An intelligent AI-driven multi-energy collaborative optimization method

Abstract

The present application relates to a kind of wisdom AI driven multi-energy collaborative optimization method applied to the field of energy optimization, including data acquisition end, wisdom AI data processing end and collaborative execution end, by constructing the closed loop optimization process of "data acquisition, wisdom AI processing and collaborative execution", in combination with the application of digital twin technology and cross-region cost accounting, the layered collaborative optimization method for multiple energy can be established, this method relies on real-time energy consumption monitoring data, and precise regulation is implemented for energy supply and demand imbalance state, significantly improves new energy consumption capacity, reduces traditional energy dependence, promotes energy structure to green low-carbon transformation, and also through the formulation of three-level optimization architecture of regional optimization, cross-regional optimization and transmission plan formulation, not only realizes the dual improvement of energy collaborative optimization efficiency and precision, but also effectively reduces collaborative optimization cost through operational optimization algorithm.

Description

Technical Field

[0001] The present invention relates to a multi-energy collaborative optimization method, and in particular to a smart AI-driven multi-energy collaborative optimization method applied in the field of energy optimization. Background Technology

[0002] Multi-energy synergistic optimization technology integrates various energy forms such as electricity, heat, gas, and renewable energy (wind and solar power), relying on advanced algorithms and intelligent management methods. Its aim is to break down the fragmented nature of traditional energy systems and build a complementary, coordinated, efficient, and low-carbon energy system. Its core value lies in maximizing energy utilization efficiency, minimizing carbon emissions, and improving the security and flexibility of energy supply.

[0003] Current technologies mainly promote and safeguard multi-energy collaborative optimization through two paths. One is to improve the scheduling efficiency of multi-energy systems through mathematical optimization algorithms. For example, Chinese invention patent application CN119231523A proposes a multi-objective collaborative optimization scheduling method for integrated energy systems. This method improves the convergence speed of optimization by adopting an improved chaotic mapping initialization method and using highly random parameter distribution. It also improves the gray wolf algorithm based on Pareto optimal solution theory to achieve collaborative optimization of both economic efficiency and carbon emission, effectively improving the efficiency of multi-energy unit parameter optimization and realizing the effectiveness of multi-energy comprehensive utilization and control.

[0004] Second, it leverages artificial intelligence technology to enhance dynamic response and decision-making capabilities. For example, Chinese invention patent application CN119922615A describes a dynamic power management and multi-energy collaborative optimization method that combines AI technology. By constructing an AI prediction model driven by historical flow-power consumption-supply data and integrating a two-layer optimization algorithm with deep learning and symbolic AI, it achieves policy transparency and dynamic planning, effectively improving the utilization rate of renewable energy and reducing dependence on traditional energy.

[0005] Current energy synergy optimization technologies are mainly applied to the coupling of traditional and new energy systems within the same energy region. When a significant imbalance occurs between the total energy supply and energy loss at the load terminals in this region, it may lead to both a shortage of terminal energy supply and the ineffective abandonment of new energy sources within the region, thereby weakening the application efficiency of renewable energy. If it is necessary to resolve the supply and demand contradiction in a single region through cross-regional energy synergy, two key factors need to be considered comprehensively: first, the construction of a cross-regional energy dispatch mechanism; and second, ensuring the economic feasibility of multi-regional energy network linkage.

[0006] However, this collaborative model faces a dual challenge—it must bear the massive consumption of computing resources and high economic costs, while also overcoming the physical limitations of traditional energy networks. However, with the continuous iteration and upgrading of artificial intelligence technology, its supercomputing power and deep learning capabilities provide technical support for the complex computing needs of multi-regional energy interconnection. Against this backdrop, how to fully unleash the empowering effect of AI technology in multi-regional energy collaboration, and minimize cross-regional collaboration costs while improving the efficiency of new energy utilization, has become one of the core issues that urgently need to be addressed in the current energy transition field. Summary of the Invention

[0007] In view of the above-mentioned prior art, the technical problem to be solved by the present invention is how to effectively apply AI technology to multi-regional energy collaboration, so as to improve the efficiency of new energy utilization while minimizing the cost of cross-regional collaboration.

[0008] To address the aforementioned problems, this invention provides a smart AI-driven multi-energy collaborative optimization method, comprising a smart AI-driven multi-regional collaborative system. The smart AI-driven multi-regional collaborative system includes a data acquisition terminal, a smart AI data processing terminal, and a collaborative execution terminal, comprising the following steps: S1. The data acquisition terminal collects basic data of each energy region and data on energy transmission methods between each energy region, and transmits the processed and transformed data to the smart AI data processing terminal. S2. The intelligent AI data processing terminal classifies and processes the data, displays digital twins of each energy region and the transmission between them, constructs digital models of multiple energy regions, and uses a collaborative optimization display platform to display information on the digital models of multiple energy regions. S3. The intelligent AI data processing terminal classifies and processes the received data, predicts and analyzes the energy consumption balance status in a single energy region, and then predicts and analyzes the synergistic effects between different energy regions based on the data of the single energy region. It also performs cross-regional cost accounting based on the analysis of the synergistic effects between different energy regions. S31. The intelligent AI data processing terminal performs cross-regional collaborative optimization on energy regions with positive costs and energy transmission means based on cross-regional cost accounting data, and transports the excess energy of energy regions with excess energy supply to energy regions with shortage energy supply through corresponding energy transmission means. S32. The intelligent AI data processing terminal formulates cross-regional transmission plans for energy regions with positive costs but lacking energy transmission means based on cross-regional cost accounting data, and performs collaborative optimization of energy within a single energy region. S33. The intelligent AI data processing terminal performs collaborative optimization of energy within a single energy region for cross-regional transmission with negative costs based on cross-regional cost accounting data. S34. When the intelligent AI data processing terminal performs coordinated optimization of energy in a single energy area, it performs appropriate coordinated optimization based on the energy consumption imbalance state. S341. When energy supply shortages occur due to energy consumption imbalance in a single energy region, the intelligent AI data processing terminal performs collaborative optimization on load terminals and traditional energy sources within the single energy region to reduce the total number of load terminals in the same period and increase the efficiency of traditional energy sources. S342. When there is an energy supply surplus due to energy consumption imbalance in a single energy region, the intelligent AI data processing terminal will coordinate and optimize the power storage and traditional energy efficiency in the single energy region, add storage equipment and reduce the efficiency of traditional energy. S4. The intelligent AI data processing terminal transmits the collaborative optimization instructions for single energy regions and cross-regional energy transmission between energy regions to the collaborative execution terminal. The collaborative execution terminal regulates the single energy region and the corresponding cross-regional transmission to ensure the energy consumption balance of each energy region. The S5 intelligent AI data processing terminal displays and stores the results of its calculations and judgments, as well as the proposed cross-regional transmission plan, in real time through the collaborative execution terminal.

[0009] In the aforementioned AI-driven multi-energy collaborative optimization method, a closed-loop optimization process of "data acquisition, AI processing, and collaborative execution" is constructed. Combined with the application of digital twin technology and cross-regional cost accounting, a hierarchical collaborative optimization method for multiple energy sources can be established. This method relies on real-time energy consumption monitoring data to implement precise regulation and control for energy supply and demand imbalances. It also effectively reduces collaborative optimization costs through operations research optimization algorithms.

[0010] As a supplement to this application, the data acquisition terminal includes a single-area energy data acquisition unit, a single-area load terminal data acquisition unit, a transmission status acquisition unit for each area, and a decision command transmission unit. The intelligent AI data processing terminal includes an intelligent AI-driven processing unit, a digital twin unit, a single-region energy consumption prediction and analysis unit, a regional energy consumption summary and analysis unit, and a cross-regional cost accounting unit. The collaborative execution unit includes a single-region energy collaboration unit, a cross-regional energy collaboration unit, and a collaborative optimization display unit; The input end of the decision command transmission unit is connected to the signal of the collaborative optimization display platform, and the output ends of the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, and the transmission status acquisition unit of each area are connected to the signal of the intelligent AI drive processing unit. The output of the intelligent AI-driven processing unit is connected to the digital twin unit and the single-area energy consumption prediction and analysis unit respectively. The output of the single-area energy consumption prediction and analysis unit is connected to the energy consumption summary and analysis unit of each area. The output of the energy consumption summary and analysis unit of each area is connected to the cross-area cost accounting unit. The input end of the intelligent AI-driven processing unit is also connected to the single-area energy consumption prediction and analysis unit, the energy consumption summary and analysis unit of each area, and the cross-regional cost accounting unit. The output end of the intelligent AI-driven processing unit is connected to the single-area energy coordination unit, the cross-regional energy coordination unit, and the collaborative optimization display unit, respectively. The output end of the digital twin unit is connected to the collaborative optimization display unit.

[0011] As a supplement to this application, the output end of the data acquisition end is connected to the signal of the intelligent AI data processing end, the output end of the intelligent AI data processing end is connected to the signal of the collaborative execution end, the input end of the data acquisition end is connected to the control system signal of each energy area, and the output end of the collaborative execution end is connected to the control system signal of each energy area. The input terminals of the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, and the transmission status acquisition unit of each area are all connected to the control system signals of each energy area. The output terminals of the single-area energy coordination unit and the cross-area energy coordination unit are connected to the control system signals of each energy area. Moreover, the command priority of the single-area energy coordination unit and the cross-area energy coordination unit is higher than the command priority in the control system of each energy area. The output terminal of the collaborative optimization display unit is connected to the signal of the collaborative optimization display platform.

[0012] As a further improvement of this application, the intelligent AI-driven processing unit includes an initial data receiving and processing module and a feedback data aggregation and processing module. The output end of the initial data receiving and processing module is connected to an intelligent AI classification and calculation module, and the output end of the feedback data aggregation module is connected to an intelligent AI calculation and analysis module. The input end of the initial data receiving and processing module is connected to the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, the transmission status acquisition unit of each area, and the decision command transmission unit, respectively. The output end of the intelligent AI classification and calculation module is connected to the digital twin unit and the single-area energy consumption prediction and analysis unit, respectively. The input end of the feedback data aggregation and processing module is connected to the single-area energy consumption prediction and analysis unit, the energy consumption aggregation and analysis unit of each area, the cross-regional cost accounting unit, and the decision instruction transmission unit, respectively. The output end of the intelligent AI computing and analysis module is connected to the digital twin unit, the single-area energy coordination unit, the cross-regional energy coordination unit, and the collaborative optimization display unit, respectively.

[0013] As a further improvement to this application, the intelligent AI classification and calculation module and the intelligent AI calculation and analysis module are also interconnected with a deep learning unit. The input end of the deep learning unit is respectively connected to the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, the transmission status acquisition unit of each area, the decision command transmission unit, the single-area energy consumption prediction and analysis unit, the energy consumption summary and analysis unit of each area, and the cross-area cost accounting unit.

[0014] As a further improvement of this application, the output end of the intelligent AI computing and analysis module is also connected to a proposed plan feasibility verification unit, and the output end of the proposed plan feasibility verification unit is signal-connected to the collaborative optimization display unit.

[0015] As a further improvement to this application, the proposed plan feasibility verification unit includes a proposed plan data acquisition module, a cross-regional basic data acquisition module, and an energy transmission means acquisition module. The output ends of the proposed plan data acquisition module, the cross-regional basic data acquisition module, and the energy transmission means acquisition module are connected to a cross-regional energy consumption cost verification module and a cross-regional risk analysis module. The outputs of the cross-regional energy consumption cost verification module and the cross-regional risk analysis module are connected to the feasibility verification analysis module, and the output of the feasibility verification analysis module is connected to the analysis result transmission module. The input terminals of the planning data acquisition module and the cross-regional basic data acquisition module are connected to the intelligent AI computing and analysis module. The input terminal of the energy transmission means acquisition module is connected to the decision command transmission unit. The output terminal of the analysis result transmission module is connected to the collaborative optimization display unit.

[0016] As another improvement of this application, the input end of the intelligent AI-driven processing unit is also connected to a single-area energy consumption imbalance cost accounting unit, and the input end of the single-area energy consumption imbalance cost accounting unit is signal-connected to the single-area energy consumption prediction and analysis unit.

[0017] As a supplement to another improvement of this application, in step S33, when the intelligent AI data processing terminal performs energy coordination optimization within a single energy area, it can calculate the energy loss measurement within the single energy area, calculate the loss cost through the energy loss measurement, and then combine the energy imbalance loss cost of the single area to formulate a corresponding coordination optimization plan for the single area. When energy supply is short, formulate a coordinated optimization plan for a single area to apply load terminals in different time periods and to enhance the efficiency of traditional energy sources. When energy supply is excessive, formulate a coordinated optimization plan for a single area to store energy and reduce the efficiency of traditional energy sources. The intelligent AI data processing terminal displays and transmits the formulated collaborative optimization plan for a single region through the collaborative execution terminal. In summary, by constructing a closed-loop optimization process of "data acquisition, intelligent AI processing, and collaborative execution," and combining digital twin technology and cross-regional cost accounting, a hierarchical collaborative optimization method for multiple energy sources can be established. This method relies on real-time energy consumption monitoring data to implement precise regulation of energy supply and demand imbalances, significantly improving the capacity for renewable energy absorption, reducing dependence on traditional energy sources, and promoting the green and low-carbon transformation of the energy structure. Furthermore, through the formulation of a three-level optimization architecture—regional optimization, cross-regional optimization, and transmission plan formulation—it not only achieves a dual improvement in the efficiency and accuracy of energy collaborative optimization but also effectively reduces collaborative optimization costs through operations research algorithms. Relying on the global decision-making capabilities of intelligent AI, it constructs a highly efficient and low-cost operating mode for multi-regional energy interconnection, forming a multi-energy collaborative optimization method that unifies technical and economic benefits with environmental advantages. Attached Figure Description

[0018] Figure 1 The flowcharts for the multi-energy collaborative optimization method in the first to third embodiments of this application are shown. Figure 2 This is a control logic diagram of the intelligent AI-driven multi-region collaborative system according to the first to third embodiments of this application; Figure 3 The flowcharts are for the operation of the intelligent AI-driven processing unit in the first to third embodiments of this application. Figure 4 This is a topology diagram showing the coordination between each energy zone and the intelligent AI-driven multi-zone collaborative system in the first to third embodiments of this application; Figure 5 This is a collaborative optimization topology diagram for the first to third embodiments of this application under energy consumption imbalance. Figure 6 The flowcharts are for the cross-regional cost accounting unit application in the first to third embodiments of this application. Figure 7 The flowcharts are shown for the calculation of the single-area energy consumption imbalance cost accounting unit in the first to third embodiments of this application. Figure 8 This is a flowchart of the feasibility verification unit for the proposed plan in the third embodiment of this application. Detailed Implementation

[0019] The three embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0020] Implementation method 1: Figure 1 - Figure 7This paper demonstrates a smart AI-driven multi-energy collaborative optimization method, including a smart AI-driven multi-regional collaborative system. The smart AI-driven multi-regional collaborative system comprises a data acquisition terminal, a smart AI data processing terminal, and a collaborative execution terminal, and includes the following steps: S1. The data acquisition terminal collects basic data of each energy region and data on energy transmission methods between each energy region, and transmits the processed and transformed data to the smart AI data processing terminal. Energy transmission means refer to the related power structures for power transmission, such as transmission lines, substation equipment, special power transmission technology equipment, distribution network equipment, and supporting structures. S2. The intelligent AI data processing terminal classifies and processes the data, displays digital twins of each energy region and the transmission between them, constructs digital models of multiple energy regions, and uses a collaborative optimization display platform to display information on the digital models of multiple energy regions. S3. The intelligent AI data processing terminal classifies and processes the received data, predicts and analyzes the energy consumption balance status in a single energy region, and then predicts and analyzes the synergistic effects between different energy regions based on the data of the single energy region. It also performs cross-regional cost accounting based on the analysis of the synergistic effects between different energy regions. Cross-regional cost accounting does not consider the direct economic cost of energy transmission, but rather a comprehensive cost indicator that combines carbon emission costs, grid security costs, and transmission losses. The calculation of short-run marginal costs between energy regions with existing energy transmission methods is based on short-run marginal costs, which are expressed in minutes. The direction of cost is determined by short-run marginal cost accounting. A positive cost is an accounting result with economic benefits, while a negative cost is an accounting result with economic losses. For energy regions that do not have energy transmission means, the calculation is the long-term capacity cost. The long-term capacity cost here is on an annual basis. Based on the long-term capacity cost accounting, the positive or negative cost of building energy transmission means for cross-regional transmission is determined. The positive cost is the accounting result that the cross-regional transmission is still economically beneficial based on the cost after building relevant energy transmission means, and the negative cost is the accounting result that the cross-regional transmission will result in economic loss based on the cost after building relevant energy transmission means. S31. The intelligent AI data processing terminal performs cross-regional collaborative optimization on energy regions with positive costs (cost-benefit ratio ≥ 1.2) and energy transmission means based on cross-regional cost accounting data, and transports the excess energy of energy regions with excess energy supply (energy utilization rate < 80%) to energy regions with shortage energy supply (generation utilization rate > 120%) through corresponding energy transmission means. S32. The intelligent AI data processing terminal formulates cross-regional transmission plans for energy regions with positive costs (cost-benefit ratio ≥ 1.2) but lacking energy transmission means based on cross-regional cost accounting data, and performs collaborative optimization of energy within a single energy region. S33. The intelligent AI data processing terminal performs collaborative optimization of energy within a single energy region for cross-regional transmission with negative costs (benefit-cost ratio < 1.2) based on cross-regional cost accounting data. S34. When the intelligent AI data processing terminal performs coordinated optimization of energy in a single energy area, it performs appropriate coordinated optimization based on the energy consumption imbalance state. S341. When energy supply shortage occurs due to energy consumption imbalance in a single energy area (generation utilization rate > 120%), the intelligent AI data processing terminal performs collaborative optimization on the load terminals and traditional energy in the single energy area to reduce the total number of load terminals in the same period and increase the efficiency of traditional energy. S342. When there is an energy supply surplus (energy utilization rate <80%) in a single energy area due to energy consumption imbalance, the intelligent AI data processing terminal will coordinate and optimize the power storage and traditional energy efficiency in the single energy area, add storage equipment and reduce the efficiency of traditional energy. S4. The intelligent AI data processing terminal transmits the collaborative optimization instructions for single energy regions and cross-regional energy transmission between energy regions to the collaborative execution terminal. The collaborative execution terminal regulates the single energy region and the corresponding cross-regional transmission to ensure the energy consumption balance of each energy region. The S5 intelligent AI data processing terminal displays and stores the results of its calculations and the proposed cross-regional transmission plans in real time through the collaborative execution terminal. By constructing a closed-loop optimization process of "data acquisition, intelligent AI processing, and collaborative execution," and combining digital twin technology and cross-regional cost accounting, a hierarchical collaborative optimization method for multiple energy sources can be established. This method relies on real-time energy consumption monitoring data to implement precise regulation of energy supply and demand imbalances, significantly improving the capacity for new energy absorption, reducing dependence on traditional energy sources, and promoting the transformation of the energy structure towards green and low-carbon development. Furthermore, through the formulation of a three-level optimization architecture of intra-regional optimization, cross-regional optimization, and transmission plan formulation, it not only achieves a dual improvement in the efficiency and accuracy of energy collaborative optimization, but also effectively reduces the cost of collaborative optimization through operations research optimization algorithms. Relying on the global decision-making capabilities of intelligent AI, it constructs an efficient and low-cost operation mode for multi-regional energy interconnection, forming a multi-energy collaborative optimization method that unifies technical and economic benefits with environmental benefits.

[0021] Figure 1In step S33, when the intelligent AI data processing terminal performs energy coordination optimization within a single energy area, it can calculate the energy loss measurement within the single energy area, calculate the loss cost through the energy loss measurement, and then formulate a corresponding coordination optimization plan for the single area in combination with the energy imbalance loss cost of the single area. When energy supply is short, formulate a coordinated optimization plan for a single area to apply load terminals in different time periods and to enhance the efficiency of traditional energy sources. When energy supply is excessive, formulate a coordinated optimization plan for a single area to store energy and reduce the efficiency of traditional energy sources. The intelligent AI data processing terminal displays and transmits the collaborative optimization plan for a single region through the collaborative execution terminal. During the collaborative optimization process within a single energy region, it can form an efficient and highly applicable regional collaborative and effective control function based on different energy consumption states. This ensures the effectiveness and accuracy of collaborative optimization within a single energy region, promotes the utilization rate of new energy sources, reduces the continuous loss of traditional energy sources, promotes the environmental protection of energy applications, and reduces carbon emissions in the multi-energy collaborative process.

[0022] Implementation Method 2: Figure 1 - Figure 7 This demonstrates a smart AI-driven multi-energy collaborative optimization method. The data acquisition end includes a single-area energy data acquisition unit, a single-area load terminal data acquisition unit, a transmission status acquisition unit for each area, and a decision command transmission unit. The intelligent AI data processing terminal includes an intelligent AI-driven processing unit, a digital twin unit, a single-region energy consumption prediction and analysis unit, a regional energy consumption summary and analysis unit, and a cross-regional cost accounting unit. The collaborative execution unit includes a single-region energy collaboration unit, a cross-regional energy collaboration unit, and a collaborative optimization display unit; The input end of the decision command transmission unit is connected to the signal of the collaborative optimization display platform, and the output ends of the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, and the transmission status acquisition unit of each area are connected to the signal of the intelligent AI drive processing unit. The output of the intelligent AI-driven processing unit is connected to the digital twin unit and the single-area energy consumption prediction and analysis unit respectively. The output of the single-area energy consumption prediction and analysis unit is connected to the energy consumption summary and analysis unit of each area. The output of the energy consumption summary and analysis unit of each area is connected to the cross-area cost accounting unit. The input end of the intelligent AI-driven processing unit is also connected to the single-area energy consumption prediction and analysis unit, the energy consumption summary and analysis unit of each area, and the cross-regional cost accounting unit. The output end of the intelligent AI-driven processing unit is connected to the single-area energy coordination unit, the cross-regional energy coordination unit, and the collaborative optimization display unit, respectively. The output end of the digital twin unit is connected to the collaborative optimization display unit. Through the coordinated cooperation of the intelligent AI-driven processing unit, the single-area energy consumption prediction and analysis unit, the energy consumption summary and analysis unit of each area, and the cross-regional cost accounting unit, the rapid and accurate state analysis of the energy status of each area can be effectively promoted. While reducing the difficulty of processing large amounts of data by the intelligent AI-driven processing unit, it can also effectively realize the collaborative optimization of energy in each area. Furthermore, through the coordinated cooperation of intra-area optimization, cross-regional optimization, and transmission plan formulation, it can effectively promote the efficiency and accuracy of collaborative optimization among multiple energy sources, while also effectively reducing the cost of collaborative optimization among multiple energy sources, and promoting the economic benefits of multi-energy collaborative optimization.

[0023] Dispatchers can transmit multi-energy collaborative optimization parameter data and collaborative instructions to the decision command transmission unit through the collaborative optimization display platform. The parameter data includes, but is not limited to, the energy consumption balance standard range of a single energy region, the construction cost of related transmission means, the energy consumption balance calculation cycle, the cost loss of cross-regional transmission, and related data on traditional and new energy types in each region. The collaborative instructions include control and stop instructions for energy collaborative instructions in a single region or across regions, effectively avoiding the operation of collaborative instructions caused by energy consumption imbalance due to extreme weather, and promoting the effectiveness and safety guarantee of multi-energy collaborative optimization.

[0024] It should be noted that the intelligent AI-driven multi-regional collaborative system is mounted on a cloud computing platform and edge devices. The intelligent AI data processing terminal is mounted on the cloud computing platform and is responsible for the calculation, storage and analysis of data. The data acquisition terminal and collaborative execution terminal are mounted on edge devices, which can preprocess the data and effectively achieve real-time and reliable data transmission with the control systems of various energy regions and the collaborative optimization display platform.

[0025] Figure 2 - Figure 7 The diagram shows that the output of the data acquisition terminal is connected to the signal of the intelligent AI data processing terminal, the output of the intelligent AI data processing terminal is connected to the signal of the collaborative execution terminal, the input of the data acquisition terminal is connected to the control system signal of each energy zone, and the output of the collaborative execution terminal is connected to the control system signal of each energy zone. By directly connecting to the signal control systems of various energy regions, it is possible to effectively collect multi-source data, reduce the construction cost of smart AI-driven multi-regional collaborative systems, and enable effective collaborative applications of existing power grid systems. The input terminals of the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, and the transmission status acquisition units of each area are all connected to the control system signals of each energy area. The output terminals of the single-area energy coordination unit and the cross-area energy coordination unit are connected to the control system signals of each energy area. Moreover, the command priority of the single-area energy coordination unit and the cross-area energy coordination unit is higher than the command priority in the control system of each energy area, which effectively avoids the occurrence of coordination conflicts. The output terminal of the coordination optimization display unit is connected to the signal of the coordination optimization display platform. The coordination optimization display platform can also be connected to mobile terminals and PC terminals through network signals to realize the remote transmission and control of multi-energy coordination optimization data.

[0026] Figure 3 The intelligent AI-driven processing unit includes an initial data receiving and processing module and a feedback data aggregation and processing module. The output of the initial data receiving and processing module is connected to an intelligent AI classification and calculation module, and the output of the feedback data aggregation module is connected to an intelligent AI calculation and analysis module. The input end of the initial data receiving and processing module is connected to the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, the transmission status acquisition unit of each area, and the decision command transmission unit, respectively. The output end of the intelligent AI classification and calculation module is connected to the digital twin unit and the single-area energy consumption prediction and analysis unit, respectively. The input terminals of the feedback data aggregation and processing module are connected to the single-region energy consumption prediction and analysis unit, the energy consumption aggregation and analysis unit of each region, the cross-regional cost accounting unit, and the decision command transmission unit, respectively. The output terminals of the intelligent AI computing and analysis module are connected to the digital twin unit, the single-region energy coordination unit, the cross-regional energy coordination unit, and the collaborative optimization display unit, respectively. The setup of the intelligent AI classification computing module and the intelligent AI computing and analysis module can effectively realize the sharing and processing of various data, promote the monitoring and coordination of multi-regional energy data by the intelligent AI classification computing module and the intelligent AI computing and analysis module, and while ensuring the accuracy of collaborative optimization, it can also achieve low-cost and efficient collaborative optimization based on the energy consumption imbalance status and the direction of collaborative optimization costs, promote the accuracy of coordination between multiple energy sources, reduce the load terminal's dependence on traditional energy, and promote the effectiveness of new energy applications.

[0027] Both the intelligent AI classification and analysis modules affect the digital twin unit, effectively enabling dynamic calibration and real-time data display. This promotes the intuitiveness of multi-energy collaboration and the accuracy of displayed data, while also enhancing model transparency and robustness.

[0028] Figure 2 - Figure 7The intelligent AI classification and calculation module and the intelligent AI calculation and analysis module are also interactively connected to a deep learning unit. The input end of the deep learning unit is connected to the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, the transmission status acquisition unit of each area, the decision command transmission unit, the single-area energy consumption prediction and analysis unit, the energy consumption summary and analysis unit of each area, and the cross-area cost accounting unit. The deep learning unit adopts a composite architecture design, including a dynamic neural network architecture mechanism and a multimodal self-supervised learning mechanism.

[0029] Specifically, the neural network architecture adopts a hierarchical and configurable design, supporting modular combinations of convolutional neural networks (CNN), recurrent neural networks (RNN), and their variant structures (such as LSTM and GRU). It also integrates an attention-based Transformer architecture to form a hybrid network with multi-scale feature extraction capabilities. The self-supervised learning mechanism includes a contrastive learning framework and a generative pre-training module. By constructing a similarity measurement loss function for positive and negative sample pairs, it achieves feature representation learning for unlabeled data. This effectively promotes the training of the intelligent AI classification and analysis modules, and effectively enhances the sustained effectiveness of the synergistic driving effect.

[0030] Figure 2 - Figure 7 The input of the intelligent AI-driven processing unit is also connected to a single-area energy consumption imbalance cost accounting unit. The input of the single-area energy consumption imbalance cost accounting unit is connected to the single-area energy consumption prediction and analysis unit. Specifically, the single-area energy consumption imbalance cost accounting unit calculates the economic losses (E) incurred by the time-of-use application of load terminals when energy supply is insufficient. t ) and the resource costs required to increase the efficiency of traditional energy sources (C 增 ), in economic losses (E t ) greater than resource cost (C 增 When traditional energy sources are used, it is necessary to optimize their efficiency and synergy, in order to mitigate economic losses (E... t Less than or equal to resource cost (C) 增 When this occurs, time-segmented collaborative optimization is performed on the load terminals; When there is an energy surplus, calculate the economic loss (E) from energy loss. 丢 ), resource costs of adding storage devices (C) 储 ) and the economic benefits of reducing the efficiency of traditional energy sources (E 降 ), in economic losses (E 丢 Subtract economic benefits (E) 降 The value after ( ) is greater than the resource cost (C) 储 In the event of economic losses (E), while optimizing the efficiency of traditional energy sources, additional storage facilities should be installed in the region.丢 After subtracting economic benefits (E) 降 The value of ) is less than or equal to the resource cost (C) 储 When this is the case, only the efficiency reduction and synergistic optimization of traditional energy sources will be carried out.

[0031] Figure 1 - Figure 5 The system demonstrates how dispatchers transmit relevant parameters and instructions regarding the effective coordination of multiple energy sources to the decision-making instruction transmission unit via a collaborative optimization display platform. The decision-making instruction transmission unit processes and transforms the data before transmitting it to the intelligent AI-driven processing unit. The single-area load terminal data acquisition unit collects and acquires load terminal data from each energy region through the control systems of each energy region. This data primarily includes the total load terminal data and energy consumption data for each time period. The regional transmission status acquisition unit acquires data on transmission methods between energy regions through the control systems of each energy region. This data primarily includes whether there are transmission methods between regions and the relevant transmission methods. The single-area energy data acquisition unit collects data on traditional and new energy sources between energy regions. This data primarily includes traditional energy output and efficiency data, new energy output data, climate data on the application of new energy sources in the region, and annual output summary data for new energy sources. The single-area load terminal data acquisition unit, the regional transmission status acquisition unit, and the single-area energy data acquisition unit transform the received data before transmitting it to the intelligent AI-driven processing unit.

[0032] The initial data receiving and processing module in the intelligent AI-driven processing unit can receive and process the aforementioned data, and then transmit it to the intelligent AI classification and calculation module. The intelligent AI classification and calculation module classifies the received data, categorizing and organizing traditional energy data, new energy data, load terminal data, and related parameter instructions belonging to the same energy region. Furthermore, it associates the data of each energy region through transmission methods. Then, the intelligent AI classification and calculation module transmits this data to the digital twin unit and the single-region energy consumption prediction and analysis unit respectively. The digital twin unit constructs digital models of each energy region based on the initial data transmitted by the intelligent AI classification and calculation module, and transmits them to the collaborative optimization display platform through the collaborative optimization display unit, so that the dispatcher can obtain the data of each energy region and the collaborative status of the intelligent AI-driven processing unit in a timely and effective manner. The single-region energy consumption prediction and analysis unit analyzes and judges the energy consumption balance data of each single energy region. Then, the single-region energy consumption prediction and analysis unit transmits the analyzed balance data to the feedback data aggregation and processing module. At the same time, the single-region energy consumption prediction and analysis unit also transmits the data of single energy regions with energy consumption imbalance to the energy consumption aggregation and analysis units of each region. The energy consumption aggregation and analysis units of each region formulate appropriate cross-regional transmission analysis based on the imbalance data of each energy region. Then, the cross-regional transmission analysis is transmitted to the feedback data aggregation and processing module and the cross-regional cost accounting unit respectively. The cross-regional cost accounting unit calculates the cost required for transmitting imbalanced energy consumption based on the cross-regional transmission data and transmits the calculation result to the feedback data aggregation and processing module. The single-region energy consumption prediction and analysis unit also transmits the energy consumption imbalance data to the single-region energy consumption imbalance cost accounting unit. The single-region energy consumption imbalance cost accounting unit calculates and analyzes the relevant costs of collaborative optimization in the imbalanced region and then transmits it to the feedback data aggregation and processing module. The feedback data aggregation and processing module aggregates and processes data related to energy balance, cross-regional transmission, cross-regional transmission costs, and single-regional imbalance costs transmitted from the single-region energy consumption prediction and analysis unit, the energy consumption aggregation and analysis unit of each region, the cross-regional cost accounting unit, and the single-region energy consumption imbalance cost accounting unit, as well as the relevant parameters and instruction data transmitted from the decision instruction transmission unit. It aggregates and processes this data based on each individual energy region and their interrelationships, and then transmits it to the intelligent AI computing and analysis module. The intelligent AI computing and analysis module analyzes and processes the data of each energy region and the data between them, and outputs relevant collaborative optimization execution instructions based on the processing results. Simultaneously, the intelligent AI computing and analysis module transmits its analysis data of each energy region to the digital twin unit, enabling the data twin unit to generate iterative models for each energy region, improving model accuracy and reducing model generation errors. Then, the data twin unit displays the iterated models of each energy region to the collaborative optimization display platform through the collaborative optimization display unit, ensuring the data display is realistic and reliable. The intelligent AI computing and analysis module regulates energy regions with positive costs and corresponding transmission methods for cross-regional transmission. It transmits the corresponding regulation commands to the cross-regional energy coordination unit, enabling it to control the control system and transmission methods of the corresponding energy region. This allows the transmission of electrical energy from energy regions with abundant electricity to energy regions with insufficient electricity, thereby achieving energy consumption balance between the two energy regions, promoting the effectiveness of new energy applications, avoiding energy waste, and reducing the cost of cross-regional transmission due to the existence of existing transmission methods, thus promoting intelligent coordination among multiple energy sources. The intelligent AI computing and analysis module regulates energy regions where cross-regional transmission incurs negative costs or lacks corresponding transmission methods. It transmits the corresponding regulation commands to the single-region energy coordination unit, enabling it to regulate the corresponding traditional energy, storage devices, and load terminals based on the energy consumption imbalance status within the single energy region. When energy supply shortages occur due to energy consumption imbalance, the intelligent AI data processing terminal performs coordinated optimization of load terminals and traditional energy within the single energy region, reducing the total number of load terminals in the same period and increasing the efficiency of traditional energy. When energy supply surplus occurs due to energy consumption imbalance, the intelligent AI data processing terminal performs coordinated optimization of power storage and the efficiency of traditional energy within the single energy region, adding storage devices and reducing the efficiency of traditional energy. This ensures the effectiveness of load terminal operation, reduces economic losses, and fully promotes the utilization efficiency of new energy sources, thereby reducing the curtailment rate. The intelligent AI computing and analysis module regulates energy regions that have positive costs for cross-regional transmission and lack corresponding transmission methods. It formulates a proposed plan for transmission methods between these energy regions and transmits the proposed plan to the collaborative optimization display unit. The collaborative optimization display unit can then output the proposed plan through the collaborative optimization display platform, allowing dispatchers to assess the feasibility of constructing transmission methods between these energy regions. This further promotes the continuous application and introduction of new energy sources, improves their application efficiency, reduces the continuous loss of traditional energy sources, and ensures the effectiveness of collaborative optimization among multiple energy sources.

[0033] Furthermore, during the operation of the intelligent AI-driven multi-regional collaborative system, the deep learning unit can continuously learn and train the intelligent AI classification and calculation modules and the intelligent AI calculation and analysis modules through data input from single-region energy data acquisition units, single-region load terminal data acquisition units, regional transmission status acquisition units, decision command transmission units, single-region energy consumption prediction and analysis units, regional energy consumption summary and analysis units, and cross-regional cost accounting units. This improves the calculation accuracy of the intelligent AI classification and calculation modules and the efficiency and accuracy of their collaborative optimization, enhances their control over collaborative optimization costs, and ensures the economic benefits of coupling between multiple energy regions.

[0034] The third implementation method: Figure 1 - Figure 8This demonstrates a smart AI-driven multi-energy collaborative optimization method. The output of the smart AI computing and analysis module is also connected to a feasibility verification unit for the proposed plan. The output of the feasibility verification unit for the proposed plan is connected to the collaborative optimization display unit. By setting up the feasibility verification unit for the proposed plan, the feasibility of the proposed output plan can be effectively verified. While showing the dispatcher the plan for cross-regional transmission, a feasibility verification report can also be transmitted at the same time, promoting the reliability of the proposed plan.

[0035] Figure 8 The proposed plan feasibility verification unit includes a proposed plan data acquisition module, a cross-regional basic data acquisition module, and an energy transmission means acquisition module. The output terminals of the proposed plan data acquisition module, the cross-regional basic data acquisition module, and the energy transmission means acquisition module are connected to a cross-regional energy consumption cost verification module and a cross-regional risk analysis module. The outputs of the cross-regional energy consumption cost verification module and the cross-regional risk analysis module are connected to the feasibility verification analysis module, and the output of the feasibility verification analysis module is connected to the analysis result transmission module. The cross-regional energy consumption cost verification module uses the basic formula C=α·Etrans+β·Eloss for verification and accounting, where C is the total energy loss or economic cost. The balance between transmission and conversion is optimized by adjusting α and β, where α+β=1, Etrans is the loss in the energy transmission process (such as power grid transmission loss and heat dissipation in heat pipes), and Eloss is the loss caused by insufficient energy conversion efficiency (such as low efficiency of power generation equipment). The feasibility verification analysis module uses the Analytic Hierarchy Process (AHP) to analyze and process cost verification data and risk verification data; The input ends of the planning data acquisition module and the cross-regional basic data acquisition module are connected to the intelligent AI computing and analysis module. The input end of the energy transmission means acquisition module is connected to the decision command transmission unit. The output end of the analysis result transmission module is connected to the collaborative optimization display unit. By combining the cross-regional energy consumption cost verification module and the cross-regional risk analysis module, the feasibility of the fitted plan can be verified in both construction cost and construction risk directions. This further promotes the reliability and effectiveness of the verification results, thereby ensuring the data authenticity and feasibility of the fitted plan and effectively realizing the level of intelligence in collaborative optimization.

[0036] Figure 1 - Figure 5The diagram shows that after the intelligent AI computing and analysis module generates the proposed plan, it simultaneously transmits relevant data to the proposed plan data acquisition module and the cross-regional basic data acquisition module within the proposed plan feasibility verification unit. Furthermore, the decision command transmission unit also transmits relevant parameters to the energy transmission means acquisition module. The proposed plan data acquisition module can collect data on the proposed cross-regional transmission means, while the cross-regional basic data acquisition module can collect basic data such as energy data between relevant energy regions, physical and geographical data between relevant energy regions, and existing transmission means data between relevant energy regions. The energy transmission means acquisition module can collect relevant data such as the construction cost of relevant transmission means, transmission loss cost, and geographical data. The planning data acquisition module, the cross-regional basic data acquisition module, and the energy transmission means acquisition module process and transform the data they acquire, and then transmit them to the cross-regional energy consumption cost verification module and the cross-regional risk analysis module, respectively. This allows the cross-regional energy consumption cost verification module to calculate and verify the cost of constructing transmission means, the cost of cross-regional transmission, and the economic benefits generated by cross-regional transmission, and transmit the cost verification results to the feasibility verification analysis module. The cross-regional risk analysis module can verify and analyze the risks of constructing transmission means, application risks, and their impact on existing transmission means, and then transmit the risk verification analysis results to the feasibility verification analysis module. The feasibility verification analysis module comprehensively analyzes and verifies cost and risk results, then transmits the analysis results to the collaborative optimization display unit via the analysis result transmission module. The results are then displayed to the dispatcher through the collaborative optimization display platform. The feasibility verification analysis module only provides the verification analysis results data and does not provide specific instructions for executing the results. The dispatcher can use the feasibility verification results data to reference and analyze the proposed plan, and, in conjunction with the actual situation, determine whether to construct transmission methods between relevant energy regions. This effectively ensures the coupling effect between energy regions while reducing economic losses in the collaborative optimization process, promoting the economic benefits of multi-energy collaborative optimization, and facilitating the application and implementation of new energy sources. Considering current practical needs, the above-described implementation method adopted in this application is not limited to this scope of protection. Various changes made within the knowledge of those skilled in the art without departing from the concept of this application still fall within the protection scope of this invention.

Claims

1. A smart AI-driven multi-energy collaborative optimization method, characterized in that: This includes a smart AI-driven multi-regional collaborative system, which comprises a data acquisition terminal, a smart AI data processing terminal, and a collaborative execution terminal, and includes the following steps: S1. The data acquisition terminal collects basic data of each energy region and data on energy transmission methods between each energy region, and transmits the processed and transformed data to the smart AI data processing terminal. S2. The intelligent AI data processing terminal classifies and processes the data, displays digital twins of each energy region and the transmission between them, constructs digital models of multiple energy regions, and uses a collaborative optimization display platform to display information on the digital models of multiple energy regions. S3. The intelligent AI data processing terminal classifies and processes the received data, predicts and analyzes the energy consumption balance status in a single energy region, and then predicts and analyzes the synergistic effects between different energy regions based on the data of the single energy region. It also performs cross-regional cost accounting based on the analysis of the synergistic effects between different energy regions. The synergistic effect refers to the state in which different energy regions are complementary in terms of energy supply and demand and can achieve cross-regional energy allocation through energy transmission. S31. The intelligent AI data processing terminal performs cross-regional collaborative optimization on energy regions with positive costs and energy transmission means based on cross-regional cost accounting data, and transports the excess energy of energy regions with energy surplus to energy regions with energy shortage through corresponding energy transmission means. The positive cost refers to the accounting result that has economic benefits and a benefit-cost ratio ≥ 1.

2. S32. The intelligent AI data processing terminal formulates cross-regional transmission plans for energy regions with positive costs but lacking energy transmission means based on cross-regional cost accounting data, and performs collaborative optimization of energy within a single energy region. S33. The intelligent AI data processing terminal performs collaborative optimization of energy within a single energy region for cross-regional transmission with negative costs based on cross-regional cost accounting data. Negative costs refer to accounting results with economic losses and a benefit-cost ratio of <1.

2. S34. When the intelligent AI data processing terminal performs coordinated optimization of energy in a single energy area, it performs appropriate coordinated optimization based on the energy consumption imbalance state. S341. When energy supply shortages occur due to energy consumption imbalance in a single energy region, the intelligent AI data processing terminal performs collaborative optimization on load terminals and traditional energy sources within the single energy region to reduce the total number of load terminals in the same period and increase the efficiency of traditional energy sources. S342. When there is an energy supply surplus due to energy consumption imbalance in a single energy region, the intelligent AI data processing terminal will coordinate and optimize the power storage and traditional energy efficiency in the single energy region, add storage equipment and reduce the efficiency of traditional energy. S4. The intelligent AI data processing terminal transmits the collaborative optimization instructions for single energy regions and cross-regional energy transmission between energy regions to the collaborative execution terminal. The collaborative execution terminal regulates the single energy region and the corresponding cross-regional transmission to ensure the energy consumption balance of each energy region. The S5 intelligent AI data processing terminal displays and stores the results of its calculations and judgments, as well as the proposed cross-regional transmission plan, in real time through the collaborative execution terminal.

2. The intelligent AI-driven multi-energy collaborative optimization method according to claim 1, characterized in that: The data acquisition terminal includes a single-area energy data acquisition unit, a single-area load terminal data acquisition unit, a transmission status acquisition unit for each area, and a decision command transmission unit. The intelligent AI data processing terminal includes an intelligent AI-driven processing unit, a digital twin unit, a single-region energy consumption prediction and analysis unit, a regional energy consumption summary and analysis unit, and a cross-regional cost accounting unit. The collaborative execution terminal includes a single-region energy collaboration unit, a cross-regional energy collaboration unit, and a collaborative optimization display unit; The input end of the decision instruction transmission unit is connected to the collaborative optimization display platform, and the output ends of the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, and the transmission status acquisition unit of each area are connected to the intelligent AI drive processing unit. The output of the intelligent AI-driven processing unit is connected to the digital twin unit and the single-region energy consumption prediction and analysis unit, respectively. The output of the single-region energy consumption prediction and analysis unit is connected to the energy consumption summary and analysis unit of each region, and the output of the energy consumption summary and analysis unit of each region is connected to the cross-regional cost accounting unit. The input end of the intelligent AI-driven processing unit is also connected to the single-region energy consumption prediction and analysis unit, the energy consumption summary and analysis unit of each region, and the cross-regional cost accounting unit. The output end of the intelligent AI-driven processing unit is connected to the single-region energy coordination unit, the cross-regional energy coordination unit, and the collaborative optimization display unit, respectively. The output end of the digital twin unit is connected to the collaborative optimization display unit.

3. The intelligent AI-driven multi-energy collaborative optimization method according to claim 2, characterized in that: The output of the data acquisition terminal is connected to the intelligent AI data processing terminal, the output of the intelligent AI data processing terminal is connected to the collaborative execution terminal, the input of the data acquisition terminal is connected to the control system signals of each energy zone, and the output of the collaborative execution terminal is connected to the control system signals of each energy zone. The input terminals of the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, and the transmission status acquisition unit of each area are all connected to the control system signals of each energy area. The output terminals of the single-area energy coordination unit and the cross-area energy coordination unit are connected to the control system signals of each energy area. The instruction priority of the single-area energy coordination unit and the cross-area energy coordination unit is higher than the instruction priority in the control system of each energy area. The output terminal of the coordination optimization display unit is connected to the signal of the coordination optimization display platform.

4. The intelligent AI-driven multi-energy collaborative optimization method according to claim 2, characterized in that: The intelligent AI-driven processing unit includes an initial data receiving and processing module and a feedback data aggregation and processing module. The output of the initial data receiving and processing module is connected to an intelligent AI classification and calculation module, and the output of the feedback data aggregation and processing module is connected to an intelligent AI calculation and analysis module. The input end of the initial data receiving and processing module is connected to the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, the transmission status acquisition unit of each area, and the decision command transmission unit, respectively. The output end of the intelligent AI classification and calculation module is connected to the digital twin unit and the single-area energy consumption prediction and analysis unit, respectively. The input end of the feedback data aggregation and processing module is connected to the single-region energy consumption prediction and analysis unit, the energy consumption aggregation and analysis unit of each region, the cross-regional cost accounting unit, and the decision instruction transmission unit, respectively. The output end of the intelligent AI computing and analysis module is connected to the digital twin unit, the single-region energy coordination unit, the cross-regional energy coordination unit, and the collaborative optimization display unit, respectively.

5. The intelligent AI-driven multi-energy collaborative optimization method according to claim 4, characterized in that: The intelligent AI classification and calculation module and the intelligent AI calculation and analysis module are also interconnected with a deep learning unit. The input end of the deep learning unit is respectively connected to the single-area energy data acquisition unit, the single-area load terminal data acquisition unit, the transmission status acquisition unit of each area, the decision command transmission unit, the single-area energy consumption prediction and analysis unit, the energy consumption summary and analysis unit of each area, and the cross-area cost accounting unit.

6. The intelligent AI-driven multi-energy collaborative optimization method according to claim 4, characterized in that: The output of the intelligent AI computing and analysis module is also connected to a feasibility verification unit for the proposed plan, and the output of the feasibility verification unit for the proposed plan is signal-connected to the collaborative optimization display unit.

7. The intelligent AI-driven multi-energy collaborative optimization method according to claim 6, characterized in that: The proposed plan feasibility verification unit includes a proposed plan data acquisition module, a cross-regional basic data acquisition module, and an energy transmission means acquisition module. The output terminals of the proposed plan data acquisition module, the cross-regional basic data acquisition module, and the energy transmission means acquisition module are connected to a cross-regional energy consumption cost verification module and a cross-regional risk analysis module. The output terminals of the cross-regional energy consumption cost verification module and the cross-regional risk analysis module are connected to a feasibility verification analysis module, and the output terminal of the feasibility verification analysis module is connected to an analysis result transmission module. The input terminals of the proposed plan data acquisition module and the cross-regional basic data acquisition module are connected to the intelligent AI computing and analysis module. The input terminal of the energy transmission means acquisition module is connected to the decision instruction transmission unit. The output terminal of the analysis result transmission module is connected to the collaborative optimization display unit.

8. The intelligent AI-driven multi-energy collaborative optimization method according to claim 2, characterized in that: The input end of the intelligent AI-driven processing unit is also connected to a single-area energy consumption imbalance cost accounting unit, and the input end of the single-area energy consumption imbalance cost accounting unit is signal-connected to the single-area energy consumption prediction and analysis unit.

9. The intelligent AI-driven multi-energy collaborative optimization method according to claim 8, characterized in that: In step S33, when the intelligent AI data processing terminal performs energy coordination optimization within a single energy area, it can calculate the energy loss measurement within the single energy area, calculate the loss cost through the energy loss measurement, and then formulate a corresponding coordination optimization plan for the single area in combination with the energy imbalance loss cost of the single area. When energy supply is scarce, a coordinated optimization plan for a single region is formulated to allocate load terminals to different time periods and enhance the efficiency of traditional energy sources. When energy supply is abundant, a coordinated optimization plan for a single region is formulated to reduce the efficiency of energy storage and traditional energy sources. The intelligent AI data processing terminal displays and transmits the formulated coordinated optimization plan for a single region through the coordinated execution terminal.

Images