An energy management and control method and system for a smart park

Abstract

The application provides an energy management and control method and system for a smart park, wherein the application receives multi-source heterogeneous extreme weather warning information, analyzes the relationship between the coverage range and the geographical position of the smart park by combining a geographic information system, evaluates the influence of extreme weather on different functional areas and energy consumption nodes, adaptively adjusts the energy supply strategy by using a distributed reinforcement learning algorithm, selects the best comprehensive adjustment scheme, constructs a multi-level real-time optimization model based on the scheme, automatically switches the optimization level according to the changes in the internal and external environment, generates an optimized energy distribution plan, real-time regulates the energy distribution through Internet of Things devices, inspects key facilities by using unmanned aerial vehicles and robot technology, collects feedback data to continuously optimize the model, and forms an energy management and control mechanism for the smart park; the energy supply stability, operation efficiency and emergency response capability of the smart park under extreme weather conditions are improved, and the energy cost and operation risk are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart park, and in particular to an energy management method for smart park. BACKGROUND

[0002] With the rapid development of smart park, energy management has become a key link to ensure the efficient and stable operation of the park. A smart park usually contains various functional areas, such as office area, production area, living area, etc., each of which has different energy demand and consumption patterns. However, the frequent occurrence of extreme weather events poses a great challenge to the energy supply and consumption of the park. For example, heavy rain, typhoon, high temperature and other extreme weather may lead to a sharp increase in energy demand or a disruption in energy supply;

[0003] Currently, the energy management of smart park mainly adopts some advanced technical solutions, such as data-driven prediction models and centralized optimization algorithms. These solutions integrate historical energy consumption data, weather forecast information and park operation status, and use machine learning and optimization algorithms to generate energy distribution plans. However, these technologies still have obvious defects in 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 caused by extreme weather; while centralized optimization algorithms can perform energy scheduling at a macro level, but lack fine-grained control of key energy consumption nodes at a micro level, resulting in low energy distribution efficiency under extreme weather conditions;

[0004] In addition, existing solutions lack real-time and adaptability in dealing with extreme weather. For example, existing systems usually use fixed time interval data update and strategy adjustment mechanism, which cannot respond to rapid changes caused by extreme weather in real time. At the same time, these solutions lack deep fusion analysis of multi-source heterogeneous extreme weather warning information, making it difficult to fully evaluate the specific impact of extreme weather on different functional areas and energy consumption nodes of the park. SUMMARY

[0005] The present application provides an energy management method and system for smart park, which solves the problem that in the prior art, data-driven prediction models rely on historical data and are difficult to accurately predict sudden changes in energy demand caused by extreme weather, lack fine-grained control of key energy consumption nodes at a micro level, resulting in low energy distribution efficiency under extreme weather conditions, use fixed time interval data update and strategy adjustment mechanism, which cannot respond to rapid changes caused by extreme weather in real time, resulting in delay in fault discovery and processing under extreme weather conditions.

[0006] In a first aspect, the present application provides an energy management method for smart park, comprising:

[0007] 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 geographic location of the smart park is analyzed by combining a geographic information system, and the influence level evaluation result of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park is evaluated;

[0008] For the key energy consumption nodes affected by the extreme weather with an influence level greater than a preset value, a distributed reinforcement learning algorithm is used to adaptively adjust the preset energy supply strategy, and the running state changes of the key energy consumption nodes under different energy supply strategies and the mutual influences of the running state changes are simulated and predicted to select the best comprehensive adjustment scheme;

[0009] Based on the comprehensive adjustment scheme and the uncertainty factors and influences on energy price fluctuations caused by the extreme weather, a multi-level real-time optimization model is constructed, 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 intelligent scheduling and cost control processing are performed from a micro single key energy consumption node to a macro whole smart park level to generate an optimized energy distribution plan;

[0010] According to the optimized energy distribution plan, the energy distribution in the smart park is immediately regulated and controlled by Internet of Things devices, and unmanned aerial vehicles and robot technologies are used to patrol key facilities to collect on-site feedback data to optimize the multi-level real-time optimization model in real time to obtain a smart park energy management and control mechanism.

[0011] Optionally, for the key energy consumption nodes affected by the extreme weather with an influence level greater than a preset value, a distributed reinforcement learning algorithm is used to adaptively adjust the preset energy supply strategy, and the running state changes of the key energy consumption nodes under different energy supply strategies and the mutual influences of the running state changes are simulated and predicted to select the best comprehensive adjustment scheme, including:

[0012] Using a data integration platform, the energy consumption mode, environmental parameters and operation mode of the key energy consumption nodes under current and historical extreme weather conditions are analyzed to obtain a dynamically updated basic database;

[0013] According to the dynamically updated basic database, the state space, action space, reward function and constraint condition of each key energy consumption node are defined to generate a definition result, and each key energy consumption node is configured based on the definition result;

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

[0015] For the initial energy supply strategy, multiple rounds and multiple levels of simulation test processing are performed in the simulation environment. In each round, based on different extreme weather scenario assumptions, combined with actual market information, the running state changes of each key energy consumption node and the complex interaction between each key energy consumption node are simulated and predicted, and a series of initial adjustment schemes are generated;

[0016] An evaluation framework is introduced to comprehensively evaluate the system performance of each initial adjustment scheme after execution, and the effectiveness evaluation results of each initial adjustment scheme are generated;

[0017] Based on the effectiveness evaluation results of each initial adjustment scheme, the best comprehensive adjustment scheme is selected in combination with the overall target preset by the smart park and the requirement of emergency response capability under extreme conditions.

[0018] Optionally, for the initial energy supply strategy, multiple rounds and multiple levels of simulation test processing are performed in the simulation environment. In each round, based on different extreme weather scenario assumptions, combined with actual market information, the running state changes of each key energy consumption node and the complex interaction between each key energy consumption node are simulated and predicted, and a series of initial adjustment schemes are generated, including:

[0019] A simulation environment building module is used to construct a virtual smart park model based on a 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 weather forecast information, multiple assumption conditions are set for each extreme weather scenario to generate a set of extreme weather scenario assumption sets;

[0021] Based on the extreme weather scenario assumption set and the actual market information obtained in real time, the initial energy supply strategy is simulated and tested for multiple rounds. In each round, for each extreme weather scenario assumption, the virtual smart park model is used to simulate and predict the running state changes of each key energy consumption node, and analyze the influence of the running state changes on the operation mode and energy efficiency of other nodes. During the simulation process, the complex interaction between different key energy consumption nodes is collected to identify potential risk points and optimization opportunities, so as to generate simulation results;

[0022] According to each simulation result, 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 multiple simulation initial results are combined;

[0023] Based on the initial results of the multiple simulations, the performance of each key energy consumption node under various extreme weather scenarios is comprehensively evaluated, and a series of initial adjustment schemes for specific extreme weather scenarios are generated.

[0024] Optionally, based on the comprehensive adjustment scheme and the uncertainty factors and influence on energy price fluctuations caused by extreme weather, a multi-level real-time optimization model is constructed, which automatically switches different optimization levels of the multi-level real-time optimization model according to changes in the internal and external environment of the smart park, and performs intelligent scheduling and cost control processing from the micro single key energy consumption node to the macro whole smart park level, to generate an optimized energy distribution plan, including:

[0025] Based on the comprehensive adjustment scheme, combined with the uncertainty factors of extreme weather and the influence of extreme weather on energy price fluctuations, a multi-level real-time optimization model integrating prediction analysis and real-time feedback mechanism is constructed;

[0026] Using the multi-level real-time optimization model, each key energy consumption node is optimized at the micro level, high-precision sensor networks are used to monitor the energy consumption mode of each node in real time, machine learning algorithms are used to predict energy consumption trends, and personalized energy supply strategies are developed for potential risks under different extreme weather scenarios, to obtain micro-level optimization results;

[0027] According to the real-time changes of the internal and external environment of the smart park, the different optimization levels of the multi-level real-time optimization model are automatically adjusted and switched using adaptive algorithms, at the meso level, distributed collaborative optimization technology is used to analyze the energy flow and interaction between subsystems, identify key paths and bottlenecks, and optimize the operation efficiency of the subsystems to obtain meso-level optimization results, wherein the subsystems are systems composed of multiple related nodes;

[0028] At the macro level, the preliminary optimization results of the micro level and the optimization results of the meso level are integrated, and high-level economic models and social responsibility evaluation frameworks are introduced to comprehensively optimize the overall energy management strategy of the smart park, to generate macro-level optimization results;

[0029] A secure transaction record system based on blockchain technology is constructed, which is used to track and verify the actual implementation of all energy transactions and control measures, and to generate secure transaction records;

[0030] Combining the micro-level optimization results, meso-level optimization results, macro-level optimization results and secure transaction records, an optimized energy distribution plan is generated.

[0031] Optionally, 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 different optimization levels of the multi-level real-time optimization model. On the mesoscopic level, the distributed collaborative optimization technology is used to analyze the energy flow and interaction between subsystems, identify the key path and bottleneck point, and optimize the operation efficiency of the subsystems to obtain the mesoscopic level optimization result, wherein the subsystem is a system composed of multiple related nodes, including:

[0032] The real-time changes of the internal and external environment of the smart park are monitored and processed in real time by using intelligent sensor networks and external data sources to obtain real-time environmental state data.

[0033] The adaptive algorithm is applied to dynamically adjust and switch different optimization levels of the multi-level real-time optimization model. Based on the changes of the real-time environmental state data, the best optimization level is selected, and the parameters of the multi-level real-time optimization model are adjusted accordingly to obtain the multi-level real-time optimization model after optimization level adjustment.

[0034] On the mesoscopic level, for a subsystem composed of multiple related key energy consumption nodes, the distributed collaborative optimization technology is used to analyze the energy flow and interaction between the subsystems in depth by using the multi-level real-time optimization model after optimization level adjustment. By establishing an energy flow model between subsystems, the running state of each subsystem and the mutual influence of each subsystem under different extreme weather scenarios are simulated, the key path and bottleneck point leading to the overall energy efficiency reduction are identified, and the key path and bottleneck point identification result is obtained.

[0035] Based on the key path and bottleneck point identification result, the running strategy of each subsystem is optimized, and the energy input-output ratio of the key energy consumption node is adjusted to obtain the optimized subsystem running strategy.

[0036] According to the optimized subsystem running strategy, the subsystem is simulated and tested multiple times by using a simulation tool. In each round of testing, based on different hypothetical scenarios, the performance indicators of the subsystem are evaluated, and the preset optimization measures are adjusted to obtain the optimization measure verification result, and the optimization measure verification results of all subsystems are combined.

[0037] Optionally, 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 position of the smart park is analyzed by using a geographic information system to 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 smart park, including:

[0038] The multi-source heterogeneous extreme weather warning information received from multiple sources is integrated by using a data integration platform to form an extreme weather warning database in a unified format.

[0039] According to the unified format of the extreme weather warning database, combined with the geographic information system, the coverage of each extreme weather warning information is spatially analyzed and processed, and the geographic coordinates of the extreme weather warning information are compared with the geographic coordinates of the intelligent park to determine the spatial relationship between each extreme weather warning information and the intelligent park, and the spatial coverage analysis result of the extreme weather warning information is obtained;

[0040] Based on the spatial coverage analysis result of the extreme weather warning information, the response mode of different functional areas and energy consumption nodes in the intelligent park under extreme weather conditions is reviewed and analyzed by using a historical data analysis tool, and a preliminary impact assessment report is generated;

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

[0042] Optionally, according to the optimized energy distribution plan, the energy distribution in the intelligent park is instantaneously regulated and processed through Internet of Things devices, and unmanned aerial vehicles and robot technology are used to patrol the key facilities to collect on-site feedback data to optimize the multi-level real-time optimization model in real time, to obtain an intelligent park energy management and control mechanism, including:

[0043] The control instructions are sent by using the optimized energy distribution plan to configure the initial energy supply strategy of each key energy consumption node in the intelligent park, and the received control instructions are instantaneously regulated and processed through Internet of Things devices, so that each key energy consumption node operates according to the optimized energy distribution plan, and an instant regulation result is obtained;

[0044] According to the instant regulation result, the unmanned aerial vehicles and robot technology are started to patrol the key facilities of the intelligent park for a preset time period to generate a patrol report, wherein the unmanned aerial vehicles are used for air monitoring and coverage inspection, and the robots are used for ground facility detection and detection in complex environments to ensure the safety and normal operation state of all key facilities;

[0045] In the patrol process, high-precision sensors and cameras are used to comprehensively monitor the state of the key facilities and collect on-site feedback data to generate the on-site feedback data;

[0046] The on-site feedback data is transmitted to the central control system in real time, and the on-site feedback data is comprehensively analyzed and processed in combination with historical data and a preset safety standard to identify potential problems and evaluate the impact of the potential problems on the optimized energy distribution plan, and an analysis report is generated;

[0047] Based on the analysis report, an adaptive algorithm is applied to dynamically adjust the multi-level real-time optimization model, optimize the energy distribution and scheduling strategy of different levels, make the multi-level real-time optimization model consistent with the actual situation, and obtain a real-time updated reinforced multi-level real-time optimization model.

[0048] According to the real-time updated reinforced multi-level real-time optimization model, the optimized energy distribution plan is adjusted again, control instructions other than the existing control instructions are executed again through the Internet of Things device, and the unmanned aerial vehicle and the robot are used for inspection again to generate an intelligent park energy management and control mechanism.

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

[0050] The receiving module is configured to analyze the relationship between the coverage of the multi-source heterogeneous extreme weather warning information and the geographic location of the intelligent park according to the received multi-source heterogeneous extreme weather warning information combined with the 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] The simulation module is configured to adaptively adjust the preset energy supply strategy for the key energy consumption nodes affected by the extreme weather to a degree greater than a preset value by using a distributed reinforcement learning algorithm, and simulate and predict the running state changes of the key energy consumption nodes under different energy supply strategies and the mutual influence of the running state changes to select the best comprehensive adjustment scheme.

[0052] The construction module is configured to construct a multi-level real-time optimization model based on the comprehensive adjustment scheme and the uncertainty factors and the influence on energy price fluctuations caused by the extreme weather, automatically switch different optimization levels of the multi-level real-time optimization model according to the changes of the internal and external environment of the intelligent park, perform intelligent scheduling and cost control processing from the micro single key energy consumption node to the macro whole intelligent park level, and generate an optimized energy distribution plan.

[0053] The control module is configured to perform real-time control processing on the energy distribution in the intelligent park through the Internet of Things device according to the optimized energy distribution plan, and use unmanned aerial vehicles and robots to patrol 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 application provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the method of any one of the first aspect.

[0055] In a fourth aspect, the embodiments of the present application provide a computer storage medium, which stores computer program instructions, and the computer program instructions are executed by a processor to implement the method in any one of the first aspect.

[0056] In the embodiments of the present application, 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 geographic location of the smart park is analyzed by combining the geographic information system, the influence level evaluation result of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park is evaluated, for the key energy consumption nodes with an influence level greater than a preset value, the preset energy supply strategy is adaptively adjusted by using a distributed reinforcement learning algorithm, and the running state changes of the key energy consumption nodes under different energy supply strategies and the mutual influence of the running state changes are simulated and predicted, so as to select the best comprehensive adjustment scheme; based on the comprehensive adjustment scheme and the uncertainty factors and the influence on energy price fluctuations caused by the extreme weather, 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 of the internal and external environment of the smart park, intelligent scheduling and cost control processing are performed from the micro single key energy consumption node to the macro whole smart park level, and an optimized energy distribution plan is generated; according to the optimized energy distribution plan, the energy distribution in the smart park is instantaneously regulated and controlled by using the Internet of Things equipment, and the key facilities are inspected by using the unmanned aerial vehicle and robot technology, the multi-level real-time optimization model is optimized in real time by collecting the on-site feedback data, so as to obtain the energy management and control mechanism of the smart park.

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

[0058] By dynamically evaluating the influence of extreme weather, adaptively adjusting the energy supply strategy, constructing a multi-level optimization model, and real-time regulation and inspection, the efficiency, intelligence and refinement of the energy management of the smart park are realized. The beneficial effects include: improving the stability and reliability of energy supply under extreme weather, optimizing energy distribution efficiency, reducing operating costs, enhancing emergency response capability, and further improving the overall energy management and control level of the park through data-driven continuous optimization;

[0059] Further, by constructing a data integration platform, the energy consumption patterns, environmental parameters and operation modes of key energy consumption nodes under current and historical extreme weather conditions are analyzed in depth, forming 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 train each node independently and share 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, the initial strategy is tested in multiple rounds and multiple levels, predicting the changes in the operating state of each node and their mutual influence, generating a series of initial adjustment schemes. Finally, through an evaluation framework, the system performance of each scheme is comprehensively evaluated, and the best comprehensive adjustment scheme is selected in combination with the overall goals of the park and emergency response requirements;

[0060] In summary, through the dynamically updated basic database and the enhanced distributed reinforcement learning algorithm, fine modeling and strategy optimization of energy consumption nodes under extreme weather conditions are achieved. Combined with 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 testing and evaluation, the scheme can effectively predict the complex influence of extreme weather on each node and generate the optimal comprehensive adjustment scheme, significantly improving the energy supply stability, operating efficiency and emergency response capability of the smart park under extreme weather conditions, while reducing energy costs and operational risks.

[0061] These and other aspects of the application will become more apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0063] Figure 1 A flowchart of an energy management and control method for a smart park provided by an embodiment of the present application is shown in the figure.

[0064] Figure 2 A structural schematic diagram of an energy management and control system for a smart park provided by an embodiment of the present application is shown in the figure.

[0065] Figure 3 A structural schematic diagram of a computing device provided by an embodiment of the present application is shown in the figure. Detailed Implementation

[0066] To enable those skilled in the art to better understand 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.

[0067] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0068] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0069] Figure 1 A flowchart of an energy management method for smart parks, as provided in this embodiment of the invention, is shown below. Figure 1 As shown, the method includes:

[0070] Step 101: Based on the received multi-source heterogeneous extreme weather warning information, and combined with the geographic information system, analyze the relationship between the coverage of each multi-source heterogeneous extreme weather warning information and the geographical location of the smart park, and evaluate the impact level assessment results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes within the smart park.

[0071] In this step, the multi-source heterogeneous extreme weather early warning information includes data from various sources such as weather stations, satellite remote sensing, and the internet. This data covers parameters such as temperature, precipitation, and wind speed, and is used to assess the impact of extreme weather on the smart park. Geographic Information System (GIS) is a technology that combines geospatial data with attribute data to analyze relationships between geographical locations.

[0072] In step 101, the received multi-source heterogeneous extreme weather warning information is first integrated and processed through a data integration platform to form a unified-format extreme weather warning database. Then, using GIS technology, the relationship between the smart park's geographical location and the coverage area of ​​each extreme weather warning is compared to assess the specific impact level of each extreme weather warning on different functional areas and energy consumption nodes within the smart park. This process not only considers weather type and intensity but also incorporates historical data analysis tools to review patterns observed in similar past events, in order to more accurately predict potential impacts.

[0073] Suppose a smart park receives a rainstorm warning and, through GIS analysis, discovers that some areas of the park are located in a high-risk zone. Based on historical data analysis, previous similar rainstorm events caused severe damage to certain critical facilities. Therefore, key energy-consuming nodes in these areas are given special attention, and their impact level is set to high.

[0074] Step 102: For critical energy consumption nodes affected by extreme weather conditions at levels greater than the preset value, use a distributed reinforcement learning algorithm to adaptively adjust the preset energy supply strategy, and simulate and predict the changes in the operating status of critical energy consumption nodes under different energy supply strategies and the mutual influence of these changes, so as to select the best comprehensive adjustment scheme.

[0075] In this step, distributed reinforcement learning algorithms, a type of machine learning method, are used to adaptively adjust preset energy supply strategies without sharing data. The comprehensive adjustment scheme refers to the optimal energy management strategy for coping with extreme weather conditions, selected based on simulation results.

[0076] In step 102, a distributed reinforcement learning algorithm is used to optimize the energy supply strategy of critical energy-consuming nodes marked as high-impact nodes. By simulating the changes in operating states under different strategies and their mutual influences, the optimal comprehensive adjustment scheme 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 from the previous example, after identifying high-risk areas, distributed reinforcement learning algorithms were used to adjust the energy supply strategies for critical facilities, such as increasing backup power supply or optimizing load allocation. After multiple simulation tests, the optimal solution that ensured facility safety while minimizing energy consumption was finally selected.

[0078] Step 103: Based on the comprehensive adjustment scheme and the uncertainties brought about by extreme weather and their 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 changes in the internal and external environment of the smart park. Intelligent scheduling and cost control are carried out from the micro-level of a single key energy consumption node to the macro-level of the entire smart park, generating an optimized energy allocation 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 changes in the internal and external environment, achieving intelligent scheduling and cost control from the micro to the macro level. This model integrates short-term forecasting and long-term planning to ensure efficient resource allocation.

[0080] Step 103, based on the optimal comprehensive adjustment scheme obtained in the previous step, and taking into account the uncertainties brought about by extreme weather and energy price fluctuations, establishes a multi-level real-time optimization model. This model can automatically switch between different optimization levels according to changes in the internal and external environment of the smart park, performing intelligent scheduling and cost control from the micro-level of a single node to the macro-level of the entire park, and generating an optimized energy allocation plan;

[0081] Based on the optimal solution selected in the previous stage, a multi-level real-time optimization model was further constructed. Taking into account weather forecasts and market price fluctuations in the coming days, a detailed energy allocation plan was developed. This included how to rationally allocate energy supply to each key node and how to respond quickly in emergencies.

[0082] Step 104: Based on the optimized energy allocation plan, the energy allocation in the smart park is adjusted and processed in real time through IoT devices, and key facilities are inspected using drones and robotics. On-site feedback data is collected to optimize the multi-level real-time optimization model in real time, so as to obtain the smart park energy management and control mechanism.

[0083] In this step, IoT devices refer to various sensors and controllers used to monitor and control energy distribution; drones and robotics are used for remote monitoring and maintenance of facilities. Field feedback data is information collected from the actual operating environment and used to optimize the energy management system in real time.

[0084] In step 104, based on the optimized energy allocation plan, energy allocation within the smart park is adjusted in real time via IoT devices, and drones and robots are used to inspect key facilities and collect on-site feedback data. This data is used to optimize a multi-level real-time optimization model in real time, thereby forming a closed-loop feedback system to continuously improve the energy management mechanism.

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

[0086] Through the four steps described above, a complete process is achieved, from receiving and analyzing extreme weather warnings, to adjusting energy supply strategies accordingly, to building a multi-level real-time optimization model, and finally to real-time control and feedback optimization through IoT devices and drone / robot technology. This approach not only enhances the emergency response capabilities of smart parks in the face of extreme weather but also ensures the efficiency and safety of energy use, promoting the intelligent upgrading of energy management and operation within the park. Each step is closely linked, forming a continuous and efficient energy management mechanism.

[0087] To address the challenges posed by extreme weather to critical energy-consuming nodes in smart parks, and to further improve the stability and energy efficiency of these nodes under extreme conditions, some embodiments, as described in step 102, utilize a distributed reinforcement learning algorithm to adaptively adjust preset energy supply strategies for critical energy-consuming nodes affected by extreme weather exceeding a preset value. The embodiments also simulate and predict the changes in the operating states of critical energy-consuming nodes under different energy supply strategies and the mutual influence of these changes, in order to select the optimal comprehensive adjustment scheme. Specifically, this includes:

[0088] Using a data integration platform, the energy consumption patterns, environmental parameters, and operational modes of key energy-consuming nodes under current and historical extreme weather conditions are analyzed to obtain a dynamically updated basic database. Based on this dynamically updated basic database, the state space, action space, reward function, and constraints of each key energy-consuming node are defined, generating definition results. Based on these definition results, each key energy-consuming node is configured. 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-consuming node while sharing learning results to protect data privacy, generating an initial energy supply... The strategy involves conducting multiple rounds and levels of simulation testing 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, the operational status changes of each key energy consumption node and the complex interactions between these nodes are simulated and predicted, generating a series of initial adjustment schemes. An evaluation framework is introduced to comprehensively evaluate the system performance after each initial adjustment scheme is executed, generating an effectiveness evaluation result for each initial adjustment scheme. Combining the overall goals preset by the smart park and the requirements for emergency response capabilities under extreme conditions, the optimal comprehensive adjustment scheme is selected based on the effectiveness evaluation results of each initial adjustment scheme.

[0089] A data integration platform refers to a platform that integrates data from multiple sources, including weather stations, historical energy consumption records, and real-time sensor feedback, to analyze the energy consumption patterns, environmental parameters, and operational modes of key energy-consuming nodes under various extreme weather conditions. It provides a dynamically updated basic database. State space, action space, reward function, and constraints are the core elements defining the behavior of each key energy-consuming node. The state space describes the various states a node can be in; the action space lists all possible actions; the reward function evaluates the merits of each action; and the constraints ensure that all actions comply with safety standards and operational rules. An enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism refers to an advanced machine learning technique that can improve the overall system's synergy by sharing some learning results while protecting the data privacy of each node.

[0090] In this embodiment, a data integration platform is first used to conduct in-depth analysis of key energy consumption nodes, resulting in a dynamically updated basic database. Next, based on this database, the state space, action space, reward function, and constraints of each node are defined to generate configuration results. Subsequently, an enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism is used to independently train each key node and share the learning results, forming a preliminary energy supply strategy. Then, these strategies are subjected to multiple rounds of multi-level simulation tests in a simulation environment. Each round is based on different extreme weather scenario assumptions and actual market information to simulate and predict the changes in the operating state of each node and their interactive effects, generating a series of initial adjustment schemes. Finally, an evaluation framework is introduced to comprehensively evaluate each scheme, and based on the overall goals of the smart park and the requirements for emergency response capabilities, the optimal comprehensive adjustment scheme is selected.

[0091] For example, in a smart park, considering an impending severe storm warning, a data integration platform analyzed the performance of key energy-consuming nodes during similar past events, creating a foundational database. Based on this database, the state space (e.g., current load level), action space (e.g., reducing load or switching to backup power), reward function (e.g., reducing energy costs), and constraints (e.g., not exceeding maximum load) of each node were defined. An enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism was used to optimize and train the key nodes, generating preliminary energy supply strategies. Next, these strategies were tested multiple times in a high-fidelity simulation environment, considering storm scenarios of varying intensities and their impact on energy prices. After analyzing the effectiveness of each scheme using an evaluation framework, the optimal comprehensive adjustment scheme that ensures node safety while minimizing operating costs was ultimately selected. This not only improves the ability to cope with extreme weather but also ensures the efficiency and safety of energy use within the park.

[0092] To address the impact of extreme weather on key energy-consuming nodes in smart parks and further improve their operational stability and energy efficiency under various extreme conditions, as described in the previous embodiment, the initial energy supply strategy undergoes multiple rounds and multi-level simulation tests in a simulation environment. In each round, based on different extreme weather scenario assumptions and combined with actual market information, the simulation predicts the changes in the operational status of each key energy-consuming node and the complex interactions between them, generating a series of initial adjustment schemes, specifically including:

[0093] A virtual intelligent park model is constructed using a simulation environment building module, based on a dynamically updated basic database and defined results. Based on different types of extreme weather scenarios encountered by the intelligent park, combined with historical extreme weather cases and meteorological forecast information, multiple assumptions are set for each extreme weather scenario, generating a set of extreme weather scenario assumptions. Based on this set of extreme weather scenario assumptions and real-time acquired market information, multiple rounds of simulation tests are conducted on the initial energy supply strategy. In each round, for each extreme weather scenario assumption, the virtual intelligent park model is used to simulate and predict the changes in the operating status of each key energy consumption node, and analyze the impact of these changes on the operating modes and energy efficiency of other nodes. During the simulation, the complex interactions between different key energy consumption nodes are collected, identifying potential risks and optimization opportunities to generate simulation results. Based on each simulation result, the performance indicators of each key energy consumption node under different extreme weather scenarios are recorded and quantified, evaluating the effectiveness of the initial energy supply strategy under each simulation condition, and obtaining a summary of multiple initial simulation results. Based on the sum of these multiple initial simulation results, the performance of each key energy consumption node under various extreme weather scenarios is comprehensively evaluated, generating a series of initial adjustment schemes for specific extreme weather scenarios.

[0094] In this embodiment, the simulation environment building module refers to a tool for constructing a virtual intelligent park model. Based on a dynamically updated basic database and defined results (such as state space and action space), it provides a high-fidelity simulation platform. The extreme weather scenario hypothesis set refers to a collection of different types of extreme weather scenarios, each containing multiple assumptions (such as intensity and duration). These scenarios are generated based on extreme weather cases from historical data and the latest weather forecast information. Performance indicators refer to parameters that quantify the performance of each key energy consumption node under different extreme weather scenarios, such as total energy consumption, operating costs, and emergency response efficiency. These indicators are used to evaluate the effectiveness of the initial energy supply strategy under each simulation condition.

[0095] In this embodiment, a high-fidelity virtual intelligent park model is first constructed using a simulation environment building module, based on a dynamically updated basic database and defined results. Next, based on different types of extreme weather scenarios the intelligent park may encounter (such as heavy rain, blizzards, and strong winds), and combining historical extreme weather cases and meteorological forecast information, multiple assumptions are set to form an extreme weather scenario hypothesis set. Then, based on this hypothesis set and real-time acquired market information (such as energy price fluctuations and policy changes), multiple rounds of simulation testing are conducted on the initial energy supply strategy. In each round, for each extreme weather scenario assumption, the virtual intelligent park model is used to simulate and predict the changes in the operating status of each key energy consumption node, and to analyze how these changes affect the operating modes and energy efficiency of other nodes. Through this process, potential risk points and optimization opportunities are identified, and detailed simulation results are generated. Finally, 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 effectiveness of the initial energy supply strategy under each simulation condition is comprehensively evaluated, generating a series of initial adjustment schemes for specific extreme weather scenarios.

[0096] For example, in a smart park, considering an upcoming winter blizzard warning, a virtual smart park model was first constructed using a simulation environment building module. This model was based on historical data from similar blizzard events and current weather forecast information. Next, multiple extreme weather scenarios were set, including different intensities (light, moderate, and severe) and durations (short and long). Based on these assumptions and real-time energy market price fluctuations, the initially formulated energy supply strategy underwent multiple simulation tests. In one simulation assuming a strong and prolonged blizzard, it was found that some critical facilities faced the risk of power outages due to overload. By adjusting the backup power usage strategies for these facilities and optimizing the load allocation scheme, the risk of power outages was significantly reduced. After each simulation, the energy consumption levels, operating costs, and other performance indicators of each node were recorded and comprehensively evaluated. Ultimately, the optimal adjustment scheme that ensured park safety while minimizing operating costs 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, the theory was effectively transformed into practice, improving the disaster resistance and energy management efficiency of the entire smart park.

[0097] To address the complex challenges posed by extreme weather to smart parks and further improve the flexibility and efficiency of energy allocation, as another embodiment, according to step 103, based on the comprehensive adjustment scheme and the uncertainties brought by extreme weather and its impact on energy price fluctuations, a multi-level real-time optimization model is constructed. This multi-level real-time optimization model automatically switches between different optimization levels according to changes in the internal and external environment of the smart park, performing intelligent scheduling and cost control from the microscopic level of individual key energy consumption nodes to the macroscopic level of the entire smart park, generating an optimized energy allocation plan, specifically including:

[0098] Based on the aforementioned comprehensive adjustment scheme, and considering the uncertainties of extreme weather and its impact on energy price fluctuations, a multi-level real-time optimization model integrating predictive analysis and real-time feedback mechanisms is constructed. Using this multi-level real-time optimization model, micro-level optimization is performed on each key energy consumption node. A high-precision sensor network is used to monitor the energy consumption patterns of each node in real time. Machine learning algorithms are used to predict energy consumption trends, and personalized energy supply strategies are developed to address potential risks under different extreme weather scenarios, yielding micro-level optimization results. Based on real-time changes in the internal and external environment of the smart park, an adaptive algorithm automatically adjusts and switches different optimization levels of the multi-level real-time optimization model. At the meso-level, distributed collaborative optimization technology is employed to analyze energy flow between subsystems and... Interactions are used to identify critical paths and bottlenecks to optimize the operational efficiency of subsystems, resulting in meso-level optimization results. Each subsystem comprises multiple related nodes. At the macro level, the preliminary micro-level and meso-level optimization results are integrated, and an advanced economic model and social responsibility assessment framework are introduced to comprehensively optimize the overall energy management strategy of the entire smart park, generating macro-level optimization results. 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, generating secure transaction records. Finally, combining the micro-level, meso-level, and macro-level optimization results with the secure transaction records, an optimized energy allocation 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 changes in the internal and external environment of the smart park. This model integrates short-term forecasting and long-term planning functions, covering different levels from individual micro-nodes to the entire macro-park. The high-precision sensor network refers to the network used to monitor the energy consumption patterns of each key energy-consuming node in real time. These sensors can accurately collect data such as current, voltage, and temperature, which are used by machine learning algorithms to predict future energy consumption trends. The distributed collaborative optimization technology refers to a technique for optimizing subsystems composed of multiple related nodes. By analyzing energy flow and interactions, it identifies critical paths and bottlenecks to improve overall operational efficiency. The advanced economic model and social responsibility assessment framework refers to a set of tools used to comprehensively evaluate 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 assessments.

[0100] In this embodiment, firstly, based on the comprehensive adjustment scheme and considering the uncertainties of extreme weather and its impact on energy price fluctuations, a multi-level real-time optimization model integrating predictive analysis and real-time feedback mechanisms is constructed. Next, this model is used to perform micro-level optimization on each key energy consumption node. A high-precision sensor network monitors the energy consumption patterns of each node in real time, and machine learning algorithms predict energy consumption trends. Personalized energy supply strategies are formulated to address potential risks under different extreme weather scenarios, yielding preliminary micro-level optimization results. Then, based on real-time changes in the internal and external environment of the smart park, adaptive algorithms are 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 used to analyze the energy flow and interactions between subsystems composed of multiple related nodes, identifying critical paths and bottlenecks, and optimizing the operating efficiency of the subsystems, yielding meso-level optimization results. Finally, at the macro-level, all optimization results from the micro and meso-levels are integrated, and an advanced economic model and social responsibility assessment framework are introduced for comprehensive optimization, ensuring both efficiency and sustainability, generating the final macro-level optimization results. Furthermore, a secure transaction record system based on blockchain technology was constructed to track and verify the actual implementation of all energy transactions and regulatory measures, enhancing transparency and trust. Finally, by combining the optimization results at the micro, meso, and macro levels with the secure transaction records, a highly customized and flexibly adjustable optimized energy allocation plan was generated.

[0101] For example, when a smart park faced an impending rainstorm warning, a multi-level real-time optimization model was first constructed based on a comprehensive adjustment plan. This model considered the uncertainty of extreme weather and fluctuations in energy market prices. Utilizing a high-precision sensor network, the energy consumption patterns of key energy-consuming nodes (such as data centers and manufacturing workshops) were monitored in real time, and machine learning algorithms were used to predict energy consumption trends over the next few hours. Personalized energy supply strategies were developed to address the potential flood risk from the rainstorm, such as increasing backup power supply or reducing the power load in non-critical areas. As the intensity and duration of the rainstorm changed, adaptive algorithms automatically adjusted the different optimization levels of the multi-level real-time optimization model. At the meso-level, distributed collaborative optimization was performed on subsystems composed of multiple related nodes, identifying certain critical paths and bottlenecks (such as the overload risk of the power distribution system) and taking measures to optimize their operational efficiency. At the macro-level, all optimization results from the micro and meso-levels were integrated, and an advanced economic model and social responsibility assessment framework were introduced to comprehensively evaluate the energy management strategy of the entire park, ensuring both efficiency and compliance with social responsibility standards. Meanwhile, a secure transaction record system based on blockchain technology documents the actual implementation of all energy transactions and control measures, enhancing transparency and trust. Ultimately, this generates a detailed and optimized energy allocation plan, ensuring the park's safe and stable operation during heavy rains while minimizing operating costs. This approach achieves comprehensive coverage from micro to macro levels, improving the entire smart park's ability to cope with extreme weather and its energy management efficiency.

[0102] To address the complex challenges posed by extreme weather to energy flow and interaction among subsystems in a smart park, and to further improve the operational efficiency and overall energy efficiency of each subsystem, as described in the previous embodiment, an adaptive algorithm is used to automatically adjust and switch different optimization levels of the multi-level real-time optimization model based on real-time changes in the internal and external environment of the smart park. At the meso-level, distributed collaborative optimization technology is employed to analyze energy flow and interaction among subsystems, identify critical paths and bottlenecks, and optimize the operational efficiency of the subsystems to obtain meso-level optimization results. The subsystems are systems composed of multiple related nodes, specifically including:

[0103] By utilizing intelligent sensor networks and external data sources, real-time monitoring and processing of changes in the internal and external environment of the intelligent park are performed to obtain real-time environmental status data. 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 optimal optimization level is selected, and the parameters of the multi-level real-time optimization model are adjusted accordingly to obtain a multi-level real-time optimization model with adjusted optimization levels. At the meso-level, for subsystems composed of multiple related key energy consumption nodes, distributed collaborative optimization technology is adopted. Using the multi-level real-time optimization model with adjusted optimization levels, the energy flow and interactions between the subsystems are analyzed in depth, and a system is built... An energy flow model is established between subsystems to simulate the operating states of each subsystem and their mutual influences under different extreme weather scenarios. Critical paths and bottlenecks leading to reduced overall energy efficiency are identified, yielding the identification results. Based on these results, the operating strategies of each subsystem are optimized, adjusting the energy input-output ratios of key energy consumption nodes to obtain optimized subsystem operating strategies. According to the optimized subsystem operating strategies, simulation tools are used to conduct multiple rounds of simulation tests on the subsystems. In each round, based on different hypothetical scenarios, the performance indicators of the subsystems are evaluated, and preset optimization measures are adjusted to obtain the verification results of the optimization measures. These verification results are then combined across all subsystems.

[0104] In this embodiment, the intelligent sensor network and external data sources include high-precision sensors distributed throughout the smart park, weather stations, energy market price information, etc. This data is collected and processed in real time to monitor changes in the internal and external environment of the smart park. Adaptive algorithms are a technique that dynamically adjusts the parameters of a multi-level real-time optimization model based on real-time environmental data, ensuring that the model always remains consistent with the actual situation. Distributed collaborative optimization technology optimizes subsystems composed of multiple related key energy-consuming nodes by analyzing energy flow and interactions to identify critical paths and bottlenecks.

[0105] In this embodiment, a smart sensor network and external data sources are first used to continuously monitor and process the real-time changes in the internal and external environment of the smart park, obtaining 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 real-time environmental status data, the optimal optimization level is selected, and the model parameters are adjusted accordingly, resulting in 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, distributed collaborative optimization technology is employed. Using the multi-level real-time optimization model with adjusted optimization levels, the energy flow and interactions between subsystems are analyzed in depth. 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, identifying critical paths and bottlenecks that lead to a reduction in overall energy efficiency, and obtaining the identification results of critical paths and bottlenecks. Based on these identification results, the operating strategies of each subsystem are optimized, and the energy input-output ratio of key energy consumption nodes is adjusted to improve the operating efficiency of the subsystems, resulting in an optimized subsystem operating strategy. Finally, simulation tools were used to conduct multiple rounds of simulation tests on the optimized subsystem. In each round of testing, the performance indicators of the subsystem were evaluated based on different hypothetical scenarios, and the preset optimization measures were adjusted to obtain the verification results of the optimization measures. The final meso-level optimization results were generated by combining the verification results of the optimization measures of all subsystems.

[0106] For example, when a smart park faces an impending severe storm warning, it first utilizes a network of smart sensors distributed throughout the park and external data sources (such as weather stations and energy market price information) to continuously monitor real-time changes in the park's internal and external environment, obtaining the latest environmental status data. Subsequently, an adaptive algorithm is applied to dynamically adjust the multi-level real-time optimization model, selecting the most suitable optimization level for the current conditions and adjusting the model parameters accordingly. At the meso-level, for subsystems composed of multiple related key energy-consuming nodes such as data centers and manufacturing workshops, distributed collaborative optimization technology is employed to establish an energy flow model between subsystems. This model simulates the operating states and mutual influences of each subsystem under storm scenarios of varying intensities, identifying critical paths and bottlenecks that may lead to a reduction in overall energy efficiency. Based on the identification results, the operating strategies of each subsystem are optimized, such as adjusting the energy input-output ratio of certain nodes or replanning the backup power usage schedule. To verify the effectiveness of these optimization measures, simulation tools are used to conduct multiple rounds of simulation tests on the optimized subsystems. In each round of testing, based on different hypothetical scenarios (such as changes in storm intensity and fluctuations in energy market prices), the performance indicators of the subsystems are evaluated, and necessary fine-tuning of the optimization measures is performed. Finally, by combining the verification results of optimization measures from all subsystems, a detailed meso-level optimization scheme was generated. 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, comprehensive coverage from the micro to the macro level was achieved, enhancing the disaster resilience and energy management efficiency of the entire smart park.

[0107] To address the potential risks posed by extreme weather to smart parks 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, and combined with a geographic information system analysis of the relationship between the coverage area of ​​each multi-source heterogeneous extreme weather warning information and the geographical location of the smart park, the impact level assessment results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes within the smart park are evaluated, specifically including:

[0108] A data integration platform is used to integrate and process multi-source heterogeneous extreme weather warning information received from multiple sources, forming a unified-format extreme weather warning database. Based on this unified-format database, and in conjunction with a geographic information system, spatial analysis is performed on the coverage of each extreme weather warning message. The geographic coordinates of the extreme weather warning messages are compared with the geographic coordinates of the smart park to determine the spatial relationship between each extreme weather warning message and the smart park, resulting in a spatial coverage analysis of the extreme weather warning messages. Based on this spatial coverage analysis, historical data analysis tools are used to review and analyze the response patterns of different functional areas and energy consumption nodes within the smart park under extreme weather conditions, generating a preliminary impact assessment report. Based on this preliminary impact assessment report, a preset impact level standard is applied to classify each functional area and key energy consumption node within the smart park, determining the specific level of impact of extreme weather on each key energy consumption node, resulting in an impact level assessment.

[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, and the internet). It converts this information into a database in a unified format for subsequent analysis. Geographic Information System (GIS) is a technology for storing, analyzing, and displaying geographic data, which can accurately determine the spatial relationship between extreme weather warning information and the smart park. Historical data analysis tools are used to review and analyze response patterns in similar past extreme weather events, helping to generate a preliminary impact assessment report.

[0110] In this embodiment, a data integration platform is first used to integrate and process multi-source heterogeneous extreme weather warning information received from multiple sources, forming a unified-format extreme weather warning database. Next, based on this database, a geographic information system (GIS) is used to perform spatial analysis on the coverage of each extreme weather warning, comparing the geographic coordinates of the warnings with those of the smart park to determine the spatial relationship between each warning and the smart park, thus obtaining the spatial coverage analysis results. Based on these results, historical data analysis tools are used to review and analyze the response patterns of different functional areas and energy consumption nodes within the smart park under extreme weather conditions, generating a preliminary impact assessment report. Finally, based on this preliminary impact assessment report, a preset impact level standard is applied to classify the various functional areas and key energy consumption nodes within the smart park, determining the specific level of impact of extreme weather on each key energy consumption node, thus obtaining the final impact level assessment result.

[0111] For example, when a smart park faced an impending severe storm warning, it first utilized a data integration platform to consolidate extreme weather warning information from multiple sources, including weather stations, satellite remote sensing, and the internet, forming a unified-format extreme weather warning database. Next, a geographic information system (GIS) was used to conduct a detailed spatial analysis of the coverage area of ​​each warning message, precisely comparing the geographic coordinates of these warnings with the geographic coordinates of the smart park to determine which areas might be affected by the storm, resulting in a spatial coverage analysis. Based on these analysis results, historical data analysis tools were used to review the performance of various functional areas and key energy-consuming nodes during similar past storm events, generating a preliminary impact assessment report. According to this report, pre-defined impact level standards were applied to classify key areas within the park, such as data centers and manufacturing workshops, identifying which nodes were in high-risk areas requiring additional protective measures. For instance, data centers, due to their high dependence on a stable power supply, were assessed as high-impact, and therefore a specific emergency plan was developed, including increasing backup power supply and optimizing load distribution. This approach not only improved the smart park's ability to cope with extreme weather but also ensured the safety and stability of critical facilities within the park. This comprehensive risk assessment approach provides park managers with a scientific basis, helping them to develop more effective prevention and mitigation measures.

[0112] To address the issues of insufficient integration of distributed energy resources, lack of flexibility in electricity market trading strategies, and inadequate security of transaction records in existing technologies, and to improve the efficiency and transparency of energy management in smart parks, in one embodiment, according to step 104, based on the energy management decision information, distributed energy resources within the park are aggregated, and the surplus energy within the smart park is processed for participation in electricity market trading. Blockchain technology is used to record all transactions during energy production and consumption, resulting in transaction records. These transaction records are then securely stored to generate an energy transaction ledger. Specifically, this includes:

[0113] The optimized energy allocation plan is used to send control commands to configure the initial energy supply strategy for each key energy consumption node in the smart park. The received control commands are then processed in real-time via IoT devices to ensure each key energy consumption node operates according to the optimized energy allocation plan, resulting in real-time control results. Based on these results, drones and robots are used to inspect key facilities in the smart park over a preset time period, generating inspection reports. Drones are used for aerial monitoring and coverage checks, while robots are used for ground-based facility and complex environment inspections, ensuring the safety and normal operation of all key facilities. During the inspection, 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. This on-site feedback data is then... Data is transmitted to the central control system in real time. Combined with historical data and preset safety standards, the on-site feedback data is comprehensively analyzed to identify potential problems and assess their impact on the optimized energy allocation plan, generating an analysis report. Based on this report, an adaptive algorithm is applied to dynamically adjust the multi-level real-time optimization model, optimizing energy allocation and scheduling strategies at different levels to ensure the model remains consistent with actual conditions, resulting in a real-time updated enhanced multi-level real-time optimization model. According to this updated enhanced multi-level real-time optimization model, the optimized energy allocation plan is adjusted again, and control commands beyond existing ones are executed again via IoT devices. Furthermore, drones and robots are used for inspections to generate a smart park energy management mechanism.

[0114] In this embodiment, IoT devices include smart meters, sensor networks, and other devices for monitoring and controlling energy distribution, capable of receiving and executing control commands from a central control system. Drones and robotics are used for aerial monitoring and ground inspection, respectively; drones can cover large areas for rapid inspections, while robots are suitable for detailed inspection tasks in complex environments. High-precision sensors and cameras are used to monitor the status of critical facilities in real time and collect detailed on-site feedback data.

[0115] In this embodiment, control commands are first sent using an optimized energy allocation plan to configure the initial energy supply strategy for each key energy-consuming node within the smart park. The received control commands are then processed in real-time via IoT devices, ensuring each key energy-consuming node operates according to the optimized energy allocation plan, resulting in real-time control results. Next, based on these real-time control results, drones and robots are used to inspect key facilities within the smart park over a preset time period. Drones are primarily used for aerial monitoring and coverage checks to ensure the safety of large areas; robots focus on detailed inspection of ground facilities and complex environments, ensuring the safety and normal operation of all key facilities and generating inspection reports. During the inspection, 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. This on-site feedback data is then transmitted in real-time to the central control system. Combined with historical data and preset safety standards, the data is comprehensively analyzed to identify potential problems and assess their impact on the optimized energy allocation 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 energy allocation and scheduling strategies at different levels. This ensures the multi-level real-time optimization model remains consistent with actual conditions, resulting in a real-time updated enhanced multi-level real-time optimization model. Finally, based on the real-time updated enhanced multi-level real-time optimization model, the optimized energy allocation plan is readjusted, and new control commands are executed via IoT devices. Simultaneously, drones and robots continue to be used for inspections, forming a closed-loop feedback system to generate a smart park energy management mechanism.

[0116] For example, when a smart park faced an impending rainstorm warning, the system first configured key energy-consuming nodes (such as data centers and manufacturing workshops) within the park using IoT devices based on an optimized energy allocation plan. This ensured that each node operated according to the optimized plan, resulting in real-time control measures. Next, drones and robots were deployed to inspect key facilities within the park. Drones covered large areas of rooftops and exterior walls, while robots conducted detailed inspections of underground facilities and power distribution rooms, generating inspection reports. During the inspections, high-precision sensors and cameras comprehensively monitored the status of each key facility, collecting detailed on-site feedback data. This data was transmitted in real-time to the central control system, where it was comprehensively analyzed in conjunction with historical data and preset safety standards. This analysis identified areas with potential leakage risks and assessed their impact on the current energy allocation plan. Based on this analysis, an adaptive algorithm was applied to dynamically adjust the multi-level real-time optimization model, optimizing energy allocation and scheduling strategies to ensure the model remained consistent with actual conditions. Finally, based on the real-time updated optimization model, the energy allocation plan was readjusted, and additional control commands were executed via IoT devices, such as increasing backup power supply to certain key facilities. Meanwhile, drones and robots continue to be used for regular inspections, forming a closed-loop feedback system that continuously optimizes the park's energy management, ensuring efficient, safe, and stable energy management even 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 within the park.

[0117] Figure 2 This invention provides a schematic diagram of the structure of an energy management system for smart parks, as shown in the embodiment of the invention. Figure 2 As shown, the system includes:

[0118] The receiving module 21 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 based on the received multi-source heterogeneous extreme weather warning information and the geographic information system, and to evaluate the impact level assessment results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park.

[0119] The simulation module 22 is used to adaptively adjust the preset energy supply strategy for key energy consumption nodes affected by extreme weather conditions that exceed the preset value, using a distributed reinforcement learning algorithm. It also simulates and predicts the changes in the operating status of key energy consumption nodes under different energy supply strategies and the mutual influence between these changes, in order to select the best comprehensive adjustment scheme.

[0120] Module 23 is used to construct a multi-level real-time optimization model based on the comprehensive adjustment scheme and the uncertainties brought about by extreme weather and their impact on energy price fluctuations. 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 from the micro-level of a single key energy consumption node to the macro-level of the entire smart park, generating an optimized energy allocation plan.

[0121] The control module 24 is used to control the energy distribution in the smart park in real time through IoT devices according to the optimized energy distribution plan, and to use drones and robots to inspect key facilities, collect on-site feedback data and optimize the multi-level real-time optimization model in real time to obtain the smart park energy management and control mechanism.

[0122] Figure 2 The aforementioned energy management system for smart parks can perform... Figure 1 The implementation principle and technical effects of the energy management method for smart parks described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit of the energy management system for smart parks in the above embodiments perform operations have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0123] In one possible design, Figure 2 An energy management system for smart parks, as shown in the embodiment, can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

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

[0125] The processing component 32 is used to: analyze the relationship between the coverage area of ​​each multi-source heterogeneous extreme weather warning and the geographical location of the smart park based on the received multi-source heterogeneous extreme weather warning information and the geographic location of the smart park, and evaluate the impact level assessment results of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes within the smart park; for key energy consumption nodes whose impact level from extreme weather exceeds a preset value, adaptively adjust the preset energy supply strategy using a distributed reinforcement learning algorithm, and simulate and predict the changes in the operating status of key energy consumption nodes under different energy supply strategies and the mutual influence of these changes, so as to select the optimal comprehensive adjustment scheme; based on the comprehensive adjustment... The plan addresses the uncertainties brought about by extreme weather and their impact on energy price fluctuations. A multi-level real-time optimization model is constructed, which automatically switches between different optimization levels based on changes in the internal and external environment of the smart park. This process involves intelligent scheduling and cost control from the micro-level of individual key energy consumption nodes to the macro-level of the entire smart park, generating an optimized energy allocation plan. Based on this optimized plan, energy allocation within the smart park is instantly regulated using IoT devices, and drones and robots are used to inspect key facilities. The collected on-site feedback data is used to continuously optimize the multi-level real-time optimization model, resulting in a smart park energy management mechanism.

[0126] 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-described method. Alternatively, the processing component may be implemented as 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 to perform the above-described method.

[0127] Storage component 31 is configured to store various types of data to support operations at 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 storage, flash memory, magnetic disk, or optical disk.

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

[0129] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0130] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0131] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0132] This invention also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The illustrated embodiment presents an energy management method for smart parks.

[0133] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

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

[0135] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments 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 not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions 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 method for a smart park, characterized in that, Comprise: 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 geographic location of the smart park is analyzed by combining the geographic information system, and the influence level evaluation result of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park is evaluated; For the key energy consumption nodes affected by the extreme weather with an influence level greater than a preset value, a distributed reinforcement learning algorithm is used to adaptively adjust the preset energy supply strategy, and the running state changes of the key energy consumption nodes under different energy supply strategies and the mutual influence of the running state changes are simulated and predicted to select the best comprehensive adjustment scheme; Based on the comprehensive adjustment scheme and the uncertainty factors and the influence on energy price fluctuations caused by the extreme weather, 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 of the internal and external environment of the smart park, and intelligent scheduling and cost control processing are performed from the micro single key energy consumption node to the macro whole smart park level to generate an optimized energy distribution 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 equipment, and the key facilities are inspected using unmanned aerial vehicles and robot technology to collect on-site feedback data and optimize the multi-level real-time optimization model in real time to obtain a smart park energy management and control mechanism; Wherein, the distributed reinforcement learning algorithm is used to adaptively adjust the preset energy supply strategy for the key energy consumption nodes affected by the extreme weather with an influence level greater than a preset value, and the running state changes of the key energy consumption nodes under different energy supply strategies and the mutual influence of the running state changes are simulated and predicted to select the best comprehensive adjustment scheme, comprising: Using a data integration platform, the energy consumption mode, environmental parameters and operation mode of the key energy consumption nodes under current and historical extreme weather conditions are analyzed to obtain a dynamically updated basic database; According to the dynamically updated basic database, the state space, action space, reward function and constraint condition of each key energy consumption node are defined to generate a definition result, and each key energy consumption node is configured based on the definition result; Based on the defined state space, action space, reward function and constraint condition, an enhanced distributed reinforcement learning algorithm combined with a federated learning mechanism is used to independently train each key energy consumption node while sharing learning achievements while protecting data privacy to generate an initial energy supply strategy; 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 scenarios, combined with actual market information, the running state changes of each key energy consumption node and the complex interaction between each key energy consumption node are simulated and predicted to generate a series of initial adjustment schemes; An evaluation framework is introduced to comprehensively evaluate the system performance of each initial adjustment scheme after execution to generate the effectiveness evaluation result of each initial adjustment scheme; The best comprehensive adjustment scheme is selected based on the effectiveness evaluation result of each initial adjustment scheme in combination with the overall target of the smart park and the requirement of emergency response capability in extreme situations. In each round, based on different extreme weather scenario assumptions, in combination with actual market information, the running state changes of each key energy consumption node and the complex interaction between the key energy consumption nodes are simulated and predicted, and an initial adjustment scheme is generated, including: A virtual smart park model is constructed based on the dynamically updated basic database and the definition result by using a simulation environment construction module; According to different types of extreme weather scenarios encountered by the smart park, in combination with extreme weather cases in historical data and meteorological forecast information, multiple assumption conditions are set for each extreme weather scenario to generate an extreme weather scenario assumption set; Based on the extreme weather scenario assumption set and the actual market information obtained in real time, the initial energy supply strategy is simulated and tested for multiple rounds. In each round, for each extreme weather scenario assumption, the virtual smart park model is used to simulate and predict the running state changes of each key energy consumption node, analyze the influence of the running state changes on the operation mode and energy efficiency of other nodes, and collect the complex interaction between different key energy consumption nodes in the simulation process to identify potential risk points and optimization opportunities to generate simulation results; According to each simulation result, 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 a combination of multiple simulation initial results is obtained; Based on the combination of multiple simulation initial results, the performance of each key energy consumption node under various extreme weather scenarios is comprehensively evaluated to generate a series of initial adjustment schemes for specific extreme weather scenarios.

2. The method of claim 1, wherein, Based on the comprehensive adjustment scheme and the uncertainty factors and influence on energy price fluctuations caused by extreme weather, 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, performs intelligent scheduling and cost control processing from the micro single key energy consumption node to the macro smart park level, and generates an optimized energy distribution plan, including: Based on the comprehensive adjustment scheme, in combination with the uncertainty factors of extreme weather and the influence of extreme weather on energy price fluctuations, a multi-level real-time optimization model integrating prediction analysis and real-time feedback mechanism is constructed; By using the multi-level real-time optimization model, each key energy consumption node is optimized at the micro level. The energy consumption mode of each node is monitored in real time by using a high-precision sensor network, the energy consumption trend is predicted by using a machine learning algorithm, and individualized energy supply strategies are developed 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 different optimization levels of the multi-level real-time optimization model. On the mesoscopic level, the distributed collaborative optimization technology is used to analyze the energy flow and interaction between subsystems, identify the key path and bottleneck, and optimize the operation efficiency of the subsystems to obtain the mesoscopic optimization result, wherein the subsystems are systems composed of multiple related nodes. On the macro level, the preliminary optimization results of the microscopic level and the optimization results of the mesoscopic level are integrated, and a senior economic model and a social responsibility evaluation framework are introduced to comprehensively optimize the overall energy management strategy of the smart park, and a macro optimization result is generated. 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 execution of all energy transactions and control measures to generate a secure transaction record. The optimized energy distribution plan is generated by combining the microscopic optimization result, the mesoscopic optimization result, the macro optimization result, and the secure transaction record.

3. The method of claim 2, wherein, 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 different optimization levels of the multi-level real-time optimization model. On the mesoscopic level, the distributed collaborative optimization technology is used to analyze the energy flow and interaction between subsystems, identify the key path and bottleneck, and optimize the operation efficiency of the subsystems to obtain the mesoscopic optimization result, wherein the subsystems are systems composed of multiple related nodes. Real-time monitoring and processing of real-time changes of the internal and external environment of the smart park are performed by using intelligent sensor networks and external data sources to obtain real-time environmental state data. An adaptive algorithm is applied to dynamically adjust and switch different optimization levels of the multi-level real-time optimization model, and based on the changes of the real-time environmental state data, the best optimization level is selected, and the parameters of the multi-level real-time optimization model are adjusted accordingly to obtain the multi-level real-time optimization model after optimization level adjustment. On the mesoscopic level, for the subsystem composed of multiple related key energy consumption nodes, the distributed collaborative optimization technology is used to analyze the energy flow and interaction between the subsystems by using the multi-level real-time optimization model after optimization level adjustment, to simulate the running state of each subsystem and the mutual influence of each subsystem under different extreme weather scenarios, to identify the key path and bottleneck that leads to the overall energy efficiency reduction, and to obtain the key path and bottleneck identification result. Based on the key path and bottleneck identification result, the operation strategy of each subsystem is optimized, and the energy input and output ratio of the key energy consumption node is adjusted to obtain the optimized subsystem operation strategy. According to the optimized subsystem operation strategy, the subsystem is simulated and tested multiple times by using a simulation tool. In each round of testing, based on different hypothetical scenarios, the performance indicators of the subsystem are evaluated, and the preset optimization measures are adjusted to obtain the optimization measure verification result, and all subsystem optimization measure verification results are combined.

4. The method of claim 1, wherein, 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 geographic location of the smart park is analyzed by combining a geographic information system, and the influence level evaluation result of the multi-source heterogeneous extreme weather warning information on different functional areas and energy consumption nodes in the smart park is evaluated, including: The multi-source heterogeneous extreme weather warning information received from multiple sources is integrated and processed by using a data integration platform to form an extreme weather warning database in a unified format; According to the extreme weather warning database in a unified format, the coverage of each extreme weather warning information is spatially analyzed and processed by combining a geographic information system, 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. The spatial coverage analysis result of the extreme weather warning information is obtained; Based on the spatial coverage analysis result of the extreme weather warning information, the response mode of different functional areas and energy consumption nodes in the smart park under extreme weather conditions is reviewed and analyzed by using a historical data analysis tool to generate a preliminary impact evaluation report; According to the preliminary impact evaluation report, a preset impact level standard is applied to classify and process each functional area and key energy consumption node in the smart park, to determine the specific level of the impact of extreme weather on each key energy consumption node, and to obtain the impact level evaluation result.

5. The method of claim 1, wherein, According to the optimized energy distribution plan, the energy distribution in the smart park is instantaneously regulated and controlled by using Internet of Things devices, and unmanned aerial vehicles and robot technologies are used to patrol key facilities to collect on-site feedback data to optimize the multi-level real-time optimization model in real time to obtain a smart park energy management and control mechanism, including: Control instructions are sent by using the optimized energy distribution plan to configure the initial energy supply strategy of each key energy consumption node in the smart park, and the received control instructions are instantaneously regulated and controlled by using Internet of Things devices to make each key energy consumption node operate according to the optimized energy distribution plan to obtain an instant regulation result; According to the instant regulation result, unmanned aerial vehicles and robot technologies are started to patrol key facilities in the smart park for a preset time period to generate a patrol report, wherein the unmanned aerial vehicles are used for air monitoring and coverage inspection, and the robots are used for ground facility detection and detection in complex environments; During the patrol process, high-precision sensors and cameras are used to comprehensively monitor the state of key facilities and collect on-site feedback data to generate on-site feedback data; The on-site feedback data is transmitted to the central control system in real time, and the on-site feedback data is comprehensively analyzed by combining historical data and a preset safety standard to identify potential problems and evaluate the impact of the potential problems on the optimized energy distribution plan 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, optimize the energy allocation and scheduling strategy of different levels, make the multi-level real-time optimization model consistent with the actual situation, and obtain a real-time updated reinforced multi-level real-time optimization model; According to the real-time updated reinforced multi-level real-time optimization model, the optimized energy distribution plan is adjusted again, control instructions other than existing control instructions are executed again through Internet of Things devices, and unmanned aerial vehicles and robots are used for inspection again to generate an intelligent park energy management and control mechanism.

6. An energy management system for smart park, applied to the energy management method for smart park in any one of claims 1-5, characterized in that, Comprise: The receiving module is used for receiving multi-source heterogeneous extreme weather warning information, combining geographic information system to analyze the relationship between the coverage of each multi-source heterogeneous extreme weather warning information and the geographic location of the intelligent park, and evaluating 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; The simulation module is used for adaptively adjusting the preset energy supply strategy for key energy consumption nodes with an extreme weather influence level greater than a preset value, and simulating and predicting the running state changes of key energy consumption nodes under different energy supply strategies and the mutual influence of the running state changes to select the best comprehensive adjustment scheme; The construction module is used for constructing a multi-level real-time optimization model based on the comprehensive adjustment scheme and the uncertainty factors and influence on energy price fluctuations caused by extreme weather, automatically switching different optimization levels of the multi-level real-time optimization model according to the changes of internal and external environment of the intelligent park, and performing intelligent scheduling and cost control processing from a micro single key energy consumption node to a macro whole intelligent park level to generate an optimized energy distribution plan; The regulation and control module is used for regulating and controlling the energy distribution in the intelligent park through Internet of Things devices according to the optimized energy distribution plan, and using unmanned aerial vehicles and robots to patrol 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.

7. A computing device, comprising: A processing component and a storage component are included; 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 realize the energy management and control method for the intelligent park according to any one of claims 1-5.

8. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, the energy management and control method for the intelligent park according to any one of claims 1-5 is realized.

Images