An optimization operation decision method and system for an agent participating in an electricity market by aggregating multiple types of resources

Abstract

The present application relates to the virtual power plant, load aggregator, new energy power generation, industrial and commercial park, microgrid, comprehensive energy service provider participates in the regulation potential evaluation, optimization operation decision, multi-type resource collaborative configuration interaction field of electric power market, disclose a kind of optimization operation decision method and system of aggregated multi-type resource agent participating in electric power market, the method comprises: the mathematical model of modularization design control flag variable parameter quantity definition configuration module mathematical model, the mathematical model of multi-type flexible resource module mathematical model, the mathematical model of main system module mathematical model, the mathematical model of modularization design control flag variable parameter quantity definition configuration module mathematical model in agent and the mathematical model of auxiliary service market module mathematical model are built in multi-agent collaborative operation model library;Agent input data information is input into the multi-agent collaborative operation model library and the output agent data information is calculated.This application effectively evaluates and calculates the multi-type flexible resource aggregation potential capacity in agent, which helps to exert the multi-type flexible resource multi-energy complementary advantage.

Description

Technical Field

[0001] This invention relates to the fields of assessment of the regulation potential of virtual power plants, load aggregators, renewable energy generators, industrial and commercial parks, microgrids, and integrated energy service providers participating in the electricity market, optimization of operation decisions, and collaborative allocation and interaction of multiple types of resources. Specifically, it relates to a method and system for optimizing the operation decisions of intelligent agents that aggregate multiple types of resources to participate in the electricity market. Background Technology

[0002] With the deepening of power market reform and the continuous improvement of the intelligentization process of the new power system, new market entities such as virtual power plants, load aggregators, and integrated energy service providers have emerged. They participate in the power market optimization and operation decision-making in the form of intelligent agents by aggregating various types of flexible resources such as new energy photovoltaics, energy storage, electric thermal storage central air conditioning, and charging piles. The optimization and operation decision-making capabilities of intelligent agents directly affect the economy, reliability, and flexibility of the power energy system, and have become a research hotspot and engineering challenge in the current power energy field.

[0003] How to aggregate multiple types of flexible resources through intelligent agents to achieve their efficient participation in the electricity market has become a key issue in improving the stability, economy, and market responsiveness of the power energy system. Existing technologies mostly focus on the optimized operation of single-type resources, simple aggregation models, or the design of market response strategies for local scenarios. While establishing corresponding mechanistic models and safety boundary conditions, they often neglect the temporal coupling between resources, the dynamic connection between operational constraints and market mechanisms, resulting in insufficient adaptability of the models in practical applications and difficulty in achieving optimal decision-making across the entire chain. Although existing research has explored resource aggregation and market participation, the following significant shortcomings remain:

[0004] (1) Existing technical models are mostly designed for specific resources or fixed scenarios, making it difficult to flexibly adapt to the access and exit of multiple types of flexible resources. They lack modular and configurable mathematical modeling support, resulting in poor resource configuration coordination flexibility. They have not formed a standardized and modular configuration system, making it difficult to adapt to the rapid adaptation needs of multiple scenarios and multiple services, leading to poor system versatility and high expansion costs.

[0005] (2) Existing technologies do not adequately characterize the operational characteristics, dynamic timing constraints and market response capabilities of resources such as photovoltaics, energy storage, charging piles, and electric thermal storage central air conditioning. It is difficult to accurately assess their aggregation and regulation potential and market economic benefits, and it is difficult to support refined operational decision-making. It fails to fully leverage the advantages of multi-energy complementarity, resulting in low resource utilization efficiency.

[0006] (3) Existing technological achievements mostly focus on the economic optimization operation after market clearing, lacking an integrated optimization model for resource declaration, potential assessment, market compensation mechanism and other links before clearing, which affects the scientific nature of the power market declaration strategy and makes it difficult to support the intelligent agent's optimal decision-making in the whole market process.

[0007] The above-mentioned technical deficiencies limit the participation and effectiveness of intelligent agents that aggregate multiple types of resources in the electricity market, and urgently require a systematic and modular optimization operation decision-making method and system to solve this problem. Summary of the Invention

[0008] To address the problems in related technologies, this invention proposes a method and system for optimizing the operation decision-making of the electricity market by aggregating intelligent agents with multiple types of resources, in order to overcome the aforementioned technical problems existing in the existing related technologies.

[0009] Therefore, the specific technical solution adopted by the present invention is as follows:

[0010] According to a first aspect of the present invention, a method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources to participate in the electricity market is provided, the method comprising:

[0011] Acquire input data information from the intelligent agent;

[0012] Construct a multi-agent collaborative operation model library that includes mathematical models for defining and configuring intelligent agent operation parameters, mathematical models for multiple types of flexible resource modules, mathematical models for the main system module, mathematical models for defining and configuring modular design control flag variable parameters in intelligent agents, and mathematical models for auxiliary service market modules;

[0013] The agent input data information is input into the multi-agent collaborative operation model library. The agent output data information is calculated by each model in the multi-agent collaborative operation model library. The agent output data information is integrated by integrating the agent output data information of each model to obtain the agent output data information.

[0014] Based on the agent's output data, the system determines whether to adjust the scene or reset the running data according to preset rules. If so, it updates the agent's input data and returns to re-execute the optimization calculation. If not, it directly outputs the agent's output data and executes the aggregated multi-type resource control scheme in the agent based on the agent's output data.

[0015] According to a second aspect of the present invention, an optimized operation decision-making system for intelligent agents aggregating multiple types of resources participating in the electricity market is provided, the system comprising:

[0016] The agent data acquisition module is used to acquire the input data information of the agent.

[0017] The decision-making model building module is used to build a multi-agent collaborative operation model library, which includes mathematical models of intelligent agent operation parameter definition and configuration modules, mathematical models of multi-type flexible resource modules, mathematical models of main system modules, mathematical models of modular design control flag variable parameter definition and configuration modules in intelligent agents, and mathematical models of auxiliary service market modules.

[0018] The intelligent agent data information processing and execution module is used to input intelligent agent input data information into the multi-agent collaborative operation model library, calculate and output intelligent agent data information through each model in the multi-agent collaborative operation model library, and integrate the intelligent agent data information output by each model to obtain intelligent agent output data information.

[0019] The decision output module is used to determine whether to adjust the scene or reset the running data based on the intelligent agent's output data information and preset rules. If yes, it updates the intelligent agent's input data information and returns to re-execute the optimization calculation. If no, it directly outputs the intelligent agent's output data and executes the aggregated multi-type resource control scheme in the intelligent agent according to the intelligent agent's output data.

[0020] According to a third aspect of the present invention, a computer device is provided; the computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described method.

[0021] According to a fourth aspect of the present invention, a computer-readable storage medium is provided; the computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-described method.

[0022] The beneficial effects of this invention are as follows:

[0023] (1) This invention fully considers the multi-type flexible resource operation characteristics of intelligent agents and establishes a refined modular mathematical model for intelligent agents participating in the power market that combines security and economy. This model is helpful for the engineering application and promotion of intelligent agents in the field of power energy and the decision analysis of power market optimization.

[0024] (2) This invention provides a method for optimizing operation decision-making before and after the participation of intelligent agents in the power market clearing, realizing a flexible configuration system for the entire chain of resource aggregation, intelligent optimization operation decision-making, and market interaction, realizing modular configuration of multiple types of flexible resources, and realizing modular configuration of intelligent agents for routine operation, economic operation, and participation in power market optimization operation decision-making, which is conducive to the flexible application of intelligent agents to multiple scenarios and multiple business needs.

[0025] (3) The method for optimizing the operation decision of the power market proposed in this invention, which aggregates multiple types of resources, can effectively evaluate the aggregation potential of multiple types of flexible resources in the intelligent agent, promote the flexibility of collaborative configuration and interaction of multiple types of resources in the intelligent agent, help to give full play to the multi-energy complementary advantages of multiple types of flexible resources, and thus improve the economic efficiency of the intelligent agent operation.

[0026] (4) This invention modularizes the various types of resources and operating modes aggregated by the intelligent agent, which has wide applicability and strong versatility. It provides reference and guidance for the construction of intelligent agent optimization operation strategy, analysis of the potential of aggregated resources, generation of power market operation regulation optimization strategy, and analysis of improving the stable operation capability of power energy system. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating the implementation of the present invention;

[0029] Figure 2 This is a graph showing the electricity price information of the intelligent agent in the example.

[0030] Figure 3 The diagram shows the power purchased from the grid by the intelligent agent in this embodiment and the conventional non-adjustable load.

[0031] Figure 4 The power consumption diagram of the electric boiler host in the normal mode of the embodiment is shown below;

[0032] Figure 5 This is a diagram showing the total photovoltaic power generation of the intelligent agent in the embodiment and the power supply to the grid under normal photovoltaic power generation mode.

[0033] Figure 6 For the implementation example, optimize the power purchase and adjustment power of the interconnection line before the intelligent agent is cleared;

[0034] Figure 7 The diagram shows the operating power of the energy storage system under the conventional planning strategy mode and the operating power under the optimized operating decision mode before clearing, as illustrated in the example.

[0035] Figure 8 The diagram shows the power consumption of the charging pile system under normal resource mode and the power consumption under the optimized operation decision mode before clearing, as shown in the example.

[0036] Figure 9The diagram shows the clearing power of the intelligent agent in the embodiment, the optimized power purchase power of the tie line after clearing, and the actual adjusted power after clearing.

[0037] Figure 10 This is a schematic diagram of the structure of a computer device. Detailed Implementation

[0038] To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0039] According to embodiments of the present invention, a method and system for optimizing the operation decision-making of the electricity market by an intelligent agent that aggregates multiple types of resources is provided.

[0040] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, according to an embodiment of the present invention, an intelligent agent aggregating multiple types of resources participates in the optimal operation decision-making of the electricity market. The method includes:

[0041] Acquire input data information from the intelligent agent;

[0042] Construct a multi-agent collaborative operation model library that includes mathematical models for defining and configuring intelligent agent operation parameters, mathematical models for multiple types of flexible resource modules, mathematical models for the main system module, mathematical models for defining and configuring modular design control flag variable parameters in intelligent agents, and mathematical models for auxiliary service market modules;

[0043] The agent input data information is input into the multi-agent collaborative operation model library. The agent output data information is calculated by each model in the multi-agent collaborative operation model library. The agent output data information is integrated by integrating the agent output data information of each model to obtain the agent output data information.

[0044] Based on the agent's output data, the system determines whether to adjust the scene or reset the running data according to preset rules. If so, it updates the agent's input data and returns to re-execute the optimization calculation. If not, it directly outputs the agent's output data and executes the aggregated multi-type resource control scheme in the agent based on the agent's output data.

[0045] In one embodiment, the multi-type flexible resource module mathematical model includes a new energy photovoltaic system resource module mathematical model, an energy storage system resource module mathematical model, an electric thermal storage central air conditioning system resource module mathematical model, and a charging pile system resource module mathematical model.

[0046] Among them, the mathematical model of the resource module of the new energy photovoltaic system includes the economic analysis model of the operation of the new energy photovoltaic system resources, the power balance model of the operation of the new energy photovoltaic system resources, and the self-consumption rate analysis model of the new energy photovoltaic system resources.

[0047] The mathematical model of the energy storage system resource module includes the energy storage system resource operation economic analysis model, the energy storage system resource operation dynamic time series model, the energy storage system resource charging and discharging power constraints, and the energy storage system resource safe operation boundary constraints.

[0048] The mathematical model of the resource module of the electric thermal storage central air conditioning system includes the economic analysis model of the operation of the electric thermal storage central air conditioning system resources, the dynamic time series model of the operation of the thermal storage tank of the electric thermal storage central air conditioning system resources, the power constraints of the charging and supply of the thermal storage tank of the electric thermal storage central air conditioning system resources, the safety boundary constraints of the thermal storage tank of the electric thermal storage central air conditioning system resources, the heat power balance constraints of the electric thermal storage central air conditioning system, and the dynamic time series model of the operation of the electric boiler of the electric thermal storage central air conditioning system resources.

[0049] The mathematical model of the charging pile system resource module includes the charging pile system resource operation economic analysis model, the charging pile system resource power regulation model, and the charging pile system resource safety regulation constraints.

[0050] In one embodiment, the intelligent agent outputs data information including: mathematical model output data information of the new energy photovoltaic system resource module, mathematical model output data information of the energy storage system resource module, mathematical model output data information of the electric thermal storage central air conditioning system resource module, mathematical model output data information of the charging pile system resource module, mathematical model output data information of the main system module, and mathematical model output data information of the auxiliary service market module.

[0051] Executing a multi-type resource control scheme based on the agent's output data includes:

[0052] The mathematical model output data of the resource module of the new energy photovoltaic system, the mathematical model output data of the resource module of the energy storage system, the mathematical model output data of the resource module of the electric thermal storage central air conditioning system, and the mathematical model output data of the resource module of the charging pile system are used to generate execution adjustment instructions. The execution adjustment instructions are output or issued to the multi-type resource execution adjustment mechanism, and the multi-type resources aggregated in the control agent operate according to the execution adjustment instructions.

[0053] The mathematical model output data information of the main system module and the mathematical model output data information of the auxiliary service market module are used to generate intelligent agent operation adjustment effect display curves or databases.

[0054] In one embodiment, the expression for the resource operation economic analysis model of a new energy photovoltaic system is:

[0055]

[0056] In the formula: The equivalent net benefit of optimizing the operation of new energy photovoltaic systems in an intelligent agent compared with conventional planned operation; The equivalent total electricity cost for the optimized operation of new energy photovoltaic systems in an intelligent agent; The equivalent total electricity cost of the conventional plan for new energy photovoltaic system resources in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The photovoltaic feed-in tariff for the intelligent agent during time period t; The power supplied to the grid by photovoltaic resources in the intelligent agent under the optimized operation decision-making mode of time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power supplied to the grid by the photovoltaic resources in the intelligent agent during the normal time period t;

[0057] The expression for the resource operation power balance model of a new energy photovoltaic system is as follows:

[0058]

[0059] In the formula: The total power generation of photovoltaic resources in the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power supplied to the grid by the photovoltaic resources in the intelligent agent during the normal time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; The power supplied to the grid by photovoltaic resources in the intelligent agent under the optimized operation decision-making mode of time period t; In the intelligent agent, the photovoltaic resources are adjusted to reduce power generation under the time period t optimization operation decision mode;

[0060] The expression for the resource self-consumption rate analysis model of new energy photovoltaic systems is as follows:

[0061]

[0062] In the formula: The total power generation of photovoltaic resources in the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; The total number of time periods within the operating cycle, and the value is a positive integer; The self-consumption rate of photovoltaic resources in the intelligent agent during the normal operating cycle; The self-consumption rate of photovoltaic resources in the intelligent agent during the operating cycle under the optimized operation decision mode.

[0063] In one embodiment, the expression for the economic analysis model of energy storage system resource operation is:

[0064]

[0065] In the formula: The net benefit difference between optimized operation and conventional planned operation of energy storage systems in an intelligent agent; The net benefit of optimizing the operation of energy storage systems in intelligent agents; The net benefit of the conventional resource planning for energy storage systems in an intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The discharge power of the energy storage system resources in the intelligent agent under the conventional planned mode during time period t; The charging power of the energy storage system resources in the intelligent agent under the conventional planned mode during time period t; The operating power of the energy storage system resources in the intelligent agent under the conventional planning mode during time period t;

[0066] The expression for the dynamic time-series model of energy storage system resource operation is:

[0067]

[0068] In the formula: The energy stored in the energy storage system of the intelligent agent is optimized under the time period t. The energy stored in the energy storage system of the intelligent agent is determined under the optimized operation decision mode of time period t-1. The self-discharge rate of energy storage system resources in an intelligent agent; To improve the charging efficiency of energy storage systems in intelligent agents; The energy storage system's resource discharge efficiency in an intelligent agent; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The operating power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t-1; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t-1; This refers to the time step for sampling running data. To optimize the energy storage system resources in the intelligent agent during the initial operation period of the energy storage system; To optimize the energy storage system's resources during the last period of operation in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; For the energy storage system resources in the intelligent agent during the time period Optimize discharge power under the operation decision mode; For the energy storage system resources in the intelligent agent during the time period Optimize charging power under the operation decision mode.

[0069] In one embodiment, the expression for the resource operation economic analysis model of an electric thermal storage central air conditioning system is:

[0070]

[0071] In the formula: The equivalent net benefit of conventional planned operation and optimized operation of the electric thermal storage central air conditioning system in the intelligent body; The total operating cost of optimizing the operation of the electric thermal storage central air conditioning system in the intelligent body; The total operating cost of the conventional resource plan for the electric thermal storage central air conditioning system in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent during the normal mode of time period t; This refers to the time step for sampling running data. The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimized operation decision mode; The operating power of the electric thermal storage central air conditioning system in the intelligent body under the conventional planning mode of time period t; The thermal storage power of the central air conditioning system with electric thermal storage in the intelligent agent under the conventional planning mode of time period t; The heating power of the electric thermal storage central air conditioning system in the intelligent body under the conventional planning mode of time period t;

[0072] The expression for the dynamic time-series model of the thermal storage tank operation of the electric thermal storage central air conditioning system is as follows:

[0073]

[0074] In the formula: The thermal energy stored in the thermal storage tank of the central air conditioning system for electric thermal storage in the intelligent agent is determined under the optimized operation decision mode of time period t. The thermal energy stored in the thermal storage tank of the central air conditioning system with electric thermal storage in the intelligent agent is determined under the optimal operation decision mode of time period t-1. The self-loss heat rate of the heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent; The heat storage efficiency of the heat storage tank in the central air conditioning system for electric heat storage in the intelligent agent; The heating efficiency of the heat storage tank in the central air conditioning system for electric thermal storage in the intelligent body; The operating power of the heat storage tank of the electric heat storage central air conditioning system in the intelligent agent under the optimized operation decision mode of time period t; The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimized operation decision mode; The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t; The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t-1; The heat storage capacity of the heat storage tank in the central air conditioning system with electric heat storage in the intelligent agent under the optimized operation decision mode of time period t-1; This refers to the time step for sampling running data. Optimize the thermal energy storage capacity of the thermal storage tank in the initial operation period of the electric thermal storage central air conditioning system in the intelligent body; Optimize the thermal energy storage of the thermal storage tank in the last period of operation of the central air conditioning system for electric thermal storage in the intelligent body; The total number of time periods within the operating cycle, and the value is a positive integer; The heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent during the time period Optimize heating power under the optimal operating decision mode; The heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent during the time period Optimize thermal storage power under the optimal operating decision mode;

[0075] The expression for the dynamic time-series model of the electric boiler operation in the electric thermal storage central air conditioning system is as follows:

[0076]

[0077] In the formula: The heating power of the electric boiler in the electric thermal storage central air conditioning system of the intelligent body under the conventional planning mode of time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent during the normal mode of time period t; The heating power of the electric boiler in the electric thermal storage central air conditioning system resource of the intelligent agent under the time period t optimized operation decision mode; This is a flag indicating the heating status of the electric boiler in the electric thermal storage central air conditioning system resource in the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the boiler is heating the thermal storage tank. When the value is 0, it indicates that the boiler is not heating the thermal storage tank. This is a flag indicating the heating status of the electric boiler in the electric thermal storage central air conditioning system of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the boiler is supplying heat to the heat load. When the value is 0, it indicates that the boiler is not supplying heat to the heat load. The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimized operation decision mode; The heating efficiency of the electric boiler host in the electric thermal storage central air conditioning system resources of the intelligent body; This is a flag indicating the thermal storage status of the thermal storage tank in the electric thermal storage central air conditioning system resources of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates the thermal storage status, and when the value is 0, it indicates the non-thermal storage status. The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimization operation decision mode.

[0078] In one embodiment, the expression for the economic analysis model of the resource operation of the charging pile system is:

[0079]

[0080] In the formula: The equivalent net benefit of optimized operation of charging pile system resources in intelligent agents compared with conventional planned operation; The equivalent total electricity cost for optimizing the operation of the charging pile system in the intelligent agent; The equivalent total electricity cost of the charging pile system resources in the intelligent agent according to the conventional plan; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price for charging stations for the intelligent agent during time period t; The power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The electricity price paid by the intelligent agent during time period t; The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t;

[0081] The expression for the resource power adjustment model of the charging pile system is:

[0082]

[0083] In the formula: The power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode of time period t; The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t; To adjust the power of the charging load transferred to the charging pile system resources in the intelligent agent under the time period t optimization operation decision mode; In the intelligent agent, the power of the outgoing charging load is adjusted under the optimized operation decision-making mode of the charging pile system resources in time period t. This refers to the time step for sampling running data. The starting period for adjusting the charging load power in the charging pile system resources of the intelligent agent under the optimized operation decision mode; This refers to the end point in which the charging load power of the charging pile system resources in the intelligent agent is allowed to be adjusted under the optimized operation decision mode.

[0084] In one embodiment, the mathematical model of the ancillary services market module includes a mathematical model of the pre-clearing phase of the ancillary services market module and a mathematical model of the post-clearing phase of the ancillary services market module.

[0085] Among them, the value of the optimization decision control flag variable before the clearing of the auxiliary service market is determined by the pre-set intelligent agent main system that aggregates multiple types of resources. The value of the optimization decision control flag variable is 0 or 1.

[0086] When the value of the optimization decision control flag variable is 1, the optimization operation decision results of the intelligent agent participating in the ancillary service market clearing stage module are generated by solving the mathematical model of the intelligent agent participating in the ancillary service market clearing stage module. The optimization operation decision results before clearing include the intelligent agent's adjustment potential assessment results and the application suggestions for participating in ancillary services.

[0087] When the value of the optimization decision control flag variable is 0, the optimization operation decision results after the intelligent agent participates in the ancillary service market clearing stage module are generated by solving the mathematical model of the intelligent agent participating in the ancillary service market clearing stage. The optimization operation decision results after clearing include the display of the intelligent agent's participation in the ancillary service market execution adjustment effect.

[0088] In one embodiment, the recommendation to participate in ancillary services application includes:

[0089] When the equivalent net income value of the intelligent agent main system that aggregates multiple types of resources is greater than 0 after participating in the optimization decision before the clearing of the ancillary service market, and at the same time the adjustment power value of the intelligent agent is greater than 0 in certain periods before the clearing of the ancillary service market, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation and management party participate in the application for ancillary services, and it is recommended that the adjustment power declared does not exceed the adjustment power value of the intelligent agent in each period before the clearing of the ancillary service market.

[0090] When the equivalent net income value of the intelligent agent main system that aggregates multiple types of resources is greater than 0 after participating in the optimization decision before the clearing of the ancillary service market, and at the same time the adjustment power value of the intelligent agent in each time period before participating in the clearing of the ancillary service market is less than or equal to 0, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation management party not participate in the application for ancillary services.

[0091] When the equivalent net income of the intelligent agent main system that aggregates multiple types of resources is less than or equal to 0 after participating in the optimization decision before the market clearing of ancillary services, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation and management party not participate in the application for ancillary services.

[0092] According to another embodiment of the present invention, an optimized operation decision-making system for aggregating multiple types of resources to participate in the electricity market is also provided, the system comprising:

[0093] The agent data acquisition module is used to acquire the input data information of the agent.

[0094] The decision-making model building module is used to build a multi-agent collaborative operation model library, which includes mathematical models of intelligent agent operation parameter definition and configuration modules, mathematical models of multi-type flexible resource modules, mathematical models of main system modules, mathematical models of modular design control flag variable parameter definition and configuration modules in intelligent agents, and mathematical models of auxiliary service market modules.

[0095] The intelligent agent data information processing and execution module is used to input intelligent agent input data information into the multi-agent collaborative operation model library, calculate and output intelligent agent data information through each model in the multi-agent collaborative operation model library, and integrate the intelligent agent data information output by each model to obtain intelligent agent output data information.

[0096] The decision output module is used to determine whether to adjust the scene or reset the running data based on the intelligent agent's output data information and preset rules. If yes, it updates the intelligent agent's input data information and returns to re-execute the optimization calculation. If no, it directly outputs the intelligent agent's output data and executes the aggregated multi-type resource control scheme in the intelligent agent according to the intelligent agent's output data.

[0097] To facilitate understanding of the above technical solutions of the present invention, the following further explains the above technical solutions of the present invention from the perspective of architecture and principle, as follows:

[0098] This invention provides a method and system for optimizing the operation of an intelligent agent aggregating multiple types of resources in the electricity market. First, based on input intelligent agent data, a mathematical model is constructed to define and configure the intelligent agent's operating parameters. A resource module mathematical model is established, including new energy photovoltaic systems, energy storage systems, electric thermal storage central air conditioning systems, and charging pile systems. Multiple flexible resources are aggregated through the main system module mathematical model. A modular design control variable parameter definition and configuration module mathematical model is constructed to flexibly configure the aggregated resource types and operating modes for participation in the electricity market. Optimized operation decisions are achieved at each stage before and after clearing through the ancillary service market module mathematical model. This invention achieves modular configuration of multiple types of resources and multiple operating modes for intelligent agents. The method has wide applicability and strong versatility, and can provide reference and guidance for constructing intelligent agent optimized operation strategies, analyzing the potential of aggregated resources, generating optimized strategies for participating in electricity market operation and regulation, and analyzing the analysis of improving the stable operation capability of power energy systems. Specifically, it includes:

[0099] (1) Input agent data information (equivalent to agent input data information), specifically including:

[0100] The mathematical model data information of the intelligent agent operation parameter definition and configuration module includes: the start and end times of the intelligent agent's participation in the auxiliary service market, and the total number of time periods; the start and end times of the charging load power that the charging pile system resources in the intelligent agent are allowed to adjust under the optimized operation decision mode;

[0101] Mathematical model data information for new energy photovoltaic system resource modules: including electricity purchase price, photovoltaic grid connection price, power supplied to the main system load under conventional mode, and power supplied to the grid under conventional mode;

[0102] Mathematical model data information of energy storage system resource modules: including discharge power under conventional planning mode, charging power under conventional planning mode, operating power under conventional planning mode, various parameters of the dynamic time series model variable characteristics of energy storage system resource operation, special limit boundary of charging power under optimized operation decision mode, and special limit boundary of discharge power under optimized operation decision mode;

[0103] Data information of the mathematical model of the resource module of the electric thermal storage central air conditioning system: including the variable characteristics of each parameter of the mathematical model of the resource module of the electric thermal storage central air conditioning system, the special limit boundary of thermal storage power under the optimized operation decision mode, the special limit boundary of heating power under the optimized operation decision mode, the value of the heat abandonment permission status flag of the electric thermal storage central air conditioning system, and the heating efficiency of the electric boiler host of the electric thermal storage central air conditioning system.

[0104] Data information of the mathematical model of the charging pile system resource module: including the electricity price of the charging pile, the power consumption in the normal mode, the maximum tolerance coefficient for adjusting the outgoing charging load in the optimized operation decision mode, and the maximum tolerance coefficient for adjusting the incoming charging load in the optimized operation decision mode;

[0105] Main system module mathematical model data information: including the sampling time step of running data, the normal power purchase capacity of the tie line, and the normal power sales capacity of the tie line;

[0106] Modular design of intelligent agents: definition and configuration of control flag variables, parameter quantities, and mathematical model data information of modules, including the values ​​of control flag variables indicating whether various types of resources participate in optimization operation;

[0107] Mathematical model data information for the ancillary services market module includes: reference benchmark power calculation rule function variables and model parameters, bid price, indicator value of the direction of intelligent agent participation in the ancillary services market regulation, clearing price, assessment penalty ratio coefficient, different numerical assessment coefficient values ​​for post-clearing optimization operation decision, and numerical values ​​of the control indicator variable value for the intelligent agent main system participating in the ancillary services market before clearing.

[0108] (2) Constructing a mathematical model for the intelligent agent's operational parameter definition and configuration module, specifically including:

[0109] (2a) The time period parameter for an agent's participation in the auxiliary service market is defined and configured, and the specific expression is as follows:

[0110]

[0111] In the formula: The set of time periods during which intelligent agents participate in the assistive services market; This marks the initial period for intelligent agents to participate in the assistive services market. The end of the period when intelligent agents participate in the assistive services market; The total number of time periods within the running cycle, and the value is a positive integer.

[0112] Among them, the parameter definition and configuration of the time period for intelligent agents to participate in the auxiliary service market initializes the start and end time periods for intelligent agents to participate in the auxiliary service market, as well as the total number of time periods within the operating cycle, thereby defining the control time range and system operating cycle for intelligent agents to participate in the auxiliary service market;

[0113] (2b) The time period parameter for the charging pile system resources in the intelligent agent to participate in the optimized operation and adjustment is defined and configured, and the specific expression is as follows:

[0114]

[0115] In the formula: The set of time periods during which charging pile system resources in an intelligent agent participate in optimized operation and adjustment; The starting period for adjusting the charging load power in the charging pile system resources of the intelligent agent under the optimized operation decision mode; This refers to the end point in which the charging load power of the charging pile system resources in the intelligent agent is allowed to be adjusted under the optimized operation decision mode; The total number of time periods within the running cycle, and the value is a positive integer.

[0116] Among them, the time period parameter definition and configuration of the charging pile system resources participating in the optimized operation adjustment in the intelligent agent initializes the start and end periods of the charging load power adjustment allowed by the charging pile system resources in the optimized operation decision mode, defines the allowable adjustment time range within the operation cycle for the charging pile system resources to participate in the ancillary service market, and constrains the time range for evaluating the adjustment potential of the charging pile system resources.

[0117] (3) Construct mathematical models of resource modules for new energy photovoltaic systems, including mathematical models of resource modules for new energy photovoltaic systems, energy storage systems, electric thermal storage central air conditioning systems, and charging pile systems.

[0118] (3a) The economic analysis model for resource operation of new energy photovoltaic systems is expressed as follows:

[0119]

[0120] In the formula: The equivalent net benefit of optimizing the operation of new energy photovoltaic systems in an intelligent agent compared with conventional planned operation; The equivalent total electricity cost for the optimized operation of new energy photovoltaic systems in an intelligent agent; The equivalent total electricity cost of the conventional plan for new energy photovoltaic system resources in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The photovoltaic feed-in tariff for the intelligent agent during time period t; The power supplied to the grid by photovoltaic resources in the intelligent agent under the optimized operation decision-making mode of time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; This refers to the power supplied to the grid by the photovoltaic resources in the intelligent agent during the normal mode of time period t.

[0121] (3b) The power balance model for the resource operation of a new energy photovoltaic system is expressed as follows:

[0122]

[0123] In the formula: The total power generation of photovoltaic resources in the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power supplied to the grid by the photovoltaic resources in the intelligent agent during the normal time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; The power supplied to the grid by photovoltaic resources in the intelligent agent under the optimized operation decision-making mode of time period t; In the intelligent agent, the photovoltaic resources are adjusted and the power generation is reduced under the optimal operation decision mode of time period t.

[0124] (3c) Analysis model for the self-consumption rate of new energy photovoltaic systems, the specific expression of which is as follows:

[0125]

[0126] In the formula: The total power generation of photovoltaic resources in the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; The total number of time periods within the operating cycle, and the value is a positive integer; The self-consumption rate of photovoltaic resources in the intelligent agent during the normal operating cycle; The self-consumption rate of photovoltaic resources in the intelligent agent during the operating cycle under the optimized operation decision mode.

[0127] (4) Mathematical model of energy storage system resource modules, specifically including:

[0128] (4a) The economic analysis model for the resource operation of the energy storage system is expressed as follows:

[0129]

[0130] In the formula: The net benefit difference between optimized operation and conventional planned operation of energy storage systems in an intelligent agent; The net benefit of optimizing the operation of energy storage systems in intelligent agents; The net benefit of the conventional resource planning for energy storage systems in an intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The discharge power of the energy storage system resources in the intelligent agent under the conventional planned mode during time period t; The charging power of the energy storage system resources in the intelligent agent under the conventional planned mode during time period t; The power of the energy storage system resources in the intelligent agent during the time period t under the conventional planning mode.

[0131] (4b) Dynamic time-series model of energy storage system resource operation, the specific expression is as follows:

[0132]

[0133] In the formula: The energy stored in the energy storage system of the intelligent agent is optimized under the time period t. The energy stored in the energy storage system of the intelligent agent is determined under the optimized operation decision mode of time period t-1. The self-discharge rate of energy storage system resources in an intelligent agent; To improve the charging efficiency of energy storage systems in intelligent agents; The energy storage system's resource discharge efficiency in an intelligent agent; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The operating power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t-1; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t-1; This refers to the time step for sampling running data. To optimize the energy storage system resources in the intelligent agent during the initial operation period of the energy storage system; To optimize the energy storage system's resources during the last period of operation in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; For the energy storage system resources in the intelligent agent during the time period Optimize discharge power under the operation decision mode; For the energy storage system resources in the intelligent agent during the time period Optimize charging power under the operation decision mode.

[0134] (4c) Energy storage system resource charging and discharging power constraints, the specific expression is as follows:

[0135]

[0136] In the formula: The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; This is a flag indicating the charging status of the energy storage system resources for the intelligent agent during time period t. The value is 0 or 1. A value of 1 indicates a charging state, and a value of 0 indicates a non-charging state. This is a flag indicating the energy storage system resource discharge status of the intelligent agent in time period t. It takes a value of 0 or 1. A value of 1 indicates a discharge state, and a value of 0 indicates a non-discharge state. The maximum charging and discharging power is determined under the resource optimization operation decision-making mode of the energy storage system in the intelligent agent.

[0137] (4d) Boundary constraints for the safe operation of energy storage system resources, the specific expressions are as follows:

[0138]

[0139] In the formula: The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The energy stored in the energy storage system of the intelligent agent is optimized under the time period t. The minimum energy state coefficient of the energy storage system in the intelligent agent; The rated energy storage capacity of the energy storage system in the intelligent agent; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The energy state coefficient of the maximum stored energy in the energy storage system of the intelligent agent; The operating power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t; A special boundary constraint on the charging power of energy storage system resources in an intelligent agent under the optimized operation decision-making mode of time period t; This refers to a special boundary for the discharge power of energy storage system resources in an intelligent agent under the optimal operation decision-making mode during time period t.

[0140] (5) Mathematical model of resource modules for electric thermal storage central air conditioning system, specifically including:

[0141] (5a) Economic analysis model for resource operation of electric thermal storage central air conditioning system, the specific expression of which is as follows:

[0142]

[0143] In the formula: The equivalent net benefit of conventional planned operation and optimized operation of the electric thermal storage central air conditioning system in the intelligent body; The total operating cost of optimizing the operation of the electric thermal storage central air conditioning system in the intelligent body; The total operating cost of the conventional resource plan for the electric thermal storage central air conditioning system in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent during the normal mode of time period t; This refers to the time step for sampling running data. The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimized operation decision mode; The operating power of the electric thermal storage central air conditioning system in the intelligent body under the conventional planning mode of time period t; The thermal storage power of the central air conditioning system with electric thermal storage in the intelligent agent under the conventional planning mode of time period t; The heating power of the electric thermal storage central air conditioning system in the intelligent body under the conventional planning mode of time period t.

[0144] (5b) The dynamic time-series model of the operation of the thermal storage tank in the electric thermal storage central air conditioning system is shown in the following expression:

[0145]

[0146] In the formula: The thermal energy stored in the thermal storage tank of the central air conditioning system for electric thermal storage in the intelligent agent is determined under the optimized operation decision mode of time period t. The thermal energy stored in the thermal storage tank of the central air conditioning system with electric thermal storage in the intelligent agent is determined under the optimal operation decision mode of time period t-1. The self-loss heat rate of the heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent; The heat storage efficiency of the heat storage tank in the central air conditioning system for electric heat storage in the intelligent agent; The heating efficiency of the heat storage tank in the central air conditioning system for electric thermal storage in the intelligent body; The operating power of the heat storage tank of the electric heat storage central air conditioning system in the intelligent agent under the optimized operation decision mode of time period t; The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimized operation decision mode; The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t; The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t-1; The heat storage capacity of the heat storage tank in the central air conditioning system with electric heat storage in the intelligent agent under the optimized operation decision mode of time period t-1; This refers to the time step for sampling running data. Optimize the thermal energy storage capacity of the thermal storage tank in the initial operation period of the electric thermal storage central air conditioning system in the intelligent body; Optimize the thermal energy storage of the thermal storage tank in the last period of operation of the central air conditioning system for electric thermal storage in the intelligent body; The total number of time periods within the operating cycle, and the value is a positive integer; The heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent during the time period Optimize heating power under the optimal operating decision mode; The heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent during the time period Optimize the thermal storage power under the operation decision mode.

[0147] (5c) The power constraint of the thermal storage tank for the electric thermal storage central air conditioning system is given by the following expression:

[0148]

[0149] In the formula: The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t; The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimized operation decision mode; This is a flag indicating the thermal storage status of the thermal storage tank in the electric thermal storage central air conditioning system resources of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates the thermal storage status, and when the value is 0, it indicates the non-thermal storage status. This is a flag indicating the heating status of the thermal storage tank in the electric thermal storage central air conditioning system resources of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the heating status is on, and when the value is 0, it indicates that the heating status is off. The maximum charging and heating power of the heat storage tank in the intelligent body's electric thermal storage central air conditioning system is determined under the optimized operation decision mode.

[0150] (5d) The boundary constraints for the safe operation of the thermal storage tank in the electric thermal storage central air conditioning system are expressed as follows:

[0151]

[0152] In the formula: The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The thermal energy stored in the thermal storage tank of the central air conditioning system for electric thermal storage in the intelligent agent is determined under the optimized operation decision mode of time period t. The minimum energy state coefficient of the thermal storage tank in the electric thermal storage central air conditioning system resource of the intelligent agent; The rated thermal energy storage capacity of the thermal storage tank in the central air conditioning system for electric thermal storage in the intelligent body; The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimized operation decision mode; The maximum thermal energy state coefficient of the thermal storage tank in the central air conditioning system of the intelligent agent. The operating power of the heat storage tank of the electric heat storage central air conditioning system in the intelligent agent under the optimized operation decision mode of time period t; The thermal storage capacity of the thermal storage tank in the central air conditioning system of the intelligent agent is subject to a special limit boundary under the time period t optimization operation decision mode. The heating power limit boundary for the heat storage tank of the electric thermal storage central air conditioning system in the intelligent agent under the time period t optimization operation decision mode.

[0153] (5e) Thermal power balance constraint of electric thermal storage central air conditioning system, the specific expression is as follows:

[0154]

[0155] In the formula: The heating power of the electric boiler in the electric thermal storage central air conditioning system resource of the intelligent agent under the time period t optimized operation decision mode; The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t; The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimized operation decision mode; The heat load power demand of the main intelligent system under the conventional plan in time period t; The heat wastage power of the main intelligent system during time period t; This is a flag indicating the permitted status of heat rejection in the electric thermal storage central air conditioning system within the intelligent agent. It takes the value 0 or 1. A value of 1 indicates that heat rejection is permitted, while a value of 0 indicates that heat rejection is not permitted.

[0156] (5f) The dynamic time-series model of electric boiler operation for electric thermal storage central air conditioning system resources is shown in the following expression:

[0157]

[0158] In the formula: The heating power of the electric boiler in the electric thermal storage central air conditioning system of the intelligent body under the conventional planning mode of time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent during the normal mode of time period t; The heating power of the electric boiler in the electric thermal storage central air conditioning system resource of the intelligent agent under the time period t optimized operation decision mode; This is a flag indicating the heating status of the electric boiler in the electric thermal storage central air conditioning system resource in the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the boiler is heating the thermal storage tank. When the value is 0, it indicates that the boiler is not heating the thermal storage tank. This is a flag indicating the heating status of the electric boiler in the electric thermal storage central air conditioning system of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the boiler is supplying heat to the heat load. When the value is 0, it indicates that the boiler is not supplying heat to the heat load. The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimized operation decision mode; The heating efficiency of the electric boiler host in the electric thermal storage central air conditioning system resources of the intelligent body; This is a flag indicating the thermal storage status of the thermal storage tank in the electric thermal storage central air conditioning system resources of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates the thermal storage status, and when the value is 0, it indicates the non-thermal storage status. The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimization operation decision mode.

[0159] (5g) The safety operation constraints of electric boilers for electric thermal storage central air conditioning systems are specifically expressed as follows:

[0160]

[0161] In the formula: This is a flag indicating the heating status of the electric boiler in the electric thermal storage central air conditioning system resource in the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the boiler is heating the thermal storage tank. When the value is 0, it indicates that the boiler is not heating the thermal storage tank. This is a flag indicating the heating status of the electric boiler in the electric thermal storage central air conditioning system of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the boiler is supplying heat to the heat load. When the value is 0, it indicates that the boiler is not supplying heat to the heat load. The start-up and shutdown coefficient of the electric boiler in the electric thermal storage central air conditioning system resources of the intelligent body; The installed capacity of electric boilers for the electric thermal storage central air conditioning system resources in the intelligent body; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimization operation decision mode.

[0162] (6) Mathematical model of charging pile system resource module, specifically including:

[0163] (6a) Economic analysis model for the resource operation of charging pile system, the specific expression of which is as follows:

[0164]

[0165] In the formula: The equivalent net benefit of optimized operation of charging pile system resources in intelligent agents compared with conventional planned operation; The equivalent total electricity cost for optimizing the operation of the charging pile system in the intelligent agent; The equivalent total electricity cost of the charging pile system resources in the intelligent agent according to the conventional plan; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price for charging stations for the intelligent agent during time period t; The power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The electricity price paid by the intelligent agent during time period t; The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t;

[0166] (6b) The resource power adjustment model for the charging pile system is expressed as follows:

[0167]

[0168] In the formula: The power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode of time period t; The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t; To adjust the power of the charging load transferred to the charging pile system resources in the intelligent agent under the time period t optimization operation decision mode; In the intelligent agent, the power of the outgoing charging load is adjusted under the optimized operation decision-making mode of the charging pile system resources in time period t. This refers to the time step for sampling running data. The starting period for adjusting the charging load power in the charging pile system resources of the intelligent agent under the optimized operation decision mode; This refers to the end point in which the charging load power of the charging pile system resources in the intelligent agent is allowed to be adjusted under the optimized operation decision mode.

[0169] (6c) Resource security adjustment constraints for charging pile systems, the specific expression of which is as follows:

[0170]

[0171] In the formula: The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t; To adjust the power of the charging load transferred to the charging pile system resources in the intelligent agent under the time period t optimization operation decision mode; In the intelligent agent, the power of the outgoing charging load is adjusted under the optimized operation decision-making mode of the charging pile system resources in time period t. The maximum tolerance coefficient for adjusting the outgoing charging load of the charging pile system resources in the intelligent agent under the time period t optimization operation decision mode; The maximum tolerance coefficient for adjusting the charging load transferred to the charging pile system resources in the intelligent agent under the time period t optimization operation decision mode.

[0172] (7) Construct the mathematical model of the main system module, specifically including:

[0173] (7a) The main system economic optimization operation analysis model is specifically expressed as follows:

[0174]

[0175] In the formula: To optimize the equivalent net income during the operation of the intelligent agent main system that aggregates multiple types of resources; The total operating cost of the main system for aggregating multiple types of resources during regular scheduled operation; To optimize the total operating cost of the main system for aggregating multiple types of resources during operation; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The normal power purchase capacity of the intelligent agent's communication line during time period t; The photovoltaic feed-in tariff for the intelligent agent during time period t; The typical electricity sales power of the intelligent agent via the interconnection line during time period t; The electricity price for charging stations for the intelligent agent during time period t; The power of a typical charging station for the intelligent agent during time period t; This refers to the time step for sampling running data. Optimize the power purchase capacity of the agent's communication line during time period t; Optimize the power sales of the intelligent agent's connection during time period t; Optimize the charging pile power for the intelligent agent during time period t; The power supplied to the grid by the photovoltaic resources in the intelligent agent during the normal time period t; The power supplied to the grid by photovoltaic resources in the intelligent agent under the optimized operation decision-making mode of time period t;

[0176] (7b) Main system tie-line capacity constraint, the specific expression is as follows:

[0177]

[0178] In the formula: Optimize the power purchase capacity of the agent's communication line during time period t; Purchase power capacity for the main system interconnection line of the intelligent agent; Optimize the power sales of the intelligent agent's connection during time period t; Power capacity for the main system interconnection line of the intelligent agent; This is the power purchase status flag of the agent in time period t, with a value of 0 or 1. A value of 1 indicates a power purchase status, and a value of 0 indicates a non-power purchase status. This is the power sales status flag of the agent in time period t, with a value of 0 or 1. A value of 1 indicates power sales status, and a value of 0 indicates no power sales status.

[0179] (7c) Main system power balance constraint, the specific expression is as follows:

[0180]

[0181] In the formula: The normal power purchase capacity of the intelligent agent's communication line during time period t; The power supplied to the grid by the photovoltaic resources in the intelligent agent during the normal time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The discharge power of the energy storage system resources in the intelligent agent under normal mode during time period t; The charging power of the energy storage system resources in the intelligent agent under the normal mode of time period t; The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent during the normal mode of time period t; The power consumption of the intelligent agent's main system during time period t is the power consumption of the non-regulating load. Optimize the power purchase capacity of the agent's communication line during time period t; The power supplied to the grid by photovoltaic resources in the intelligent agent under the optimized operation decision-making mode of time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode of time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimization operation decision mode.

[0182] Among them, the main system power balance constraint couples the mathematical models of the new energy photovoltaic system resource module, the energy storage system resource module, the electric thermal storage central air conditioning system resource module, and the charging pile system resource module through the interface variables of the photovoltaic system resource module, the interface variables of the energy storage system resource module, the interface variables of the electric thermal storage central air conditioning system resource module, and the interface variables of the charging pile system resource module, so that multiple types of resources are aggregated to form aggregated multi-type resource group interface variables;

[0183] The interface variables of the photovoltaic system resource module are the power supplied to the grid by the photovoltaic resources in the agent under the optimized operation decision mode in each time period, and the power supplied to the main system load by the photovoltaic resources in the agent under the optimized operation decision mode in each time period.

[0184] The interface variables of the energy storage system resource module are the discharge power and charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in each time period.

[0185] The interface variable of the resource module of the electric thermal storage central air conditioning system is the power consumption of the electric boiler host of the electric thermal storage central air conditioning system in the intelligent agent under the optimized operation decision mode at various time periods;

[0186] The interface variable of the charging pile system resource module is the power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode at various time periods;

[0187] The main system power balance constraint optimizes the coupling of the purchased power variable and the interface variable of the aggregated multi-type resource group through the tie line, so that the agent is coupled with the power grid.

[0188] The main system power balance constraint couples the power consumption variables of non-regulated loads with the interface variables of aggregated multi-type resource groups, so that the agent is coupled with the load internally;

[0189] The tie-line optimized power purchase variable is the tie-line optimized power purchase of the agent at each time period;

[0190] The unregulated load power consumption variable is the unregulated load power consumption of the intelligent agent master system at various time periods.

[0191] (8) Construct a mathematical model for the modular design control flag variable parameter quantity definition and configuration module in the intelligent agent. The specific expression is as follows:

[0192]

[0193] In the formula: Modular design of the set of control flag variables for intelligent agents; This is a control flag variable indicating whether energy storage system resources participate in optimized operation. It takes a value of 0 or 1. A value of 0 indicates that energy storage system resources do not participate in optimized operation, and a value of 1 indicates that energy storage system resources participate in optimized operation. This is a control flag variable indicating whether new energy photovoltaic system resources participate in optimized operation. The value is 0 or 1. A value of 0 indicates that new energy photovoltaic system resources do not participate in optimized operation, and a value of 1 indicates that new energy photovoltaic system resources participate in optimized operation. This is a control flag variable for whether the charging pile system resources participate in optimized operation. The value is 0 or 1. A value of 0 indicates that the charging pile system resources do not participate in optimized operation, and a value of 1 indicates that the charging pile system resources participate in optimized operation. This is a control flag variable indicating whether the resources of the electric thermal storage central air conditioning system participate in optimized operation. The value is 0 or 1. A value of 0 indicates that the resources of the electric thermal storage central air conditioning system do not participate in optimized operation, and a value of 1 indicates that the resources of the electric thermal storage central air conditioning system participate in optimized operation. The operating power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t; The operating power of the energy storage system resources in the intelligent agent under the conventional planning mode during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode of time period t; The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimized operation decision mode; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent body during the normal mode of time period t.

[0194] In the intelligent agent, the modular design control flag variable parameter quantity definition configuration module mathematical model defines and decides which variables among the photovoltaic system resource module interface variables, energy storage system resource module interface variables, electric thermal storage central air conditioning system resource module interface variables, and charging pile system resource module interface variables participate in the optimized operation decision. That is, it defines and decides which resources in the aggregated multi-type resource group participate in the optimized operation decision. The control flag variable for whether a resource participates in the optimized operation takes a value of 0 or 1. A value of 0 indicates that the energy storage system resource does not participate in the optimized operation and adopts the conventional mode, while a value of 1 indicates that the energy storage system resource participates in the optimized operation but does not adopt the conventional mode.

[0195] (9) Construct a mathematical model for the auxiliary service market module. The mathematical model for the auxiliary service market module includes a mathematical model for the stage before the clearing of the auxiliary service market by the intelligent agent and a mathematical model for the stage after the clearing of the auxiliary service market by the intelligent agent. In actual optimization operation, the value of the optimization decision control flag variable of the intelligent agent main system of aggregated multi-resources participating in the clearing of the auxiliary service market determines whether it is the stage before clearing. The value of the optimization decision control flag variable of the intelligent agent main system of aggregated multi-resources participating in the clearing of the auxiliary service market is 0 or 1. When the value is 1, it represents the optimization decision of the intelligent agent main system of aggregated multi-resources participating in the clearing of the auxiliary service market. When the value is 0, it represents the optimization decision of the intelligent agent main system of aggregated multi-resources participating in the clearing of the auxiliary service market.

[0196] (9a) Mathematical model for the pre-clearing phase of the auxiliary service market involving intelligent agents, specifically including:

[0197] (9a-1) Objective function for the agent's optimization decision-making before clearing;

[0198] The objective function for optimizing the operation of an intelligent agent before market clearing refers to maximizing the equivalent net income of the main system of an intelligent agent aggregating multiple types of resources before market clearing in the ancillary services market. The specific expression of the objective function for optimizing the operation before market clearing is as follows:

[0199]

[0200] In the formula: The equivalent net income after the main system of the aggregated intelligent agent participates in the optimization decision-making process before the clearing of the auxiliary service market; The total operating cost of the main system of the intelligent agent under the normal operating mode before the market clearing out of the auxiliary services market; The total operating cost of the main system of the intelligent agent under the optimized operation decision-making model before the market clearing of the auxiliary services market; This variable serves as a control flag for the optimization decision-making of the aggregated multi-resource intelligent agent main system before the ancillary service market clearing process. It takes a value of 0 or 1. A value of 1 indicates the optimization decision-making of the aggregated multi-resource intelligent agent main system before the ancillary service market clearing process, while a value of 0 indicates the optimization decision-making of the aggregated multi-resource intelligent agent main system after the ancillary service market clearing process.

[0201] (9a-2) Total operating cost of the agent's main system under normal operating conditions;

[0202] The specific expression for the calculation model of the total operating cost of the agent's main system under the normal operating mode before the clearing of the auxiliary service market is as follows:

[0203]

[0204] In the formula: The total operating cost of the main system of the intelligent agent under the normal operating mode before the market clearing out of the auxiliary services market; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The normal power purchase capacity of the intelligent agent's communication line during time period t; The photovoltaic feed-in tariff for the intelligent agent during time period t; The typical electricity sales power of the intelligent agent via the interconnection line during time period t; The electricity price for charging stations for the intelligent agent during time period t; The power of a typical charging station for the intelligent agent during time period t; This is the time step for sampling running data.

[0205] (9a-3) The total operating cost of the agent's main system before clearing under the optimized operation decision mode;

[0206] The specific expression for the calculation model of the total operating cost of the agent's main system under the optimal operation decision-making mode before the clearing of the auxiliary service market is as follows:

[0207]

[0208] In the formula: The total operating cost of the main system of the intelligent agent under the optimized operation decision-making model before the market clearing of the auxiliary services market; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; Optimize the power purchase capacity of the agent's communication line during time period t; The photovoltaic feed-in tariff for the intelligent agent during time period t; Optimize the power sales of the intelligent agent's connection during time period t; The electricity price for charging stations for the intelligent agent during time period t; Optimize the charging pile power for the intelligent agent during time period t; This refers to the time step for sampling running data. The total compensation cost obtained from the optimization assessment before the clearing of the auxiliary services market for intelligent agents.

[0209] (9a-4) Pre-clearance optimization assessment compensation cost calculation model;

[0210] The specific expression for the calculation model of the total compensation cost obtained from the optimization assessment before the clearing of the ancillary services market by the intelligent agent is as follows:

[0211]

[0212] In the formula: This represents the reference power of the agent during time period t. The conventional power purchase capacity of the agent's communication line in time period t, based on historical data; The reference power calculation rule function; Optimize the power purchase capacity of the agent's communication line during time period t; Optimize the power purchase capacity of the tie line during time period t before the clearing out of the ancillary services market for intelligent agents; The adjustment power of the intelligent agent in time period t before the market clearing of the auxiliary services market; This is a marker indicating the direction of intelligent agents' participation in the auxiliary service market regulation. The value is 1 or -1. When the value is 1, it indicates the direction of filling valleys, and when the value is -1, it indicates the direction of peak shaving. This marks the initial period for intelligent agents to participate in the assistive services market. The end of the period when intelligent agents participate in the assistive services market; The effective power of compensation adjustment in time period t before the clearing out of the auxiliary service market for intelligent agents; Compensation fees obtained for the intelligent agent's optimization assessment during time period t before the market clearing of the auxiliary services market; The bid price for intelligent agents in time period t before the market clearing out of the auxiliary services market; This refers to the time step for sampling running data. The total compensation cost obtained from the optimization assessment before the clearing of the auxiliary services market for intelligent agents.

[0213] The mathematical model for the module of intelligent agents participating in the ancillary services market clearing stage is a mixed integer nonlinear optimization model. After processing by optimization solution algorithm or general optimization solution engine, the optimization operation decision results of intelligent agents participating in the ancillary services market clearing stage are obtained. The optimization operation decision results include intelligent agent adjustment potential assessment results and participation in ancillary services application suggestions.

[0214] The assessment results of the agent's regulatory potential refer to the regulatory power values ​​of the agent in each time period before the agent participates in the ancillary services market clearing, and the effective amount of compensation regulatory power values ​​of the agent in each time period before the agent participates in the ancillary services market clearing.

[0215] The suggestion to participate in the ancillary services application refers to:

[0216] ① When the equivalent net income value of the intelligent agent main system that aggregates multiple types of resources is greater than 0 after participating in the optimization decision before the market clearing of ancillary services, and at the same time the adjustment power value of the intelligent agent is greater than 0 in certain periods before the market clearing of ancillary services, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation and management party participate in the application for ancillary services, and it is recommended that the adjustment power declared does not exceed the adjustment power value of the intelligent agent in each period before the market clearing of ancillary services.

[0217] ② When the equivalent net income value of the intelligent agent main system that aggregates multiple types of resources is greater than 0 after participating in the optimization decision before the clearing of the ancillary service market, and at the same time the adjustment power value of the intelligent agent in each time period before participating in the clearing of the ancillary service market is less than or equal to 0, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation management party not participate in the application for ancillary services.

[0218] ③ When the equivalent net income of the main system of the aggregated multi-resource intelligent agent is less than or equal to 0 after participating in the optimization decision before the market clearing of ancillary services, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation and management party not participate in the application for ancillary services.

[0219] (9b) Mathematical model of the module for intelligent agents participating in the post-clearing phase of the ancillary services market, specifically including:

[0220] (9b-1) The objective function for the agent's optimization decision-making after clearing;

[0221] The objective function for optimizing the operation of the intelligent agent after clearing refers to maximizing the equivalent net income of the main system of the intelligent agent aggregating multiple types of resources after participating in the clearing of the ancillary service market. The specific expression of the objective function for optimizing the operation after clearing is as follows:

[0222]

[0223] In the formula: The equivalent net income after the main system of aggregating multiple types of resource intelligent agents participates in the optimization decision-making process following the clearing of the auxiliary service market; The total operating cost of the main system of the intelligent agent under the normal operating mode after the market clearing out of the intelligent agent's participation in the auxiliary services market; The total operating cost of the agent's main system under the optimized operational decision-making model after the clearing of the auxiliary service market; This variable serves as a control flag for the optimization decision-making of the aggregated multi-resource intelligent agent main system before the ancillary service market clearing process. It takes a value of 0 or 1. A value of 1 indicates the optimization decision-making of the aggregated multi-resource intelligent agent main system before the ancillary service market clearing process, while a value of 0 indicates the optimization decision-making of the aggregated multi-resource intelligent agent main system after the ancillary service market clearing process.

[0224] (9b-2) Total operating cost of the agent's main system under normal operating conditions;

[0225] The specific expression for the calculation model of the total operating cost of the agent's main system under the normal operating mode after the clearing of the auxiliary service market is as follows:

[0226]

[0227] In the formula: The total operating cost of the main system of the intelligent agent under the normal operating mode after the market clearing out of the intelligent agent's participation in the auxiliary services market; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The normal power purchase capacity of the intelligent agent's communication line during time period t; The photovoltaic feed-in tariff for the intelligent agent during time period t; The typical electricity sales power of the intelligent agent via the interconnection line during time period t; The electricity price for charging stations for the intelligent agent during time period t; The power of a typical charging station for the intelligent agent during time period t; This is the time step for sampling running data.

[0228] (9b-3) The total operating cost of the agent's main system after clearing under the optimized operation decision mode;

[0229] The specific expression for the calculation model of the total operating cost of the agent's main system under the optimized operation decision-making mode after the agent participates in the auxiliary service market clearing is as follows:

[0230]

[0231] In the formula: The total operating cost of the agent's main system under the optimized operational decision-making model after the clearing of the auxiliary service market; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; Optimize the power purchase capacity of the agent's communication line during time period t; The photovoltaic feed-in tariff for the intelligent agent during time period t; Optimize the power sales of the intelligent agent's connection during time period t; The electricity price for charging stations for the intelligent agent during time period t; Optimize the charging pile power for the intelligent agent during time period t; This refers to the time step for sampling running data. The total penalty cost for optimizing operational decision-making assessment after the clearing of the auxiliary service market for intelligent agents; The total compensation cost obtained by intelligent agents for optimizing operational decisions after the market clearing of auxiliary services.

[0232] (9b-4) Calculation model for compensation costs of optimized operation decision-making after clearing;

[0233] The specific expression for the calculation model of the total compensation cost obtained by the intelligent agent in optimizing operational decisions after the clearing of the auxiliary service market is as follows:

[0234]

[0235] In the formula: The compensation fee obtained by the intelligent agent for optimizing operational decisions during time period t after the market clearing of the auxiliary services market; The total compensation fee obtained by the intelligent agent for optimizing operational decisions after the market clearing of the auxiliary services market; The effective power of compensation adjustment in time period t after the intelligent agent participates in the auxiliary service market clearing; The clearing price for the intelligent agent in time period t after the agent participates in the auxiliary services market clearing; This indicates whether an auxiliary service market is needed and whether regulation is required; its value is 0 or 1. This refers to the time step for sampling running data. This marks the initial period for intelligent agents to participate in the assistive services market. The end of the period when intelligent agents participate in the assistive services market;

[0236] (9b-5) Calculation model for penalty costs of optimized operation decision-making after clearing;

[0237] The specific expression for the penalty cost calculation model of the assessment of the optimized operation decision-making evaluation after the clearing of the auxiliary service market by the intelligent agent is as follows:

[0238]

[0239] In the formula: The penalty cost for evaluating the optimized operation decision-making of the intelligent agent in time period t after the market clearing of the auxiliary services market; The total penalty cost for optimizing operational decision-making assessment after the clearing of the auxiliary service market for intelligent agents; The assessment and penalty ratio coefficient for intelligent agents after the market clearing of auxiliary services in time period t; The actual adjustment power of the intelligent agent in time period t after the market clearing out of the auxiliary services market; The clearing price for the intelligent agent in time period t after the agent participates in the auxiliary services market clearing; This refers to the time step for sampling running data. This indicates whether an auxiliary service market is needed and whether regulation is required; its value is 0 or 1. This marks the initial period for intelligent agents to participate in the assistive services market. This refers to the end of the period when intelligent agents participate in the auxiliary services market.

[0240] (9b-6) Post-clearance optimization operation decision-making assessment compensation settlement model;

[0241] The specific expression for the post-clearance optimization operation decision-making assessment compensation settlement model is as follows:

[0242]

[0243] In the formula: This represents the reference power of the agent during time period t. The conventional power purchase capacity of the agent's communication line in time period t, based on historical data; The reference power calculation rule function; Optimize the power purchase capacity of the agent's communication line during time period t; Optimize the power purchase capacity of the tie line during time period t after the intelligent agent participates in the ancillary services market clearing; The actual adjustment power of the intelligent agent in time period t after the market clearing out of the auxiliary services market; This is a marker indicating the direction of intelligent agents' participation in the auxiliary service market regulation. The value is 1 or -1. When the value is 1, it indicates the direction of filling valleys, and when the value is -1, it indicates the direction of peak shaving. Optimize the power purchase capacity of the agent's communication line during time period t; This marks the initial period for intelligent agents to participate in the assistive services market. The end of the period when intelligent agents participate in the assistive services market; The effective power of compensation adjustment in time period t after the intelligent agent participates in the auxiliary service market clearing; The clearing power of an intelligent agent in the auxiliary service market during time period t after the agent has exited the market; This indicates whether an auxiliary service market is needed and whether regulation is required; its value is 0 or 1. , Different numerical assessment coefficients are used to optimize operational decisions after the clearing process.

[0244] The mathematical model for the post-clearing phase of the ancillary services market for intelligent agents is a mixed-integer nonlinear optimization model. After processing by an optimization solution algorithm or a general optimization solution engine, the optimized operation decision results for the post-clearing phase of the ancillary services market for intelligent agents are obtained. The optimized operation decision results include a demonstration of the main effects of the intelligent agents' participation in the ancillary services market's implementation of adjustments.

[0245] The main effects of intelligent agents participating in the ancillary services market regulation are demonstrated by the following: the equivalent net income after the intelligent agent main system participates in the ancillary services market clearing and makes optimized decisions; the total operating cost of the intelligent agent main system under normal operating mode after the intelligent agent participates in the ancillary services market clearing; the total operating cost of the intelligent agent main system under optimized operating decision mode after the intelligent agent participates in the ancillary services market clearing; the compensation fee obtained by the intelligent agent participating in the ancillary services market clearing in each time period; the total compensation fee obtained by the intelligent agent participating in the ancillary services market clearing in each time period; the effective compensation regulation power in time period t after the intelligent agent participates in the ancillary services market clearing; the penalty fee for the optimized operating decision assessment in each time period after the intelligent agent participates in the ancillary services market clearing; the total penalty fee for the optimized operating decision assessment in each time period after the intelligent agent participates in the ancillary services market clearing; the optimized power purchase of the tie line in each time period after the intelligent agent participates in the ancillary services market clearing; and the actual regulation power in each time period after the intelligent agent participates in the ancillary services market clearing.

[0246] The demonstration of the main effects of intelligent agents participating in the regulation of the ancillary services market can effectively assist intelligent agent operators or managers in directly and quickly grasping and understanding the overall effect and resource power operation status of intelligent agents, and then making necessary operation and maintenance and manual intervention adjustments.

[0247] (10) Outputting agent data information (equivalent to the agent outputting data information), specifically including:

[0248] Mathematical model data information for new energy photovoltaic system resource modules: including the power supplied to the main system load under the optimized operation decision mode, the power supplied to the grid under the optimized operation decision mode, the equivalent net benefit of the optimized operation of new energy photovoltaic system resources compared with the conventional planned operation, the equivalent total electricity cost of the optimized operation of new energy photovoltaic system resources, the equivalent total electricity cost of the conventional plan of new energy photovoltaic system resources, the power generation reduction under the optimized operation decision mode of photovoltaic resources, the photovoltaic self-consumption rate of photovoltaic resources during the operation cycle under the conventional mode, and the photovoltaic self-consumption rate of photovoltaic resources during the operation cycle under the optimized operation decision mode;

[0249] Mathematical model data information for energy storage system resource modules: including the net benefit difference between optimized operation and conventional planned operation of energy storage system resources, net benefit of optimized operation of energy storage system resources, net benefit of conventional planned operation of energy storage system resources, discharge power under optimized operation decision mode of energy storage system resources, charging power under optimized operation decision mode of energy storage system resources, operating power under optimized operation decision mode of energy storage system resources, and stored energy under optimized operation decision mode of energy storage system resources;

[0250] Mathematical model data information for the resource module of the electric thermal storage central air conditioning system: including the equivalent net benefit of the electric thermal storage central air conditioning system resource conventional planned operation and optimized operation, the total operating cost of the electric thermal storage central air conditioning system resource optimized operation, the total operating cost of the electric thermal storage central air conditioning system resource conventional planned operation, the power consumption of the electric boiler host of the electric thermal storage central air conditioning system resource under the optimized operation decision mode, the heat storage power of the heat storage tank of the electric thermal storage central air conditioning system resource under the optimized operation decision mode, the heating power of the heat storage tank of the electric thermal storage central air conditioning system resource under the optimized operation decision mode, and the operating power of the heat storage tank of the electric thermal storage central air conditioning system resource under the optimized operation decision mode;

[0251] Mathematical model data information of charging pile system resource module: including power consumption under the charging pile system resource optimization operation decision mode, power of adjusting the incoming charging load under the charging pile system resource optimization operation decision mode, and power of adjusting the outgoing charging load under the charging pile system resource optimization operation decision mode.

[0252] Mathematical model data information of the main system module: including the equivalent net income during the economic optimization operation of the main system of aggregated multi-resource intelligent agent, the total operating cost during the conventional planned operation of the main system of aggregated multi-resource intelligent agent, the total operating cost during the economic optimization operation of the main system of aggregated multi-resource intelligent agent, the optimized power purchase capacity of the tie line, and the optimized power sale capacity of the tie line;

[0253] The mathematical model data information for the ancillary service market module includes: the equivalent net income after optimization decisions by the intelligent agent main system participating in the ancillary service market before market clearing; the total operating cost of the intelligent agent main system under normal operating mode before market clearing; the total operating cost of the intelligent agent main system under optimized operating decision mode before market clearing; the total compensation cost obtained from optimization assessment before market clearing; the effective adjustment power of compensation before market clearing; the equivalent net income after optimization decisions by the intelligent agent main system participating in the ancillary service market after market clearing; the total operating cost of the intelligent agent main system under normal operating mode after market clearing; the total operating cost of the intelligent agent main system under optimized operating decision mode after market clearing; the total penalty cost of optimized operating decision assessment after market clearing; the total compensation cost obtained from optimized operating decision after market clearing; the actual adjustment power after market clearing; and the effective adjustment power of compensation after market clearing.

[0254] The mathematical model data of the new energy photovoltaic system resource module, the energy storage system resource module, the electric thermal storage central air conditioning system resource module, and the charging pile system resource module in the output intelligent agent data information are used to generate execution adjustment instructions. The execution adjustment instructions are output or sent to the multi-type resource execution adjustment mechanism to regulate the operation of the aggregated multi-type resources in the intelligent agent according to the execution adjustment instructions. At the same time, the execution adjustment instructions are backed up to the data storage device / server / workstation of the intelligent agent operation and maintenance party or the intelligent agent operation and management party, so that the intelligent agent operation and maintenance party or the intelligent agent operation and management party can view them at any time.

[0255] The mathematical model data of the main system module and the mathematical model data of the auxiliary service market module in the output intelligent agent data information are used to generate intelligent agent operation adjustment effect display curves or data tables. This can effectively assist the intelligent agent operation and maintenance party or intelligent agent operation and management party to directly and quickly grasp and understand the overall effect of intelligent agent operation, resource power operation status, and cost operation status, and then carry out necessary operation and maintenance and manual intervention adjustments. The intelligent agent operation adjustment effect display curves or data tables are also backed up to the data storage device / server / workstation of the intelligent agent operation and maintenance party or intelligent agent operation and management party, so that the intelligent agent operation and maintenance party or intelligent agent operation and management party can view them at any time.

[0256] Determining whether to adjust the scene or reset the operating data refers to the intelligent agent operation and maintenance party or intelligent agent operation management party determining whether to adjust the scene or reset the operating data based on the output intelligent agent data information, through human intention judgment, preset rules, preset typical thresholds or other standards.

[0257] Among these, the human willingness judgment, preset rules, preset typical thresholds, or other standards can be:

[0258] ① If the equivalent net income exceeds a certain value, do not adjust the scenario or reset the operating data; otherwise, adjust the scenario or reset the operating data.

[0259] ②If the power value is adjusted to a higher value than a certain value, do not adjust the scene or reset the operating data; otherwise, adjust the scene or reset the operating data.

[0260] ③ If the total compensation cost exceeds a certain value, the scene will not be adjusted or the running data will not be reset; otherwise, the scene will be adjusted or the running data will be reset.

[0261] ④ If the total operating cost of the main system exceeds a certain value, do not adjust the scenario or reset the operating data; otherwise, adjust the scenario or reset the operating data.

[0262] Example

[0263] The embodiment of the intelligent agent participating in the power market with multiple types of resources proposed in this invention is an intelligent agent system, and adopts the proposed optimal operation decision-making method. The specific implementation process of the embodiment is as follows: Figure 1 As shown in the figure. The data for photovoltaic grid connection price, electricity purchase price, and charging pile electricity sales price in the intelligent agent are as follows: Figure 2 As shown, the electricity price information can be either a fixed time-of-use price or a real-time price. Data on downstream power purchases and regular non-adjustable loads are as follows: Figure 3 As shown, according to Figure 3 Under the intelligent agent, the overall power consumption of the electric boiler is higher at night and lower during the day, while the power consumption of the conventional non-adjustable load remains stable throughout the day. The power consumption data of the electric boiler main unit in normal mode is as follows: Figure 4 As shown, according to Figure 4 The electric boiler's main unit is turned on at night and turned off during the day. During the day, heating is mainly supplied by the thermal storage tank to meet the heating load demand. The photovoltaic system resources include the total power generation of the photovoltaic resources and the power supplied to the grid under normal conditions. Figure 5 As shown. The period from 11:00 to 13:00 is the market adjustment period for ancillary services. The bid price for intelligent agents before participating in the ancillary services market clearing is RMB 0.25 / kWh, and the clearing price after participating in the ancillary services market clearing is also RMB 0.25 / kWh.

[0264] In the pre-clearance phase, the optimized power purchase capacity of the tie line and the regulation capacity before clearing are as follows: Figure 6 As shown, according to Figure 6Before the clearing process, the optimized power purchase capacity of the interconnection lines decreased significantly during the periods of 0:00-2:00 and 19:00-23:00. The optimized operation decision results before the clearing led to a change in the operating mode. Through this optimized operation mode, the regulating power before clearing exceeded 4000kW, indicating a significant regulating potential for the intelligent agent. The intelligent agent was optimized to demonstrate its potential to participate in the ancillary services market, enabling it to participate in electricity market ancillary services. The operating power of the energy storage system under the conventional planning strategy mode and the operating power under the optimized operation decision mode before clearing are as follows: Figure 7 As shown, according to Figure 7 Under the optimized operation decision-making mode before clearing, the operating power fully utilizes electricity price information. Through time-series shifting and changes in charging and discharging strategies, it adjusts the potential for participating in the ancillary services market, thereby further improving the equivalent net benefit of the intelligent agent. The power consumption of the charging pile system under the normal mode and the power consumption under the optimized operation decision-making mode before clearing are as follows: Figure 8 As shown, according to Figure 8 The power consumption of the charging station can be finely adjusted within a tolerable range, which reduces the operating cost of the intelligent agent and increases its adjustment flexibility without affecting the charging capacity and cost.

[0265] In the post-clearing phase, the cleared power, the optimized power purchase capacity of the tie line after clearing, and the actual regulating power after clearing are as follows: Figure 9 As shown, according to Figure 9 During the participation in the ancillary services market of the electricity market, the cleared power is 2500kW, and the actual regulating power after clearing is around 3500kW. This achieves the optimal results in post-clearing optimized operation decision-making, assessment, compensation, and settlement, resulting in the lowest overall operating cost for the intelligent agent and fully leveraging the resource allocation and regulation capabilities of various types of resources within the intelligent agent. The optimized net income after the intelligent agent main system, which aggregates multiple resource types, participates in the ancillary services market clearing is 12363.92 yuan. The optimal operating result can be obtained through the optimized operation decision-making method for intelligent agents aggregating multiple resource types participating in the electricity market proposed in this invention.

[0266] Based on the above analysis, the embodiments of the present invention fully consider the multi-type flexible resource operation characteristics of intelligent agents, provide a method for optimizing operation decision-making before and after intelligent agents participate in the power market clearing, realize a flexible configuration system for the entire chain of resource aggregation, intelligent optimization operation decision-making, and market interaction, achieve modular configuration configuration of multi-type flexible resources, leverage the multi-energy complementary advantages of multi-type flexible resources, and realize modular configuration configuration of intelligent agents for routine operation, economic operation, and participation in power market optimization operation decision-making. This is conducive to the flexible application of intelligent agents to multiple scenarios and business needs, realizes the collaborative configuration and interaction flexibility of multiple types of resources such as new energy photovoltaics, energy storage, electric thermal storage central air conditioning, and charging piles in intelligent agents, can effectively evaluate and calculate the aggregation potential of multiple types of flexible resources in intelligent agents, provide guidance and support for actual participation in ancillary service market capacity declaration, improve the economic efficiency of intelligent agent operation, and provide reference and guidance for the construction of intelligent agent optimization operation strategies, analysis of the potential of aggregation of multiple types of resources, generation of power market operation regulation optimization strategies, and analysis of improving the stable operation capability of power energy systems. In turn, it helps to promote the engineering application of intelligent agents in the power energy field and the analysis of power market-oriented optimization operation decision-making.

[0267] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores static and dynamic information data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the above method embodiments.

[0268] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0269] In addition, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0270] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0271] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention 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, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0272] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources in the electricity market, characterized in that, The method includes: Acquire input data information from the intelligent agent; Construct a multi-agent collaborative operation model library that includes mathematical models for defining and configuring intelligent agent operation parameters, mathematical models for multiple types of flexible resource modules, mathematical models for the main system module, mathematical models for defining and configuring modular design control flag variable parameters in intelligent agents, and mathematical models for auxiliary service market modules; The agent input data information is input into the multi-agent collaborative operation model library. The agent output data information is calculated by each model in the multi-agent collaborative operation model library. The agent output data information is integrated by integrating the agent output data information of each model to obtain the agent output data information. Based on the intelligent agent's output data, the system determines whether to adjust the scene or reset the running data according to preset rules. If so, it updates the intelligent agent's input data and returns to re-execute the optimization calculation. If not, it directly outputs the intelligent agent's output data and executes the intelligent agent's aggregated multi-type resource control scheme based on the intelligent agent's output data. The mathematical models for the various types of flexible resource modules include mathematical models for new energy photovoltaic system resource modules, energy storage system resource modules, electric thermal storage central air conditioning system resource modules, and charging pile system resource modules. The mathematical model of the ancillary services market module includes a mathematical model of the pre-clearing stage module for intelligent agents participating in the ancillary services market and a mathematical model of the post-clearing stage module for intelligent agents participating in the ancillary services market. Among them, the value of the optimization decision control flag variable before the clearing of the auxiliary service market is determined by the pre-set intelligent agent main system that aggregates multiple types of resources. The value of the optimization decision control flag variable is 0 or 1. When the value of the optimization decision control flag variable is 1, the optimization operation decision results of the intelligent agent participating in the auxiliary service market clearing stage module are generated by solving the mathematical model of the intelligent agent participating in the auxiliary service market clearing stage module. The optimization operation decision results before clearing include the intelligent agent adjustment potential assessment results and the application suggestions for participating in auxiliary services. When the value of the optimization decision control flag variable is 0, the optimization operation decision result after the participation of the intelligent agent in the ancillary service market clearing stage module is generated by solving the mathematical model of the intelligent agent participating in the ancillary service market clearing stage module. The optimization operation decision result after clearing includes the display of the intelligent agent's participation in the ancillary service market execution adjustment effect.

2. The method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources in the electricity market according to claim 1, characterized in that, The mathematical model of the resource module of the new energy photovoltaic system includes the economic analysis model of the resource operation of the new energy photovoltaic system, the power balance model of the resource operation of the new energy photovoltaic system, and the self-consumption rate analysis model of the new energy photovoltaic system. The mathematical model of the energy storage system resource module includes an economic analysis model for the operation of energy storage system resources, a dynamic time-series model for the operation of energy storage system resources, charging and discharging power constraints for energy storage system resources, and boundary constraints for the safe operation of energy storage system resources. The mathematical model of the electric thermal storage central air conditioning system resource module includes an economic analysis model of the operation of the electric thermal storage central air conditioning system resources, a dynamic time series model of the operation of the thermal storage tank of the electric thermal storage central air conditioning system resources, a power constraint of the charging and supply of the thermal storage tank of the electric thermal storage central air conditioning system resources, a safe operation boundary constraint of the thermal storage tank of the electric thermal storage central air conditioning system resources, a heat power balance constraint of the electric thermal storage central air conditioning system, and a dynamic time series model of the operation of the electric boiler of the electric thermal storage central air conditioning system resources. The mathematical model of the charging pile system resource module includes an economic analysis model for the operation of charging pile system resources, a power regulation model for charging pile system resources, and safety regulation constraints for charging pile system resources.

3. The method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources in the electricity market according to claim 2, characterized in that, The intelligent agent output data information includes: mathematical model output data information of new energy photovoltaic system resource module, mathematical model output data information of energy storage system resource module, mathematical model output data information of electric thermal storage central air conditioning system resource module, mathematical model output data information of charging pile system resource module, mathematical model output data information of main system module, and mathematical model output data information of auxiliary service market module; The execution of the multi-type resource regulation scheme in the intelligent agent based on the output data of the intelligent agent includes: The output data information of the mathematical model of the new energy photovoltaic system resource module, the output data information of the mathematical model of the energy storage system resource module, the output data information of the mathematical model of the electric thermal storage central air conditioning system resource module, and the output data information of the mathematical model of the charging pile system resource module are used to generate execution adjustment instructions. The execution adjustment instructions are output or issued to multiple types of resource execution adjustment mechanisms, and the multiple types of resources aggregated in the control agent operate according to the execution adjustment instructions. The output data information of the mathematical model of the main system module and the output data information of the mathematical model of the auxiliary service market module are used to generate intelligent agent operation adjustment effect display curves or databases.

4. The method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources in the electricity market according to claim 2, characterized in that, The expression for the resource operation economic analysis model of the new energy photovoltaic system is as follows: ； In the formula: The equivalent net benefit of optimizing the operation of new energy photovoltaic systems in an intelligent agent compared with conventional planned operation; The equivalent total electricity cost for the optimized operation of new energy photovoltaic systems in an intelligent agent; The equivalent total electricity cost of the conventional plan for new energy photovoltaic system resources in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The photovoltaic feed-in tariff for the intelligent agent during time period t; The power supplied to the grid by photovoltaic resources in the intelligent agent under the optimized operation decision-making mode of time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power supplied to the grid by the photovoltaic resources in the intelligent agent during the normal time period t; The expression for the resource operation power balance model of the new energy photovoltaic system is as follows: ； In the formula: The total power generation of photovoltaic resources in the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power supplied to the grid by the photovoltaic resources in the intelligent agent during the normal time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; The power supplied to the grid by photovoltaic resources in the intelligent agent under the optimized operation decision-making mode of time period t; In the intelligent agent, the photovoltaic resources are adjusted to reduce power generation under the time period t optimization operation decision mode; The expression for the resource self-consumption rate analysis model of the new energy photovoltaic system is as follows: ； In the formula: The total power generation of photovoltaic resources in the intelligent agent during time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the normal mode of time period t; The power supplied by photovoltaic resources in the intelligent agent to the main system load under the optimized operation decision mode of time period t; The total number of time periods within the operating cycle, and the value is a positive integer; The self-consumption rate of photovoltaic resources in the intelligent agent during the normal operating cycle; The self-consumption rate of photovoltaic resources in the intelligent agent during the operating cycle under the optimized operation decision mode.

5. The method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources in the electricity market according to claim 2, characterized in that, The expression for the energy storage system resource operation economic analysis model is as follows: ； In the formula: The net benefit difference between optimized operation and conventional planned operation of energy storage systems in an intelligent agent; The net benefit of optimizing the operation of energy storage systems in intelligent agents; The net benefit of the conventional resource planning for energy storage systems in an intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The discharge power of the energy storage system resources in the intelligent agent under the conventional planned mode during time period t; The charging power of the energy storage system resources in the intelligent agent under the conventional planned mode during time period t; The operating power of the energy storage system resources in the intelligent agent under the conventional planning mode during time period t; The expression for the dynamic time-series model of the energy storage system resource operation is: ； In the formula: The energy stored in the energy storage system of the intelligent agent is optimized under the time period t. The energy stored in the energy storage system of the intelligent agent is determined under the optimized operation decision mode of time period t-1. The self-discharge rate of energy storage system resources in an intelligent agent; To improve the charging efficiency of energy storage systems in intelligent agents; The energy storage system's resource discharge efficiency in an intelligent agent; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode of time period t; The operating power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t; The discharge power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t-1; The charging power of the energy storage system resources in the intelligent agent under the optimized operation decision mode in time period t-1; This refers to the time step for sampling running data. To optimize the energy storage system resources in the intelligent agent during the initial operation period of the energy storage system; To optimize the energy storage system's resources during the last period of operation in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; For the energy storage system resources in the intelligent agent during the time period Optimize discharge power under the operation decision mode; For the energy storage system resources in the intelligent agent during the time period Optimize charging power under the operation decision mode.

6. The method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources in the electricity market according to claim 2, characterized in that, The expression for the resource operation economic analysis model of the electric thermal storage central air conditioning system is as follows: ； In the formula: The equivalent net benefit of conventional planned operation and optimized operation of the electric thermal storage central air conditioning system in the intelligent body; The total operating cost of optimizing the operation of the electric thermal storage central air conditioning system in the intelligent body; The total operating cost of the conventional resource plan for the electric thermal storage central air conditioning system in the intelligent agent; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price paid by the intelligent agent during time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent during the normal mode of time period t; This refers to the time step for sampling running data. The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimized operation decision mode; The operating power of the electric thermal storage central air conditioning system in the intelligent body under the conventional planning mode of time period t; The thermal storage power of the central air conditioning system with electric thermal storage in the intelligent agent under the conventional planning mode of time period t; The heating power of the electric thermal storage central air conditioning system in the intelligent body under the conventional planning mode of time period t; The expression for the dynamic time-series model of the thermal storage tank operation of the electric thermal storage central air conditioning system is as follows: ； In the formula: The thermal energy stored in the thermal storage tank of the central air conditioning system for electric thermal storage in the intelligent agent is determined under the optimized operation decision mode of time period t. The thermal energy stored in the thermal storage tank of the central air conditioning system with electric thermal storage in the intelligent agent is determined under the optimal operation decision mode of time period t-1. The self-loss heat rate of the heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent; The heat storage efficiency of the heat storage tank in the central air conditioning system for electric heat storage in the intelligent agent; The heating efficiency of the heat storage tank in the central air conditioning system for electric thermal storage in the intelligent body; The operating power of the heat storage tank of the electric heat storage central air conditioning system in the intelligent agent under the optimized operation decision mode of time period t; The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimized operation decision mode; The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t; The heating power of the heat storage tank in the electric thermal storage central air conditioning system of the intelligent agent under the optimized operation decision mode of time period t-1; The heat storage capacity of the heat storage tank in the central air conditioning system with electric heat storage in the intelligent agent under the optimized operation decision mode of time period t-1; This refers to the time step for sampling running data. Optimize the thermal energy storage capacity of the thermal storage tank in the initial operation period of the electric thermal storage central air conditioning system in the intelligent body; Optimize the thermal energy storage of the thermal storage tank in the last period of operation of the central air conditioning system for electric thermal storage in the intelligent body; The total number of time periods within the operating cycle, and the value is a positive integer; The heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent during the time period Optimize heating power under the optimal operating decision mode; The heat storage tank for the electric thermal storage central air conditioning system resources in the intelligent agent during the time period Optimize thermal storage power under the optimal operating decision mode; The expression for the dynamic time-series model of the electric boiler operation of the electric thermal storage central air conditioning system resources is as follows: ； In the formula: The heating power of the electric boiler in the electric thermal storage central air conditioning system of the intelligent body under the conventional planning mode of time period t; The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent during the normal mode of time period t; The heating power of the electric boiler in the electric thermal storage central air conditioning system resource of the intelligent agent under the time period t optimized operation decision mode; This is a flag indicating the heating status of the electric boiler in the electric thermal storage central air conditioning system resource in the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the boiler is heating the thermal storage tank. When the value is 0, it indicates that the boiler is not heating the thermal storage tank. This is a flag indicating the heating status of the electric boiler in the electric thermal storage central air conditioning system of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates that the boiler is supplying heat to the heat load. When the value is 0, it indicates that the boiler is not supplying heat to the heat load. The power consumption of the electric boiler host in the electric thermal storage central air conditioning system of the intelligent agent under the time period t optimized operation decision mode; The heating efficiency of the electric boiler host in the electric thermal storage central air conditioning system resources of the intelligent body; This is a flag indicating the thermal storage status of the thermal storage tank in the electric thermal storage central air conditioning system resources of the intelligent agent during time period t. The value is 0 or 1. When the value is 1, it indicates the thermal storage status, and when the value is 0, it indicates the non-thermal storage status. The heat storage capacity of the heat storage tank in the intelligent agent's electric heat storage central air conditioning system resource under the time period t optimization operation decision mode.

7. The method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources in the electricity market according to claim 2, characterized in that, The expression for the economic analysis model of the charging pile system resource operation is as follows: ； In the formula: The equivalent net benefit of optimized operation of charging pile system resources in intelligent agents compared with conventional planned operation; The equivalent total electricity cost for optimizing the operation of the charging pile system in the intelligent agent; The equivalent total electricity cost of the charging pile system resources in the intelligent agent according to the conventional plan; The total number of time periods within the operating cycle, and the value is a positive integer; The electricity price for charging stations for the intelligent agent during time period t; The power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode of time period t; This refers to the time step for sampling running data. The electricity price paid by the intelligent agent during time period t; The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t; The expression for the resource power adjustment model of the charging pile system is: ； In the formula: The power consumption of the charging pile system resources in the intelligent agent under the optimized operation decision mode of time period t; The power consumption of the charging pile system resources in the intelligent agent during the normal mode of time period t; To adjust the power of the charging load transferred to the charging pile system resources in the intelligent agent under the time period t optimization operation decision mode; In the intelligent agent, the power of the outgoing charging load is adjusted under the optimized operation decision-making mode of the charging pile system resources in time period t. This refers to the time step for sampling running data. The starting period for adjusting the charging load power in the charging pile system resources of the intelligent agent under the optimized operation decision mode; This refers to the end point in which the charging load power of the charging pile system resources in the intelligent agent is allowed to be adjusted under the optimized operation decision mode.

8. The method for optimizing the operation decision-making of an intelligent agent that aggregates multiple types of resources to participate in the electricity market, as described in claim 7, is characterized in that... The recommendations for participating in ancillary service applications include: When the equivalent net income value of the intelligent agent main system that aggregates multiple types of resources is greater than 0 after participating in the optimization decision before the clearing of the ancillary service market, and at the same time the adjustment power value of the intelligent agent is greater than 0 in certain periods before the clearing of the ancillary service market, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation and management party participate in the application for ancillary services, and it is recommended that the adjustment power declared does not exceed the adjustment power value of the intelligent agent in each period before the clearing of the ancillary service market. When the equivalent net income value of the intelligent agent main system that aggregates multiple types of resources is greater than 0 after participating in the optimization decision before the clearing of the ancillary service market, and at the same time the adjustment power value of the intelligent agent in each time period before participating in the clearing of the ancillary service market is less than or equal to 0, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation management party not participate in the application for ancillary services. When the equivalent net income of the intelligent agent main system that aggregates multiple types of resources is less than or equal to 0 after participating in the optimization decision before the market clearing of ancillary services, it is recommended that the intelligent agent operation and maintenance party or the intelligent agent operation and management party not participate in the application for ancillary services.

9. A decision-making system for the optimal operation of an intelligent agent aggregating multiple types of resources participating in the electricity market, used to implement the decision-making method for the optimal operation of an intelligent agent aggregating multiple types of resources participating in the electricity market as described in any one of claims 1-8, characterized in that, The system includes: The agent data acquisition module is used to acquire the input data information of the agent. The decision-making model building module is used to build a multi-agent collaborative operation model library, which includes mathematical models of intelligent agent operation parameter definition and configuration modules, mathematical models of multi-type flexible resource modules, mathematical models of main system modules, mathematical models of modular design control flag variable parameter definition and configuration modules in intelligent agents, and mathematical models of auxiliary service market modules. The intelligent agent data information processing and execution module is used to input intelligent agent input data information into the multi-agent collaborative operation model library, calculate and output intelligent agent data information through each model in the multi-agent collaborative operation model library, and integrate the intelligent agent data information output by each model to obtain intelligent agent output data information. The decision output module is used to determine whether to adjust the scene or reset the running data based on the intelligent agent's output data information and preset rules. If yes, it updates the intelligent agent's input data information and returns to re-execute the optimization calculation. If no, it directly outputs the intelligent agent's output data and executes the aggregated multi-type resource control scheme in the intelligent agent according to the intelligent agent's output data.

Images