Energy management method and energy management system

Abstract

The invention relates to the technical field of energy management, and provides an energy management method and an energy management system. The method comprises the steps of obtaining distribution design parameter information of a target park, performing 3D visualization based on the distribution design parameter information, and generating a park three-dimensional space model; carrying out equipment marking on the park three-dimensional space model to obtain N energy equipment, carrying out computing power network division deployment by taking the N energy equipment as a key point set, and building M distributed energy networks; calling an energy analysis network warehouse based on the M distributed energy networks to perform energy data acquisition and analysis processing to obtain M distributed energy utilization parameter sets; carrying out regulation and control strategy analysis and analogue simulation optimization by utilizing a digital twinborn technology, and determining energy regulation and control strategy parameters; and energy equipment response management and closed-loop control are performed based on the strategy parameters, so that the technical problem of low energy utilization rate caused by non-uniform energy equipment distribution and low energy regulation and control efficiency in traditional park energy management can be solved.

Description

Technical Field

[0001] The present application relates to the field of energy management technology, and in particular to an energy management method and an energy management system. Background Art

[0002] In modern industrial parks and industrial facilities, energy management has become a key factor in optimizing production efficiency and reducing operating costs. Traditional energy management models rely heavily on manual experience or local automation systems, making it difficult to cope with problems such as the wide distribution of energy equipment, strong heterogeneity, and dynamic demand fluctuations. In existing technologies, industrial park energy networks typically adopt a centralized management architecture, resulting in uneven distribution of computing resources, delayed equipment responses, and the inability to optimize energy scheduling strategies in real time. In addition, the physical space layout of energy equipment lacks deep integration with its energy consumption characteristics, making it difficult for control strategies to accurately match actual scenario requirements. Energy waste is widespread, restricting the park's energy efficiency improvement and the achievement of its carbon neutrality goals. Summary of the Invention

[0003] This application provides an energy management method and an energy management system, aiming to solve the technical problem of low energy utilization in traditional park energy management due to uneven distribution of energy equipment and low energy regulation efficiency, realize the simulation optimization of energy regulation strategies using digital twin technology, improve the response efficiency of energy equipment and energy utilization efficiency, and ensure the technical effect of the intelligent level of energy management.

[0004] In view of the above problems, the present application provides an energy management method and an energy management system.

[0005] The first aspect disclosed in the present application provides an energy management method, which includes: obtaining distribution design parameter information of a target park, performing 3D visualization based on the distribution design parameter information, and generating a three-dimensional spatial model of the park; performing energy equipment identification marking on the three-dimensional spatial model of the park to obtain N energy devices, and using the N energy devices as a set of key points to divide and deploy computing power networks, and build M distributed energy networks, where N≥M; building an energy analysis network warehouse, and calling the energy analysis network warehouse based on the M distributed energy networks to collect and analyze energy data to obtain M distributed energy utilization parameter sets; using digital twin technology to perform control strategy analysis and simulation optimization on the M distributed energy utilization parameter sets based on the three-dimensional spatial model of the park to determine energy control strategy parameters; performing energy equipment response management on the target park based on the energy control strategy parameters to obtain energy equipment feedback parameters, and performing closed-loop control of the energy equipment through the energy equipment feedback parameters.

[0006] Another aspect disclosed in the present application provides an energy management system, which includes: a 3D visualization module: obtaining distribution design parameter information of the target park, performing 3D visualization based on the distribution design parameter information, and generating a three-dimensional spatial model of the park; a computing power network division and deployment module: performing energy equipment identification and marking on the three-dimensional spatial model of the park to obtain N energy equipment, and using the N energy equipment as a set of key points to perform computing power network division and deployment, and building M distributed energy networks, where N≥M; a data acquisition and processing module: building an energy analysis network warehouse, calling the energy analysis network warehouse based on the M distributed energy networks to collect and analyze energy data, and obtain M distributed energy utilization parameter sets; a strategy analysis and optimization module: using digital twin technology to perform control strategy analysis and simulation optimization on the M distributed energy utilization parameter sets based on the three-dimensional spatial model of the park, and determine the energy control strategy parameters; a closed-loop control module: performing energy equipment response management on the target park based on the energy control strategy parameters, obtaining energy equipment feedback parameters, and performing closed-loop control of the energy equipment through the energy equipment feedback parameters.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The above-mentioned energy management method first obtains the distribution design parameter information of the target park, including basic data such as building layout, energy equipment distribution, pipeline direction, etc., and performs three-dimensional visual modeling based on these data to construct a complete three-dimensional space model of the park, so that energy management has an intuitive and visual basis; then, the energy equipment is identified and marked in the three-dimensional space model, and N energy equipment in the park, such as power transformers, air-conditioning systems, lighting equipment, heating equipment, etc., are determined. These energy equipment are regarded as key nodes, and by analyzing their geographical location, energy consumption characteristics and data interaction requirements, computing power networks are divided and deployed, and then M distributed energy networks are built to realize distributed management and scheduling control of energy equipment; in order to achieve efficient data analysis and decision support, an energy analysis network warehouse is further built, which can call real-time data from M distributed energy networks for Energy data is collected, processed and analyzed to generate M distributed energy utilization parameter sets, covering key indicators such as equipment operating status, energy consumption data, and load fluctuations. On this basis, digital twin technology is used to deeply integrate the actual energy operation scenarios of the park with the three-dimensional spatial model, and analysis and simulation of the control strategy are carried out based on M energy utilization parameter sets. Through multiple rounds of simulation optimization, the optimal energy control strategy parameters are found to achieve refined control and optimal configuration of energy use. Finally, based on the optimized energy control strategy parameters, real-time response management of energy equipment in the park is carried out, the operating status of the equipment is dynamically adjusted, and the feedback parameters of the equipment are obtained to form a data-strategy-feedback closed-loop control system. This closed-loop control can not only correct deviations in energy use in a timely manner, but also continuously optimize the energy management strategy, ultimately achieving efficient, intelligent, green and sustainable development of park energy management.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 The figure is a flow chart of an energy management method in one embodiment.

[0011] Figure 2The figure is an architecture diagram of an energy management system in one embodiment.

[0012] Explanation of the accompanying symbols: 3D visualization module 11, computing power network division and deployment module 12, data acquisition and processing module 13, strategy analysis and optimization module 14, closed-loop control module 15. DETAILED DESCRIPTION

[0013] The embodiments of the present application provide an energy management method and an energy management system to solve the technical problem of low energy utilization rate caused by uneven distribution of energy equipment and low energy regulation efficiency in traditional park energy management.

[0014] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0016] Example 1, as Figure 1 As shown, the present application provides an energy management method, the method comprising: The distribution design parameter information of the target park is obtained, and 3D visualization is performed based on the distribution design parameter information to generate a three-dimensional spatial model of the park.

[0017] In the embodiment of the present application, during the energy management process, it is first necessary to obtain the distribution design parameter information of the target park. This information includes key data such as the building structure layout, installation location of energy equipment, pipeline distribution, road direction, green area, and energy transmission path in the park. These parameters can fully reflect the spatial structure and distribution of energy facilities in each area of the park, and are the basic data for subsequent energy management and optimization control; then, based on these distribution design parameter information, 3D modeling software (such as Revit, SketchUp, 3ds Max, Blender, etc.) into a visual 3D spatial model, constructing the park's infrastructure model, including buildings, roads, landscaping, and pipelines. Energy equipment models are then precisely placed within the 3D space of the infrastructure model, annotated with information such as equipment name, number, and operating status to ensure the model is consistent with its actual distribution. Textures, materials, and lighting effects are then added to the model to enhance its realism and facilitate subsequent visualization and interactive operations. The infrastructure model with added energy equipment is then connected to the energy management system (EMS) through a data interface, displaying energy flow, equipment status, and energy consumption data in real time, resulting in the final 3D spatial model of the park. This 3D visualization allows managers to intuitively view the specific location of each energy device within the park, the connections between them, and the energy flow paths. This eliminates the need for complex floor plans or cumbersome equipment data sheets, allowing managers to monitor and schedule energy within an intuitive 3D scene, significantly improving management efficiency and decision-making accuracy.

[0018] Energy equipment identification and marking are performed on the three-dimensional spatial model of the park to obtain N energy equipment, and the N energy equipment are used as a set of key points to divide and deploy the computing power network to build M distributed energy networks, where N≥M.

[0019] In one embodiment, all energy equipment models located within the park's three-dimensional spatial model are identified based on the device names annotated within the model. These equipment models are uniformly labeled, resulting in N energy devices, such as power transformers, distribution cabinets, air conditioning systems, lighting equipment, heating devices, and photovoltaic equipment. Subsequently, these N energy devices are considered a key point set, and the computing resource requirements of each key device are analyzed, including data acquisition frequency, processing complexity, and real-time requirements. The required computing resources for each device are determined. A computing network partitioning scheme is then designed based on the park's geographic layout and device density. This partitioning scheme divides the key point set into M distributed energy networks, ensuring efficient coordination of data processing and energy regulation within each network. N ≥ M, meaning that a distributed energy network can simultaneously manage multiple energy devices. This process not only improves the management efficiency of the park's energy equipment but also lays a solid foundation for intelligent energy regulation.

[0020] Furthermore, the present application provides the construction of M distributed energy networks, including: Obtain computing power network division factor information, wherein the computing power network division factor information includes the geographical layout of the park, the distribution of energy equipment, and the equipment data processing requirements; prioritize the division factors in the computing power network division factor information to obtain a computing power network division factor reference sequence; use the N energy devices as a set of key points, and perform computing power network evaluation and planning on the key point set based on the computing power network division factor reference sequence to obtain M energy computing power networks; connect to the computing power resource scheduling center to perform resource allocation and deployment on the M energy computing power networks respectively, and build M distributed energy networks.

[0021] Preferably, when building M distributed energy networks, the geographical layout data of the park is first obtained, including the area of the park, building distribution, road layout, and functional positioning of different areas (such as office area, production area, storage area, etc.). This part of the data can help determine the spatial distribution of energy equipment and its distance, so as to reasonably arrange the distribution of computing resources to reduce network latency and data transmission distance, and obtain the equipment distribution data of all energy equipment in the park (such as transformers, air conditioners, lighting equipment, heating equipment, etc.). Different types of equipment have different processing requirements and importance. The distribution of equipment directly affects the planning of the computing network. The data processing requirement data of each energy device is obtained, including data collection frequency, processing complexity (such as real-time requirements, computing power, data storage requirements, etc.). For example, some equipment requires real-time monitoring and rapid response, while other equipment has lower processing requirements. This data helps quantify the allocation and configuration of computing resources. The obtained data will together constitute the computing network division factor information for subsequent computing power. Network assessment and planning. Subsequently, based on business needs, an impact weight is assigned to each factor. Typically, device data processing requirements are assigned a higher impact weight because they directly affect the allocation and deployment of computing resources. After obtaining the impact weight of each factor, the impact weights are sorted in descending order to determine the computing network partition factor reference sequence for the computing network partition factor information. For example, device data processing requirements may rank first, followed by the distribution characteristics of energy equipment, and finally factors such as the geographical layout of the park. Next, N energy devices are used as a set of key points, and computing network assessment and planning is performed on the key point set based on the computing network partition factor reference sequence. Specifically, because device data processing requirements rank first in the computing network partition factor reference sequence, data processing requirement parameters such as the expected collection frequency, real-time requirements, computing power, and data storage requirements are first obtained for each key point. These parameters are then normalized (using the maximum and minimum value normalization method) to obtain data processing requirement parameters in the same dimension.Subsequently, the processed data processing demand parameters are weightedly calculated according to the weight of each parameter (determined according to business needs and expert decisions) to obtain the quantitative value of the data processing demand of each key point. By comparing the quantitative value of the data processing demand of each key point with the preset high computing power demand value, the key points whose quantitative value of the data processing demand is greater than or equal to the preset high computing power demand value are screened out. These key points will be directly divided into independent computing power networks (first distributed energy network, second distributed energy network, etc.) to ensure performance requirements. The remaining key points will enter the next step of screening, that is, divided according to the distribution of energy equipment ranked second. In this process, starting from any undivided key point, a first partition set is created, and other key points are traversed. The distance between the key point and each key point in the first partition set is calculated using the geographical coordinates of the key point through Euclidean distance. If they are all less than or equal to the preset maximum distance, the key point is added to the first partition set. Otherwise, the second partition set is created with the key point. The above process is repeated until all key points have been compared, thereby obtaining multiple partition sets. Afterwards, according to the park location, The system then determines each partition set. If there are key points in different functional areas within the partition set, these key points are split to form new partition sets to reduce cross-regional communication costs. This process is repeated until each partition set has been determined. The key points in each determined partition set form an energy computing network. All energy computing networks are then aggregated to obtain M energy computing networks, each responsible for processing a certain number of key points to ensure efficient resource utilization and real-time device response. These M distributed energy computing networks are then connected to the computing resource dispatching center, which coordinates and allocates resources across the various computing networks to ensure optimal resource allocation for the entire park's energy management system. Under the guidance of the dispatching center, resources are allocated to each energy computing network based on the computing network partitioning factor information, resulting in M energy network computing power allocation resources. These energy network computing power allocation resources are then combined with sensor monitoring network parameters to build M distributed energy networks, achieving efficient and intelligent park energy management, improving energy utilization efficiency, and laying the foundation for the sustainable development of the park's energy management system.

[0022] Furthermore, the present application provides the construction of M distributed energy networks, including: Based on the computing power network division factor information, the M energy computing power networks are identified to obtain M energy network factor parameter sets; the computing power resource scheduling center is connected to perform resource configuration analysis on the M energy network factor parameter sets respectively to obtain M energy network computing power allocation resources; according to the energy equipment monitoring requirements, the sensor parameters of the M energy computing power networks are analyzed respectively to obtain M sensor monitoring network parameters; based on the M energy network computing power allocation resources and the M sensor monitoring network parameters, resource configuration and deployment are performed on the M energy computing power networks respectively to build the M distributed energy networks.

[0023] Optionally, after obtaining M energy computing power networks, the device data processing requirements will be extracted from the computing power network division factor information, including the quantitative value of the data processing requirements of each key point, and the total data processing requirements of each energy computing power network will be obtained by adding the quantitative values of the data processing requirements of the key points involved in each energy computing power network. The energy computing power network is identified using this total data processing requirement to obtain M energy network factor parameter sets; subsequently, a communication connection is established with the computing power resource scheduling center, and the M energy network factor parameter sets are transmitted to the computing power resource scheduling center, which will then identify the M energy network factor parameter sets. The energy network factor parameter set is used to perform resource configuration analysis. During this process, M energy network factor parameter sets are traversed, and the traversed energy network factor parameters are multiplied by the unit energy network computing power resources stored in the computing power resource scheduling center to obtain M energy network computing power allocation resources. Among them, the unit energy network computing power resource refers to the standardized unit resource defined in the computing power resource scheduling center, which represents the basic unit of resource configuration required for each energy network and is used to quantify and allocate the computing power requirements of different energy networks. For example, the unit energy network computing power resource can be 1 CPU core + 4GB Memory + 10MB / s bandwidth + 100GB storage. Subsequently, the required sensor types and parameters are determined based on the device types and monitoring requirements in each energy computing network. For example, an appropriate sampling frequency is set according to the device monitoring requirements. For devices with high precision requirements, high-precision sensors are selected to ensure the accuracy of data collection. The sensor communication protocol and bandwidth requirements are determined to ensure that sensor data can be smoothly transmitted to the energy management system. By summarizing the sensor parameters of each energy computing network, M sensor monitoring network parameters are obtained, providing detailed parameter information for subsequent sensor deployment. After obtaining the energy network computing power allocation resources and sensor monitoring network parameters, resources (such as computing nodes and storage devices) are deployed to each energy computing network to ensure that all devices in the network can obtain computing resources on demand. Appropriate sensor devices are also installed based on the sensor parameters and data connections are established with the corresponding energy network to ensure real-time monitoring. This completes the construction of the network topology and obtains the resource configuration and deployment of M distributed energy networks, ensuring that each network has the required computing power resources and sensor support, ultimately achieving efficient energy management and improving the efficiency and reliability of the overall energy management system.

[0024] An energy analysis network warehouse is built, and the energy analysis network warehouse is called based on the M distributed energy networks to collect and analyze energy data to obtain M distributed energy utilization parameter sets.

[0025] In one embodiment, an energy analysis network warehouse is built, which is based on relevant analysis networks of energy equipment, such as energy consumption analysis network, energy efficiency analysis network, etc.; based on multiple distributed energy networks in the park (i.e., M distributed energy networks), each energy network contains a different set of energy equipment. Through the energy data of these devices, the corresponding analysis network in the energy analysis network warehouse can be called to collect and analyze the data. In this way, energy data can not only be accurately captured, but also processed by advanced algorithms to generate corresponding energy utilization parameter sets. Specifically, each distributed energy network will generate energy utilization parameter sets based on the type of equipment it contains and The energy analysis network warehouse sends a request to the energy analysis network warehouse to retrieve the analysis networks related to these devices. For example, if a distributed energy network contains multiple transformers, air conditioning systems, and lighting equipment, it will call the energy analysis networks of the corresponding equipment in the warehouse to perform operations such as energy consumption analysis and energy efficiency prediction for these devices. The energy analysis network in the warehouse performs a series of calculations based on the specific parameters collected for each device, and ultimately obtains various parameters related to energy utilization, including energy consumption, efficiency, and other data. These parameters are fed back to each distributed energy network in the form of an energy utilization parameter set, allowing the park's energy management system to monitor the operating status of each network and device in real time. By continuously collecting, analyzing, and processing data, it is possible to optimize energy allocation, improve resource utilization efficiency, and adjust energy scheduling strategies through a data feedback mechanism to ensure that energy use within the park is operating in an optimal state.

[0026] Furthermore, the present application provides the energy analysis network warehouse construction, including: Based on the N energy devices, an energy utilization feature task list is constructed, and the energy utilization feature task list includes energy consumption, energy efficiency and energy cost analysis tasks of each energy device; a historical data set of energy device utilization is collected and obtained, and the historical data set of energy device utilization is diverted and identified based on the N energy devices to obtain N energy device utilization sample sets; migration analysis training is performed on the N energy device utilization sample sets based on the energy utilization feature task list to obtain N energy device analysis networks; the N energy device analysis networks are encoded and identified and stored in a data warehouse to obtain the energy analysis network warehouse.

[0027] Preferably, the energy utilization characteristic task list is the basis for systematic analysis of each energy device, which includes various tasks and indicators in the operation of the equipment, such as the energy consumption, energy efficiency and energy cost analysis tasks of each energy device. Among them, the energy consumption analysis task involves the energy consumption of each device in a specific time period, the energy efficiency analysis task focuses on the energy efficiency ratio of the equipment, that is, the ratio between the energy consumed by the equipment and the work completed or the benefits generated. The energy cost analysis task is to evaluate the operating cost of each device. Through the definition of these tasks, a detailed task list can be created for each device to facilitate subsequent data collection, analysis and optimization; then, a large amount of historical data can be obtained from the historical database. These data include the operating time, energy consumption, load conditions, efficiency performance, etc. of the equipment. These data will constitute the historical utilization data set of the energy equipment, and then be used N energy devices divert the energy device utilization history data set, that is, using the identification information of each energy device, the utilization history data of each device is extracted from the energy device utilization history data set to form N energy device utilization sample sets; then, based on the constructed energy utilization feature task list and the collected historical data, the energy device analysis network of each device is generated through training through the transfer learning algorithm. In this process, the N energy device utilization sample sets are input into the matching analysis network for analysis and training, thereby obtaining N energy device analysis networks. These energy device analysis networks can predict the energy efficiency, energy consumption, etc. of specific devices, and provide decision support for the energy management system; finally, the generated N energy device analysis networks are coded and identified (to the device they belong to) and stored in the energy analysis network warehouse for subsequent call and management.

[0028] Furthermore, the present application provides the method of obtaining N energy device analysis networks, including: According to the energy utilization feature task list, a source domain energy feature network set is selected, and the source domain energy feature network set includes an energy consumption analysis network, an energy efficiency analysis network, and an energy cost analysis network; the energy consumption analysis network, the energy efficiency analysis network, and the energy cost analysis network are connected and integrated in parallel to obtain a source domain energy analysis network; model parameters of the source domain energy analysis network are extracted to determine model architecture parameters; based on the model architecture parameters, transfer learning training and optimization are performed on the N energy device utilization sample sets to obtain the N energy device analysis networks.

[0029] Optionally, according to the task requirements in the energy utilization feature task list, search for existing or similar relatively accurate energy feature analysis models (based on neural networks, decision trees, etc.) from the model library, and store the searched models as a source domain energy feature network set. The models in this source domain energy feature network set correspond one-to-one to the tasks in the energy utilization feature task list, such as the energy consumption analysis network corresponding to the energy consumption task, the energy efficiency analysis network corresponding to the energy efficiency task, and the energy cost analysis network corresponding to the energy cost task; then, connect the energy consumption analysis network, the energy efficiency analysis network and the energy cost analysis network in parallel to form a multi-task joint network, namely the source domain energy analysis network, which can simultaneously analyze energy consumption, efficiency and cost, and provide comprehensive data support for subsequent equipment optimization; after the source domain energy analysis network is fused, extract the weights, biases and other parameters of each sub-network from the fused network. The model architecture parameters such as the number of layers, and the number of neurons in each layer represent the complexity and learning ability of the model, and serve as the basis for transfer learning so that they can be tuned in subsequent training. Afterwards, the extracted architecture parameters are used to perform transfer learning training on the energy utilization sample set of the device. Transfer learning can utilize the knowledge in the source domain (existing energy feature analysis model) to help quickly customize the optimization model for new devices or new application scenarios. By using the architecture and parameters of the source domain energy analysis network, transfer learning training is performed on the energy device utilization samples, that is, the energy device utilization samples are input into the source domain energy analysis network. Through forward propagation, loss calculation, back propagation, parameter optimization and other steps, the weights are gradually adjusted and the network is optimized to adapt to the new device characteristics and requirements, thereby obtaining N energy device analysis networks. These analysis networks will help devices optimize energy utilization in real time and provide accurate decision support for subsequent energy management systems.

[0030] Digital twin technology is used to analyze and optimize the control strategy of the M distributed energy utilization parameter sets based on the three-dimensional spatial model of the park to determine the energy control strategy parameters.

[0031] In one embodiment, by building an energy management database, historical data, equipment performance, load conditions, energy consumption and other information of each distributed energy network in the park are collected and organized. These data provide the basis for subsequent control strategies. Subsequently, based on the energy management database, an energy control state prediction network is established through supervised training. By learning from historical data, this network can predict the operating status of each energy system in the park under different conditions, helping to identify potential energy waste and inefficient areas or equipment. After that, the prediction network is embedded in the three-dimensional spatial model of the park, and digital twin technology is used for simulation to generate an energy state digital twin model, thereby mapping the energy utilization of the park in real time. The impact of different control strategies on the energy system is simulated in this virtual environment, providing operational space for energy scheduling. Based on this, control strategies are analyzed for M distributed energy utilization parameter sets. Based on energy management objectives (such as improving energy efficiency, reducing energy consumption, and lowering costs), various possible control schemes are analyzed. By analyzing these schemes, a set of energy control strategy parameter solutions is derived. Finally, based on the generated digital twin model of the energy state, these control strategy parameter solutions are simulated and optimized. This process simulates the implementation effects of different strategies, evaluates their actual performance, and finds the optimal energy control strategy. This process helps the park develop the best energy management plan, thereby optimizing energy utilization, improving efficiency, and reducing costs. Through this process, the park can not only monitor energy usage in real time but also dynamically adjust and optimize according to different needs and operating conditions, ensuring the efficient and stable operation of the energy management system.

[0032] Furthermore, the present application provides the method for determining energy regulation strategy parameters, including: Mining and constructing an energy management database, using a deep learning network to perform predictive supervision training on the energy management database to obtain an energy control state prediction network; using digital twin technology to embed the energy control state prediction network into the three-dimensional space model of the park for twin simulation to generate an energy state digital twin model; performing control strategy analysis on the M distributed energy utilization parameter sets according to the energy control demand target to obtain an energy control strategy parameter solution set; based on the energy state digital twin model, performing simulation and optimization on the energy control strategy parameter solution set to determine the energy control strategy parameters.

[0033] Optionally, historical energy data in the park is obtained through data mining, including energy consumption, efficiency, operating time, load conditions and environmental factors of various types of equipment, to build an energy management database. This energy management database provides the necessary input for subsequent deep learning training; then, a deep learning network (such as a multi-layer perceptron, a recursive neural network, etc.) is used to train the constructed energy management database. The training method is the same as mentioned above, and is still carried out through steps such as forward propagation, loss calculation, back propagation, and parameter optimization. The goal of the training process is to enable the network to accurately predict the energy regulation status under different conditions, such as energy consumption, efficiency changes and costs. By continuously adjusting the parameters of the model, the network gradually learns how to extract valuable features from historical data to form an energy regulation status prediction network. This network can evaluate the operating status of each energy system in the park in real time and provide decision support for energy management. Once the energy regulation status prediction network is obtained, the next step is to use digital twin technology to embed the energy regulation status prediction network into the three-dimensional spatial model of the park. The three-dimensional spatial model of the park is not only the physical layout of the equipment. , also including the operating characteristics and energy consumption patterns of the equipment. By combining the energy control state prediction network with the three-dimensional spatial model, an energy state digital twin model is formed. This virtual model can dynamically simulate the operation of each energy system in the park, making energy scheduling and management more intuitive and accurate, and also provides a virtual environment for subsequent control strategy testing; then, according to the energy control demand target, the M distributed energy utilization parameter sets of the park are analyzed. That is, based on historical data, multiple energy control strategies that can achieve M distributed energy utilization parameter sets are obtained (the specific number can be determined according to actual needs), thereby obtaining the energy control strategy parameter solution set; then, based on the previously obtained energy state digital twin model, the energy control strategy parameter solution set is simulated. The simulation will evaluate the effects of different strategies in actual operation, simulate the impact of each strategy on energy consumption, energy efficiency, energy cost, etc., and optimize by comparing the effects of different strategies. The purpose of this process is to find the optimal control strategy so that the park energy management system can achieve maximum energy utilization efficiency while maintaining system stability.

[0034] Furthermore, the present application provides the method for determining energy regulation strategy parameters, including: According to the energy regulation demand target, an energy regulation effect fitness function is constructed; the energy regulation effect fitness function is used to perform simulation evaluation on each parameter solution in the energy regulation strategy parameter solution set based on the energy state digital twin model to obtain the regulation effect fitness of multiple parameter solutions; based on the regulation effect fitness of multiple parameter solutions, the energy regulation strategy parameter solution set is cross-mutated and expanded to obtain the regulation strategy parameter solution space; global optimization is performed in the regulation strategy parameter solution space to determine the energy regulation strategy parameters.

[0035] Optionally, based on the energy regulation demand targets of the park, an energy regulation effect fitness function is constructed. This function is a quantitative evaluation of the effects of different regulation strategies, reflecting the pros and cons of the regulation strategies in meeting various demand targets. The fitness function is generally calculated by weighted summation. For example, the energy regulation effect fitness function is: ; Among them, F is the adaptability of energy regulation effect, 、 、 are the weight coefficients of each goal, reflecting the importance of each goal, E is the energy consumption parameter, is the target energy demand, is the energy efficiency parameter, is the target efficiency requirement, is the energy cost parameter, is the target cost requirement; then, each parameter solution in the energy control strategy parameter solution set is input into the energy state digital twin model for simulation, and then the simulation results are passed to the internal energy control state prediction network to generate the energy control state prediction results of each parameter solution, including energy consumption, energy efficiency and energy cost, and then the energy control state prediction results are input into the energy control effect fitness function to calculate the fitness of multiple parameter solutions; then, crossover and mutation expansion are performed according to the fitness value to generate more control strategy combinations. Crossover is to combine two preferred strategy solutions to generate a new solution. For example, the parameters of the two strategies are combined to form a new control strategy parameter solution. Mutation is to randomly change certain parameters in the existing solution, so as to explore new solution space and avoid falling into local optimality; after crossover and mutation, new control strategy parameter solutions are generated, and these control strategy parameter solutions together constitute the control strategy parameter solution space. These new solutions will contain more possibilities in order to find the optimal solution; after obtaining the expanded control strategy parameter solution space, the next step is to perform global optimization and select the best control strategy from it. In this process, a global optimization algorithm (such as particle swarm optimization, genetic algorithm, etc.) is used to search in the expanded solution space to find the strategy solution with the highest fitness. Taking particle swarm optimization as an example, the particle swarm optimization algorithm represents each potential solution in the solution space as a particle. Each particle has its own position and speed. In each iteration, the particle adjusts its speed and position according to its own historical best position and the global best position, thereby Internal search for the optimal solution. Specifically, when particles are updated in each generation, they evaluate the pros and cons of the current solution by calculating the energy control effect fitness function, and use information exchange to guide the entire particle swarm to converge to the optimal solution. The position of each particle represents a control strategy parameter solution. The energy control effect fitness function calculates the pros and cons of each solution according to the target requirements (such as energy efficiency, cost, etc.). Through multiple generations of iteration, the particle swarm will gradually find the most suitable control strategy; the final control strategy parameters after optimization will be used as the energy control strategy parameters to determine the specific energy scheduling plan within the park, ensuring that the energy management system maintains efficient and stable operation while achieving the optimization goals.

[0036] Energy equipment response management is performed on the target park based on the energy regulation strategy parameters to obtain energy equipment feedback parameters, and energy equipment closed-loop control is performed using the energy equipment feedback parameters.

[0037] In one embodiment, adjustment instructions are issued to each energy device in the park based on the determined energy regulation strategy parameters to ensure that they operate according to the new regulation strategy. As the devices begin to execute these instructions, feedback parameters are generated. These feedback parameters reflect the actual operation of the devices under the new strategy, including energy consumption feedback, efficiency feedback, cost feedback, etc. These feedback parameters are collected in real time to form energy device feedback parameters and transmitted back to the energy management system for further monitoring and adjustment, thereby achieving closed-loop control of energy devices. The goal of closed-loop control of energy devices is to continuously optimize and adjust the operating status of the devices based on this feedback data, ensure optimal energy use within the park, and promptly correct any possible deviations or abnormalities. Through this feedback control mechanism, it is possible to dynamically respond to changes in energy demand within the park and continuously self-regulate, thereby achieving more accurate and efficient energy management.

[0038] In summary, the embodiments of the present application have at least the following technical effects: The embodiment of the present application obtains the distribution design parameter information of the target park, performs 3D visualization based on the distribution design parameter information, and generates a three-dimensional spatial model of the park; performs energy equipment identification marking on the three-dimensional spatial model of the park to obtain N energy devices, and uses the N energy devices as a set of key points to divide and deploy computing power networks, and build M distributed energy networks, where N≥M; builds an energy analysis network warehouse, and calls the energy analysis network warehouse based on the M distributed energy networks to collect and analyze energy data, and obtain M distributed energy utilization parameter sets; uses digital twin technology to perform control strategy analysis and simulation optimization on the M distributed energy utilization parameter sets based on the three-dimensional spatial model of the park, and determines energy control strategy parameters; performs energy equipment response management on the target park based on the energy control strategy parameters, obtains energy equipment feedback parameters, and performs closed-loop control of energy equipment through the energy equipment feedback parameters. These technical effects jointly solve the technical problem of low energy utilization in traditional park energy management due to uneven distribution of energy equipment and low energy regulation efficiency, realize the use of digital twin technology to simulate and optimize energy regulation strategies, improve the response efficiency of energy equipment and energy utilization efficiency, and ensure the intelligent level of energy management.

[0039] Example 2, based on the same inventive concept as an energy management method in the above embodiment, Figure 2As shown, the present application provides an energy management system, which includes: a 3D visualization module 11: obtaining the distribution design parameter information of the target park, performing 3D visualization based on the distribution design parameter information, and generating a three-dimensional space model of the park; a computing power network division and deployment module 12: performing energy equipment identification and marking on the three-dimensional space model of the park to obtain N energy devices, and using the N energy devices as a key point set to perform computing power network division and deployment, and building M distributed energy networks, where N≥M; a data acquisition and processing module 13: building an energy analysis network warehouse, calling the energy analysis network warehouse based on the M distributed energy networks to collect and analyze energy data, and obtain M distributed energy utilization parameter sets; a strategy analysis and optimization module 14: using digital twin technology to perform control strategy analysis and simulation optimization on the M distributed energy utilization parameter sets based on the three-dimensional space model of the park, and determine the energy control strategy parameters; a closed-loop control module 15: performing energy equipment response management on the target park based on the energy control strategy parameters, obtaining energy equipment feedback parameters, and performing closed-loop control of the energy equipment through the energy equipment feedback parameters.

[0040] Furthermore, the computing power network division and deployment module 12 is further configured to execute the following method: Obtain computing power network division factor information, wherein the computing power network division factor information includes the geographical layout of the park, the distribution of energy equipment, and the equipment data processing requirements; prioritize the division factors in the computing power network division factor information to obtain a computing power network division factor reference sequence; use the N energy devices as a set of key points, and perform computing power network evaluation and planning on the key point set based on the computing power network division factor reference sequence to obtain M energy computing power networks; connect to the computing power resource scheduling center to perform resource allocation and deployment on the M energy computing power networks respectively, and build M distributed energy networks.

[0041] Furthermore, the computing power network division and deployment module 12 is further configured to execute the following method: Based on the computing power network division factor information, the M energy computing power networks are identified to obtain M energy network factor parameter sets; the computing power resource scheduling center is connected to perform resource configuration analysis on the M energy network factor parameter sets respectively to obtain M energy network computing power allocation resources; according to the energy equipment monitoring requirements, the sensor parameters of the M energy computing power networks are analyzed respectively to obtain M sensor monitoring network parameters; based on the M energy network computing power allocation resources and the M sensor monitoring network parameters, resource configuration and deployment are performed on the M energy computing power networks respectively to build the M distributed energy networks.

[0042] Furthermore, the data acquisition and processing module 13 is further configured to execute the following method: Based on the N energy devices, an energy utilization feature task list is constructed, and the energy utilization feature task list includes energy consumption, energy efficiency and energy cost analysis tasks of each energy device; a historical data set of energy device utilization is collected and obtained, and the historical data set of energy device utilization is diverted and identified based on the N energy devices to obtain N energy device utilization sample sets; migration analysis training is performed on the N energy device utilization sample sets based on the energy utilization feature task list to obtain N energy device analysis networks; the N energy device analysis networks are encoded and identified and stored in a data warehouse to obtain the energy analysis network warehouse.

[0043] Furthermore, the data acquisition and processing module 13 is further configured to execute the following method: According to the energy utilization feature task list, a source domain energy feature network set is selected, and the source domain energy feature network set includes an energy consumption analysis network, an energy efficiency analysis network, and an energy cost analysis network; the energy consumption analysis network, the energy efficiency analysis network, and the energy cost analysis network are connected and integrated in parallel to obtain a source domain energy analysis network; model parameters of the source domain energy analysis network are extracted to determine model architecture parameters; based on the model architecture parameters, transfer learning training and optimization are performed on the N energy device utilization sample sets to obtain the N energy device analysis networks.

[0044] Furthermore, the strategy analysis and optimization module 14 is also used to execute the following method: Mining and constructing an energy management database, using a deep learning network to perform predictive supervision training on the energy management database to obtain an energy control state prediction network; using digital twin technology to embed the energy control state prediction network into the three-dimensional space model of the park for twin simulation to generate an energy state digital twin model; performing control strategy analysis on the M distributed energy utilization parameter sets according to the energy control demand target to obtain an energy control strategy parameter solution set; based on the energy state digital twin model, performing simulation and optimization on the energy control strategy parameter solution set to determine the energy control strategy parameters.

[0045] Furthermore, the strategy analysis and optimization module 14 is also used to execute the following method: According to the energy regulation demand target, an energy regulation effect fitness function is constructed; the energy regulation effect fitness function is used to perform simulation evaluation on each parameter solution in the energy regulation strategy parameter solution set based on the energy state digital twin model to obtain the regulation effect fitness of multiple parameter solutions; based on the regulation effect fitness of multiple parameter solutions, the energy regulation strategy parameter solution set is cross-mutated and expanded to obtain the regulation strategy parameter solution space; global optimization is performed in the regulation strategy parameter solution space to determine the energy regulation strategy parameters.

[0046] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0047] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0048] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. An energy management method, characterized in that: The method comprises: Obtaining distribution design parameter information of the target park, performing 3D visualization based on the distribution design parameter information, and generating a three-dimensional spatial model of the park; Identify and mark energy devices on the three-dimensional spatial model of the park to obtain N energy devices, and use the N energy devices as a set of key points to divide and deploy computing power networks to build M distributed energy networks, where N ≥ M; Building an energy analysis network warehouse, and calling the energy analysis network warehouse based on the M distributed energy networks to collect and analyze energy data to obtain M distributed energy utilization parameter sets; Using digital twin technology to perform control strategy analysis and simulation optimization on the M distributed energy utilization parameter sets based on the three-dimensional spatial model of the park, and determine energy control strategy parameters; Energy equipment response management is performed on the target park based on the energy regulation strategy parameters to obtain energy equipment feedback parameters, and energy equipment closed-loop control is performed using the energy equipment feedback parameters.

2. An energy management method according to claim 1, characterized in that: The construction of M distributed energy networks includes: Obtaining information on factors that determine the division of computing power networks, including the geographic layout of the park, the distribution of energy equipment, and equipment data processing requirements; Prioritizing each division factor in the computing power network division factor information to obtain a computing power network division factor reference sequence; Taking the N energy devices as a set of key points, performing computing network evaluation planning on the key point set based on the reference sequence of computing network division factors, and obtaining M energy computing networks; The computing power resource dispatching center is connected to configure and deploy resources for the M energy computing power networks respectively, and M distributed energy networks are built.

3. An energy management method according to claim 2, characterized in that: The construction of M distributed energy networks includes: Identifying the M energy computing power networks based on the computing power network division factor information to obtain M energy network factor parameter sets; Connecting to a computing power resource dispatching center to perform resource configuration analysis on the M energy network factor parameter sets respectively to obtain M energy network computing power allocation resources; According to the energy equipment monitoring requirements, sensor parameters of the M energy computing power networks are analyzed to obtain M sensor monitoring network parameters; Based on the M energy network computing power allocation resources and the M sensors monitoring network parameters, resource configuration and deployment are performed on the M energy computing power networks respectively to build the M distributed energy networks.

4. The energy management method according to claim 1, wherein: The energy analysis network warehouse is constructed, including: Constructing an energy utilization feature task list based on the N energy devices, wherein the energy utilization feature task list includes energy consumption, energy efficiency, and energy cost analysis tasks for each energy device; Acquire an energy device utilization history data set, and perform diversion identification on the energy device utilization history data set based on the N energy devices to obtain N energy device utilization sample sets; Performing migration analysis training on the N energy equipment utilization sample sets based on the energy utilization feature task list to obtain N energy equipment analysis networks; The N energy equipment analysis networks are coded and identified and stored in a data warehouse to obtain the energy analysis network warehouse.

5. An energy management method according to claim 4, characterized in that: The N energy equipment analysis networks are obtained, including: selecting a source domain energy feature network set according to the energy utilization feature task list, wherein the source domain energy feature network set includes an energy consumption analysis network, an energy efficiency analysis network, and an energy cost analysis network; The energy consumption analysis network, the energy efficiency analysis network and the energy cost analysis network are connected and integrated in parallel to obtain a source domain energy analysis network; Extracting model parameters of the source domain energy analysis network and determining model architecture parameters; Based on the model architecture parameters, transfer learning training and optimization are performed on the N energy devices using sample sets to obtain the N energy device analysis networks.

6. An energy management method according to claim 1, characterized in that: Determining energy control strategy parameters includes: Mining and constructing an energy management database, using a deep learning network to perform predictive supervision training on the energy management database to obtain an energy regulation state prediction network; Using digital twin technology, the energy control state prediction network is embedded into the three-dimensional spatial model of the park for twin simulation to generate an energy state digital twin model; Performing regulation strategy analysis on the M distributed energy utilization parameter sets according to the energy regulation demand target to obtain an energy regulation strategy parameter solution set; Based on the energy state digital twin model, the energy regulation strategy parameter solution set is simulated and optimized to determine the energy regulation strategy parameters.

7. An energy management method according to claim 6, characterized in that: Determining energy control strategy parameters includes: Constructing an energy regulation effect fitness function according to the energy regulation demand target; Using the energy regulation effect fitness function to perform simulation evaluation on each parameter solution in the energy regulation strategy parameter solution set based on the energy state digital twin model, to obtain the regulation effect fitness of multiple parameter solutions; Performing cross-mutation expansion on the energy control strategy parameter solution set based on the adaptability of the multiple parameter solution control effects to obtain a control strategy parameter solution space; A global optimization is performed in the control strategy parameter solution space to determine the energy control strategy parameters.

8. An energy management method, characterized in that, The steps for implementing an energy management method according to any one of claims 1 to 7 include: 3D visualization module: obtains the distribution design parameter information of the target park, performs 3D visualization based on the distribution design parameter information, and generates a three-dimensional spatial model of the park; A computing power network division and deployment module: identifies and marks energy devices in the three-dimensional spatial model of the park to obtain N energy devices, and divides and deploys computing power networks using the N energy devices as a set of key points to build M distributed energy networks, where N ≥ M. Data acquisition and processing module: building an energy analysis network warehouse, calling the energy analysis network warehouse based on the M distributed energy networks to perform energy data acquisition and analysis processing, and obtaining M distributed energy utilization parameter sets; Strategy analysis and optimization module: using digital twin technology to perform control strategy analysis and simulation optimization on the M distributed energy utilization parameter sets based on the three-dimensional spatial model of the park, and determine the energy control strategy parameters; Closed-loop control module: performs energy equipment response management on the target park based on the energy regulation strategy parameters, obtains energy equipment feedback parameters, and performs closed-loop control of the energy equipment through the energy equipment feedback parameters.

Images