Scheduling method of distributed multi-agent power system based on computerized collaboration

Abstract

The invention relates to a scheduling method and device of a distributed multi-agent power system based on compute cooperation, computer equipment, a storage medium and a computer program product. The method comprises the following steps: determining an operation cost model and an operation cost model constraint condition for each distributed multi-agent; according to the operation cost model of each distributed multi-agent and the constraint condition of the operation cost model, constructing a power dispatching optimization model for the distributed multi-agent power system; the power dispatching optimization model takes the minimization of the total operation cost of the distributed multi-agent power system as a solving target and takes the balance of power supply and demand as a constraint condition; solving the power dispatching optimization model by adopting a diffusion strategy to obtain a power dispatching strategy for the distributed multi-agent power system; the power dispatching strategy is used for carrying out power dispatching on each distributed intelligent agent. By adopting the method, power dispatching can be efficiently carried out on the distributed multi-agent power system.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a dispatching method, apparatus, computer equipment, storage medium and computer program product for a distributed multi-agent power system based on computer collaboration. Background Art

[0002] As the scale of grid-connected network elements continues to expand, the newly added installed capacity of network elements has exceeded the newly added installed capacity of traditional power generation.

[0003] Large-scale photovoltaic power plants are typically built in remote areas, while small-scale photovoltaic systems can be installed on any available rooftop in residential areas, maximizing the utilization of solar resources. However, as the number of network elements increases, the complexity of the power grid also increases. Traditional centralized power dispatch methods for power systems typically require a dispatch center and need to process large amounts of data, which requires high computing power from data processors. Centralized power dispatch methods have low scalability, flexibility, and reliability.

[0004] Therefore, there is a problem in traditional technologies that the power dispatching of the power system is not efficient enough. Summary of the Invention

[0005] Based on this, it is necessary to provide a scheduling method, device, computer equipment, computer-readable storage medium and computer program product for a distributed multi-agent power system based on computer collaboration that can efficiently perform power scheduling in response to the above technical problems.

[0006] A dispatching method for a distributed multi-agent power system based on computer collaboration is applied to a distributed multi-agent power system including a plurality of distributed agents. The method comprises:

[0007] Determine the operating cost model and operating cost model constraints for each distributed intelligent agent;

[0008] Based on the operating cost model and operating cost model constraints of each distributed agent, a power dispatch optimization model for the distributed multi-agent power system is constructed. The power dispatch optimization model takes minimizing the total operating cost of the distributed multi-agent power system as the solution objective and the balance of power supply and demand as the constraint condition.

[0009] The diffusion strategy is used to solve the power dispatch optimization model and obtain the power dispatch strategy for the distributed multi-agent power system; the power dispatch strategy is used to perform power dispatch on each distributed agent.

[0010] In an exemplary embodiment, a power dispatch optimization model for a distributed multi-agent power system is constructed based on the operating cost model and operating cost model constraints of each distributed multi-agent, including:

[0011] Obtain the weight coefficient of the operating cost model for each distributed intelligent agent;

[0012] According to the operating cost model and operating cost model weight coefficient of each distributed intelligent body, the solution target of the power dispatch optimization model is determined.

[0013] In an exemplary embodiment, a diffusion strategy is used to solve a power dispatch optimization model to obtain a power dispatch strategy for a distributed multi-agent power system, including:

[0014] Determine the combined state update rules corresponding to the combination step and the local state update rules corresponding to the adaptation step in the diffusion strategy; the combined state update rules corresponding to the combination step are used to determine the information fusion method between distributed intelligent agents; the local state update rules corresponding to the adaptation step are used to determine the self-optimization method of any distributed intelligent agent;

[0015] Based on the combined state update rules corresponding to the combination step and the local state update rules corresponding to the adaptation step, the power dispatch optimization model is iteratively solved to obtain the output power information of each distributed intelligent agent when the total operating cost is minimized;

[0016] Based on the output power information of each distributed intelligent agent when the total operating cost is minimized, a power dispatching strategy is generated.

[0017] In an exemplary embodiment, the method further comprises:

[0018] According to the power dispatching strategy, the distributed multi-agent power system is dispatched and the system status information of the distributed multi-agent power system is obtained;

[0019] The diffusion strategy is adopted to re-solve the power dispatch optimization model based on the system status information to obtain a new power dispatch strategy for the distributed multi-agent power system; the new power dispatch strategy is used to perform a new round of power dispatch for each distributed agent.

[0020] In an exemplary embodiment, the distributed intelligent body includes a photovoltaic power generation system, an energy storage system, and a flexible load; wherein the photovoltaic power generation system adopts a maximum power point tracking control strategy to adjust the output voltage or output current.

[0021] In an exemplary embodiment, the photovoltaic power generation system The operating cost model of a generator set is expressed as: , Indicates the The output power of the generator set, For the The operating cost of a generator set, Respectively The quadratic term coefficient, linear term coefficient and constant term coefficient of the operating cost model of the generator set are used to describe the The relationship between the output power of each generator set and its operating cost;

[0022] No. The operating cost model constraints for each generator set include The output power constraints and power variation constraints of the generator sets; The output power constraint of each generator set is expressed as: , and Respectively represent The minimum and maximum output power allowed for each generator set; the power variation constraint is expressed as: , Indicates the The output power change of each generator set per unit time, Indicates the The minimum output power change of a generator set per unit time, Indicates the The maximum output power change of each generator set per unit time;

[0023] Energy storage system The operating cost model of an energy storage device is expressed as: , Indicates the The actual output power of each energy storage device during operation is For the The operating cost of an energy storage device, Respectively The cubic coefficient, quadratic coefficient and linear coefficient of the operating cost model of the energy storage device are used to describe the The nonlinear relationship between the output power and operating cost of each energy storage device;

[0024] No. The operating cost model constraints for each energy storage device include The output power constraint and remaining power constraint of the energy storage device; The output power constraint of each energy storage device is expressed as: , Respectively represent The minimum output power and maximum output power of the energy storage device; The remaining capacity constraint of each energy storage device is expressed as: , represents the remaining capacity of the i-th energy storage device, represents the minimum remaining capacity of the i-th energy storage device, represents the maximum remaining capacity of the i-th energy storage device;

[0025] The operating cost model of flexible load is expressed as: , Indicates the The operating cost of a flexible load, Indicates the The output power of a flexible load, Respectively The coefficients of the operating cost model for each flexible load;

[0026] No. The constraints of the operating cost model for each flexible load include The output power constraint condition of the flexible load; The output power constraint of a flexible load is expressed as: , Indicates the The minimum output power of a flexible load, Indicates the The maximum output power of a flexible load.

[0027] A dispatching device for a distributed multi-agent power system based on computer collaboration is applied to a distributed multi-agent power system. The distributed multi-agent power system includes multiple distributed agents. The device includes:

[0028] A determination module, used to determine the operating cost model and operating cost model constraints for each distributed intelligent agent;

[0029] A construction module is used to construct a power dispatch optimization model for a distributed multi-agent power system based on the operating cost model and operating cost model constraints of each distributed agent. The power dispatch optimization model takes minimizing the total operating cost of the distributed multi-agent power system as the solution objective and balances power supply and demand as the constraint condition.

[0030] The optimization module is used to solve the power dispatch optimization model using a diffusion strategy to obtain a power dispatch strategy for a distributed multi-agent power system; the power dispatch strategy is used to perform power dispatch on each distributed agent.

[0031] A computer device includes a memory and a processor, wherein the memory stores a computer program and the processor implements the steps of the above method when executing the computer program.

[0032] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0033] A computer program product comprises a computer program, which implements the steps of the above method when executed by a processor.

[0034] The above-mentioned dispatching method, device, computer equipment, storage medium and computer program product of the distributed multi-agent power system based on computer collaboration determine the operating cost model and operating cost model constraints for each distributed agent; according to the operating cost model and operating cost model constraints of each distributed agent, a power dispatching optimization model for the distributed multi-agent power system is constructed; the power dispatching optimization model takes minimizing the total operating cost of the distributed multi-agent power system as the solution goal and the balance of power supply and demand as the constraint condition; the power dispatching optimization model is solved by using a diffusion strategy to obtain a power dispatching strategy for the distributed multi-agent power system; the power dispatching strategy is used to dispatch power to each distributed agent; in this way, the power dispatching strategy of the distributed multi-agent power system can be optimized by applying the diffusion strategy, which can effectively improve the absorption capacity of renewable energy, optimize the power system dispatch, and ensure the effectiveness of voltage stability and frequency regulation in actual operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 This is an application environment diagram of a dispatching method for a distributed multi-agent power system based on computer collaboration in one embodiment;

[0037] Figure 2 1 is a flow chart of a method for dispatching a distributed multi-agent power system based on computer collaboration in one embodiment;

[0038] Figure 3 1 is a flow chart of a method for dispatching a distributed multi-agent power system based on computer collaboration in another embodiment;

[0039] Figure 4is a structural block diagram of a dispatching device for a distributed multi-agent power system based on computer collaboration in one embodiment;

[0040] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0042] The scheduling method of distributed multi-agent power system based on computer collaboration provided by the embodiment of the present application can be applied to Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104, or placed on a cloud or other network server. Server 104 determines the operating cost model and operating cost model constraints for each distributed agent. Based on the operating cost model and operating cost model constraints for each distributed agent, server 104 constructs a power dispatch optimization model for the distributed multi-agent power system. The power dispatch optimization model minimizes the total operating cost of the distributed multi-agent power system and uses power supply and demand balance as a constraint. Server 104 uses a diffusion strategy to solve the power dispatch optimization model and obtain a power dispatch strategy for the distributed multi-agent power system. The power dispatch strategy is used to dispatch power for each distributed agent. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart car devices, etc. Portable wearable devices can include smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0043] In an exemplary embodiment, Figure 2 As shown in the figure, a dispatching method for distributed multi-agent power system based on computer collaboration is provided. Figure 1 The server 104 in the example is used as an example to illustrate the process, including the following steps S202 to S206.

[0044] Step S202: Determine the operating cost model and operating cost model constraints for each distributed intelligent agent.

[0045] Among them, the distributed agent refers to a basic unit in the distributed multi-agent power system, and the distributed multi-agent power system is a distributed system composed of multiple distributed agents.

[0046] Among them, the operating cost model of the distributed intelligent agent refers to a model used to measure the operating cost consumed by the distributed intelligent agent in the power dispatching process.

[0047] The operating cost model constraint conditions of the distributed intelligent agent refer to the conditions used to constrain the state of the distributed intelligent agent during the power dispatching process.

[0048] Optionally, the server determines an operating cost model and operating cost model constraints for each distributed agent.

[0049] Step S204: construct a power dispatching optimization model for the distributed multi-agent power system based on the operating cost model and operating cost model constraints of each distributed intelligent agent; the power dispatching optimization model takes minimizing the total operating cost of the distributed multi-agent power system as the solution goal and the balance of power supply and demand as the constraint condition.

[0050] Among them, the power dispatch optimization model refers to a model used to optimize the power dispatch of distributed multi-agent power systems to achieve good frequency conditions and improve the reliability and stability of the system.

[0051] Among them, the total operating cost refers to the sum of all types of operating costs in the distributed multi-agent power system.

[0052] Optionally, the server constructs a power dispatch optimization model for the distributed multi-agent power system based on the operation cost model and operation cost model constraints of each distributed agent.

[0053] Step S206 , using a diffusion strategy to solve the power dispatch optimization model, and obtaining a power dispatch strategy for the distributed multi-agent power system; the power dispatch strategy is used to perform power dispatch on each distributed agent.

[0054] The diffusion strategy is a strategy for optimizing distributed multi-agent power systems. Its purpose is to optimize global objectives while satisfying various constraints of distributed multi-agent power systems through information exchange and collaboration among distributed agents. The core idea of ​​the diffusion strategy is to decompose the global optimization problem into multiple local optimization problems. Each distributed agent only needs to process its local information and interact with its neighboring distributed agents, gradually converging to the global optimal solution through iterative information sharing and local optimization.

[0055] The power dispatching strategy may include the output power information of each distributed intelligent agent.

[0056] Optionally, the server adopts a diffusion strategy to solve the power dispatch optimization model to obtain a power dispatch strategy for the distributed multi-agent power system to perform power dispatch on each distributed agent.

[0057] In the above-mentioned dispatching method of the distributed multi-agent power system based on computer collaboration, the operating cost model and operating cost model constraints for each distributed agent are determined; according to the operating cost model and operating cost model constraints of each distributed agent, a power dispatching optimization model for the distributed multi-agent power system is constructed; the power dispatching optimization model takes minimizing the total operating cost of the distributed multi-agent power system as the solution goal and the balance of power supply and demand as the constraint condition; the power dispatching optimization model is solved by using a diffusion strategy to obtain a power dispatching strategy for the distributed multi-agent power system; the power dispatching strategy is used to perform power dispatch on each distributed agent; in this way, the power dispatching strategy of the distributed multi-agent power system can be optimized by applying the diffusion strategy, which can effectively improve the absorption capacity of renewable energy, optimize the power system dispatch, and ensure the effectiveness of voltage stability and frequency regulation in actual operation.

[0058] In an exemplary embodiment, a power dispatching optimization model for a distributed multi-agent power system is constructed based on the operating cost model and operating cost model constraints of each distributed intelligent agent, including: obtaining the operating cost model weight coefficient for each distributed intelligent agent; and determining the solution target of the power dispatching optimization model based on the operating cost model and operating cost model weight coefficient of each distributed intelligent agent.

[0059] Among them, the weight coefficient of the distributed agent's operating cost model can represent the relative importance of the distributed agent's cost.

[0060] In practical applications, the weight coefficient of the distributed agent's operating cost model can be:

[0061] First, it reflects the relative importance of agent costs. In priority setting, the weight coefficient reflects the priority of different agents in the system. Agents with larger weights play a more important role in the total cost, and their cost changes have a greater impact on the total cost. For example, in a power system with multiple power generation resources, renewable energy generation agents may have a larger weight to prioritize their cost optimization, thereby encouraging greater use of clean energy. In resource allocation, the weight coefficient provides a basis for resource allocation. When resources are limited, the system can prioritize the needs of agents with larger weights based on the weight coefficient to maximize overall benefits.

[0062] Second, balance the cost and performance of different intelligent agents. During the cost balancing process, weight coefficients can be used to balance the costs of different intelligent agents, allowing the system to take into account the economy and efficiency of various aspects during operation. For example, in a power system containing multiple generators and energy storage systems, by reasonably setting weight coefficients, the costs of different generators and energy storage systems can be reasonably balanced, avoiding the adverse effects of excessively high or low costs of a particular intelligent agent on the overall performance of the system. During the performance optimization process, reasonable weight coefficients can help optimize the overall performance of the system. By adjusting the weight coefficients, the system can be guided to prioritize the optimization of the performance of key intelligent agents while meeting the constraints, thereby improving the operating efficiency and stability of the entire system.

[0063] Third, reflect the characteristics and constraints of the intelligent agent. Regarding characteristic reflection, the weight coefficient can reflect the characteristics and operating conditions of different intelligent agents. For example, some intelligent agents may have lower operating costs but higher environmental impacts, while other intelligent agents may have higher operating costs but lower environmental impacts. By setting different weight coefficients, these factors can be comprehensively considered during the optimization process; regarding constraint coordination, the weight coefficient can coordinate the constraints between different intelligent agents. In a distributed system, each intelligent agent may be subject to different constraints, such as the output limit of the generator set and the capacity limit of the energy storage system. The weight coefficient can help the system better coordinate these constraints during the optimization process, allowing each intelligent agent to operate within its own constraint range while achieving overall optimization of the system.

[0064] Fourth, it influences the direction of optimization and decision-making results. It can guide the optimization goal. The weight coefficient directly affects the direction and focus of optimization. A larger weight coefficient will prompt the optimization algorithm to pay more attention to the cost optimization of the agent, thereby prioritizing the reduction of the agent's cost in the process of minimizing the total cost. For example, in the power system, if you want to reduce reliance on high-cost generators, you can reduce their weight while increasing the weight of energy storage systems and flexible loads to encourage greater use of these resources. It can also adjust the decision results. Adjusting the weight coefficient can change the results of the optimization decision. By changing the weight coefficient, the system can be guided to make different decisions under different operating states and conditions to adapt to changing system requirements and environmental conditions.

[0065] Optionally, the server obtains the weight coefficient of the operating cost model for each distributed intelligent agent, and determines the solution target of the power dispatch optimization model according to the operating cost model and the operating cost model weight coefficient of each distributed intelligent agent.

[0066] In practical applications, the solution objective of the power dispatch optimization model can be expressed as:

[0067] ;

[0068] in, is the total cost, For the The cost of a distributed agent, For the The weight coefficient corresponding to the cost of each distributed agent.

[0069] In this embodiment, the operating cost model weight coefficient for each distributed intelligent agent is obtained; the solution target of the power dispatching optimization model is determined according to the operating cost model and the operating cost model weight coefficient of each distributed intelligent agent; in this way, the overall benefit can be maximized according to the priority of different distributed intelligent agents in the distributed multi-agent power system, and the cost and performance of different distributed intelligent agents can be balanced. Power dispatch can be flexibly implemented based on the actual power dispatching needs of the distributed multi-agent power system.

[0070] In an exemplary embodiment, a diffusion strategy is used to solve a power dispatching optimization model to obtain a power dispatching strategy for a distributed multi-agent power system, including: determining a combined state update rule corresponding to the combination step in the diffusion strategy and a local state update rule corresponding to the adaptation step; the combined state update rule corresponding to the combination step is used to determine the information fusion method between distributed agents; the local state update rule corresponding to the adaptation step is used to determine the self-optimization method of any distributed agent; based on the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step, the power dispatching optimization model is iteratively solved to obtain the output power information of each distributed agent when the total operating cost is minimized; based on the output power information of each distributed agent when the total operating cost is minimized, a power dispatching strategy is generated.

[0071] The main purpose of the combination step is to achieve information sharing and state fusion in a distributed multi-agent power system. Each distributed agent communicates with its neighbors, collects their state information, and then performs a weighted fusion of this information to update its own state. This helps the distributed agents understand the global situation and prepare for the next optimization step.

[0072] The main purpose of the adaptation step is to adjust the agent's state based on the local objective function or optimization criterion. During this phase, the distributed agent uses the fused information obtained in the combination step, combined with its own local objective function, to update its state through gradient descent or other optimization methods to reduce the value of the local objective function, thereby gradually approaching the global optimization goal.

[0073] Among them, the combined state update rule can be expressed as: ,in, represents the combined state of distributed agent i at time k, is the weight coefficient of distributed agent i to neighbor distributed agent j, which is used to measure the influence of the state of agent j on agent i, and the weight coefficient satisfies , to ensure the rationality of the combined state in terms of numerical range and stability.

[0074] Among them, the local state update rule can be expressed as: , is the new state of distributed agent i at time k+1, α is the step size parameter that controls the update amplitude, It is the gradient of the local objective function of the distributed agent i at the combined state, indicating the fastest growth direction of the objective function in the current state. By updating the state in the opposite direction of the gradient, the objective function value can be reduced.

[0075] Optionally, the server determines the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step in the diffusion strategy. Based on the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step, the server iteratively solves the power dispatching optimization model to obtain the output power information of each distributed intelligent body when the total operating cost is minimized. Based on the output power information of each distributed intelligent body when the total operating cost is minimized, the server generates a power dispatching strategy.

[0076] In practical applications, when a power system needs to add new power generation units, energy storage devices, or power consumption areas, a distributed dispatch system using a diffusion strategy is much easier to scale than a centralized system. New distributed agents simply need to establish connections with nearby distributed agents and exchange information according to the diffusion strategy to integrate into the system, without requiring a major overhaul of the dispatch control center.

[0077] In this embodiment, the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step in the diffusion strategy are determined; the combined state update rule corresponding to the combination step is used to determine the information fusion method between distributed intelligent agents; the local state update rule corresponding to the adaptation step is used to determine the self-optimization method of any distributed intelligent agent; based on the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step, the power dispatching optimization model is iteratively solved to obtain the output power information of each distributed intelligent agent when the total operating cost is minimized; based on the output power information of each distributed intelligent agent when the total operating cost is minimized, a power dispatching strategy is generated; in this way, each distributed intelligent agent can continuously adjust its own dispatching strategy according to the received neighbor information, and ultimately the dispatch of the entire power system can reach the global optimal state.

[0078] In an exemplary embodiment, the method also includes: performing power dispatching on a distributed multi-agent power system according to a power dispatching strategy to obtain system status information of the distributed multi-agent power system; resolving the power dispatching optimization model based on the system status information using a diffusion strategy to obtain a new power dispatching strategy for the distributed multi-agent power system; and the new power dispatching strategy is used to perform a new round of power dispatching on each distributed agent.

[0079] The system status information may include status parameters such as the output power of each distributed agent in the distributed multi-agent power system after power dispatching.

[0080] Optionally, the server determines the optimal output power of each distributed multi-agent according to the power dispatching strategy, performs power dispatch on the distributed multi-agent power system based on the optimal output power of each distributed multi-agent, obtains the system status information of the distributed multi-agent power system, and adopts a diffusion strategy to re-solve the power dispatching optimization model based on the system status information, and obtains a new power dispatching strategy for the distributed multi-agent power system to perform a new round of power dispatch on each distributed agent.

[0081] In this embodiment, the distributed multi-agent power system is dispatched according to the power dispatching strategy to obtain the system status information of the distributed multi-agent power system; the power dispatching optimization model is re-solved based on the system status information using the diffusion strategy to obtain a new power dispatching strategy for the distributed multi-agent power system; the new power dispatching strategy is used to perform a new round of power dispatching on each distributed agent; in this way, the power dispatching strategy can be generated in real time according to the real-time status of the distributed multi-agent power system using the diffusion strategy to achieve accurate power dispatching of the distributed multi-agent power system.

[0082] In an exemplary embodiment, the distributed intelligent body includes a photovoltaic power generation system, an energy storage system, and a flexible load; wherein the photovoltaic power generation system adopts a maximum power point tracking control strategy to adjust the output voltage or output current.

[0083] Among them, the maximum power point tracking control strategy refers to the MPPT (Maximum Power Point Tracking) technology, which aims to ensure that photovoltaic cells always operate near their maximum power point (MPP) to maximize power output.

[0084] Optionally, the photovoltaic power generation system, energy storage system, and flexible load can be regarded as distributed intelligent entities, and the traditional power plant can also be regarded as a distributed intelligent entity, so that the frequency regulation capability of the photovoltaic power generation system and flexible load can be incorporated into the power dispatch optimization model; the photovoltaic power generation system adopts the maximum power point tracking control strategy to adjust the output voltage or output current, which can ensure that the photovoltaic cell always operates near its maximum power point, thereby improving the utilization rate of photovoltaic energy.

[0085] In this embodiment, by treating the photovoltaic power generation system, energy storage system, and flexible load as distributed intelligent entities, and adopting the maximum power point tracking control strategy to adjust the output voltage or output current of the photovoltaic power generation system, the frequency regulation capabilities of the photovoltaic power generation system and the flexible load are incorporated into the power dispatch optimization model, which can improve the absorption capacity of the photovoltaic power generation system, dynamically adjust the flexible load, effectively alleviate the load fluctuations of the power grid, optimize the operation of the power grid, reduce the phenomenon of wind and solar power abandonment, and ensure voltage stability during peak load periods.

[0086] In an exemplary embodiment, the photovoltaic power generation system The operating cost model of a generator set is expressed as: , Indicates the The output power of the generator set, For the The operating cost of a generator set, Respectively The quadratic term coefficient, linear term coefficient and constant term coefficient of the operating cost model of the generator set are used to describe the The relationship between the output power and operating cost of each generator set; The operating cost model constraints for each generator set include The output power constraints and power variation constraints of the generator sets; The output power constraint of each generator set is expressed as: , and Respectively represent The minimum and maximum output power allowed for each generator set; the power variation constraint is expressed as: , Indicates the The output power change of each generator set per unit time, Indicates the The minimum output power change of a generator set per unit time, Indicates the The maximum output power change of each generator set per unit time; The operating cost model of an energy storage device is expressed as: , Indicates the The actual output power of each energy storage device during operation is For the The operating cost of an energy storage device, Respectively The cubic coefficient, quadratic coefficient and linear coefficient of the operating cost model of the energy storage device are used to describe the The nonlinear relationship between the output power and operating cost of the energy storage device; The operating cost model constraints for each energy storage device include The output power constraint and remaining power constraint of the energy storage device; The output power constraint of each energy storage device is expressed as: , Respectively represent The minimum output power and maximum output power of the energy storage device; The remaining capacity constraint of each energy storage device is expressed as: , represents the remaining capacity of the i-th energy storage device, represents the minimum remaining capacity of the i-th energy storage device, represents the maximum remaining capacity of the i-th energy storage device; the operating cost model of the flexible load is expressed as: , Indicates the The operating cost of a flexible load, Indicates the The output power of a flexible load, Respectively The coefficient of the operating cost model of the flexible load; The constraints of the operating cost model for each flexible load include The output power constraint condition of the flexible load; The output power constraint of a flexible load is expressed as: , Indicates the The minimum output power of a flexible load, Indicates the The maximum output power of a flexible load.

[0087] Optionally, first, based on the operating cost model and operating cost model constraints of the photovoltaic power generation system generator set, the energy storage device of the energy storage system, and the flexible load in this embodiment, the solution objective of the power dispatch optimization model is determined as follows:

[0088] ;

[0089] in, is the total cost, For the The cost of a distributed agent, For the The weight coefficient corresponding to the cost of each distributed agent.

[0090] Then, the constraints of the power dispatch optimization model are determined as follows:

[0091] ;

[0092] ;

[0093] ;

[0094] in, Characterizes the total system load range constraint, the total system load Less than the total load limit , less than the lower limit of total load ; Characterize the voltage constraint of distributed agent i, the voltage of distributed agent i must be less than the upper voltage limit of distributed agent i , which is less than the voltage lower limit of distributed agent i ; Characterizes the total system load constraint, the total system load It must be smaller than the total output power of the photovoltaic power generation system, energy storage system and flexible load.

[0095] In order to incorporate these constraints into the optimization problem, the Lagrange multiplier method is used to define the Lagrange function ,in, is the Lagrange multiplier, representing the marginal cost of each agent, is the output power of the ith distributed agent. The constraints can be transformed into When the marginal costs of all agents are equal, the total cost of the system reaches the minimum. By adjusting the output power of each agent, the marginal cost of each agent is equal, thereby minimizing the total cost.

[0096] Finally, the optimal output power of the device in each agent can be expressed as:

[0097] ;

[0098] ;

[0099] ;

[0100] in, Represent the operating cost functions of the generator set, fuel cell unit and energy storage device respectively, The actual output power of the three types of equipment are respectively: It indicates the extent to which the power output of each agent needs to be adjusted when the system meets the power balance constraint.

[0101] In this embodiment, operating cost models and operating cost model constraints of different distributed intelligent entities are provided, which is conducive to accurately constructing the solution objectives and constraints for the power dispatch optimization model, thereby helping to optimize the power system dispatch and ensure the effectiveness of voltage stability and frequency regulation in actual operation.

[0102] This application proposes a scheduling optimization method based on a diffusion strategy, combining flexible loads with grid-connected photovoltaic systems. This method improves the power system's regulation capability and renewable energy absorption capacity through scheduling optimization. Specifically, a diffusion strategy is used to optimize power dispatch in a distributed multi-agent power system, and the frequency regulation capabilities of photovoltaic power generation and flexible loads are incorporated into the optimization model. Simulation results validate the effectiveness of this proposed scheduling optimization method based on a diffusion strategy, demonstrating that the optimization strategy can achieve good frequency regulation and significantly improve the absorption capacity of photovoltaic power generation. It also plays a significant role in improving the reliability and stability of the power grid, effectively supporting the large-scale application of renewable energy.

[0103] In another embodiment, Figure 3 As shown in the figure, a dispatching method for distributed multi-agent power system based on computer collaboration is provided. Figure 1 Taking the server 104 in the example as an example, the following steps are included:

[0104] Step S302: Determine the operating cost model and operating cost model constraints for each distributed intelligent agent.

[0105] Step S304: construct a power dispatching optimization model for the distributed multi-agent power system based on the operating cost model and operating cost model constraints of each distributed intelligent agent; the power dispatching optimization model takes minimizing the total operating cost of the distributed multi-agent power system as the solution goal and the balance of power supply and demand as the constraint condition.

[0106] Step S306, determine the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step in the diffusion strategy; the combined state update rule corresponding to the combination step is used to determine the information fusion method between distributed intelligent agents; the local state update rule corresponding to the adaptation step is used to determine the self-optimization method of any distributed intelligent agent.

[0107] Step S308, based on the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step, the power dispatch optimization model is iteratively solved to obtain the output power information of each distributed intelligent agent when the total operating cost is minimized.

[0108] Step S310 : generating a power dispatching strategy based on the output power information of each distributed intelligent agent when the total operating cost is minimized.

[0109] It should be noted that the specific limitations of the above steps can be found in the specific limitations of the above-mentioned method for dispatching a distributed multi-agent power system based on computer collaboration.

[0110] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0111] Based on the same inventive concept, an embodiment of the present application further provides a dispatching device for a distributed multi-agent power system based on computer collaboration, which is used to implement the aforementioned dispatching method for a distributed multi-agent power system based on computer collaboration. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the dispatching device for a distributed multi-agent power system based on computer collaboration provided below can be found in the limitations of the dispatching method for a distributed multi-agent power system based on computer collaboration above, and will not be repeated here.

[0112] In an exemplary embodiment, Figure 4 As shown, a dispatching device for a distributed multi-agent power system based on computer collaboration is provided, comprising: a determination module 402, a construction module 404 and an optimization module 406, wherein:

[0113] Determination module 402, for determining the operating cost model and operating cost model constraints for each distributed agent;

[0114] A construction module 404 is configured to construct a power dispatch optimization model for a distributed multi-agent power system based on the operating cost model and operating cost model constraints of each distributed agent; the power dispatch optimization model takes minimizing the total operating cost of the distributed multi-agent power system as a solution objective and takes power supply and demand balance as a constraint condition;

[0115] The optimization module 406 is used to solve the power dispatch optimization model using a diffusion strategy to obtain a power dispatch strategy for the distributed multi-agent power system; the power dispatch strategy is used to perform power dispatch on each distributed agent.

[0116] In an exemplary embodiment, the construction module 404 is used to obtain the weight coefficient of the operating cost model for each distributed intelligent agent; and determine the solution target of the power dispatch optimization model according to the operating cost model and the operating cost model weight coefficient of each distributed intelligent agent.

[0117] In an exemplary embodiment, the optimization module 406 is used to determine the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step in the diffusion strategy; the combined state update rule corresponding to the combination step is used to determine the information fusion method between distributed intelligent agents; the local state update rule corresponding to the adaptation step is used to determine the self-optimization method of any distributed intelligent agent; based on the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step, the power dispatching optimization model is iteratively solved to obtain the output power information of each distributed intelligent agent when the total operating cost is minimized; based on the output power information of each distributed intelligent agent when the total operating cost is minimized, a power dispatching strategy is generated.

[0118] In an exemplary embodiment, the device also includes: a scheduling module, which is used to perform power scheduling on the distributed multi-agent power system according to the power scheduling strategy and obtain system status information of the distributed multi-agent power system; adopt a diffusion strategy to re-solve the power scheduling optimization model based on the system status information to obtain a new power scheduling strategy for the distributed multi-agent power system; the new power scheduling strategy is used to perform a new round of power scheduling on each distributed agent.

[0119] In an exemplary embodiment, the distributed intelligent body includes a photovoltaic power generation system, an energy storage system, and a flexible load; wherein the photovoltaic power generation system adopts a maximum power point tracking control strategy to adjust the output voltage or output current.

[0120] In an exemplary embodiment, the photovoltaic power generation system The operating cost model of a generator set is expressed as: , Indicates the The output power of the generator set, For the The operating cost of a generator set, Respectively The quadratic term coefficient, linear term coefficient and constant term coefficient of the operating cost model of the generator set are used to describe the The relationship between the output power and operating cost of each generator set; The operating cost model constraints for each generator set include The output power constraints and power variation constraints of the generator sets; The output power constraint of each generator set is expressed as: , and Respectively represent The minimum and maximum output power allowed for each generator set; the power variation constraint is expressed as: , Indicates the The output power change of each generator set per unit time, Indicates the The minimum output power change of a generator set per unit time, Indicates the The maximum output power change of each generator set per unit time; The operating cost model of an energy storage device is expressed as: , Indicates the The actual output power of each energy storage device during operation is For the The operating cost of an energy storage device, Respectively The cubic coefficient, quadratic coefficient and linear coefficient of the operating cost model of the energy storage device are used to describe the The nonlinear relationship between the output power and operating cost of the energy storage device; The operating cost model constraints for each energy storage device include The output power constraint and remaining power constraint of the energy storage device; The output power constraint of each energy storage device is expressed as: , Respectively represent The minimum output power and maximum output power of the energy storage device; The remaining capacity constraint of each energy storage device is expressed as: , represents the remaining capacity of the i-th energy storage device, represents the minimum remaining capacity of the i-th energy storage device, represents the maximum remaining capacity of the i-th energy storage device; the operating cost model of the flexible load is expressed as: , Indicates the The operating cost of a flexible load, Indicates the The output power of a flexible load, Respectively The coefficient of the operating cost model of the flexible load; The constraints of the operating cost model for each flexible load include The output power constraint condition of the flexible load; The output power constraint of a flexible load is expressed as: , Indicates the The minimum output power of a flexible load, Indicates the The maximum output power of a flexible load.

[0121] Each module in the aforementioned distributed multi-agent power system dispatching device based on computer collaboration can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0122] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store dispatch data of a distributed multi-agent power system based on electronic computing collaboration. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a dispatch method for a distributed multi-agent power system based on electronic computing collaboration is implemented.

[0123] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0124] In one embodiment, a computer device is provided, comprising a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor performs the steps of the aforementioned method for dispatching a distributed multi-agent power system based on computer collaboration. The steps of the method for dispatching a distributed multi-agent power system based on computer collaboration may be the steps of the method for dispatching a distributed multi-agent power system based on computer collaboration in each of the aforementioned embodiments.

[0125] In one embodiment, a computer-readable storage medium is provided, storing a computer program. When executed by a processor, the computer program causes the processor to perform the steps of the aforementioned method for dispatching a distributed multi-agent power system based on computer collaboration. The steps of the method for dispatching a distributed multi-agent power system based on computer collaboration may be the steps of the method for dispatching a distributed multi-agent power system based on computer collaboration in each of the aforementioned embodiments.

[0126] In one embodiment, a computer program product is provided, comprising a computer program. When executed by a processor, the computer program causes the processor to perform the steps of the aforementioned method for dispatching a distributed multi-agent power system based on computer collaboration. The steps of the method for dispatching a distributed multi-agent power system based on computer collaboration may be the steps of the method for dispatching a distributed multi-agent power system based on computer collaboration in each of the aforementioned embodiments.

[0127] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0128] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A dispatching method for a distributed multi-agent power system based on computer collaboration, characterized in that: Applied to a distributed multi-agent power system, the distributed multi-agent power system includes a plurality of distributed agents, the method comprising: Determining an operating cost model and operating cost model constraints for each of the distributed intelligent agents; Constructing a power dispatch optimization model for the distributed multi-agent power system based on the operating cost model and operating cost model constraints of each distributed agent; the power dispatch optimization model takes minimizing the total operating cost of the distributed multi-agent power system as a solution objective and takes power supply and demand balance as a constraint; The power dispatch optimization model is solved by adopting a diffusion strategy to obtain a power dispatch strategy for the distributed multi-agent power system; the power dispatch strategy is used to perform power dispatch on each of the distributed agents.

2. The method according to claim 1, characterized in that The step of constructing a power dispatch optimization model for the distributed multi-agent power system based on the operation cost model and the operation cost model constraints of each distributed agent includes: Obtaining a weight coefficient of an operation cost model for each of the distributed intelligent agents; The solution target of the power dispatch optimization model is determined according to the operation cost model and the operation cost model weight coefficient of each distributed intelligent body.

3. The method according to claim 1, characterized in that The adopting of a diffusion strategy to solve the power dispatch optimization model to obtain a power dispatch strategy for the distributed multi-agent power system includes: Determine the combined state update rule corresponding to the combination step and the local state update rule corresponding to the adaptation step in the diffusion strategy; the combined state update rule corresponding to the combination step is used to determine the information fusion method between the distributed intelligent agents; the local state update rule corresponding to the adaptation step is used to determine the self-optimization method of any of the distributed intelligent agents; Based on the combined state update rule corresponding to the combining step and the local state update rule corresponding to the adapting step, the power dispatch optimization model is iteratively solved to obtain the output power information of each of the distributed intelligent agents when the total operating cost is minimized; The power dispatching strategy is generated based on the output power information of each of the distributed intelligent agents when the total operating cost is minimized.

4. The method according to claim 1, wherein The method further comprises: Performing power dispatch on the distributed multi-agent power system according to the power dispatch strategy, and obtaining system status information of the distributed multi-agent power system; The diffusion strategy is adopted to re-solve the power dispatch optimization model based on the system status information to obtain a new power dispatch strategy for the distributed multi-agent power system; the new power dispatch strategy is used to perform a new round of power dispatch for each of the distributed agents.

5. The method according to claim 1, characterized in that The distributed intelligent body includes a photovoltaic power generation system, an energy storage system and a flexible load; wherein the photovoltaic power generation system adopts a maximum power point tracking control strategy to adjust the output voltage or output current.

6. The method according to claim 5, characterized in that The photovoltaic power generation system The operating cost model of a generator set is expressed as: , Indicates the The output power of the generator set, For the said The operating cost of a generator set, They are respectively The quadratic term coefficient, linear term coefficient and constant term coefficient of the operating cost model of the generator set are used to describe the The relationship between the output power of each generator set and its operating cost; The said The operating cost model constraints for the first generator set include The output power constraints and power variation constraints of the generator sets; The output power constraint of each generator set is expressed as: , and Respectively represent the The minimum and maximum output power allowed by each generator set; the power variation constraint is expressed as: , Indicates the The output power change of each generator set per unit time, Indicates the The minimum output power change of a generator set per unit time, Indicates the The maximum output power change of each generator set per unit time; The energy storage system The operating cost model of an energy storage device is expressed as: , Indicates the The actual output power of each energy storage device during operation is For the said The operating cost of an energy storage device, They are respectively The cubic coefficient, quadratic coefficient and linear coefficient of the operating cost model of the energy storage device are used to describe the The nonlinear relationship between the output power and operating cost of each energy storage device; The said The operating cost model constraints for each energy storage device include The output power constraint condition and the remaining power constraint condition of the energy storage device; The output power constraint of each energy storage device is expressed as: , Respectively represent the The minimum output power and maximum output power of the energy storage device; The remaining capacity constraint of each energy storage device is expressed as: , represents the remaining power of the i-th energy storage device, represents the minimum remaining capacity of the i-th energy storage device, represents the maximum remaining power of the i-th energy storage device; The operating cost model of the flexible load is expressed as: , Indicates the The operating cost of a flexible load, Indicates the The output power of a flexible load, Respectively The coefficients of the operating cost model for each flexible load; The said The constraints of the operating cost model for the flexible load include The output power constraint condition of the flexible load; The output power constraint of a flexible load is expressed as: , Indicates the The minimum output power of a flexible load, Indicates the The maximum output power of a flexible load.

7. A dispatching device for a distributed multi-agent power system based on computer collaboration, characterized in that: Applied to a distributed multi-agent power system, the distributed multi-agent power system includes a plurality of distributed agents, and the device includes: A determination module, configured to determine an operating cost model and operating cost model constraints for each of the distributed intelligent agents; a construction module for constructing a power dispatch optimization model for the distributed multi-agent power system based on the operating cost model and operating cost model constraints of each distributed agent; the power dispatch optimization model takes minimizing the total operating cost of the distributed multi-agent power system as a solution objective and takes power supply and demand balance as a constraint; The optimization module is used to solve the power dispatch optimization model by adopting a diffusion strategy to obtain a power dispatch strategy for the distributed multi-agent power system; the power dispatch strategy is used to perform power dispatch on each of the distributed agents.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images