Energy scheduling strategy adjustment method and device, storage medium and electronic device

Abstract

The invention discloses an energy scheduling strategy adjusting method and device, a storage medium and an electronic device.The method comprises the steps that a first scheme used for guiding energy scheduling is determined through historical operation parameters of an energy system, and the energy system at least comprises a power generation subsystem, a load subsystem and an energy storage subsystem; under the condition that the first scheme is started, acquiring multiple groups of feedback data corresponding to different time nodes of other subsystems except the power generation subsystem in an operation period; performing numerical evaluation on the first scheme through the plurality of groups of feedback data to obtain a plurality of value sets; and screening out a target value set meeting a preset value set threshold value from the plurality of value sets, and adjusting the first scheme according to the target value set. The problems that the scheduling efficiency of the energy storage system is low and the emission reduction requirement cannot be met in the related technology are solved.

Description

Technical Field

[0001] The present application relates to the field of energy technology, and in particular to a method and device for adjusting an energy scheduling strategy, a storage medium, and an electronic device. Background Art

[0002] With the advancement of the "dual carbon" goals, the coordinated optimization of integrated energy systems has become a research hotspot. Traditional energy systems face challenges such as environmental pollution and energy consumption. However, integrated energy systems, by coupling multiple energy sources, can effectively improve energy efficiency and reduce carbon emissions. Within integrated energy systems, carbon trading and green certificate trading mechanisms have been introduced to promote the use of renewable energy and reduce carbon emissions.

[0003] Existing research has made some progress in source-load coordinated carbon reduction, but it also has limitations. For example, some studies fail to fully exploit the regulatory potential of energy storage and overlook the application of energy storage systems in multiple scenarios, resulting in low energy storage utilization and insufficient economic efficiency. Furthermore, most studies focus on a single market mechanism and lack a systematic analysis of the coupling effects of carbon trading and green certificate markets.

[0004] During the optimization and dispatching process, it is necessary to consider both economic and environmental benefits and achieve a balance between them. However, within the integrated energy system, there is a clear competitive advantage between the power generation side, the load side, and the energy storage equipment. Scientifically and effectively coordinating the interests of these parties and improving the comprehensive regulation capabilities of the power system are key aspects of building a new power system.

[0005] Currently, no effective solution has been proposed to the problem that the scheduling efficiency of energy storage systems in related technologies is low and cannot meet the needs of emission reduction.

[0006] Therefore, it is necessary to improve the existing related technologies to overcome the above-mentioned defects in the related technologies and meet the needs of current actual production. Summary of the Invention

[0007] The embodiments of the present application provide a method and device for adjusting an energy scheduling strategy, a storage medium, and an electronic device to at least solve the problem in related technologies that the scheduling efficiency of energy storage systems is low and cannot meet emission reduction needs.

[0008] According to one aspect of an embodiment of the present application, a method for adjusting an energy scheduling strategy is provided, comprising: determining a first scheme for guiding energy scheduling through historical operating parameters of an energy system, wherein the energy system includes at least: a power generation subsystem, a load subsystem, and an energy storage subsystem; when the first scheme is enabled, obtaining multiple sets of feedback data corresponding to different time nodes within an operating cycle of subsystems other than the power generation subsystem; performing numerical evaluation on the first scheme through the multiple sets of feedback data to obtain multiple value sets; screening out a target value set that meets a preset value set threshold from the multiple value sets, and adjusting the first scheme according to the target value set.

[0009] In an exemplary embodiment, a first scheme for guiding energy scheduling is determined through historical operating parameters of an energy system, including: determining cost data corresponding to the energy system from the historical operating parameters, wherein the cost data includes at least: transaction cost, electricity purchase cost, operating cost, depreciation cost, and fuel cost; determining a first objective function corresponding to the energy system based on the cost data and a first preset function; and determining a first scheme based on a solution result corresponding to the first objective function when the first objective function satisfies a first objective constraint condition corresponding to the energy system.

[0010] In an exemplary embodiment, a first scheme is numerically evaluated using multiple sets of feedback data to obtain multiple value sets, including: determining a second objective function constructed by the load subsystem and a third objective function constructed by the energy storage subsystem based on the multiple sets of feedback data; solving the second objective function and the third objective function based on multiple second constraints to obtain second solution results and third solution results; and numerically evaluating the first scheme using the second solution results and the third solution results to obtain multiple value sets.

[0011] In an exemplary embodiment, before filtering out a target value set that meets a preset value set threshold from multiple value sets, the above method also includes: filtering multiple value sets based on a preset Nash equilibrium solution, wherein the preset Nash equilibrium solution includes: a first part of the value set corresponding to the optimal operation of the power generation subsystem, a second part of the value set corresponding to the optimal operation of the load subsystem, and a third part of the value set corresponding to the optimal operation of the energy storage subsystem; when the screening result indicates that there is a value set that meets the Nash equilibrium solution among the multiple value sets, the value set is determined as the target value set to be confirmed; when the screening result indicates that there is no value set that meets the Nash equilibrium solution among the multiple value sets, a prompt message is generated that the energy system does not have a target value set.

[0012] In an exemplary embodiment, before screening multiple value sets based on a preset Nash equilibrium solution, the above method also includes: determining whether there is a subsystem with a continuously unchanged state among the power generation subsystem, the load subsystem, and the energy storage subsystem; when the load subsystem and the energy storage subsystem are subsystems with a continuously unchanged state, determining whether the first sub-score set corresponding to the power generation subsystem satisfies the first partial value set corresponding to the preset Nash equilibrium solution; when the power generation subsystem and the energy storage subsystem are subsystems with a continuously unchanged state, determining whether the second sub-score set corresponding to the load subsystem satisfies the second partial value set corresponding to the preset Nash equilibrium solution; when the power generation subsystem and the load subsystem are subsystems with a continuously unchanged state, determining whether the third sub-score set corresponding to the energy storage subsystem satisfies the third partial value set corresponding to the preset Nash equilibrium solution.

[0013] In an exemplary embodiment, before determining the first scheme for guiding energy scheduling through the historical operating parameters of the energy system, the above method also includes: obtaining multiple safety limits in the energy system, wherein the multiple safety limits include at least one of the following: a maximum limit of energy balance in the energy system, a minimum limit of energy balance in the energy system, an upper power limit in the energy system, a lower power limit in the energy system, and an energy limit of a heat storage tank in the energy system; and constructing a first target constraint condition based on the multiple safety limits.

[0014] In an exemplary embodiment, after filtering out a target value set that meets a preset value set threshold from multiple value sets and adjusting the first plan according to the target value set, the above method also includes: obtaining the periodic operation results of the second plan after the adjustment of the first plan; when the periodic operation results meet the energy-saving requirements of the energy system, marking the second plan as a commonly used plan; when the periodic operation results do not meet the energy-saving requirements of the energy system, marking the second plan as a suspended plan.

[0015] According to another aspect of an embodiment of the present application, an energy scheduling device is also provided, including: a first determination module, used to determine a first scheme for guiding energy scheduling through historical operating parameters of the energy system, wherein the energy system includes at least: a power generation subsystem, a load subsystem, and an energy storage subsystem; an acquisition module, used to obtain multiple sets of feedback data corresponding to different time nodes in the operating cycle of subsystems other than the power generation subsystem when the first scheme is enabled; an evaluation module, used to perform numerical evaluation of the first scheme through multiple sets of feedback data to obtain multiple value sets; an adjustment module, used to screen out a target value set that meets a preset value set threshold from the multiple value sets, and adjust the first scheme according to the target value set.

[0016] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned energy scheduling strategy adjustment method during operation.

[0017] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the energy scheduling strategy adjustment method through the computer program.

[0018] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and the method for adjusting the energy scheduling strategy when the computer program is executed by a processor.

[0019] Through this application, an initial energy scheduling scheme, referred to as the first scheme, is determined based on the energy system's historical operating parameters, including the power generation of the power generation subsystem, the power demand of the load subsystem, and the charge and discharge status of the energy storage subsystem. During the actual implementation of the first scheme, the system automatically collects operating data from the load and energy storage subsystems. This data reflects the actual effectiveness of the energy scheduling scheme at different time points, including but not limited to actual load consumption, actual charge and discharge of energy storage, and system stability indicators. The collected feedback data is used to evaluate the performance of the first scheme, which typically involves a series of quantitative indicators such as scheduling efficiency, supply-demand matching, or system cost. This evaluation results in a set of values ​​reflecting the scheme's effectiveness. Next, optimization objectives that meet preset thresholds, such as minimum cost or optimal supply-demand balance, are selected from these evaluation results. Based on these optimization objectives, the first scheme is adjusted to better align with actual operating conditions, improving scheduling accuracy and cost-effectiveness. The above technical solution then addresses the problem in related technologies of low scheduling efficiency of energy storage systems, which cannot meet emission reduction requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 This is a hardware structure block diagram of a computer terminal according to an energy scheduling strategy adjustment method of an embodiment of the present application;

[0023] Figure 2 is a flow chart of a method for adjusting an energy scheduling strategy according to an embodiment of the present application;

[0024] Figure 3 is a schematic diagram of a carbon reduction architecture according to an embodiment of the present application;

[0025] Figure 4 This is a structural block diagram of an energy scheduling strategy adjustment device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal, a mobile terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1 This is a hardware structure block diagram of a computer terminal according to an energy scheduling strategy adjustment method of an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or N ( Figure 1Only one is shown) a processor 102 (the processor 102 may include but is not limited to a central processing unit (CPU) or a programmable logic device (FPGA)) and a memory 104 for storing data. The computer terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0029] Memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the method for adjusting monitoring network points in the embodiments of the present application. Processor 102 executes the computer programs stored in memory 104 to execute various functional applications and data processing, thereby implementing the aforementioned methods. Memory 104 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or N magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remotely located from processor 102, and such remote memory may be connected to the computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0030] The transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by a computer terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] In this embodiment, a method for adjusting an energy scheduling strategy is provided. Figure 2 is a flow chart of a method for adjusting an energy scheduling strategy according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps S202-S206:

[0032] Step S202: determining a first plan for guiding energy scheduling based on historical operating parameters of an energy system, wherein the energy system includes at least: a power generation subsystem, a load subsystem, and an energy storage subsystem;

[0033] Step S204: when the first solution is enabled, obtaining multiple sets of feedback data corresponding to different time nodes in the operation cycle of other subsystems except the power generation subsystem;

[0034] Step S206: numerically evaluating the first solution using the multiple sets of feedback data to obtain multiple value sets;

[0035] Step S208: Filtering out a target value set that meets a preset value set threshold from the multiple value sets, and adjusting the first solution according to the target value set.

[0036] Through the above steps, an initial energy scheduling plan, known as the first plan, is determined based on the energy system's historical operating parameters, including the power generation of the power generation subsystem, the power demand of the load subsystem, and the charge and discharge status of the energy storage subsystem. During the implementation of the first plan, the system automatically collects operating data from the load and energy storage subsystems. This data reflects the actual effectiveness of the energy scheduling plan at different time points, including but not limited to actual load consumption, actual charge and discharge status of the energy storage, and system stability indicators. The collected feedback data is used to evaluate the performance of the first plan, which typically involves a series of quantitative indicators such as scheduling efficiency, supply-demand matching, or system cost. This evaluation produces a set of values ​​reflecting the effectiveness of the plan. Next, optimization objectives that meet preset thresholds, such as minimizing cost or balancing supply and demand, are selected from these evaluation results. Based on these optimization objectives, the first plan is adjusted to better align with actual operating conditions, improving scheduling accuracy and cost-effectiveness. This technical solution addresses the problem of low scheduling efficiency of energy storage systems in related technologies, which cannot meet emission reduction requirements.

[0037] In an exemplary embodiment, a first scheme for guiding energy scheduling is determined through historical operating parameters of an energy system, including: determining cost data corresponding to the energy system from the historical operating parameters, wherein the cost data includes at least: transaction cost, electricity purchase cost, operating cost, depreciation cost, and fuel cost; determining a first objective function corresponding to the energy system based on the cost data and a first preset function; and determining the first scheme according to a solution result corresponding to the first objective function when the first objective function satisfies a first objective constraint condition corresponding to the energy system.

[0038] It is understood that cost-related data extracted from the historical operating records of the energy system covers various cost elements in energy dispatch and operation, including but not limited to: Transaction costs: Energy transaction fees within the energy system or with other market participants, such as the cost of purchasing or selling carbon emission allowances in the carbon trading market or the cost of trading green certificates in the green certificate trading market. Power purchase costs: Costs incurred when the energy system needs to purchase electricity from the external grid, which may be affected by fluctuations in electricity prices. Operating costs: Costs incurred during the operation of each subsystem in the energy system (such as the power generation subsystem, load subsystem, and energy storage subsystem), such as equipment operating energy consumption and operation and maintenance personnel salaries. Depreciation costs: The depreciation of energy system equipment over time, which reflects the cost of equipment aging and maintenance. Fuel costs: For power generation equipment using fossil fuels or biomass fuels, the cost of purchasing and consuming fuel is an important consideration. Next, based on the extracted cost data and combined with a preset function (i.e., a first preset function), an objective function is constructed. This first preset function may reflect a specific optimization goal, such as minimizing overall operating costs, maximizing carbon emission reductions, or improving energy efficiency. The construction of the first objective function integrates all the cost data mentioned above to facilitate subsequent optimization calculations.

[0039] After constructing the objective function, a set of objective constraints need to be defined. These constraints ensure that the optimization is carried out within a realistic and feasible range. They may include: Energy balance constraints: ensuring that the supply and demand of the energy system are balanced at each point in time. Equipment operation constraints: for example, the power output of the power generation equipment cannot exceed its rated power, and the charging and discharging status of the energy storage equipment must follow a certain logic. Market trading restrictions: such as restrictions on carbon trading volume or green certificate trading volume. Finally, when the objective function and all constraints are clear, the system will solve the first objective function through numerical optimization methods to find a solution that can achieve the best (usually minimum) objective function value while satisfying all constraints. This step may involve complex mathematical optimization algorithms, such as linear programming, dynamic programming or genetic algorithms, to find the most appropriate scheduling strategy, that is, the first solution. This solution will guide the actual operation of the energy system in order to achieve the pre-set optimization goals.

[0040] In an exemplary embodiment, the first scheme is numerically evaluated using the multiple sets of feedback data to obtain multiple value sets, including: determining the second objective function constructed by the load subsystem and the third objective function constructed by the energy storage subsystem based on the multiple sets of feedback data; solving the second objective function and the third objective function based on multiple second constraints to obtain second solution results and third solution results; and numerically evaluating the first scheme using the second solution results and the third solution results to obtain multiple value sets.

[0041] Simply put, during the implementation of the first solution, the system continuously collects operational feedback data from the load subsystem and energy storage subsystem at different time points. This data may include actual load demand, electricity prices, the charge and discharge status of the energy storage device, and price fluctuations in external markets (such as the power grid). It reflects the performance and effectiveness of the first solution in the actual operating environment. The collected feedback data will be used to construct a new objective function.

[0042] Optionally, the second objective function in the above embodiment is for the load subsystem, and an objective function is constructed based on feedback data. It may reflect the optimization goal of the load subsystem, such as minimizing electricity costs, maximizing user satisfaction, or minimizing carbon emissions. The third objective function is for the energy storage subsystem, and an objective function is constructed. It may take into account the economic benefits (such as charging and discharging benefits) and operating constraints (such as charging and discharging power, state of charge, etc.) of the energy storage equipment.

[0043] Optionally, a set of constraints, known as second constraints, may be set for the second and third objective functions. These constraints may include: load demand constraints: ensuring that the load subsystem has sufficient power supply at every point in time; energy storage device constraints: such as upper and lower limits on state of charge, and limits on charge and discharge power, to ensure the normal operation and long-term benefits of the energy storage device. Next, the system uses an appropriate solution method (possibly linear optimization, dynamic programming, or mixed integer programming) to solve the second and third objective functions, respectively, obtaining second and third solution results. These results reflect the optimal scheduling solution taking into account real-time feedback data and specific constraints. Finally, the second and third solution results are used to numerically evaluate the first solution. This may involve comparing the solution results with the desired target of the first solution, calculating the differences or deviations, and forming multiple evaluation value sets. Based on these evaluation value sets, the system can identify potential shortcomings or optimization opportunities in the first solution and adjust the first solution to bring it closer to the optimal state. For example, if the evaluation finds that the electricity purchase cost resulting from the first option is higher than the solution of the second objective function, or the operating cost of the energy storage equipment does not reach the expected optimization, then the system will adjust the power generation plan, electricity purchase strategy, energy storage scheduling, etc. based on these feedbacks, in order to achieve better economic and environmental benefits in the next scheduling cycle.

[0044] In an exemplary embodiment, before filtering out a target value set that meets a preset value set threshold from the multiple value sets, the above method further includes: filtering the multiple value sets based on a preset Nash equilibrium solution, wherein the preset Nash equilibrium solution includes: a first part of the value set corresponding to the optimal operation of the power generation subsystem, a second part of the value set corresponding to the optimal operation of the load subsystem, and a third part of the value set corresponding to the optimal operation of the energy storage subsystem; when the screening result indicates that there is a value set that meets the Nash equilibrium solution among the multiple value sets, the value set is determined as the target value set to be confirmed; when the screening result indicates that there is no value set that meets the Nash equilibrium solution among the multiple value sets, a prompt message is generated that the target value set does not exist in the energy system.

[0045] It should be noted that before selecting the optimal scheduling solution, a set of Nash equilibrium solutions is pre-determined. These solutions contain the value sets corresponding to the optimal operation of the three subsystems: the first value set (the power generation subsystem), the second value set (the load subsystem), and the third value set (the energy storage subsystem). In the previous step, multiple value sets for the first solution were evaluated using real-time feedback data. Next, these value sets are checked to see if they meet the pre-determined Nash equilibrium criteria. Specifically, the algorithm determines whether these value sets allow each subsystem to achieve or approach its optimal operating state under Nash equilibrium. If at least one of the multiple value sets is found where the values ​​of the power generation subsystem, the load subsystem, and the energy storage subsystem are close to or consistent with the pre-determined first, second, and third value sets, respectively, then this set is marked as the target value set to be confirmed. This means that the scheduling solution under this set is fair and optimal for all subsystems in the game. If no set is found among the multiple value sets that is close to the pre-determined Nash equilibrium solution, the system will generate a prompt message indicating that no scheduling solution has been found that can achieve optimal operation for all subsystems. This means that the first option needs to be adjusted, or that market conditions, system constraints, etc. have changed significantly, making the original Nash equilibrium solution no longer applicable. Once the set of target values ​​to be confirmed is identified, this set will be used to guide the subsequent operation and scheduling of the energy system, because it represents the optimal operating state that each subsystem can achieve under the current market conditions and system constraints. If a value set that meets the Nash equilibrium solution cannot be found, this prompts decision makers to re-evaluate the environment or system parameters. It may be necessary to adjust the first option or update the preset conditions of the Nash equilibrium solution to cope with the changing market and operating conditions, and to ensure the continuous optimization of energy scheduling and the balance of interests of each subsystem.

[0046] In an exemplary embodiment, before screening the multiple value sets based on a preset Nash equilibrium solution, the above method also includes: determining whether there is a subsystem with a continuously unchanged state among the power generation subsystem, the load subsystem, and the energy storage subsystem; when the load subsystem and the energy storage subsystem are subsystems with a continuously unchanged state, determining whether the first sub-score set corresponding to the power generation subsystem satisfies the first partial value set corresponding to the preset Nash equilibrium solution; when the power generation subsystem and the energy storage subsystem are subsystems with a continuously unchanged state, determining whether the second sub-score set corresponding to the load subsystem satisfies the second partial value set corresponding to the preset Nash equilibrium solution; when the power generation subsystem and the load subsystem are subsystems with a continuously unchanged state, determining whether the third sub-score set corresponding to the energy storage subsystem satisfies the third partial value set corresponding to the preset Nash equilibrium solution.

[0047] It is understandable that by checking whether there are subsystems with unchanged states among the power generation subsystem, load subsystem, and energy storage subsystem, the subsystems with changed states are identified as the key adjustment targets. This is because a continuously unchanged state means that a subsystem has not performed any substantial operations or activities during the entire scheduling cycle. For example, the load subsystem has relatively stable demand in certain time periods, or the energy storage subsystem has not performed any charging or discharging operations for a period of time.

[0048] Once the subsystem with a persistent state is identified, the other subsystems can be evaluated to see if they meet the criteria for a Nash equilibrium solution. The specific evaluation is as follows:

[0049] If the load and energy storage subsystems are relatively stable during the dispatch cycle, the focus is on evaluating the performance of the power generation subsystem. At this point, the value set (the first sub-value set) formed by the power generation subsystem's operating data is compared to see if it is consistent with the first sub-value set corresponding to the power generation subsystem in the preset Nash equilibrium solution. This step ensures that the power generation end can maintain optimal operation even when the load and energy storage system states remain unchanged, while also taking into account the overall coordination of the system.

[0050] If the states of the power generation and energy storage subsystems remain unchanged, the focus shifts to the load subsystem. In this case, the value set formed by the load subsystem operating data (the second subset) is compared with the second subset of values ​​corresponding to the load subsystem in the Nash equilibrium solution to confirm whether load management has reached the optimal point.

[0051] If the generation and load subsystems remain unchanged, the evaluation focuses on the energy storage subsystem. The energy storage subsystem's operational data set (the third sub-value set) is checked to see if it satisfies the third sub-value set corresponding to the energy storage subsystem in the Nash equilibrium solution, ensuring that the energy storage equipment can continue to operate effectively and optimally when generation and load demand are stable.

[0052] In summary, through this series of evaluation steps, energy scheduling solutions are meticulously checked and verified under varying subsystem state conditions, ensuring that each subsystem operates within the principles of Nash equilibrium. This approach is particularly applicable to complex systems involving the coordinated operation of multiple entities, such as integrated campus energy systems, where each entity may have different optimal operating states under varying market conditions.

[0053] If, in any case, the subsystem's value set satisfies the corresponding partial value set in the Nash equilibrium solution, then this indicates that the subsystem has achieved optimal operation in the current environment and no further adjustment is required. Conversely, if the value set of a subsystem does not satisfy the corresponding part of the Nash equilibrium solution, this may be due to changes in market conditions, equipment failure, or other unforeseen factors. In this case, the scheduling policy needs to be updated to push the system back towards the Nash equilibrium point, that is, to achieve the common optimal state of all participants under the current conditions.

[0054] In an exemplary embodiment, before determining the first scheme for guiding energy scheduling through the historical operating parameters of the energy system, the above method also includes: obtaining multiple safety limits in the energy system, wherein the multiple safety limits include at least one of the following: a maximum limit of the energy balance in the energy system, a minimum limit of the energy balance in the energy system, an upper power limit in the energy system, a lower power limit in the energy system, and an energy limit of the heat storage tank in the energy system; and constructing a first target constraint condition based on the multiple safety limits.

[0055] In short, before determining the first option based on historical operating parameters, it is necessary to first determine multiple limits related to safe operation in the energy system. These safety limits are crucial parameters in system design and operation, ensuring stable operation under any scheduling scenario and avoiding overload, undersupply, or other situations that could lead to system failure. Safety limits may include: Maximum energy balance limit: This refers to the maximum allowable difference between energy supply and demand within a given timeframe to prevent oversupply or overconsumption. Minimum energy balance limit: Similarly, this refers to the minimum allowable difference between energy supply and demand to ensure that the system can meet basic needs. Upper and lower power limits: These respectively define the maximum and minimum limits on the power output or consumption of each sub-device in the system (e.g., power generation subsystem and energy storage subsystem) to prevent overload or inefficient operation. Energy limits for thermal storage tanks: These set the upper and lower limits on the energy storage capacity of the thermal storage tank (thermal energy storage device) to ensure the safety and efficiency of the thermal energy storage and release processes. Once these safety limits are determined, they are then converted into first objective constraints. Objective constraints are rules used in optimization models to limit the solution space, ensuring that the found solution not only meets the optimization objectives (such as minimizing cost and maximizing energy efficiency) but also does not violate the safe operation criteria of the system.

[0056] Optionally, the first objective constraint may include, but is not limited to: Energy balance constraint: ensuring that the total energy supply and total demand of the system meet the maximum and minimum limits of energy balance at any point in time. Power constraint: stipulating that the power output or consumption of each device in the system must be within their respective upper and lower power limits. Thermal storage tank constraint: requiring that the energy storage level of the thermal storage tank during the scheduling cycle must be maintained within the set energy limit to ensure the safety and effectiveness of thermal energy storage.

[0057] In an exemplary embodiment, after filtering out a target value set that meets a preset value set threshold from the multiple value sets and adjusting the first scheme according to the target value set, the above method further includes: obtaining a periodic operation result of a second scheme after adjustment of the first scheme; if the periodic operation result meets the energy-saving requirement of the energy system, marking the second scheme as a commonly used scheme; if the periodic operation result does not meet the energy-saving requirement of the energy system, marking the second scheme as a suspended scheme.

[0058] Optionally, after a series of analysis and optimization methods (e.g., numerical evaluation based on feedback data, Nash equilibrium solution screening, and solution adjustment), the first solution may need to be modified to better adapt to the actual operation of the system or improve its energy-saving effect. After the first solution is adjusted, a new scheduling solution, namely the second solution, is formed. After the actual implementation of the second solution, there will be a periodic operation process, and the operation data during this cycle will be collected, including but not limited to key indicators such as the actual energy consumption, carbon emissions, and operating costs of the energy system under this solution.

[0059] Optionally, the energy conservation requirements may specify energy conservation and emission reduction targets that the energy system must achieve within a specific timeframe, such as reducing energy consumption by a certain percentage, reducing carbon emissions to a specific level, or achieving a certain energy utilization rate. The periodic operation result evaluation primarily compares the periodic operation results of the second scenario with the preset energy conservation requirements to verify whether the scenario's actual performance meets these energy conservation targets.

[0060] Based on the comparison between the cycle operation results and the energy-saving requirements, the second option is marked to determine the subsequent usage strategy: If the cycle operation results show that the second option has successfully achieved the predetermined energy-saving target, then the second option will be marked as the "common option". This means that the option is considered effective and will be given priority for use under similar conditions in the future, which will help to continuously optimize the operating efficiency and economy of the energy system. On the contrary, if the cycle operation results fail to meet the energy-saving requirements, the second option will be marked as a "suspended option". This mark indicates that the option may not be the best choice under the current conditions and needs to be temporarily shelved, either to be re-evaluated and adjusted, or to find other more effective scheduling options as an alternative.

[0061] Through the above implementation, the energy scheduling plan is optimized and iteratively improved in a closed loop. By continuously monitoring the plan's performance in actual operation and comparing it with energy conservation requirements, shortcomings can be promptly identified and appropriate adjustments can be made. This feedback mechanism based on actual operational results ensures the continuous optimization of the energy scheduling plan and promotes the stable and efficient operation of the energy system while meeting energy conservation goals.

[0062] Obviously, the embodiments described above are only part of the embodiments of the present application, rather than all the embodiments. In order to better understand the method, the above process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application. Specifically:

[0063] An optional embodiment of the present application provides a master-slave game-robust optimization scheduling method for a campus integrated energy system involving multi-scenario coordinated carbon reduction. By introducing a carbon-green certificate trading mechanism, a multi-dimensional flexible load regulation mechanism, and multi-scenario application of energy storage, based on a master-slave game optimization framework, an integrated energy system optimization scheduling model is constructed that takes into account the economy of the energy storage system and the uncertainty of renewable energy.

[0064] Optionally, the above-mentioned integrated energy system of the park includes new energy power generation (wind power and photovoltaics), gas turbines, gas boilers, heat storage tanks and electric-thermal flexible loads (including shiftable loads, transferable loads and curtailable loads), and achieves energy balance and load demand satisfaction through the orderly charging and discharging of energy storage equipment and interaction with the electricity market.

[0065] Optional, Figure 3 This is a schematic diagram of a carbon reduction architecture according to an embodiment of the present application. The multi-scenario coordinated carbon reduction scheduling strategy includes at least the following:

[0066] The first is an integrated energy system architecture that utilizes carbon and green certificate trading. Building on the traditional integrated energy system, this system introduces a combined carbon and green certificate trading mechanism to achieve low-carbon economic operation of the electricity and heat integrated energy system. Energy, information, and market interactions create a collaborative optimization mechanism among various energy devices and market players, including renewable energy generation, energy storage equipment, flexible loads, gas turbines, and gas boilers.

[0067] The second type involves a multi-scenario coordinated carbon reduction mechanism. Based on a coupled carbon-green certificate market, this multi-scenario coordinated carbon reduction strategy across power generation, load, and energy storage achieves renewable energy consumption and load optimization, improving the economic efficiency of energy storage systems. This strategy encompasses three application scenarios: renewable energy consumption, the reserve market, and the energy market. This multi-scenario coordinated carbon reduction mechanism leverages the coupled carbon-green certificate market. On the power generation side, the rational allocation of carbon allowances and green certificates increases renewable energy utilization and reduces reliance on fossil fuels. On the load side, flexible load regulation is combined with demand response mechanisms. By shifting, transferring, and reducing electricity consumption, the system effectively reduces pressure during peak load periods, achieving load shaving and valley filling. Energy storage, through flexible scheduling of charging and discharging processes, coordinates with flexible loads in three scenarios: renewable energy consumption (Scenario 1), the energy market (Scenario 2), and the reserve market (Scenario 3).

[0068] Optionally, the baseline method is used to determine the initial carbon quota and a stepped carbon trading price model is constructed to achieve effective control of carbon emissions and improve economic efficiency. It should be noted that carbon emission trading is a mechanism that supports the achievement of emission reduction targets through market-based means, and the regulatory agency is responsible for allocating carbon quotas to various participants in the market. The baseline method is used to determine the initial carbon quota, and its model expression is: R = R GT +R GB +R buy ; Where: R is the total system carbon quota; R GT The carbon quota required by GT for the carbon emission of the turbine; R GB The carbon quota required to allocate GB for the carbon emissions of gas boilers; R buy The carbon quota required to purchase electricity from the upstream grid. Where: h is the emission quota per unit thermal power; γ h,e The efficiency of the conversion between GT electricity and heat energy to allocate carbon emissions to the turbine; The electric power output by GT during period t, unit: Kw; is the thermal power output by GT during period t, in kW. Where: The thermal power provided by GB during period t, unit: kW. Where: e The emission quota for generating unit electric power; The amount of electricity purchased from the superior power grid during period t, unit: kW.

[0069] The third type is the green certificate trading model: Based on policy requirements, the proportion of different types of renewable energy in the overall energy supply or the power generation is stipulated, and a green certificate trading model is constructed to promote the use of renewable energy.

[0070]

[0071] Where: R res The daily electricity generation quota of renewable energy; R q The actual number of green certificates obtained by renewable energy, unit: piece; is the load demand, unit: kW; γ res is the renewable energy power generation quota coefficient; C GCT is the transaction cost of green certificates, unit: yuan; β GCT The price of green certificate transaction, unit: Yuan.

[0072] Optionally, each market entity model includes:

[0073] Model 1: Integrated energy system optimization scheduling model:

[0074] Optionally, the daily comprehensive cost C of the park's integrated energy system optimization scheduling model includes green certificate transaction costs, carbon transaction costs, electricity purchase costs, new energy operation costs, new energy equipment operation and maintenance costs, new energy equipment depreciation costs, thermal storage tank depreciation costs, and gas boiler fuel costs. The cost function of the park's integrated energy system is shown below:

[0075] C=C GCT +C CT +C buy +C GB +C HS +

[0076] C NE +C OM +C DP .

[0077] Where: C is the total cost, unit: yuan; C buy is the energy purchase cost, unit: yuan; C GB is the fuel cost of the gas boiler, unit: yuan; C HS is the depreciation cost of the heat storage tank, unit: yuan; C NE is the operating cost of new energy, unit: yuan; C OM is the maintenance cost of new energy equipment, unit: yuan; C DP is the depreciation cost of new energy equipment, unit: Yuan.

[0078] Optionally, the constraints of the park integrated energy system optimization scheduling model include energy balance constraints, power upper and lower limit constraints, and heat storage tank constraints, as follows:

[0079] (1) Energy balance constraints. The balance of electrical power and thermal power in the park's integrated energy system must meet the following constraints:

[0080]

[0081] In the above formula: is the electric load demand during period t, unit: KW; is the heat load demand during period t, in kW.

[0082] (2) Power upper and lower limit constraints.

[0083] Optionally, the upper and lower limits of electric power include renewable energy output constraints, grid power purchase constraints, and gas turbine power constraints, as shown in the following formula:

[0084]

[0085] Where: P w,max The upper limit of wind turbine output, unit: KW; P w,min The lower limit of wind turbine output, unit: KW; P pv,max is the upper limit of photovoltaic output, unit: kW; P pv,min The lower limit of photovoltaic output, unit: KW; P buy,max The maximum power purchased from the power grid, unit: KW; P GT,max is the rated power of the gas turbine, unit: kW.

[0086] Optionally, the upper and lower thermal power constraints include the power constraints of the heat recovery system, gas boiler, and heat storage tank, as shown in the following formula:

[0087]

[0088] Where: P GB,max is the rated output thermal power of the gas boiler, unit: kW; P HT,max is the rated output thermal power of the heat recovery system, unit: KW; P HS,max The maximum power of the heat storage tank to absorb heat, unit: KW; P HS,min The maximum power of heat storage tank to release heat, unit: KW.

[0089] (3) Heat storage tank constraints. Since the heat storage tank cannot absorb and release heat at the same time in the same scheduling period, in order to ensure that only one heat absorption and release state occurs in the period, the heat storage tank's heat absorption and release state needs to be constrained accordingly:

[0090]

[0091] Where: ω e ω is the variable of the heat storage tank's heat release state, 0 means the heat storage tank is not releasing heat, and 1 means the heat storage tank is releasing heat; a A variable indicating the heat absorbing state of the heat storage tank. 0 indicates that the heat storage tank is not absorbing heat, and 1 indicates that the heat storage tank is absorbing heat.

[0092] Optionally, to ensure that the heat storage tank has sufficient heat to participate in the optimal scheduling in the next scheduling cycle, the energy state of the heat storage tank is required to be consistent at the beginning and end of the scheduling cycle, as shown in the following formula:

[0093] H0=H T .

[0094] Where: H0 is the heat of the heat storage tank in the initial state; H T The heat of the heat storage tank in the final state.

[0095] Model 2: Energy storage multi-application scenario model:

[0096] Optionally, the revenue from energy storage equipment is mainly composed of the revenue from absorbing new energy, the revenue from the energy market, and the revenue from the reserve market, while also taking into account the operating costs of the energy storage power station, as shown in the following formula:

[0097]

[0098] Where: E con,t E is the income from consuming new energy in period t, unit: yuan; em,t E is the energy market income in period t, unit: yuan; rm,t is the reserve market income in period t, unit: yuan.

[0099] Optionally, the energy storage device's revenue from absorbing new energy is as follows:

[0100]

[0101] Where: θ wind is the incentive coefficient for absorbing wind power output; θ pv The incentive coefficient for absorbing photovoltaic output power; is the wind power absorbed by the energy storage during period t, unit: kW; It is the photovoltaic power consumed by the energy storage during the period t, unit: kW.

[0102] Alternatively, the energy market revenue of the energy storage device is as follows:

[0103] E em,t =L e,t P e,t .

[0104] Where: P e,t is the energy storage capacity participating in the energy market during period t, unit: kW; L e,t is the energy market price during period t, unit: yuan.

[0105] Optionally, the operating cost of the energy storage power station is considered, as shown in the following formula:

[0106]

[0107] Where: SES is the unit operating cost of the energy storage power station, unit: yuan; P c,t is the charging power of the energy storage station during period t, unit: KW; P d,t is the discharge power of the energy storage power station in period t, unit: kW.

[0108] Optionally, the constraints of the energy storage multi-application scenario model include state of charge constraints and energy storage power constraints, as follows:

[0109] (1) State of charge constraint. The state of charge (SOC) refers to the ratio of the remaining capacity of the energy storage device at that moment to the rated capacity of the energy storage device. In order to ensure that the energy storage device can provide sufficient charge and discharge capacity to participate in the application scenario in the next scheduling cycle, it is necessary to ensure that the SOC of the energy storage device remains consistent at the beginning and end of a scheduling cycle, as shown in the following formula:

[0110] S T =S1.

[0111] Where: S1 is the initial state of charge of the energy storage within a scheduling cycle; S T It is the final state of charge of the energy storage within a scheduling cycle.

[0112] Optionally, the energy storage system needs to consider the remaining power during charging and discharging operations, so the SOC of the energy storage is constrained accordingly, as shown in the following formula:

[0113]

[0114] S min ≤S t ≤S max .

[0115] Where: S t is the state of charge during the energy storage period t; η ch is the charging efficiency of the energy storage system; η dis is the discharge efficiency of the energy storage system; S min is the upper limit of the SOC of the energy storage system; S max It is the lower limit of the SOC of the energy storage system.

[0116] (2) Energy storage power constraint. To ensure that the energy storage system does not charge and discharge simultaneously in each period of the scheduling cycle, and that the power in each period is within the energy storage charge and discharge power constraint, its charge and discharge state and power are constrained as shown in the following formula:

[0117]

[0118] Where: is the charging state variable in period t. When the variable is 0, it means that the energy storage is not charging, and when the variable is 1, it means that the energy storage is charging. c,max is the maximum charging power, unit: KW; P d,max is the maximum discharge power, unit: KW; is the discharge state variable of time period t. When the variable is 0, it means that the energy storage does not perform discharge action at time t. When the variable is 1, it means that discharge action is performed.

[0119]

[0120] Where: is the minimum power of the energy storage system, unit: KW; The maximum power of the energy storage system, unit: kW.

[0121] Model 3: Electricity and heating flexible load demand response model:

[0122] According to different ways of load demand response optimization, the load types in the integrated energy system are divided into four categories: basic load, shiftable load, transferable load and curtailable load, and corresponding models and constraints are established for each category, as follows:

[0123] (1) Shiftable load. By setting the shift interval, the shiftable load can shift the load across multiple time periods. Assume that the shiftable interval of the load in the scheduling period is The translation duration is t e,r , the set of shiftable starting periods is:

[0124]

[0125] The compensation cost of the shiftable electric load is:

[0126]

[0127] Where: is the translational electric power within the translational range, unit: KW; μ e,sf is the subsidy coefficient for the portable electric load.

[0128] Optional, shiftable heat load refers to the overall heat load that can be reasonably adjusted within a certain period of time while ensuring the user's heat experience. If the shiftable range of heat load is The duration of translation is t h,r , then the set of shifted starting periods is:

[0129]

[0130] The compensation cost of the shiftable heat load is:

[0131]

[0132] Where: μ h,sf is the subsidy coefficient for the movable heat load; It is the translational heat load power within the translational range, unit: kW.

[0133] (2) Transferable load. Transferable load can be flexibly adjusted in each period of the cycle under the premise of ensuring that the load demand is met within the scheduling cycle. Due to the special characteristics of the user's heating demand, transferable heat load is not considered. The transferable electric load range within the cycle is defined as Constrain the minimum continuous operation time and transfer power of the equipment to solve the problem of frequent start and stop of the equipment. The specific constraint conditions are shown in the following formula:

[0134]

[0135] Where: B tr is a binary variable used to represent the transferable load status; The minimum time for continuous operation.

[0136]

[0137] Where: P tr,max The upper limit of the transferable electric load power, unit: KW; P tr,min It is the lower limit of the transferable electric load power, unit: kW.

[0138] The compensation cost of the transferable electric load is:

[0139]

[0140] Where: μ e,tr is the subsidy coefficient for transferable electric load.

[0141] Optionally, the construction of a multi-scenario collaborative optimization scheduling model based on master-slave game-robust optimization includes the construction of an upper-layer robust optimization model taking uncertainty into account and the construction of a lower-layer follower optimization model, as follows:

[0142] (1) Construction of an upper-level robust optimization model taking uncertainty into account. The integrated energy system operator is the leader of the master-slave game. Based on the day-ahead forecast of load and renewable energy, the objective function is to minimize system cost and provide a reasonable optimized electricity price. A two-stage robust optimization model is constructed that takes into account the uncertainty of wind power and photovoltaic output. The upper-level leader objective function can be expressed as:

[0143] minC=C GCT +C CT +C buy +C GB +C HS +

[0144] C NE +C OM +C DP .

[0145] It should be noted that due to the large volatility of renewable power output, this characteristic will have a significant impact on the economy and low-carbon operation of the park's integrated energy system.

[0146] (2) The construction of the lower-level follower optimization model uses energy storage operators and load aggregators as followers to adjust charging and discharging and demand response strategies.

[0147] Optionally, after receiving the optimized electricity price, the energy storage operator determines the charge and discharge state and power based on the cooperative model under multiple scenarios and constraints such as energy storage capacity and charge and discharge constraints. The lower-level energy storage operator objective function can be expressed as:

[0148] max(E SE -C SES ).

[0149] Optionally, load aggregators can respond to reasonable electricity consumption behavior by minimizing compensation costs based on real-time electricity prices and power output on the generation side. In a master-slave system, system operators can reduce system carbon emissions while increasing operating profits by regulating and purchasing electricity from the grid, gas turbine power, and real-time electricity prices. The objective function of the load aggregator at the lower level can be expressed as:

[0150] minC FL =C e,sf +C e,tr +C e,cut .

[0151] Optionally, energy storage operators and load aggregators can participate in a master-slave strategy, adjusting charging, discharging, and demand response strategies based on real-time electricity prices to maximize profitability.

[0152] Optionally, the game strategy set of the master-slave game is The Nash equilibrium solution of the master-slave model is the optimal decision-making solution that maximizes the interests of all parties. In other words, in the equilibrium state, no party can unilaterally change its strategy to gain profit. It is the Nash equilibrium solution of the master-slave game and satisfies the following conditions:

[0153]

[0154] Optionally, an improved Grey Wolf Optimizer (IGWO) is used to solve the upper robust optimization model of the master-slave game model, and a Commercial Programming Language Execution (CPLEX) solver is used to solve the lower problem.

[0155] In summary, the optional embodiments of this application analyze the coupling relationship between multiple stakeholders in the carbon trading and green certificate markets, develop a scheduling strategy for coordinated carbon reduction in multiple scenarios, fully leverage the regulatory potential of energy storage, and achieve low-carbon economic operation of the system. Furthermore, based on the master-slave game-robust optimization scheduling model, a master-slave game model is constructed with the integrated energy system operator as the leader and the load aggregator and energy storage operator as followers. This model depicts the competitive and cooperative relationships among multiple stakeholders and balances their interests. Furthermore, considering the uncertainty of renewable energy output, a two-stage robust optimization model is constructed to enhance the adaptability of the optimized scheduling scheme and ensure the stability and practical feasibility of the optimization results. Finally, an improved gray wolf algorithm is employed, which uses the Tent chaos map to generate the initial population and introduces a nonlinear convergence factor to improve the algorithm's global search capability and solution efficiency, effectively solving the robust optimization model above the master-slave game model. This fully taps the regulatory potential of the energy storage system, achieves multi-stakeholder interest coordination through a master-slave game framework, and achieves coordinated carbon reduction in multiple scenarios under the carbon-green certificate trading mechanism.

[0156] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0157] This embodiment also provides an energy scheduling strategy adjustment device for implementing the above-mentioned embodiments and preferred implementations. Details already described are omitted for clarity. As used below, the term "module" refers to a combination of software and / or hardware that implements a predetermined function. While the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0158] Figure 4 : is a structural block diagram of an energy scheduling strategy adjustment device according to an embodiment of the present application, the device comprising:

[0159] A first determining module 42 is configured to determine a first solution for guiding energy scheduling based on historical operating parameters of an energy system, wherein the energy system includes at least: a power generation subsystem, a load subsystem, and an energy storage subsystem;

[0160] An acquisition module 44 is configured to acquire, when the first solution is enabled, multiple sets of feedback data corresponding to different time nodes within an operation cycle of subsystems other than the power generation subsystem;

[0161] An evaluation module 46 is configured to perform a numerical evaluation on the first solution using the multiple sets of feedback data to obtain multiple value sets;

[0162] The adjustment module 48 is configured to select a target value set that satisfies a preset value set threshold from the multiple value sets, and adjust the first solution according to the target value set.

[0163] The above-mentioned device determines an initial energy scheduling plan, known as the first plan, based on the energy system's historical operating parameters, including the power generation of the power generation subsystem, the power demand of the load subsystem, and the charge and discharge status of the energy storage subsystem. During the execution of the first plan, the system automatically collects operating data from the load and energy storage subsystems. This data reflects the actual effectiveness of the energy scheduling plan at different time points, including but not limited to actual load consumption, actual charge and discharge of the energy storage, and system stability indicators. The collected feedback data is used to evaluate the performance of the first plan, which typically involves a series of quantitative indicators such as scheduling efficiency, supply-demand matching, or system cost. This evaluation yields a set of values ​​reflecting the effectiveness of the plan. Next, from these evaluation results, optimization objectives that meet preset thresholds, such as minimizing cost or balancing supply and demand, are selected. Based on these optimization objectives, the first plan is adjusted to better align with actual operating conditions, improving scheduling accuracy and cost-effectiveness. This technical solution addresses the problem of low scheduling efficiency of energy storage systems in related technologies, which cannot meet emission reduction requirements.

[0164] In an exemplary embodiment, the above-mentioned first determination module is also used to determine the cost data corresponding to the energy system from the historical operating parameters, wherein the cost data includes at least: transaction cost, electricity purchase cost, operating cost, depreciation cost, and fuel cost; determine the first objective function corresponding to the energy system based on the cost data and a first preset function; and determine the first solution according to the solution result corresponding to the first objective function when the first objective function satisfies the first objective constraint condition corresponding to the energy system.

[0165] In an exemplary embodiment, the above-mentioned evaluation module is also used to determine the second objective function constructed by the load subsystem and the third objective function constructed by the energy storage subsystem based on the multiple sets of feedback data; solve the second objective function and the third objective function based on multiple second constraints to obtain second solution results and third solution results; and numerically evaluate the first solution through the second solution results and the third solution results to obtain multiple value sets.

[0166] In an exemplary embodiment, the above-mentioned device also includes: a screening module, which is used to screen the multiple value sets based on a preset Nash equilibrium solution before screening out the target value set that meets the preset value set threshold from the multiple value sets, wherein the preset Nash equilibrium solution includes: a first part of the value set corresponding to the optimal operation of the power generation subsystem, a second part of the value set corresponding to the optimal operation of the load subsystem, and a third part of the value set corresponding to the optimal operation of the energy storage subsystem; when the screening result indicates that there is a value set that meets the Nash equilibrium solution among the multiple value sets, the value set is determined as the target value set to be confirmed; when the screening result indicates that there is no value set that meets the Nash equilibrium solution among the multiple value sets, a prompt message is generated that the target value set does not exist in the energy system.

[0167] In an exemplary embodiment, the above-mentioned device also includes: a second determination module, which is used to determine whether there is a subsystem with a continuously unchanged state in the power generation subsystem, load subsystem, and energy storage subsystem before screening the multiple value sets based on the preset Nash equilibrium solution; when the load subsystem and the energy storage subsystem are subsystems with a continuously unchanged state, determine whether the first sub-score set corresponding to the power generation subsystem satisfies the first partial value set corresponding to the preset Nash equilibrium solution; when the power generation subsystem and the energy storage subsystem are subsystems with a continuously unchanged state, determine whether the second sub-score set corresponding to the load subsystem satisfies the second partial value set corresponding to the preset Nash equilibrium solution; when the power generation subsystem and the load subsystem are subsystems with a continuously unchanged state, determine whether the third sub-score set corresponding to the energy storage subsystem satisfies the third partial value set corresponding to the preset Nash equilibrium solution.

[0168] In an exemplary embodiment, the above-mentioned device also includes: a construction module for obtaining multiple safety limits in the energy system before determining the first scheme for guiding energy scheduling through the historical operating parameters of the energy system, wherein the multiple safety limits include at least one of the following: the maximum limit of the energy balance in the energy system, the minimum limit of the energy balance in the energy system, the upper power limit in the energy system, the lower power limit in the energy system, and the energy limit of the heat storage tank in the energy system; and constructing the first target constraint condition based on the multiple safety limits.

[0169] In an exemplary embodiment, the above-mentioned device also includes: an identification module, which is used to filter out a target value set that meets the preset value set threshold from the multiple value sets, and after adjusting the first plan according to the target value set, obtain the periodic operation result of the second plan after the adjustment of the first plan; when the periodic operation result meets the energy-saving requirements of the energy system, the second plan is identified as a commonly used plan; when the periodic operation result does not meet the energy-saving requirements of the energy system, the second plan is identified as a suspended plan.

[0170] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any of the above method embodiments when run.

[0171] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0172] S1. Determining a first scheme for guiding energy scheduling based on historical operating parameters of an energy system, wherein the energy system includes at least: a power generation subsystem, a load subsystem, and an energy storage subsystem;

[0173] S2. When the first solution is enabled, obtaining multiple sets of feedback data corresponding to different time nodes within the operation cycle of subsystems other than the power generation subsystem;

[0174] S3. Performing numerical evaluation on the first solution using the multiple sets of feedback data to obtain multiple value sets;

[0175] S4. Filter out a target value set that meets a preset value set threshold from the multiple value sets, and adjust the first solution according to the target value set.

[0176] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0177] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0178] An embodiment of the present application further provides a computer program product, including a computer program, and the computer program performs the steps of any of the above method embodiments when executed by a processor.

[0179] An embodiment of the present application further provides another computer program product, comprising a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above method embodiments are implemented.

[0180] An embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0181] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0182] S1. Determining a first scheme for guiding energy scheduling based on historical operating parameters of an energy system, wherein the energy system includes at least: a power generation subsystem, a load subsystem, and an energy storage subsystem;

[0183] S2. When the first solution is enabled, obtaining multiple sets of feedback data corresponding to different time nodes within the operation cycle of subsystems other than the power generation subsystem;

[0184] S3. Performing numerical evaluation on the first solution using the multiple sets of feedback data to obtain multiple value sets;

[0185] S4. Filter out a target value set that meets a preset value set threshold from the multiple value sets, and adjust the first solution according to the target value set.

[0186] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0187] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0188] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices, they can be implemented using program code executable by the computing device, and thus, they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be performed in a different order than herein, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0189] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for adjusting an energy scheduling strategy, characterized in that: include: Determining a first plan for guiding energy scheduling based on historical operating parameters of an energy system, wherein the energy system includes at least: a power generation subsystem, a load subsystem, and an energy storage subsystem; When the first solution is enabled, multiple sets of feedback data corresponding to different time nodes in the operation cycle of subsystems other than the power generation subsystem are obtained; Performing numerical evaluation on the first solution using the multiple sets of feedback data to obtain multiple value sets; A target value set that meets a preset value set threshold is screened out from the multiple value sets, and the first solution is adjusted according to the target value set.

2. The energy scheduling strategy adjustment method according to claim 1, characterized in that: A first plan for guiding energy dispatch is determined based on historical operating parameters of the energy system, including: Determining cost data corresponding to the energy system from the historical operating parameters, wherein the cost data includes at least: transaction cost, electricity purchase cost, operating cost, depreciation cost, and fuel cost; Determining a first objective function corresponding to the energy system based on the cost data and a first preset function; In the case where the first objective function satisfies a first objective constraint condition corresponding to the energy system, the first solution is determined according to a solution result corresponding to the first objective function.

3. The energy scheduling strategy adjustment method according to claim 1, characterized in that: Numerical evaluation is performed on the first solution using the multiple sets of feedback data to obtain multiple value sets, including: Determine a second objective function constructed by the load subsystem and a third objective function constructed by the energy storage subsystem according to the multiple sets of feedback data; Solving the second objective function and the third objective function based on the plurality of second constraints to obtain a second solution result and a third solution result; The first solution is numerically evaluated using the second solution result and the third solution result to obtain multiple value sets.

4. The energy scheduling strategy adjustment method according to claim 1, characterized in that: Before selecting a target value set that satisfies a preset value set threshold from the multiple value sets, the method further includes: The multiple value sets are screened based on a preset Nash equilibrium solution, wherein the preset Nash equilibrium solution includes: a first value set corresponding to the optimal operation of the power generation subsystem, a second value set corresponding to the optimal operation of the load subsystem, and a third value set corresponding to the optimal operation of the energy storage subsystem; If the screening result indicates that there is a value set that satisfies the Nash equilibrium solution among the multiple value sets, determining the value set as the target value set to be confirmed; When the screening result indicates that there is no value set satisfying the Nash equilibrium solution among the multiple value sets, prompt information is generated indicating that there is no target value set for the energy system.

5. The energy scheduling strategy adjustment method according to claim 4, characterized in that: Before screening the multiple value sets based on a preset Nash equilibrium solution, the method further includes: Determine whether there is a subsystem with a persistent state among the power generation subsystem, load subsystem, and energy storage subsystem; In a case where the load subsystem and the energy storage subsystem are subsystems with persistent states, determining whether the first sub-value set corresponding to the power generation subsystem satisfies the first partial value set corresponding to the preset Nash equilibrium solution; In a case where the power generation subsystem and the energy storage subsystem are subsystems with a persistent state, determining whether the second sub-value set corresponding to the load subsystem satisfies the corresponding second partial value set in the preset Nash equilibrium solution; In the case where the power generation subsystem and the load subsystem are subsystems with a persistent state, it is determined whether the third sub-value set corresponding to the energy storage subsystem satisfies the corresponding third partial value set in the preset Nash equilibrium solution.

6. The energy scheduling strategy adjustment method according to claim 1, characterized in that: Before determining the first plan for guiding energy scheduling based on historical operating parameters of the energy system, the method further includes: obtaining a plurality of safety limits in the energy system, wherein the plurality of safety limits include at least one of the following: a maximum limit of an energy balance in the energy system, a minimum limit of an energy balance in the energy system, an upper power limit in the energy system, a lower power limit in the energy system, and an energy limit of a heat storage tank in the energy system; A first target constraint condition is constructed based on the plurality of safety limits.

7. The energy scheduling strategy adjustment method according to claim 1, characterized in that: After selecting a target value set that meets a preset value set threshold from the multiple value sets and adjusting the first solution according to the target value set, the method further includes: Obtaining a periodic operation result of the second plan after adjustment of the first plan; In the case where the periodic operation result meets the energy-saving requirement of the energy system, marking the second solution as a common solution; In a case where the periodic operation result does not meet the energy-saving requirement of the energy system, the second solution is marked as a suspended use solution.

8. An energy scheduling strategy adjustment device, characterized in that: include: A first determining module is configured to determine a first scheme for guiding energy scheduling based on historical operating parameters of an energy system, wherein the energy system includes at least: a power generation subsystem, a load subsystem, and an energy storage subsystem; an acquisition module, configured to acquire, when the first solution is enabled, multiple sets of feedback data corresponding to different time nodes within an operation cycle of subsystems other than the power generation subsystem; an evaluation module, configured to perform a numerical evaluation on the first solution using the multiple sets of feedback data to obtain multiple value sets; The adjustment module is configured to select a target value set that satisfies a preset value set threshold from the multiple value sets, and adjust the first solution according to the target value set.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images