Power grid resource scheduling method and device based on distributed artificial intelligence agent

Abstract

The invention relates to a power grid resource scheduling method and device based on distributed artificial intelligence agency. The method is applied to an artificial intelligence agent, and comprises the steps of deploying the artificial intelligence agent on each resource scheduling node of a target power grid, obtaining power grid operation parameters, external weather and equipment state data in real time, optimizing a power grid resource scheduling model of the nodes, and uploading the power grid resource scheduling model to a power grid resource scheduling network. And the scheduling network combines the optimization models of the nodes into a global power grid resource scheduling calculation model, inputs the latest operation parameters, meteorological data and equipment states into the global model, and generates scheduling information for the nodes. And then, global scheduling information is sent to each node through a network, and power transmission parameters and equipment parameters of the nodes are dynamically adjusted to realize load balance and resource optimization, so that efficient and stable operation of the whole power grid is guaranteed. By adopting the method, the uncertainty of power demand and supply can be flexibly handled, and the fault risk of power grid operation is effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of smart grid technology, and in particular to a method and device for scheduling grid resources based on distributed artificial intelligence agents. Background Art

[0002] With the development of new energy and renewable energy generation technology, traditional power grid resource scheduling relies on centralized control systems. This approach often has problems such as slow response, inability to adjust loads in real time, and system fragility caused by single point failures when dealing with complex dynamic changes in the power grid. With the access of new energy and renewable energy and the distributed development of power grid structure, the operating environment of the power grid has become more complex and dynamic. The existing resource scheduling system is difficult to flexibly respond to the uncertainty of power demand and supply. Summary of the invention

[0003] Based on this, it is necessary to provide a power grid resource scheduling method, device and computer equipment, computer-readable storage medium and computer program product based on distributed artificial intelligence agents, which can improve the resource scheduling system's ability to flexibly respond to power demand and eliminate supply uncertainty, in response to the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a method for dispatching power grid resources based on a distributed artificial intelligence agent. The method comprises:

[0005] Obtaining power grid operation parameters, external meteorological parameters, and equipment status parameters corresponding to the artificial intelligence agent; each of the artificial intelligence agents is deployed on a power grid resource dispatching node corresponding to the target power grid;

[0006] Optimizing the model parameters of the node power grid resource dispatching calculation model according to the power grid operation parameters, the external meteorological parameters and the equipment status parameters, and sending them to the power grid resource dispatching network;

[0007] Acquire a global power grid resource dispatching calculation model sent by the power grid resource dispatching network; the global power grid resource dispatching calculation model is obtained by merging each optimized power grid resource dispatching calculation model through the power grid resource dispatching network;

[0008] Inputting the power grid operation parameters, the external meteorological parameters and the equipment status parameters into the global power grid resource scheduling calculation model, obtaining node power grid resource scheduling information, and sending it to the power grid resource scheduling network;

[0009] According to the global power grid resource dispatching information sent by the power grid resource dispatching network, the power grid transmission parameters and power grid equipment parameters of the power grid resource dispatching node are adjusted; the global power grid resource dispatching information is obtained by integrating the power grid resource dispatching information of each node through the power grid resource dispatching network.

[0010] In a second aspect, the present application also provides a power grid resource scheduling device based on a distributed artificial intelligence agent. The device includes:

[0011] A parameter acquisition module, used to acquire power grid operation parameters, external meteorological parameters and equipment status parameters corresponding to the artificial intelligence agent; each of the artificial intelligence agents is deployed on a power grid resource dispatching node corresponding to the target power grid;

[0012] A model optimization module, used to optimize the model parameters of the node power grid resource scheduling calculation model according to the power grid operation parameters, the external meteorological parameters and the equipment status parameters, and send them to the power grid resource scheduling network;

[0013] A model acquisition module, used to acquire a global power grid resource dispatching calculation model sent by the power grid resource dispatching network; the global power grid resource dispatching calculation model is obtained by merging various optimized power grid resource dispatching calculation models through the power grid resource dispatching network;

[0014] A parameter calculation module, used to input the power grid operation parameters, the external meteorological parameters and the equipment status parameters into the global power grid resource scheduling calculation model, obtain node power grid resource scheduling information, and send it to the power grid resource scheduling network;

[0015] A resource scheduling module is used to adjust the power grid transmission parameters and power grid equipment parameters of the power grid resource scheduling node according to the global power grid resource scheduling information sent by the power grid resource scheduling network; the global power grid resource scheduling information is obtained by integrating the power grid resource scheduling information of each node through the power grid resource scheduling network.

[0016] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0017] Obtaining power grid operation parameters, external meteorological parameters, and equipment status parameters corresponding to the artificial intelligence agent; each of the artificial intelligence agents is deployed on a power grid resource dispatching node corresponding to the target power grid;

[0018] Optimizing the model parameters of the node power grid resource dispatching calculation model according to the power grid operation parameters, the external meteorological parameters and the equipment status parameters, and sending them to the power grid resource dispatching network;

[0019] Acquire a global power grid resource dispatching calculation model sent by the power grid resource dispatching network; the global power grid resource dispatching calculation model is obtained by merging each optimized power grid resource dispatching calculation model through the power grid resource dispatching network;

[0020] Inputting the power grid operation parameters, the external meteorological parameters and the equipment status parameters into the global power grid resource scheduling calculation model, obtaining node power grid resource scheduling information, and sending it to the power grid resource scheduling network;

[0021] According to the global power grid resource dispatching information sent by the power grid resource dispatching network, the power grid transmission parameters and power grid equipment parameters of the power grid resource dispatching node are adjusted; the global power grid resource dispatching information is obtained by integrating the power grid resource dispatching information of each node through the power grid resource dispatching network.

[0022] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0023] Obtaining power grid operation parameters, external meteorological parameters, and equipment status parameters corresponding to the artificial intelligence agent; each of the artificial intelligence agents is deployed on a power grid resource dispatching node corresponding to the target power grid;

[0024] Optimizing the model parameters of the node power grid resource dispatching calculation model according to the power grid operation parameters, the external meteorological parameters and the equipment status parameters, and sending them to the power grid resource dispatching network;

[0025] Acquire a global power grid resource dispatching calculation model sent by the power grid resource dispatching network; the global power grid resource dispatching calculation model is obtained by merging each optimized power grid resource dispatching calculation model through the power grid resource dispatching network;

[0026] Inputting the power grid operation parameters, the external meteorological parameters and the equipment status parameters into the global power grid resource scheduling calculation model, obtaining node power grid resource scheduling information, and sending it to the power grid resource scheduling network;

[0027] According to the global power grid resource dispatching information sent by the power grid resource dispatching network, the power grid transmission parameters and power grid equipment parameters of the power grid resource dispatching node are adjusted; the global power grid resource dispatching information is obtained by integrating the power grid resource dispatching information of each node through the power grid resource dispatching network.

[0028] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0029] Obtaining power grid operation parameters, external meteorological parameters, and equipment status parameters corresponding to the artificial intelligence agent; each of the artificial intelligence agents is deployed on a power grid resource dispatching node corresponding to the target power grid;

[0030] Optimizing the model parameters of the node power grid resource dispatching calculation model according to the power grid operation parameters, the external meteorological parameters and the equipment status parameters, and sending them to the power grid resource dispatching network;

[0031] Acquire a global power grid resource dispatching calculation model sent by the power grid resource dispatching network; the global power grid resource dispatching calculation model is obtained by merging each optimized power grid resource dispatching calculation model through the power grid resource dispatching network;

[0032] Inputting the power grid operation parameters, the external meteorological parameters and the equipment status parameters into the global power grid resource scheduling calculation model, obtaining node power grid resource scheduling information, and sending it to the power grid resource scheduling network;

[0033] According to the global power grid resource dispatching information sent by the power grid resource dispatching network, the power grid transmission parameters and power grid equipment parameters of the power grid resource dispatching node are adjusted; the global power grid resource dispatching information is obtained by integrating the power grid resource dispatching information of each node through the power grid resource dispatching network.

[0034] The above-mentioned power grid resource scheduling method, device, computer equipment, storage medium and computer program product based on distributed artificial intelligence agent obtains the power grid operation parameters, external meteorological parameters and equipment status parameters corresponding to the artificial intelligence agent; each artificial intelligence agent is deployed on the power grid resource scheduling node corresponding to the target power grid; according to the power grid operation parameters, external meteorological parameters and equipment status parameters, the model parameters of the node power grid resource scheduling calculation model are optimized and sent to the power grid resource scheduling network; the global power grid resource scheduling calculation model sent by the power grid resource scheduling network is obtained; the global power grid resource scheduling calculation model is obtained by merging each optimized power grid resource scheduling calculation model through the power grid resource scheduling network; the power grid operation parameters, external meteorological parameters and equipment status parameters are input into the global power grid resource scheduling calculation model to obtain the node power grid resource scheduling information, and send it to the power grid resource scheduling network; according to the global power grid resource scheduling information sent by the power grid resource scheduling network, the power grid transmission parameters and power grid equipment parameters of the power grid resource scheduling node are adjusted; the global power grid resource scheduling information is obtained by fusing the power grid resource scheduling information of each node through the power grid resource scheduling network.

[0035] Through the intelligent agent, the grid operation parameters, external meteorological data and equipment status information are obtained in real time, and the parameters of the dispatch calculation model are optimized in a targeted manner at the grid resource dispatch node to form a more adaptable local dispatch strategy. Each node integrates the optimized model into a global grid resource dispatch model through the grid resource dispatch network, realizing information sharing and overall dispatch coordination between nodes. Ultimately, the intelligent adjustment of grid operation parameters and equipment status greatly enhances the adaptability to meteorological and equipment status fluctuations, can flexibly respond to the uncertainty of power demand and supply, effectively reduces the risk of failure in grid operation, and improves the level of optimal configuration of grid resources; further improves the operation efficiency and overall safety of the grid, and supports more stable energy supply and dispatch management. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] FIG1 is an application environment diagram of a power grid resource scheduling method based on a distributed artificial intelligence agent in one embodiment;

[0037] FIG2 is a schematic diagram of a flow chart of a method for dispatching power grid resources based on a distributed artificial intelligence agent in one embodiment;

[0038] FIG3 is a schematic diagram of a flow chart of a model parameter optimization method in one embodiment;

[0039] FIG4 is a schematic diagram of a flow chart of a first model parameter optimization method in one embodiment;

[0040] FIG5 is a schematic diagram of a flow chart of a method for adjusting power grid parameters in one embodiment;

[0041] FIG6 is a schematic diagram of a flow chart of a second method for adjusting power grid parameters in one embodiment;

[0042] FIG7 is a schematic diagram of a flow chart of a method for merging computing models in one embodiment;

[0043] FIG8 is a schematic diagram of a flow chart of a third model parameter optimization method in one embodiment;

[0044] FIG9 is a structural block diagram of a power grid resource scheduling device based on a distributed artificial intelligence agent in one embodiment;

[0045] FIG. 10 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The embodiment of the present application provides a distributed artificial intelligence agent-based power grid resource scheduling method, which can be applied in the application environment shown in FIG1. ​​Among them, the artificial intelligence agent 102 communicates with the power grid resource scheduling network 104 through the network. The data storage system can store data that the power grid resource scheduling network 104 needs to process. The data storage system can be integrated on the power grid resource scheduling network 104, or it can be placed on the cloud or other network power grid resource scheduling networks. Obtain the grid operation parameters, external meteorological parameters and equipment status parameters corresponding to the artificial intelligence agent 102; each artificial intelligence agent 102 is respectively deployed on the grid resource dispatching node corresponding to the target grid; according to the grid operation parameters, external meteorological parameters and equipment status parameters, optimize the model parameters of the node grid resource dispatching calculation model and send it to the grid resource dispatching network; obtain the global grid resource dispatching calculation model sent by the grid resource dispatching network; the global grid resource dispatching calculation model is obtained by merging each optimized grid resource dispatching calculation model through the grid resource dispatching network; input the grid operation parameters, external meteorological parameters and equipment status parameters into the global grid resource dispatching calculation model, obtain the node grid resource dispatching information, and send it to the grid resource dispatching network; according to the global grid resource dispatching information sent by the grid resource dispatching network, adjust the grid transmission parameters and grid equipment parameters of the grid resource dispatching node; the global grid resource dispatching information is obtained by merging the grid resource dispatching information of each node through the grid resource dispatching network. Among them, the grid resource dispatching network 104 can be implemented by an independent grid resource dispatching network or a grid resource dispatching network cluster composed of multiple grid resource dispatching networks.

[0048] In one embodiment, as shown in FIG2 , a method for dispatching power grid resources based on a distributed artificial intelligence agent is provided, and the method is described by taking the application of the method to the artificial intelligence agent in FIG1 as an example, and includes the following steps:

[0049] Step 202, obtaining power grid operation parameters, external meteorological parameters and equipment status parameters corresponding to the artificial intelligence agent.

[0050] Among them, the artificial intelligence agent can be an intelligent computing unit deployed on the power grid node, which has the capabilities of data collection, model analysis and adaptive optimization. It is responsible for obtaining data such as power grid operation, meteorology and equipment status in real time, and generating corresponding local scheduling strategies.

[0051] The grid operation parameters may be data reflecting the actual operation status of the grid, including voltage, current, load, frequency, etc.

[0052] Among them, external meteorological parameters can be meteorological data of the area where the power grid is located, such as temperature, wind speed, humidity and precipitation, which can affect the load demand of the power grid and the operating efficiency of equipment.

[0053] Among them, the equipment status parameters can be information such as the operating status, temperature, load level, etc. of various equipment in the power grid (such as transformers, circuit breakers, etc.).

[0054] Among them, the power grid resource dispatching node can be a distributed management unit of the power grid system. Each node is responsible for the power resource dispatching in a specific area, and collects data and performs local dispatching through intelligent agents.

[0055] Specifically, each AI agent deployed at a grid resource dispatching node is responsible for obtaining real-time grid operation parameters, external meteorological parameters, and equipment status information in the area where the node is located, including load demand, current and voltage data, wind speed, temperature and other meteorological data, as well as the working status of transformers, switches and other equipment. The agent uses edge computing technology to pre-process the collected data to reduce data transmission delays and network loads, ensuring the immediacy and accuracy of information.

[0056] Step 204, according to the power grid operation parameters, external meteorological parameters and equipment status parameters, the model parameters of the node power grid resource scheduling calculation model are optimized and sent to the power grid resource scheduling network.

[0057] Among them, the node power grid resource scheduling calculation model can be a preset intelligent model inside the power grid scheduling node, which can generate a resource scheduling strategy for this node through real-time data, but has not yet been adapted to the current situation.

[0058] Among them, the power grid resource dispatching network can be a communication and collaboration platform connecting each node, responsible for data transmission, dispatching information sharing and realizing server computing functions.

[0059] Specifically, each artificial intelligence agent will input the collected power grid operation parameters, external meteorological parameters, and equipment status parameters into the node's power grid resource scheduling calculation model, and adaptively optimize the core parameters of the model. For example, by updating key parameters such as the load adjustment coefficient, wind speed and temperature influencing factors, and equipment load limits in the model in real time, the model can automatically adjust the output scheduling strategy under different environmental and load conditions. At the same time, the agent uses a feedback loop to compare and learn the node's scheduling results with the actual operating conditions, and continuously corrects the model parameters to improve its prediction and scheduling accuracy. After optimizing the parameters, each optimized power grid resource scheduling calculation model is encapsulated and encrypted and uploaded to the power grid resource scheduling network to ensure the security and efficiency of data transmission.

[0060] Step 206: Obtain a global power grid resource scheduling calculation model sent by the power grid resource scheduling network.

[0061] Among them, the global power grid resource scheduling calculation model can be a comprehensive scheduling model generated by summarizing the optimized power grid resource scheduling calculation models of each node, providing a scheduling decision-making plan from the perspective of the entire network to ensure the balance and consistency of load and resource allocation between different nodes.

[0062] Among them, the optimized power grid resource scheduling calculation model can be a node scheduling model whose parameters are updated by an artificial intelligence agent. The model parameters are adaptively adjusted based on real-time data, reflecting the current optimal scheduling strategy of the node.

[0063] Specifically, the power grid resource dispatching network receives and integrates the optimized power grid resource dispatching calculation model after the optimization parameters from each node, and calibrates and integrates each optimized power grid resource dispatching calculation model from a global perspective through aggregation algorithms and collaborative optimization methods. For example, the network will analyze the correlation, load complementarity and environmental impact differences between the node models, extract global optimization parameters, and finally form a global power grid resource dispatching calculation model applicable to the entire power grid; and send the global power grid resource dispatching calculation model to each artificial intelligence agent, so that each artificial intelligence agent can obtain the global power grid resource dispatching calculation model sent by the power grid resource dispatching network. Because the global model adopts a collaborative optimization method, it comprehensively considers the power grid parameter association, load complementarity and meteorological linkage effects between nodes to ensure that the optimization parameters of each node are compatible with each other throughout the entire network.

[0064] Step 208, inputting the power grid operation parameters, external meteorological parameters and equipment status parameters into the global power grid resource scheduling calculation model, obtaining the node power grid resource scheduling information, and sending it to the power grid resource scheduling network.

[0065] The node power grid resource dispatching information may be dispatching data generated by the node based on the global power grid resource dispatching calculation model and current operating parameters, including information such as the resource configuration, load demand and equipment status of the current node.

[0066] Specifically, after the global power grid resource dispatch calculation model is built, the artificial intelligence agent of each node will input the real-time collected power grid operation parameters, external meteorological data and equipment status information into the global power grid resource dispatch model. The global power grid resource dispatch calculation model will conduct multi-level analysis on the load demand, meteorological impact and equipment operation of the current node based on these input data, and generate the resource dispatch information of the node, including the current optimal load distribution, equipment start-stop and operation parameter adjustment suggestions. While generating the node power grid resource dispatch information, it will be fed back to the power grid resource dispatch network to provide data support for the optimization of the whole network in the next round of dispatch.

[0067] Step 210: adjusting the grid transmission parameters and grid equipment parameters of the grid resource scheduling node according to the global grid resource scheduling information sent by the grid resource scheduling network.

[0068] Among them, the global power grid resource dispatching information can be a comprehensive dispatching plan generated by the power grid resource dispatching network after integrating the dispatching information of each node, providing consistent resource allocation and load adjustment suggestions for the entire network, and guiding each node to perform coordinated dispatching.

[0069] Among them, the grid transmission parameters can be physical parameters that affect the power transmission process, such as transmission voltage, frequency, phase, etc. Adjusting these parameters can optimize the efficiency and stability of power transmission and adapt to changes in demand under different load conditions.

[0070] Among them, the power grid equipment parameters can be the configuration and operating status data of key equipment in the power grid, such as the output power of the transformer, the opening and closing status of the switch, etc. By adjusting these parameters, the safe operation of the equipment can be guaranteed and adapt to real-time changes in power demand.

[0071] Specifically, after the artificial intelligence agent of each node generates local resource scheduling information based on the global model, the power grid resource scheduling network collects and comprehensively processes these local scheduling information, and integrates the independent scheduling results of each node through cross-node data aggregation, priority sorting and weight allocation. The network first identifies the relationship between the load demand, meteorological impact and equipment status of each node, evaluates the scheduling priority of each node using weighted average, distance priority and other algorithms, and balances the allocation according to the target load and operating efficiency of the overall power grid. For example, for areas with higher loads, the network will appropriately allocate more resource support, and for nodes with greater equipment operating pressure, its load pressure will be reduced accordingly to generate global power grid resource scheduling information. The power grid resource scheduling network sends the integrated global power grid resource scheduling information back to each node, and the artificial intelligence agent of the node adjusts the local power grid transmission parameters and power grid equipment parameters according to the feedback global information. For example, the node may adjust the transmission voltage, switch the backup power supply, increase or decrease the load or change the power output of the equipment according to the scheduling instruction. Through this collaborative adjustment, the node can respond quickly to sudden load fluctuations or meteorological changes to ensure the stability and efficiency of the power grid. In addition, the real-time adjustment data of each node will be further uploaded to the power grid resource dispatching network, providing closed-loop support for the continuous updating and optimization of the global model, so that the power grid operation can be adaptive and efficient in more refined dynamic regulation.

[0072] In the above-mentioned power grid resource scheduling method based on distributed artificial intelligence agent, the power grid operation parameters, external meteorological parameters and equipment status parameters corresponding to the artificial intelligence agent are obtained; each artificial intelligence agent is deployed on the power grid resource scheduling node corresponding to the target power grid; according to the power grid operation parameters, external meteorological parameters and equipment status parameters, the model parameters of the node power grid resource scheduling calculation model are optimized and sent to the power grid resource scheduling network; the global power grid resource scheduling calculation model sent by the power grid resource scheduling network is obtained; the global power grid resource scheduling calculation model is obtained by merging each optimized power grid resource scheduling calculation model through the power grid resource scheduling network; the power grid operation parameters, external meteorological parameters and equipment status parameters are input into the global power grid resource scheduling calculation model to obtain the node power grid resource scheduling information, and send it to the power grid resource scheduling network; according to the global power grid resource scheduling information sent by the power grid resource scheduling network, the power grid transmission parameters and power grid equipment parameters of the power grid resource scheduling node are adjusted; the global power grid resource scheduling information is obtained by fusing the power grid resource scheduling information of each node through the power grid resource scheduling network.

[0073] Through the intelligent agent, the grid operation parameters, external meteorological data and equipment status information are obtained in real time, and the parameters of the dispatch calculation model are optimized in a targeted manner at the grid resource dispatch node to form a more adaptable local dispatch strategy. Each node integrates the optimized model into a global grid resource dispatch model through the grid resource dispatch network, realizing information sharing and overall dispatch coordination between nodes. Ultimately, the intelligent adjustment of grid operation parameters and equipment status greatly enhances the adaptability to meteorological and equipment status fluctuations, can flexibly respond to the uncertainty of power demand and supply, effectively reduces the risk of failure in grid operation, and improves the level of optimal configuration of grid resources; further improves the operation efficiency and overall safety of the grid, and supports more stable energy supply and dispatch management.

[0074] In one embodiment, as shown in FIG3 , the model parameters of the node power grid resource scheduling calculation model are optimized according to the power grid operation parameters, external meteorological parameters and equipment status parameters, including:

[0075] Step 302, based on the historical power grid operation parameters, historical external meteorological parameters and historical equipment status parameters corresponding to the artificial intelligence agent, the node power grid resource scheduling calculation model is initialized to obtain an initial resource scheduling calculation model.

[0076] Among them, the historical power grid operation parameters, historical external meteorological parameters and historical equipment status parameters are respectively the power grid operation parameters, external meteorological parameters and equipment status parameters obtained by the artificial intelligence agent at different times or time periods in the past.

[0077] Among them, the initial resource scheduling calculation model can be a basic model established based on the node's historical power grid operation data, meteorological conditions and equipment status information. By analyzing these historical data to define the initial scheduling parameters and configurations, a reference scheduling benchmark is provided for the node under normal conditions.

[0078] Specifically, in the model initialization stage, the artificial intelligence agent uses data backtracking and pattern recognition methods to analyze the long-term trend of power grid operation and equipment load based on the node's historical power grid operation data, past meteorological conditions, and equipment operation history. At the same time, the historical power grid operation data, past meteorological conditions, and equipment operation history are input into the node resource scheduling model. Through the model's analysis of these data, the agent can infer the long-term trend of power grid operation and equipment load under historical conditions of the node power grid. The difference between the long-term trend of power grid operation and equipment load obtained by data backtracking and pattern recognition methods and the long-term trend of power grid operation and equipment load obtained by model prediction is used to initialize the model parameters of the node power grid resource scheduling calculation model, that is, to adjust the model parameters of the node power grid resource scheduling calculation model by bias. In order to meet the typical load response mode and the optimal operating conditions of the equipment under different environments, the initial resource scheduling calculation model is obtained.

[0079] Step 304, updating the calculation target of the initial resource scheduling calculation model according to the power grid operation parameters, external meteorological parameters and equipment status parameters, and obtaining an updated target resource scheduling calculation model.

[0080] The calculation target can be a specific optimization target or result that the power grid resource scheduling model needs to achieve during operation, such as load balancing, maximizing equipment utilization, or minimizing energy consumption.

[0081] Among them, the updated target resource scheduling calculation model can be a model adjusted based on the initial model according to real-time grid operating parameters, meteorological conditions and equipment status, with the latest scheduling target settings, so that it can more accurately reflect the operating requirements of the current node, thereby generating a scheduling strategy that meets the current power system needs.

[0082] Specifically, during the actual operation, the artificial intelligence agent updates the calculation target of the initial resource scheduling model in real time based on the latest collected real-time grid operation parameters, external meteorological parameters, and equipment status parameters. For example, when the load demand increases or the meteorological conditions change dramatically, the agent will readjust the objective function of the model and switch the focus of resource scheduling from conventional load balancing to precise management of fluctuating loads. Through this real-time target update, the model will reset the scheduling target according to the current needs of the node, such as prioritizing load peak reduction, optimizing the power output of the equipment, or adjusting the equipment operation timing, to generate an updated target resource scheduling calculation model to adapt to the current operating environment and power demand.

[0083] Step 306, optimizing the model parameters of the updated target resource scheduling calculation model according to the power grid operation parameters, external meteorological parameters, equipment status parameters and the first calculation target.

[0084] Among them, the first computing target can be the core optimization target in the updated target resource scheduling model, which usually represents the scheduling demand with the highest priority under the current operating conditions, such as giving priority to load distribution balance under high load conditions, or ensuring the safe operation of equipment during extreme weather changes.

[0085] Specifically, after obtaining the updated computing target, the AI ​​agent inputs the latest grid operation data, meteorological data, equipment status, and adjusted computing targets into the updated target resource scheduling model, and applies optimization algorithms such as deep learning or reinforcement learning to iteratively adjust the core parameters of the model. For example, based on the current load demand and meteorological changes, the model will re-optimize parameters such as weight coefficients and equipment priorities, while dynamically adjusting power allocation and equipment switching strategies. Through this refined parameter optimization process, the model is able to generate the optimal scheduling solution that adapts to the current node conditions, achieve more efficient and reliable resource scheduling, and ensure the stable operation of the power grid under high load or extreme weather.

[0086] In this embodiment, the node resource scheduling model is initialized by using historical power grid operating parameters, meteorological data and equipment status through an artificial intelligence agent. This method enables the scheduling model to have basic adaptability to node load and environment in the initial stage. As real-time power grid parameters and external environment change, the model's calculation objectives can be dynamically updated to enable it to quickly adapt to actual operating conditions such as load demand and equipment status changes. Furthermore, by optimizing model parameters guided by the first calculation objective, the scheduling model can continuously adjust itself, achieving a sensitive response to sudden load fluctuations and equipment status changes, ensuring the efficiency and stability of power grid operation and accurate allocation of resources.

[0087] In one embodiment, as shown in FIG4 , according to the power grid operation parameters, the external meteorological parameters, the equipment state parameters and the first calculation target, the model parameters of the updated target resource scheduling calculation model are optimized, including:

[0088] Step 402, inputting the power grid operation parameters, external meteorological parameters and equipment status parameters into the updated target resource scheduling calculation model to obtain the test node scheduling information.

[0089] Among them, the test node scheduling information can be a preliminary scheduling plan generated by the updated target resource scheduling calculation model based on real-time power grid parameters and current calculation targets, including node resource allocation suggestions, load adjustment plans and equipment operation strategies, which are used to simulate and evaluate the effectiveness of the scheduling plan in actual applications.

[0090] Specifically, the artificial intelligence agent inputs the latest grid operating parameters (such as voltage, current, load data), external meteorological data (such as wind speed, temperature, etc.) and equipment status (such as transformer load condition, switch status) into the updated target resource scheduling calculation model. Based on these input information and the set first calculation goal (such as load balancing or optimal energy efficiency), the model generates test node scheduling information, including preliminary resource allocation suggestions, load adjustment strategies, equipment start and stop plans, etc., which are used to evaluate the ideal scheduling plan under current conditions.

[0091] Step 404 , performing virtual scheduling on the power grid resources of the power grid resource scheduling node according to the test node scheduling information to obtain a virtual scheduling result.

[0092] Among them, the virtual scheduling result can be the result generated by applying the test node scheduling information in a virtual environment and simulating the scheduling of the node's resource allocation and equipment operation. It reflects the expected performance of the current scheduling scheme in the actual environment and is used to compare the effect with the ideal scheduling.

[0093] Specifically, the AI ​​agent uses the generated test node scheduling information to simulate the actual scheduling operation of the power grid resource scheduling node, and predicts its possible performance in the real environment by virtually scheduling the operating status and resource configuration of the test node. Virtual scheduling will consider the load bearing conditions, resource utilization efficiency, and scheduling response speed of each device in the node under the scheme, and obtain a virtual scheduling result through calculation and simulation. This result provides a metric to compare whether the current effect of the scheduling model meets the real-time needs of the node, providing clear feedback for subsequent optimization.

[0094] Step 406: When the difference between the virtual scheduling result and the preset scheduling result is greater than a threshold, the calculation target of the target resource scheduling calculation model is adjusted and updated according to the virtual scheduling result to obtain a second calculation target.

[0095] Among them, the preset scheduling result can be an ideal scheduling state based on node operation requirements, load balancing and safety standards, which is used as a target benchmark for measuring the model scheduling effect, and is used to compare with the virtual scheduling results to determine the effectiveness of the current scheduling plan.

[0096] Specifically, the artificial intelligence agent will analyze the difference between the virtual dispatch results and the preset ideal dispatch results. If the difference exceeds the preset threshold (for example, load distribution deviation, equipment overload rate exceeding the standard, etc.), the calculation target of the current model will be re-evaluated and adjusted. At this time, the calculation target of the updated target resource dispatch model will be redefined to be closer to the overall dispatch demand of the power grid, and the re-set second calculation target will be obtained to replace the first calculation target in the updated target resource dispatch calculation model, which can pay more attention to the response measures under different environmental conditions, such as power supply security in extreme climates or equipment protection under load fluctuations, so as to generate a dispatch strategy that better meets actual needs.

[0097] Step 408, optimizing the model parameters of the updated target resource scheduling calculation model according to the power grid operation parameters, external meteorological parameters, equipment status parameters and the second calculation target.

[0098] Among them, the second calculation target can be the re-optimization target set in the updated target resource scheduling calculation model, which is usually based on the specific needs or load pressure of the current power grid operation (such as equipment protection under extreme weather conditions) to guide the further optimization of the model parameters and ensure that the scheduling strategy achieves higher adaptability and efficiency under the adjusted target.

[0099] Specifically, the AI ​​agent inputs the updated grid operation parameters, meteorological data, equipment status data, and the second computing target into the updated target resource scheduling calculation model, and initiates a further model parameter optimization process. This optimization process refines the model's key parameters such as scheduling weights, load distribution ratios, equipment priorities, and resource scheduling thresholds through deep learning or adaptive algorithms. The model dynamically adjusts these parameters based on the new computing target, so that the scheduling results can better meet the real-time operation requirements and safety standards of the grid nodes, and ultimately generates a highly accurate and responsive scheduling plan to achieve optimal utilization and reliable operation of grid resources.

[0100] In this embodiment, the grid operation parameters, meteorological data and equipment status are input into the updated resource scheduling model to generate test node scheduling information, and the expected performance of the model in the actual scenario is evaluated through virtual scheduling. When there is a large gap between the virtual scheduling result and the preset target, the system automatically adjusts the calculation target of the model, generates a second calculation target and replaces the initial target to more accurately reflect the actual demand. Subsequently, the system deeply optimizes the model parameters so that the model can dynamically adapt to real-time load and environmental changes, thereby significantly improving the accuracy and response speed of grid resource scheduling, ensuring the efficient and stable operation of the grid, and reducing the risks caused by load deviation.

[0101] In one embodiment, as shown in FIG5 , according to the global grid resource scheduling information sent by the grid resource scheduling network, the grid transmission parameters and grid equipment parameters of the grid resource scheduling node are adjusted, including:

[0102] Step 502: parse the global power grid resource dispatch information to determine the dispatch strategy type and adjustment target state of the power grid resource dispatch node.

[0103] Among them, the dispatch strategy type can be the dispatch scheme category set in the power grid resource dispatch model for specific operating requirements, such as load balancing, energy consumption optimization or equipment protection, etc. It determines the main dispatch direction of the node under different operating conditions to ensure that the power grid maintains the best state under changing demands or environments.

[0104] Among them, the adjustment target state can be the specific operating indicators or conditions that the power grid resource scheduling node needs to achieve when executing the scheduling strategy, such as maintaining voltage stability at a certain level, ensuring that the equipment temperature does not exceed a specific upper limit, or achieving a specific load distribution.

[0105] Specifically, after receiving the global power grid resource scheduling information, the artificial intelligence agent of each power grid resource scheduling node uses the information parsing module to read the information content one by one, identify the core strategy direction that needs to be scheduled at present, and further convert it into the scheduling strategy type (such as load balancing, energy saving or equipment protection) and the node's specific adjustment target state (such as voltage level, equipment temperature upper limit or load distribution requirements).

[0106] Step 504, calculating the equipment parameter adjustment amount and the transmission parameter adjustment amount according to the scheduling strategy type and the adjustment target state.

[0107] The equipment parameter adjustment amount may be a specific adjustment value for the operating parameters of each device in the power grid (such as a transformer, a circuit breaker, etc.), which is used to adjust the output power, operating temperature, load bearing capacity, etc. of the equipment.

[0108] Among them, the transmission parameter adjustment amount can be the parameter adjustment value of the power grid transmission line to implement the scheduling strategy, such as adjusting the transmission parameters such as voltage, current or phase; it can optimize power transmission efficiency, maintain load balance, and adapt to real-time demand changes in the power grid.

[0109] Specifically, after parsing out the dispatch strategy type and the adjustment target state, the artificial intelligence agent of each node inputs these target parameters into the equipment parameter and transmission parameter calculation modules respectively. The calculation module combines the actual operation data of the current equipment and the power grid transmission parameters, and determines the specific adjustment amount of each device and transmission line based on the difference calculation and optimization algorithm. For example, if the dispatch goal is load balancing, the calculation module will adjust the power output of the transformer, or redistribute the load between different areas to ensure the stability of voltage and current and that the equipment temperature does not exceed the safety threshold. Therefore, the calculated equipment parameter adjustment amount and transmission parameter adjustment amount ensure that the changes in each parameter adapt to the current dispatch strategy and avoid over-adjustment or under-adjustment.

[0110] Step 506: Adjust the power grid transmission parameters and the power grid equipment parameters respectively according to the equipment parameter adjustment amount and the power transmission parameter adjustment amount.

[0111] Specifically, after obtaining the equipment parameter adjustment amount and the transmission parameter adjustment amount, the artificial intelligence agent of each node respectively performs adjustment operations on the equipment and the transmission system. Specifically, the node will optimize the current power grid transmission parameters (such as voltage, current) and equipment operating status (such as temperature, output power) by controlling the output power of the transformer, adjusting the voltage setting, changing the switch state, or adjusting the load configuration of the equipment. These adjustment operations are based on a correction mechanism based on real-time feedback, and gradually approach the set adjustment target state during execution, ensuring that the operation of the power grid nodes meets the global scheduling requirements and optimizes resource allocation, so as to achieve safe, stable and efficient operation of the power grid.

[0112] In this embodiment, by parsing the global power grid resource scheduling information, the system can clarify the scheduling strategy type and the required target state of each power grid node, thereby formulating accurate resource scheduling directions for the nodes. Based on this strategy, the system calculates the specific equipment parameters and transmission parameter adjustments, allowing the nodes to finely control the changes in transmission and equipment parameters. This precise adjustment not only improves the response speed of power grid nodes to load and environmental changes, but also significantly optimizes the allocation and use efficiency of power grid resources, ensuring the stability and efficient operation of the power grid under different load conditions, while effectively reducing energy waste and equipment operation risks.

[0113] In one embodiment, as shown in FIG6 , according to the device parameter adjustment amount and the transmission parameter adjustment amount, the power grid transmission parameter and the power grid device parameter are adjusted respectively, including:

[0114] Step 602: According to the equipment parameter adjustment amount and the transmission parameter adjustment amount, the power grid transmission parameters and the power grid equipment parameters are adjusted respectively to obtain the initially adjusted transmission parameters and the initially adjusted equipment parameters.

[0115] Among them, the initial adjustment of transmission parameters can be parameters obtained after preliminary adjustment of transmission system parameters such as voltage and current of the power grid according to the transmission demand in the scheduling strategy to adapt to the load demand and resource allocation goals of the current node.

[0116] Among them, the initial adjustment of equipment parameters can be parameters obtained after adjusting the preliminary operating parameters of power grid equipment (such as transformers, switches, etc.), such as power output or switch status, to achieve the preliminary equipment configuration required by the dispatching strategy.

[0117] Specifically, the artificial intelligence agent of the power grid resource dispatching node makes preliminary adjustments to the current power grid transmission parameters and power grid equipment parameters based on the calculated equipment parameter adjustment (such as the adjustment of transformer power output and the change of switch state) and transmission parameter adjustment (such as the adjustment range of voltage and current). This adjustment operation is used to quickly adapt the operating state of the node to the current dispatching strategy, and to preliminarily achieve the target state in the dispatching strategy by adjusting the output power, load, voltage, current and other parameters of each device. After this step, the node obtains the adjusted transmission parameters and equipment parameters, laying the foundation for further dispatching balance of the entire network.

[0118] Step 604: Generate equipment parameter fine-tuning data and power transmission parameter fine-tuning data according to the dynamic load balancing data of the target power grid.

[0119] The dynamic load balancing data may be data calculated by the grid resource dispatching network through a network-wide load balancing algorithm after aggregating the initial adjustment results of all nodes, reflecting the load distribution and resource utilization among the nodes.

[0120] The device parameter fine-tuning data may be further adjustment data generated based on the dynamic load balancing result, and detailed adjustment suggestions may be made for the device operating parameters of each node.

[0121] Among them, the transmission parameter fine-tuning data can be a fine-tuning suggestion based on the load balance calculation of the entire network, which is used to further optimize the voltage, current and other parameters of the transmission system.

[0122] Specifically, after collecting the initial adjustment parameters of each node, the power grid resource dispatching network calculates the initial adjustment transmission parameters of each node and the impact of the initial adjustment equipment parameters on the global operation based on the load balance model of the entire network, and identifies the nodes and their parameters that need to be fine-tuned through the global dynamic balance algorithm to eliminate the resource imbalance caused by the initial adjustment and obtain dynamic load balance data. Further, based on the dynamic load balance data, the artificial intelligence agent identifies the remaining resource imbalance points and load deviations, and generates more detailed adjustment data based on the identification results, namely, equipment parameter fine-tuning data and transmission parameter fine-tuning data.

[0123] Step 606: fine-tune the initially adjusted power transmission parameters and the initially adjusted device parameters respectively according to the device parameter fine-tune data and the power transmission parameter fine-tune data.

[0124] Specifically, after calculating the fine-tuning data of equipment parameters and transmission parameters, the grid node accurately fine-tunes the parameters adjusted for the first time. The node gradually adjusts the equipment output, load distribution, voltage, and current settings according to the fine-tuning data to make it more in line with the requirements of the balance of the entire network. For example, if the load of a node is still high, the fine-tuning will further reduce its power output or redistribute the load. The fine-tuning operation ensures that the node achieves refined resource allocation and ultimately achieves the dispatching goals of the entire network, making the resource allocation of the power grid more efficient and balanced, and ensuring stable operation and safety and reliability.

[0125] In this embodiment, by making preliminary adjustments to the equipment parameters and transmission parameters, the grid nodes can quickly respond to the current load demand and optimize the initial allocation of resources. However, in order to ensure load balancing across the entire network, the grid resource dispatching network analyzes the initial adjustment results of all nodes based on the dynamic load balancing data to generate more refined equipment and transmission fine-tuning data. Subsequently, by further fine-tuning the initial adjustment parameters, each node achieves more accurate resource scheduling and load balancing. This method not only improves the overall stability and resource utilization of the power grid, but also effectively prevents the risks caused by load deviations, ensuring efficient and reliable operation of the power grid in a dynamic environment.

[0126] In one embodiment, as shown in FIG. 7 , the global power grid resource scheduling calculation model is obtained by merging the optimized power grid resource scheduling calculation models through the power grid resource scheduling network, and includes:

[0127] Step 702: Determine the model weight corresponding to each optimized power grid resource scheduling calculation model according to each power grid resource scheduling node.

[0128] Specifically, after collecting the optimized calculation models of each grid resource dispatching node, the grid resource dispatching network first calculates the model weight of each model in the global dispatching based on the operating conditions, historical load demand, geographical characteristics, climate impact, and equipment stability of each node. For example, nodes with frequent load fluctuations and high equipment criticality are given higher weights to ensure that their needs are given priority response in the resource dispatching of the entire network. The weight calculation ensures that the influence of different nodes in the global dispatching model matches their actual operating needs and their contribution to the overall stability of the grid through multivariate analysis.

[0129] Step 704 , merging the optimized power grid resource scheduling calculation models according to the weights of the models to obtain an initial power grid resource scheduling calculation model.

[0130] Among them, the initial power grid resource scheduling calculation model can be a unified model generated by the power grid resource scheduling network after merging the optimized scheduling models of each node. The model is weighted integration based on the weights of different nodes, and initially has the function of global power grid resource scheduling, and can integrate the load demand and scheduling strategies of different regions.

[0131] Specifically, after the model weights corresponding to each model are determined, the power grid resource dispatching network performs weighted merging of the optimization models of each node, and integrates the dispatching strategies and demands of each node through arithmetic averaging, weighted summation and other methods to generate an initial power grid resource dispatching calculation model. Among them, the merging process retains the core dispatching parameters of high-weight nodes and integrates the characteristics of other nodes to form a comprehensive model with a global perspective. This initial power grid resource dispatching calculation model integrates the optimization strategies of each node to adapt to the demands and load characteristics of different regions of the entire network, providing a basis for subsequent fault-tolerant optimization.

[0132] Step 706, optimizing the fault tolerance parameters of the initial power grid resource scheduling calculation model according to each power grid resource scheduling node to obtain a global power grid resource scheduling calculation model.

[0133] Among them, fault-tolerant parameters can be key parameters set in the power grid resource scheduling calculation model to deal with sudden load fluctuations and equipment failures, such as load fluctuation response thresholds or fault tolerance. The setting and optimization of fault-tolerant parameters can improve the robustness of the model, enabling it to automatically adjust resource allocation in sudden situations and ensure the stable operation of the power grid.

[0134] Specifically, after generating the initial calculation model, the power grid resource dispatch network further adjusts the fault tolerance parameters of the model to adapt to the unique needs of each node. For example, for nodes whose equipment is susceptible to climate, fault tolerance optimization will increase the response sensitivity to load fluctuations, while for nodes with a higher risk of equipment failure, it will increase fault tolerance. In the process of adjusting the fault tolerance parameters of the model, a dynamic fault tolerance adjustment algorithm is used to optimize the fault tolerance range and response speed of the initial model based on the actual operation record and risk coefficient of each node, and finally form a global power grid resource dispatch calculation model with higher robustness and adaptability. The model can efficiently allocate resources under complex or sudden conditions to ensure the overall stability and operation efficiency of the power grid.

[0135] In this embodiment, by assigning weights to the optimized calculation models of each power grid resource dispatching node, the system ensures that the influence of key nodes on global dispatching is fully reflected, so that the merged initial power grid resource dispatching model can more accurately reflect the actual needs of the entire network. Subsequently, based on the optimization of the fault-tolerant parameters of the initial model, the system further enhances the robustness and adaptability of the global dispatching model, so that it can maintain effective dispatching capabilities even in the case of load fluctuations or equipment failures. This method improves the dispatching accuracy and risk resistance of the power grid in complex environments, ensuring the efficient allocation of resources across the entire network and the long-term stability of the power system.

[0136] In one embodiment, as shown in FIG8 , the method further includes:

[0137] Step 802: Determine evolution adjustment information of a global power grid resource scheduling calculation model according to global power grid resource scheduling information of different scenarios.

[0138] Among them, the evolution adjustment information can be the parameter adjustment guidance information generated by the power grid resource dispatching network after analyzing the global dispatching requirements under different operating scenarios (such as peak load, extreme weather, equipment maintenance, etc.). It includes the special requirements of various scenarios for the dispatching model and the corresponding parameter adjustment direction, such as load response sensitivity, fault tolerance threshold, equipment priority, etc.

[0139] Specifically, the power grid resource dispatch network conducts in-depth analysis based on the global power grid resource dispatch information collected under different scenarios to determine the special dispatch requirements and load distribution characteristics of the power grid under each scenario (such as peak hours, sudden load increases, extreme weather conditions, equipment maintenance periods, etc.); combined with the requirements of these scenarios in terms of resource allocation, load response, and safety and stability, it identifies the dispatch differences between scenarios and generates "evolution adjustment information". This information contains the key parameter adjustment directions and targets under the conditions of each scenario that the global model needs to adapt to, covering load distribution, fault tolerance thresholds, equipment priorities, and response sensitivity under different scenarios, to ensure that the model can effectively balance the allocation of power grid resources under different conditions.

[0140] Step 804: adjusting the model parameters of the global power grid resource scheduling calculation model according to the evolution adjustment information.

[0141] Specifically, based on the evolutionary adjustment information, the power grid resource dispatching network makes detailed adjustments to the model parameters of the global power grid resource dispatching calculation model. For example, in high-load scenarios, the system will increase the sensitivity and fault tolerance of load response to adapt to high-demand environments; in equipment maintenance scenarios, the system will redistribute loads to prioritize the protection of key equipment operations. Specific adjustments include careful optimization of resource allocation weights, fault tolerance parameters, response speeds, and dynamic dispatching thresholds in the model, so that the model can more flexibly and accurately adapt to the operational needs of different scenarios. Through such parameter adjustments, the global power grid resource dispatching calculation model can adaptively optimize resource dispatching, thereby improving the robustness and efficiency of the power grid in complex and changing environments.

[0142] In this embodiment, by analyzing the global power grid resource dispatch information under different scenarios, the system can identify the special requirements of each operating condition (such as peak load, extreme weather, equipment maintenance, etc.) for power grid resource allocation and generate corresponding evolution adjustment information. Subsequently, the parameters of the global dispatch model are dynamically adjusted based on this information, so that the model can adaptively optimize resource allocation in various scenarios. This method significantly enhances the adaptability and dispatch flexibility of the power grid in a changing environment, ensures more accurate resource allocation, thereby improving the stability and efficiency of the power grid and reducing the operating risks under extreme conditions.

[0143] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0144] Based on the same inventive concept, the embodiment of the present application also provides a distributed artificial intelligence agent-based power grid resource scheduling device for implementing the above-mentioned distributed artificial intelligence agent-based power grid resource scheduling method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the distributed artificial intelligence agent-based power grid resource scheduling device provided below can refer to the above-mentioned limitations on a distributed artificial intelligence agent-based power grid resource scheduling method, which will not be repeated here.

[0145] In one embodiment, as shown in FIG9 , a distributed artificial intelligence agent-based power grid resource scheduling device is provided, including: a parameter acquisition module 902, a model optimization module 904, a model acquisition module 906, a parameter calculation module 908 and a resource scheduling module 910, wherein:

[0146] Parameter acquisition module 902, used to obtain power grid operation parameters, external meteorological parameters and equipment status parameters corresponding to the artificial intelligence agent; each artificial intelligence agent is deployed on the power grid resource dispatching node corresponding to the target power grid;

[0147] The model optimization module 904 is used to optimize the model parameters of the node power grid resource scheduling calculation model according to the power grid operation parameters, external meteorological parameters and equipment status parameters, and send them to the power grid resource scheduling network;

[0148] Model acquisition module 906, used to acquire the global power grid resource dispatching calculation model sent by the power grid resource dispatching network; the global power grid resource dispatching calculation model is obtained by merging the optimized power grid resource dispatching calculation models through the power grid resource dispatching network;

[0149] The parameter calculation module 908 is used to input the power grid operation parameters, external meteorological parameters and equipment status parameters into the global power grid resource scheduling calculation model, obtain the node power grid resource scheduling information, and send it to the power grid resource scheduling network;

[0150] The resource scheduling module 910 is used to adjust the grid transmission parameters and grid equipment parameters of the grid resource scheduling node according to the global grid resource scheduling information sent by the grid resource scheduling network; the global grid resource scheduling information is obtained by integrating the grid resource scheduling information of each node through the grid resource scheduling network.

[0151] In one embodiment, the model optimization module 904 is also used to initialize the node power grid resource scheduling calculation model according to the historical power grid operation parameters, historical external meteorological parameters and historical equipment status parameters corresponding to the artificial intelligence agent to obtain an initial resource scheduling calculation model; update the calculation target of the initial resource scheduling calculation model according to the power grid operation parameters, external meteorological parameters and equipment status parameters to obtain an updated target resource scheduling calculation model; the updated target resource scheduling calculation model includes a first calculation target; optimize the model parameters of the updated target resource scheduling calculation model according to the power grid operation parameters, external meteorological parameters, equipment status parameters and the first calculation target.

[0152] In one embodiment, the model optimization module 904 is also used to input the power grid operation parameters, external meteorological parameters and equipment status parameters into the updated target resource scheduling calculation model to obtain the test node scheduling information; perform virtual scheduling on the power grid resources of the power grid resource scheduling node according to the test node scheduling information to obtain a virtual scheduling result; when the difference between the virtual scheduling result and the preset scheduling result is greater than a threshold, adjust the calculation target of the updated target resource scheduling calculation model according to the virtual scheduling result to obtain a second calculation target; the second calculation target is used to replace the first calculation target in the updated target resource scheduling calculation model; optimize the model parameters of the updated target resource scheduling calculation model according to the power grid operation parameters, external meteorological parameters, equipment status parameters and the second calculation target.

[0153] In one embodiment, the resource scheduling module 910 is also used to parse the global power grid resource scheduling information, determine the scheduling strategy type and the adjustment target state of the power grid resource scheduling node; calculate the equipment parameter adjustment amount and the transmission parameter adjustment amount according to the scheduling strategy type and the adjustment target state; and adjust the power grid transmission parameters and power grid equipment parameters respectively according to the equipment parameter adjustment amount and the transmission parameter adjustment amount.

[0154] In one embodiment, the resource scheduling module 910 is also used to adjust the power grid transmission parameters and the power grid equipment parameters according to the equipment parameter adjustment amount and the transmission parameter adjustment amount, respectively, to obtain the initially adjusted transmission parameters and the initially adjusted equipment parameters; generate equipment parameter fine-tuning data and transmission parameter fine-tuning data according to the dynamic load balancing data of the target power grid; the dynamic load balancing data is obtained by the power grid resource scheduling network performing a global dynamic balance calculation on the initially adjusted transmission parameters and the initially adjusted equipment parameters of each power grid resource scheduling node; and the initially adjusted transmission parameters and the initially adjusted equipment parameters are respectively fine-tuned according to the equipment parameter fine-tuning data and the transmission parameter fine-tuning data.

[0155] In one embodiment, the model acquisition module 906 is also used to determine the model weights corresponding to each optimized power grid resource scheduling calculation model according to each power grid resource scheduling node; merge each optimized power grid resource scheduling calculation model according to each model weight to obtain an initial power grid resource scheduling calculation model; optimize the fault tolerance parameters of the initial power grid resource scheduling calculation model according to each power grid resource scheduling node to obtain a global power grid resource scheduling calculation model.

[0156] In one embodiment, the resource scheduling module 910 is also used to determine the evolution adjustment information of the global power grid resource scheduling calculation model according to the global power grid resource scheduling information of different scenarios; and adjust the model parameters of the global power grid resource scheduling calculation model according to the evolution adjustment information.

[0157] Each module in the above-mentioned distributed artificial intelligence agent-based power grid resource dispatching device can be implemented in whole or in part by software, hardware, and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0158] In one embodiment, a computer device is provided, which may be an artificial intelligence agent, and its internal structure diagram may be shown in FIG10. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external artificial intelligence agent in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a power grid resource scheduling method based on a distributed artificial intelligence agent is implemented. The display screen of the computer device may have a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0159] Those skilled in the art will understand that the structure shown in FIG. 10 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0160] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0161] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0162] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0163] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0164] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0165] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0166] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for dispatching power grid resources based on distributed artificial intelligence agents, applied to artificial intelligence agents, characterized in that: The method comprises: Obtaining power grid operation parameters, external meteorological parameters, and equipment status parameters corresponding to the artificial intelligence agent; each of the artificial intelligence agents is deployed on a power grid resource dispatching node corresponding to the target power grid; Optimizing the model parameters of the node power grid resource dispatching calculation model according to the power grid operation parameters, the external meteorological parameters and the equipment status parameters, and sending them to the power grid resource dispatching network; Acquire a global power grid resource dispatching calculation model sent by the power grid resource dispatching network; the global power grid resource dispatching calculation model is obtained by merging each optimized power grid resource dispatching calculation model through the power grid resource dispatching network; Inputting the power grid operation parameters, the external meteorological parameters and the equipment status parameters into the global power grid resource scheduling calculation model, obtaining node power grid resource scheduling information, and sending it to the power grid resource scheduling network; According to the global power grid resource dispatching information sent by the power grid resource dispatching network, the power grid transmission parameters and power grid equipment parameters of the power grid resource dispatching node are adjusted; the global power grid resource dispatching information is obtained by integrating the power grid resource dispatching information of each node through the power grid resource dispatching network.

2. The method according to claim 1, characterized in that: The optimizing the model parameters of the node power grid resource scheduling calculation model according to the power grid operation parameters, the external meteorological parameters and the device status parameters includes: Initializing the node power grid resource scheduling calculation model according to the historical power grid operation parameters, historical external meteorological parameters, and historical equipment status parameters corresponding to the artificial intelligence agent to obtain an initial resource scheduling calculation model; According to the power grid operation parameters, the external meteorological parameters and the equipment status parameters, the calculation target of the initial resource scheduling calculation model is updated to obtain an updated target resource scheduling calculation model; the updated target resource scheduling calculation model includes a first calculation target; The model parameters of the updated target resource scheduling calculation model are optimized according to the power grid operation parameters, the external meteorological parameters, the equipment status parameters and the first calculation target.

3. The method according to claim 2, characterized in that The optimizing the model parameters of the updated target resource scheduling calculation model according to the power grid operation parameters, the external meteorological parameters, the device state parameters and the first calculation target includes: Inputting the power grid operation parameters, the external meteorological parameters and the equipment status parameters into the updated target resource scheduling calculation model to obtain test node scheduling information; Performing virtual scheduling on the power grid resources of the power grid resource scheduling node according to the test node scheduling information to obtain a virtual scheduling result; When the difference between the virtual scheduling result and the preset scheduling result is greater than a threshold, adjusting the calculation target of the updated target resource scheduling calculation model according to the virtual scheduling result to obtain a second calculation target; the second calculation target is used to replace the first calculation target in the updated target resource scheduling calculation model; The model parameters of the updated target resource scheduling calculation model are optimized according to the power grid operation parameters, the external meteorological parameters, the equipment status parameters and the second calculation target.

4. The method according to claim 1, characterized in that: The adjusting the power grid transmission parameters and power grid equipment parameters of the power grid resource scheduling node according to the global power grid resource scheduling information sent by the power grid resource scheduling network includes: Parsing the global power grid resource dispatching information to determine the dispatching strategy type and adjustment target state of the power grid resource dispatching node; Calculating the equipment parameter adjustment amount and the transmission parameter adjustment amount according to the scheduling strategy type and the regulation target state; According to the equipment parameter adjustment amount and the power transmission parameter adjustment amount, the power grid transmission parameter and the power grid equipment parameter are adjusted respectively.

5. The method according to claim 4, characterized in that The adjusting the power grid transmission parameter and the power grid equipment parameter respectively according to the equipment parameter adjustment amount and the power transmission parameter adjustment amount comprises: According to the device parameter adjustment amount and the power transmission parameter adjustment amount, the power grid transmission parameter and the power grid device parameter are adjusted respectively to obtain the initially adjusted power transmission parameter and the initially adjusted device parameter; Generate device parameter fine-tuning data and transmission parameter fine-tuning data according to the dynamic load balancing data of the target power grid; the dynamic load balancing data is obtained by the power grid resource dispatching network performing global dynamic balancing calculations on the initial adjustment of the transmission parameters and the initial adjustment of the device parameters of each power grid resource dispatching node; According to the device parameter fine-tuning data and the power transmission parameter fine-tuning data, the initially adjusted power transmission parameters and the initially adjusted device parameters are fine-tuned respectively.

6. The method according to any one of claims 1 to 5, applied to the power grid resource dispatching network, characterized in that: The global power grid resource dispatching calculation model is obtained by merging the optimized power grid resource dispatching calculation models through the power grid resource dispatching network, and includes: Determining, according to each of the power grid resource dispatching nodes, a model weight corresponding to each of the optimized power grid resource dispatching calculation models; According to the weights of the models, the optimized power grid resource scheduling calculation models are merged to obtain an initial power grid resource scheduling calculation model; According to each of the power grid resource scheduling nodes, the fault tolerance parameters of the initial power grid resource scheduling calculation model are optimized to obtain the global power grid resource scheduling calculation model.

7. The method according to any one of claims 1 to 5, applied to the power grid resource dispatching network, characterized in that: The method further comprises: Determining evolution adjustment information of the global power grid resource scheduling calculation model according to global power grid resource scheduling information of different scenarios; According to the evolution adjustment information, the model parameters of the global power grid resource scheduling calculation model are adjusted.

8. A distributed artificial intelligence agent-based power grid resource dispatching device, applied to artificial intelligence agents, characterized in that: The device comprises: A parameter acquisition module, used to acquire power grid operation parameters, external meteorological parameters and equipment status parameters corresponding to the artificial intelligence agent; each of the artificial intelligence agents is deployed on a power grid resource dispatching node corresponding to the target power grid; A model optimization module, used to optimize the model parameters of the node power grid resource scheduling calculation model according to the power grid operation parameters, the external meteorological parameters and the equipment status parameters, and send them to the power grid resource scheduling network; A model acquisition module, used to acquire a global power grid resource dispatching calculation model sent by the power grid resource dispatching network; the global power grid resource dispatching calculation model is obtained by merging various optimized power grid resource dispatching calculation models through the power grid resource dispatching network; A parameter calculation module, used to input the power grid operation parameters, the external meteorological parameters and the equipment status parameters into the global power grid resource scheduling calculation model, obtain node power grid resource scheduling information, and send it to the power grid resource scheduling network; A resource scheduling module is used to adjust the power grid transmission parameters and power grid equipment parameters of the power grid resource scheduling node according to the global power grid resource scheduling information sent by the power grid resource scheduling network; the global power grid resource scheduling information is obtained by integrating the power grid resource scheduling information of each node through the power grid resource scheduling network.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images