continuously monitor and process the real-time changes in the internal and external environments of the smart park, so as to obtain the latest environmental status data. Next, an adaptive algorithm is applied to dynamically adjust and switch different optimization levels of the multi-level real-time optimization model. Based on the changes in the real-time environmental status data, the best optimization level is selected, and the model parameters are adjusted accordingly to obtain the multi-level real-time optimization model after the optimization level adjustment. At the mesoscopic level, for a subsystem composed of multiple related key energy consumption nodes, a distributed collaborative optimization technology is adopted, and the multi-level real-time optimization model after the optimization level adjustment is used to deeply analyze the energy flow and interaction between subsystems. By establishing an energy flow model between subsystems, the operating states of each subsystem and their mutual influences under different extreme weather scenarios are simulated, the key paths and bottleneck points leading to the reduction of the overall energy efficiency are identified, and the identification results of the key paths and bottleneck points are obtained. Based on this identification result, the operating strategies of each subsystem are optimized, and the energy input-output ratio of the key energy consumption nodes is adjusted to improve the operating efficiency of the subsystem, and the optimized operating strategy of the subsystem is obtained. Finally, a simulation tool is used to perform multiple rounds of simulation tests on the optimized subsystem. In each round of tests, the performance indicators of the subsystem are evaluated based on different hypothetical scenarios, and the preset optimization measures are adjusted to obtain the verification results of the optimization measures. Combining the verification results of the optimization measures of all subsystems, the final mesoscopic level optimization result is generated.

[0106] For example, when a smart park faces an upcoming severe storm warning, it first uses the smart sensor network throughout the park and external data sources (such as weather stations and energy market price information) to continuously monitor the real-time changes in the internal and external environment of the park and obtain the latest environmental status data. Subsequently, the adaptive algorithm is used to dynamically adjust the multi-level real-time optimization model, select the optimization level that best suits the current conditions, and adjust the model parameters accordingly. At the meso-level, for subsystems composed of multiple related key energy consumption nodes such as data centers and manufacturing workshops, distributed collaborative optimization technology is used to establish an energy flow model between subsystems, simulate the operating status and mutual influence of each subsystem under storm scenarios of different intensities, and identify the key paths and bottlenecks that may lead to overall energy efficiency reduction. Based on the identification results, the operating strategies of each subsystem are optimized, such as adjusting the energy input and output ratio of certain nodes or replanning the backup power use plan. In order to verify the effectiveness of these optimization measures, the optimized subsystems are simulated multiple times using simulation tools. In each round of testing, the performance indicators of the subsystems are evaluated based on different hypothetical scenarios (such as changes in storm intensity, fluctuations in energy market prices, etc.), and the optimization measures are fine-tuned as necessary. Finally, by combining the optimization measures of all subsystems and verifying the results, a detailed meso-level optimization plan was generated, which not only improved the ability to cope with extreme weather, but also ensured the efficiency and safety of energy use in the park. In this way, comprehensive coverage from micro to macro was achieved, improving the disaster resistance and energy management efficiency of the entire smart park.

[0107] In order to solve the potential risks brought by extreme weather to the smart park and further improve the ability to identify and respond to these risks, as another embodiment, according to step 101, based on the received multi-source heterogeneous extreme weather warning information, combined with the geographic information system, the relationship between the coverage of each multi-source heterogeneous extreme weather warning information and the geographical location of the smart park is analyzed, and the impact level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park are evaluated, specifically including:

[0108] Utilize a data integration platform to integrate and process multi-source heterogeneous extreme weather warning information received from multiple sources to form an extreme weather warning database in a unified format; according to the extreme weather warning database in the unified format, in combination with a geographic information system, perform spatial analysis processing on the coverage range of each extreme weather warning information, and compare the geographic coordinates of the extreme weather warning information with the geographic coordinates of the intelligent park to determine the spatial relationship between each extreme weather warning information and the intelligent park, obtaining the spatial coverage analysis result of the extreme weather warning information; based on the spatial coverage analysis result of the extreme weather warning information, use a historical data analysis tool to review and analyze the response patterns of different functional areas and energy consumption nodes in the intelligent park under extreme weather conditions, generating a preliminary impact assessment report; according to the preliminary impact assessment report, apply a preset impact level standard to classify each functional area and key energy consumption node in the intelligent park, determining the specific level of impact of each key energy consumption node by extreme weather, obtaining the impact level assessment result;

[0109] In this embodiment, the data integration platform is a system for integrating extreme weather warning information from multiple sources (such as weather stations, satellite remote sensing, the Internet, etc.), which converts this information into a database in a unified format for subsequent analysis. The geographic information system (GIS) is a technology for storing, analyzing, and displaying geographic data, through which the spatial relationship between the extreme weather warning information and the intelligent park can be accurately determined. The historical data analysis tool is used to review and analyze the response patterns in past similar extreme weather events to help generate a preliminary impact assessment report.

[0110] In the embodiment of this application, first, utilize a data integration platform to integrate and process multi-source heterogeneous extreme weather warning information received from multiple sources to form an extreme weather warning database in a unified format. Next, according to this database, in combination with a geographic information system, perform spatial analysis processing on the coverage range of each extreme weather warning information, and compare the geographic coordinates of the extreme weather warning information with the geographic coordinates of the intelligent park to determine the spatial relationship between each extreme weather warning information and the intelligent park, obtaining the spatial coverage analysis result of the extreme weather warning information. Based on this spatial coverage analysis result, use a historical data analysis tool to review and analyze the response patterns of different functional areas and energy consumption nodes in the intelligent park under extreme weather conditions, generating a preliminary impact assessment report. Finally, according to this preliminary impact assessment report, apply a preset impact level standard to classify each functional area and key energy consumption node in the intelligent park, determining the specific level of impact of each key energy consumption node by extreme weather, obtaining the final impact level assessment result.

[0111] For example, when a certain intelligent park faces an upcoming strong storm warning, it first uses a data integration platform to integrate extreme weather warning information from multiple sources such as weather stations, satellite remote sensing, and the Internet, forming an extreme weather warning database in a unified format. Then, it uses a geographic information system to conduct a detailed spatial analysis of the coverage area of each warning message, and precisely compares the geographic coordinates of these warning messages with the geographic coordinates of the intelligent park to determine which areas may be affected by the storm, obtaining the spatial coverage analysis results. Based on these analysis results, it uses a historical data analysis tool to review the performance of each functional area and key energy consumption nodes in past similar storm events, generating a preliminary impact assessment report. According to this report, it applies a preset impact level standard to classify key areas such as data centers and manufacturing workshops in the park, determining which nodes are in high-risk areas and need to take additional protective measures. For example, due to its high dependence on stable power supply, the data center is rated as a high-impact level, so a special emergency plan is formulated, including increasing the supply of backup power and optimizing the load distribution plan. In this way, not only the ability of the intelligent park to respond to extreme weather is improved, but also the safety and stability of key facilities in the park are ensured. This comprehensive risk assessment method provides a scientific basis for park managers and helps to formulate more effective prevention and mitigation measures.

[0112] In order to solve the problems of insufficient integration of distributed energy resources, lack of flexibility in electricity market trading strategies, and insufficient security of trading records in the existing technology, and to improve the efficiency and transparency of energy management in intelligent parks in the existing technology, in one embodiment, according to step 104, based on the energy control decision information, aggregate the distributed energy resources in the park, process the participation of the internal energy surplus of the intelligent park in electricity market trading, and use blockchain technology to record all transactions in the process of energy production and consumption to obtain transaction records, and perform secure storage processing on the transaction records to generate an energy trading ledger, specifically including:

[0113] Send control instructions using the optimized energy distribution plan to configure the initial energy supply strategies for each key energy consumption node in the smart park, and perform immediate regulation processing on the control instructions received by the Internet of Things devices, so that each key energy consumption node operates according to the optimized energy distribution plan to obtain an immediate regulation result; according to the immediate regulation result, start the inspection of key facilities in the smart park by drones and robotics technology for a preset period of time to generate an inspection report, where drones are used for aerial monitoring and coverage inspection, and robots are used for ground facilities and detection in complex environments to ensure the safety and normal operation status of all key facilities; during the inspection process, use high-precision sensors and cameras to comprehensively monitor the status of key facilities and collect on-site feedback data to generate on-site feedback data; transmit the on-site feedback data to the central control system in real time, and combine historical data and preset safety standards to comprehensively analyze and process the on-site feedback data, identify potential problems, and evaluate the impact degree of the potential problems on the optimized energy distribution plan to generate an analysis report; based on the analysis report, apply an adaptive algorithm to dynamically adjust the multi-level real-time optimization model, optimize the energy distribution and scheduling strategies at different levels, so that the multi-level real-time optimization model is consistent with the actual situation, and obtain a real-time updated enhanced multi-level real-time optimization model; according to the real-time updated enhanced multi-level real-time optimization model, adjust the optimized energy distribution plan again, and execute control instructions other than the existing control instructions through the Internet of Things devices again, and use drones and robots for inspection again to generate an energy management and control mechanism for the smart park;

[0114] In this embodiment, the Internet of Things devices include smart meters, sensor networks, and other devices for monitoring and controlling energy distribution, which can receive and execute control instructions from the central control system. Drones and robotics technology are used for aerial monitoring and ground detection respectively, where drones can cover large areas for rapid inspection, while robots are suitable for detailed detection tasks in complex environments. Devices such as high-precision sensors and cameras are used to monitor the status of key facilities in real time and collect detailed on-site feedback data.

[0115] In the embodiments of the present application, first, control instructions are sent using the optimized energy distribution plan to configure the initial energy supply strategies of each key energy consumption node in the smart park, and the received control instructions are immediately regulated through Internet of Things devices, enabling each key energy consumption node to operate according to the optimized energy distribution plan to obtain an immediate regulation result. Next, based on the immediate regulation result, drones and robotics technologies are activated to conduct inspections of the key facilities in the smart park for a preset period of time. The drones are mainly used for aerial monitoring and coverage inspection to ensure the safety of large areas; the robots focus on detailed inspections of ground facilities and in complex environments to ensure the safety and normal operating status of all key facilities, generating an inspection report. During the inspection process, high-precision sensors and cameras are used to comprehensively monitor the status of key facilities and collect on-site feedback data, generating on-site feedback data. Subsequently, this on-site feedback data is transmitted in real time to the central control system, and combined with historical data and preset safety standards, the data is comprehensively analyzed and processed to identify potential problems and evaluate the degree of impact of these problems on the optimized energy distribution plan, generating an analysis report. Based on the analysis report, an adaptive algorithm is applied to dynamically adjust the multi-level real-time optimization model, optimizing the energy distribution and scheduling strategies at different levels, so that the multi-level real-time optimization model is consistent with the actual situation, obtaining a real-time updated enhanced multi-level real-time optimization model. Finally, according to the real-time updated enhanced multi-level real-time optimization model, the optimized energy distribution plan is adjusted again, and new control instructions are executed through Internet of Things devices, while continuing to use drones and robots for inspections, forming a closed-loop feedback system to generate an energy management and control mechanism for the smart park.

[0116] For example, when a certain intelligent park faces an upcoming rainstorm warning, first, according to the optimized energy distribution plan, the Internet of Things devices are used to configure each key energy consumption node (such as data centers, manufacturing workshops, etc.) in the park to ensure that each node can operate according to the optimized plan, and immediate regulation results are obtained. Then, drones and robots are launched to conduct inspections on the key facilities in the park. The drones cover large areas of roofs and exterior walls for inspection, while the robots conduct detailed inspections in underground facilities and power distribution rooms, generating inspection reports. During the inspection process, high-precision sensors and cameras are used to comprehensively monitor the status of each key facility and collect detailed on-site feedback data. These data are transmitted to the central control system in real time and comprehensively analyzed in combination with historical data and preset safety standards to identify problems with water leakage risks in certain areas and evaluate their impact on the current energy distribution plan. Based on this analysis result, an adaptive algorithm is applied to dynamically adjust the multi-level real-time optimization model, optimizing the energy distribution and scheduling strategies to ensure that the model is consistent with the actual situation. Finally, according to the real-time updated optimization model, the energy distribution plan is adjusted again, and additional control instructions are executed through the Internet of Things devices, such as increasing the backup power supply for certain key facilities. At the same time, drones and robots are continuously used for regular inspections, forming a closed-loop feedback system to continuously optimize the energy management of the park and ensure that the intelligent park can achieve efficient, safe, and stable energy management under various extreme weather conditions. This closed-loop feedback mechanism not only improves the ability to respond to emergencies but also ensures the efficiency and safety of energy use in the park.

[0117] Figure 2 FIG. provides a schematic structural diagram of an energy management and control system for an intelligent park according to an embodiment of the present invention, as Figure 2 shown, the system includes:

[0118] A receiving module 21, configured to analyze the relationship between the coverage range of each multi-source heterogeneous extreme weather warning information and the geographical location of the intelligent park according to the received multi-source heterogeneous extreme weather warning information, and evaluate the impact level evaluation result of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the intelligent park;

[0119] A simulation module 22, configured to adaptively adjust a preset energy supply strategy for key energy consumption nodes whose influence level by extreme weather is greater than a preset value by using a distributed reinforcement learning algorithm, and simulate and predict the changes in the operating states of key energy consumption nodes under different energy supply strategies and the mutual influence of the changes in the operating states, so as to select an optimal comprehensive adjustment plan;

[0120] The building module 23 is used to construct a multi-level real-time optimization model based on the comprehensive adjustment plan, the uncertainty factors brought by extreme weather, and the impact on energy price fluctuations, automatically switch different optimization levels for the multi-level real-time optimization model according to the changes in the internal and external environments of the smart park, and perform intelligent scheduling and cost control processing from the micro-level of individual key energy consumption nodes to the macro-level of the entire smart park to generate an optimized energy distribution plan.

[0121] The regulation module 24 is used to perform immediate regulation processing on the energy distribution in the smart park through Internet of Things devices according to the optimized energy distribution plan, and use drones and robot technologies to inspect key facilities, collect on-site feedback data, and optimize the multi-level real-time optimization model in real time to obtain an energy management and control mechanism for the smart park.

[0122] Figure 2 The described energy management and control system for a smart park can execute Figure 1 The energy management and control method for a smart park described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated further. For the energy management and control system for a smart park in the above embodiment, the specific ways for each module and unit to perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0123] In a possible design, Figure 2 The energy management and control system for a smart park in the illustrated embodiment can be implemented as a computing device, as Figure 3 shown, and this computing device can include a storage component 31 and a processing component 32;

[0124] The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0125] The processing component 32 is used for: according to the received multi-source heterogeneous extreme weather warning information, combining with the geographic information system to analyze the relationship between the coverage range of each multi-source heterogeneous extreme weather warning information and the geographical location of the intelligent park, and evaluating the influence level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the intelligent park; for the key energy consumption nodes with the influence level of extreme weather greater than the preset value, using the distributed reinforcement learning algorithm to adaptively adjust the preset energy supply strategy, and simulating and predicting the changes in the operating states of the key energy consumption nodes and the mutual influence of the changes in the operating states under different energy supply strategies, so as to select the best comprehensive adjustment plan; based on the comprehensive adjustment plan and the uncertainty factors brought by extreme weather and the influence on energy price fluctuations, constructing a multi-level real-time optimization model, automatically switching different optimization levels for the multi-level real-time optimization model according to the changes in the internal and external environments of the intelligent park, and performing intelligent scheduling and cost control processing from the micro single key energy consumption node to the macro entire intelligent park level to generate an optimized energy distribution plan; according to the optimized energy distribution plan, immediately regulating and controlling the energy distribution in the intelligent park through Internet of Things devices, and using drone and robot technologies to inspect key facilities, collecting on-site feedback data to optimize the multi-level real-time optimization model in real time, so as to obtain the energy management and control mechanism of the intelligent park.

[0126] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0127] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0128] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0129] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0130] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0131] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device can refer to a cloud server. The above processing component, storage component, etc. can be basic server resources rented or purchased from a cloud computing platform.

[0132] An embodiment of the present invention also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 An energy management and control method for an intelligent park shown in the embodiment.

[0133] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0134] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0135] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An energy management and control method for a smart park, characterized in that: include: According to the received multi-source heterogeneous extreme weather warning information, the relationship between the coverage of each multi-source heterogeneous extreme weather warning information and the geographical location of the smart park is analyzed in combination with the geographic information system, and the impact level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park are evaluated; For key energy consumption nodes whose extreme weather impact level is greater than the preset value, the preset energy supply strategy is adaptively adjusted using the distributed reinforcement learning algorithm, and the operating state changes of key energy consumption nodes under different energy supply strategies and the impact of operating state changes on each other are simulated and predicted to select the best comprehensive adjustment plan; Based on the comprehensive adjustment plan and the uncertainty factors brought by extreme weather and the impact on energy price fluctuations, a multi-level real-time optimization model is constructed, and the multi-level real-time optimization model automatically switches different optimization levels according to changes in the internal and external environment of the smart park, and performs intelligent scheduling and cost control processing from the micro level of a single key energy consumption node to the macro level of the entire smart park, and generates an optimized energy allocation plan; According to the optimized energy distribution plan, the energy distribution in the smart park is immediately regulated and processed through the Internet of Things devices, and key facilities are inspected using drones and robot technologies. On-site feedback data is collected to optimize the multi-level real-time optimization model in real time, so as to obtain the energy management and control mechanism of the smart park.

2. The method according to claim 1, characterized in that For key energy consumption nodes whose extreme weather impact level is greater than the preset value, the distributed reinforcement learning algorithm is used to adaptively adjust the preset energy supply strategy, and simulate and predict the operating state changes of key energy consumption nodes under different energy supply strategies and the impact of operating state changes on each other, so as to select the best comprehensive adjustment plan, including: Using the data integration platform, analyze the energy consumption patterns, environmental parameters, and operation modes of key energy consumption nodes under current and historical extreme weather conditions to obtain a dynamically updated basic database; According to the dynamically updated basic database, define the state space, action space, reward function and constraint conditions of each key energy consumption node, generate definition results, and configure each key energy consumption node based on the definition results; Based on the defined state space, action space, reward function and constraints, an enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism is used to independently train each key energy consumption node and share the learning results while protecting data privacy, thereby generating an initial energy supply strategy. For the initial energy supply strategy, multiple rounds and multi-level simulation tests are carried out in the simulation environment. In each round, based on different extreme weather scenario assumptions and combined with actual market information, the operating status changes of key energy consumption nodes and the complex interactions between key energy consumption nodes are simulated and predicted to generate a series of initial adjustment plans. An evaluation framework is introduced to comprehensively evaluate the system performance after each initial adjustment plan is executed, and the effectiveness evaluation results of each initial adjustment plan are generated; In combination with the preset overall goals of the smart park and the requirements for emergency response capabilities in extreme situations, the best comprehensive adjustment plan is selected based on the effectiveness evaluation results of each initial adjustment plan.

3. The method according to claim 2, characterized in that For the initial energy supply strategy, multiple rounds and multi-level simulation tests are carried out in the simulation environment. In each round, based on different extreme weather scenario assumptions and combined with actual market information, the operating status changes of key energy consumption nodes and the complex interactive effects between key energy consumption nodes are simulated and predicted to generate the initial adjustment plan, including: Use the simulation environment to build modules and construct a virtual smart park model based on the dynamically updated basic database and definition results; According to the different types of extreme weather scenarios encountered by the smart park, combined with extreme weather cases in historical data and weather forecast information, multiple assumptions are set for each extreme weather scenario to generate an extreme weather scenario assumption set; Based on the extreme weather scenario assumptions and the actual market information obtained in real time, multiple rounds of simulation tests are conducted on the initial energy supply strategy. In each round, for each extreme weather scenario assumption, the virtual smart park model is used to simulate and predict the operating state changes of each key energy consumption node, and the operating state changes that affect the operation mode and energy efficiency performance of other nodes are analyzed. In the simulation process, the complex interactive effects between different key energy consumption nodes are collected, and potential risk points and optimization opportunities are identified to generate simulation results; Based on the results of each simulation, the performance indicators of each key energy consumption node under different extreme weather scenarios are recorded and quantified, the effect of the initial energy supply strategy under each simulation condition is evaluated, and the sum of the initial results of multiple simulations is obtained; Based on the summary of the initial results of the multiple simulations, the performance of key energy consumption nodes under various extreme weather scenarios is comprehensively evaluated to generate a series of initial adjustment plans for specific extreme weather scenarios.

4. The method according to claim 1, characterized in that: Based on the comprehensive adjustment plan and the uncertainty factors brought by extreme weather and the impact on energy price fluctuations, a multi-level real-time optimization model is constructed. The multi-level real-time optimization model automatically switches different optimization levels according to the changes in the internal and external environment of the smart park, and performs intelligent scheduling and cost control processing from the micro level of a single key energy consumption node to the macro level of the entire smart park, generating an optimized energy distribution plan, including: Based on the comprehensive adjustment plan, combined with the uncertainty factors of extreme weather and the impact of extreme weather on energy price fluctuations, a multi-level real-time optimization model integrating prediction analysis and real-time feedback mechanism is constructed; Using the multi-level real-time optimization model, each key energy consumption node is optimized at the micro level, the energy consumption pattern of each node is monitored in real time using a high-precision sensor network, energy consumption trends are predicted using a machine learning algorithm, and personalized energy supply strategies are formulated for potential risks under different extreme weather scenarios to obtain micro-level optimization results; According to the real-time changes of the internal and external environment of the smart park, the adaptive algorithm is used to automatically adjust and switch the different optimization levels of the multi-level real-time optimization model. At the meso-level, the distributed collaborative optimization technology is used to analyze the energy flow and interaction between subsystems, identify the key paths and bottlenecks, and optimize the operation efficiency of the subsystem to obtain the meso-level optimization results, wherein the subsystem is a subsystem composed of multiple related key energy consumption nodes; At the macro level, the preliminary optimization results at the micro level and the optimization results at the meso level are integrated, and the advanced economic model and social responsibility assessment framework are introduced to comprehensively optimize the overall energy management strategy of the entire smart park and generate macro-level optimization results; Constructing a secure transaction record system based on blockchain technology, using the secure transaction record system to track and verify the actual implementation of all energy transactions and regulatory measures, and generate secure transaction records; An optimized energy allocation plan is generated by combining the micro-level optimization results, the meso-level optimization results, the macro-level optimization results and the secure transaction records.

5. The method according to claim 4, characterized in that According to the real-time changes in the internal and external environment of the smart park, the adaptive algorithm is used to automatically adjust and switch the different optimization levels of the multi-level real-time optimization model. At the meso-level, the distributed collaborative optimization technology is used to analyze the energy flow and interaction between subsystems, identify the key paths and bottlenecks, and optimize the operating efficiency of the subsystems to obtain the meso-level optimization results. The subsystem is a system composed of multiple related nodes, including: Using smart sensor networks and external data sources, real-time changes in the internal and external environment of the smart park are monitored and processed to obtain real-time environmental status data; Applying an adaptive algorithm to dynamically adjust and switch different optimization levels of the multi-level real-time optimization model, selecting the best optimization level based on the change of the real-time environmental status data, and adjusting the parameters of the multi-level real-time optimization model accordingly, to obtain the multi-level real-time optimization model after the optimization level is adjusted; At the meso-level, for the subsystems, distributed collaborative optimization technology is adopted, and the multi-level real-time optimization model after the optimization level adjustment is used to conduct in-depth analysis on the energy flow and interaction between the subsystems. By establishing an energy flow model between subsystems, the operating status of each subsystem under different extreme weather scenarios and the mutual influence of each subsystem are simulated, and the key paths and bottleneck points that lead to the reduction of overall energy efficiency are identified, and the key path and bottleneck point identification results are obtained; Based on the critical path and bottleneck point identification results, the operation strategy of each subsystem is optimized, and the energy input-output ratio of the key energy consumption node is adjusted to obtain an optimized subsystem operation strategy; According to the optimized subsystem operation strategy, the subsystem is subjected to multiple rounds of simulation tests using simulation tools. In each round of testing, the subsystem's performance indicators are evaluated based on different hypothetical scenarios, and the preset optimization measures are adjusted to obtain the optimization measure verification results, which are then combined with the optimization measure verification results of all subsystems.

6. The method according to claim 1, characterized in that According to the received multi-source heterogeneous extreme weather warning information, the relationship between the coverage of each multi-source heterogeneous extreme weather warning information and the geographical location of the smart park is analyzed in combination with the geographic information system, and the impact level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park are evaluated, including: Use the data integration platform to integrate and process multi-source heterogeneous extreme weather warning information received from multiple sources to form an extreme weather warning database in a unified format; According to the extreme weather warning database in the unified format, in combination with the geographic information system, a spatial analysis is performed on the coverage of each extreme weather warning information, and the geographic coordinates of the extreme weather warning information are compared with the geographic coordinates of the smart park to determine the spatial relationship between each extreme weather warning information and the smart park, and obtain the spatial coverage analysis result of the extreme weather warning information; Based on the spatial coverage analysis results of the extreme weather warning information, historical data analysis tools are used to review and analyze the response patterns of different functional areas and energy consumption nodes in the smart park under extreme weather conditions to generate a preliminary impact assessment report; According to the preliminary impact assessment report, the preset impact level standards are applied to classify the functional areas and key energy consumption nodes in the smart park, determine the specific level of impact of extreme weather on each key energy consumption node, and obtain the impact level assessment results.

7. The method according to claim 1, characterized in that According to the optimized energy distribution plan, the energy distribution in the smart park is immediately regulated and processed through the Internet of Things devices, and key facilities are inspected using drones and robot technologies, and on-site feedback data is collected to optimize the multi-level real-time optimization model in real time, so as to obtain the energy management and control mechanism of the smart park, including: The optimized energy allocation plan is used to send control instructions to configure the initial energy supply strategy of each key energy consumption node in the smart park, and the received control instructions are immediately regulated and processed through the Internet of Things device, so that each key energy consumption node operates according to the optimized energy allocation plan and obtains an immediate regulation result; According to the instant control results, the drone and robot technologies are activated to inspect the key facilities of the smart park in a preset time period to generate an inspection report, wherein the drone is used for aerial monitoring and coverage inspection, and the robot is used for detection of ground facilities and complex environments; During the inspection process, high-precision sensors and cameras are used to comprehensively monitor the status of key facilities and collect on-site feedback data to generate on-site feedback data; The field feedback data is transmitted to the central control system in real time, and the field feedback data is comprehensively analyzed and processed in combination with historical data and preset safety standards to identify potential problems, and the impact of the potential problems on the optimized energy distribution plan is evaluated to generate an analysis report; Based on the analysis report, an adaptive algorithm is applied to dynamically adjust the multi-level real-time optimization model, and the energy allocation and scheduling strategies at different levels are optimized, so that the multi-level real-time optimization model is consistent with the actual situation, and a reinforced multi-level real-time optimization model is obtained that is updated in real time; According to the real-time updated enhanced multi-level real-time optimization model, the optimized energy distribution plan is adjusted again, and control instructions other than existing control instructions are executed again through the Internet of Things devices, and drones and robots are used again for inspections to generate an intelligent park energy management and control mechanism.

8. An energy management and control system for a smart park, characterized in that: include: A receiving module is used to analyze the relationship between the coverage of each multi-source heterogeneous extreme weather warning information and the geographical location of the smart park in combination with the geographic information system according to the received multi-source heterogeneous extreme weather warning information, and evaluate the impact level evaluation results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park; The simulation module is used to adaptively adjust the preset energy supply strategy using a distributed reinforcement learning algorithm for key energy consumption nodes whose extreme weather impact level is greater than the preset value, and simulate and predict the operating state changes of key energy consumption nodes under different energy supply strategies and the impact of operating state changes on each other, so as to select the best comprehensive adjustment plan; A construction module is used to construct a multi-level real-time optimization model based on the comprehensive adjustment plan and the uncertainty factors caused by extreme weather and the impact on energy price fluctuations, automatically switch different optimization levels of the multi-level real-time optimization model according to changes in the internal and external environment of the smart park, perform intelligent scheduling and cost control processing from the micro level of a single key energy consumption node to the macro level of the entire smart park, and generate an optimized energy allocation plan; The control module is used to perform real-time control and processing of energy distribution in the smart park through Internet of Things devices according to the optimized energy distribution plan, and use drones and robot technology to inspect key facilities, collect on-site feedback data, and optimize the multi-level real-time optimization model in real time to obtain the energy management and control mechanism of the smart park.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an energy management and control method for a smart park as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an energy management and control method for a smart park as described in any one of claims 1 to 7 is implemented.

Images