13 results about "Single agent" patented technology

The application discloses a virtual power plant cooperative control method based on multi-agent layered reinforcement learning, and a layered multi-agent system (MAS) processes complex tasks through hierarchical cooperation and distributed decision among agents, and specifically comprises the following steps: S1, an attribute information of a single agent is acquired by a bottom execution layer, specific equipment is directly controlled, and an inverter output power is adjusted or a load transfer instruction is executed according to a middle management layer; S2, a middle management layer receives an instruction of a top coordination layer, a sub-group is mixedly divided according to a region or a resource type, the instruction of the top coordination layer is executed, and real-time data is fed back; S3, the top coordination layer serves as a global decision center, is responsible for power market strategy formulation and resource aggregation optimization, and finally outputs a structured decision instruction and dynamic feedback; after the virtual power plant (VPP) receives the structured decision instruction and dynamic feedback output by the top coordination layer, layered processing and dynamic optimization are carried out. The application can obviously reduce delay and reduce load.

The present invention discloses a method and system for collaborative detection of static targets based on multi-agent collaboration, comprising the following steps: S1, setting the range constraints of the area to be detected, initializing each agent and the static target; S2, mathematically modeling the collaborative detection problem, and completing the problem setting; S3, setting the task utility of each agent; S4, setting the static target collaborative detection algorithm, and completing the dynamic task allocation; S5, dynamically updating the state quantities of the agent and the static target, and realizing the detection of the static target. The present invention selects the optimal task for a single agent by the utility value of the agent or maximizing the expected utility, and allows the agents within the communication range to share their own state vectors, and then realizes a bidding auction based on the state vectors and the utility of the individual agents, abstracting the optimal task allocation into the problem of solving the bidding vector in the auction, and adopting a greedy decentralized auction algorithm to solve it, realizing the optimal task allocation of multiple agents with dynamic adjustment of the number of detections and detection angles, and guiding the detection of agents.

The invention discloses a multi-agent-based product research and development decision optimization method and system, and belongs to the technical field of artificial intelligence. The invention aims to solve the technical problems that an existing product aided design system adopts a single agent architecture and lacks an effective cooperation mechanism, so that an information island phenomenon is serious, and a unified product research and development scheme is difficult to form. According to the method, an assistant agent analyzes an issue and automatically calls cross-domain professional agents, each agent makes a proposal for the issue according to the own professional field, and the assistant agent organizes to perform review, screens out the proposal decided by the review, and arranges the proposal into a comprehensive decision scheme. The method is mainly used for optimizing the product research and development decision scheme.

The invention provides a cross-role agent network construction method and device. Aiming at the problems of low complex task processing efficiency and poor result reliability caused by fixed roles, inaccurate capability matching and lack of dynamic collaboration of a traditional agent system, the method is realized by the following steps of: vectorizing the multi-dimensional capability of an agent to generate role capability vectors; extracting compound task demand keywords, generating demand vectors with consistent dimensions, and calculating the cosine similarity of the keywords and the demand vectors; and if the matching degree of a single agent reaches the standard, selecting a main executor, otherwise, combining high-similarity agents to form a temporary network, and supplementing a gap or verifying a conclusion through an auxiliary executor. According to the method, the matching precision of the intelligent agent and the task requirement and the complex task processing coverage degree are improved, the result reliability is guaranteed, and the method is suitable for composite task cooperative processing of multiple scenes such as medical treatment, enterprise management and meta universe.

The invention relates to the technical field of power distribution network dispatching and virtual power plant cooperative control, in particular to a power distribution network load recovery method based on a multi-agent coordination mechanism under a virtual power plant, which comprises the following steps of: modeling adjustable resources of the virtual power plant to quantify power regulation potential, abstracting a load recovery process into a Markov decision process, and extracting the load recovery process into the Markov decision process; then configuring three types of agents, namely a switch control agent, a virtual power plant coordination agent and a global coordination agent, and finally realizing multi-agent training and execution; according to the method, the power supporting potential of the virtual power plant can be fully released, the problems that a single agent is slow in convergence and prone to sinking into local optimum, and multi-agent mixed action space adaptation defects exist are solved, the operation safety of the power grid is guaranteed, and the flexibility, efficiency and safety of load recovery after the power distribution network breaks down are improved.

The invention provides a test case generation method and device, equipment and a storage medium, test demand information is obtained, the test demand information comprises task content information of a test task and a knowledge fragment associated with the test task, then the test demand information is input into an agent model comprising a plurality of different agents, and a test case is generated according to the agent model. The target test case of the test task is generated and output, the target test case can be automatically generated according to the test task, the labor cost is saved, the case generation efficiency is improved, in addition, the agent model comprises a plurality of different agents, and compared with test case generation through a single agent, the test case generation efficiency is improved. The quality of the generated target test case can be improved.

The invention relates to the technical field of intelligent decision, and discloses a PPO-based multi-agent cooperation mechanism generation method, device, equipment and medium, and the method comprises the steps: generating a single-agent output action through PPO, an independent agent and a current state vector, and calculating a single-agent advantage value according to GAE; and generating an agent cooperation mechanism according to the negative extrinsic punishment mechanism, the priority rule, the single agent output action and the single agent advantage value. Through the above mode, the heterogeneous data is converted into the unified state vector, the single-agent action is generated through the PPO algorithm, and the single-agent advantage value is calculated through the GAE algorithm, so that the problems of training oscillation and convergence difficulty of multiple agents are inhibited, and through a penalty mechanism and a priority rule, the multi-agent training efficiency is improved. The problem of deviation between local optimum and global target of multiple agents is solved. The method can be applied to the business fields such as financial science and technology and medical health care, and the reliability of parallel processing of multiple businesses by the intelligent customer service system is improved.

The present application relates to the technical field of virtual power plant operation, and particularly relates to a multi-agent cooperative game virtual power plant configuration optimization method and system. The method evaluates the cooperation value of a single agent by analyzing the difference between the individual operation income and the cooperative operation income of each agent in the virtual power plant; determines the contribution ability of the agent according to the dynamic response degree determined based on the current power of the agent and the power fluctuation deviation of the agent in the historical operation, and in combination with the loss risk that can be borne by each agent in the operation of the virtual power plant; and optimizes the configuration operation based on the matching of the dynamic contribution ability and the cooperation value. The present application introduces the contribution perception to optimize the overall configuration scheme by the matching relationship between the contribution and the obtained income of each agent in the cooperative process, improves the operation efficiency of the virtual power plant, the incentive effectiveness of the income distribution and the stability of the multi-agent alliance, and reduces the structural disconnection problem between the configuration optimization and the income distribution.

The present application belongs to the technical field of virtual power plant instruction decomposition, and particularly relates to a kind of virtual power plant scheduling instruction fast decomposition method based on multi-agent.The present application can more flexibly cope with the change and demand fluctuation of power system, based on the historical data and current state of agent, calculates compensation value, ensures the reasonable distribution and optimized use of system resource, load and power, improves the overall operation efficiency of virtual power plant, through the setting of instruction decomposition level, the task allocation of agent can be dynamically adjusted according to the actual situation, avoids the overload of single agent, improves the execution efficiency of scheduling instruction, combined with current power data, high energy consumption tasks can be arranged preferentially when power is low, or power generation is reduced when power is high, reduces operating cost, improves economic benefit, uses the historical data of agent for compensation value calculation and decision-making, improves the scientificity and accuracy of scheduling instruction decomposition, reduces the influence of uncertain factors in scheduling process.

The present invention relates to a universal large-model-based Agent task execution cross-cascade framework. The framework task execution method includes: a master agent receives user task instructions, decomposes them into subtasks, and outputs a subtask list; a format correction slave agent verifies the list format and corrects it; a planning correction slave agent optimizes the subtask content to ensure rationality and executability; the master agent calls tools to execute subtasks one by one and monitors anomalies; a tool call slave agent analyzes and corrects tool anomalies and resolves problems through tool installation or configuration adjustment; a result correction slave agent verifies the execution results and corrects the operation until it meets the task requirements; the master agent receives the final result and delivers it to the user. This cross-cascade design improves system automation, stability, and reliability, and reduces dependence on the performance of a single agent.

The invention discloses a prevention and control method and device based on multi-agent deep reinforcement learning, and belongs to the technical field of power system control. According to the method, the electric power system prevention and control mathematical model is constructed through the operation data of the electric power system, and then the agent state space, the agent action space and the reward function are constructed through the electric power system prevention and control mathematical model and the operation data, so that a plurality of initial agents of the electric power system are constructed; the deep fusion of the intelligent agent of deep reinforcement learning and the mathematical model is realized; the problem of dimension explosion caused by using a single agent in the prior art is avoided through a plurality of initial agents; training is carried out by improving a multi-agent depth deterministic strategy gradient algorithm and operation data, so that the first agent can still output an accurate prevention and control strategy under the complex working condition of the power system, and the method can better adapt to the dynamic change and uncertainty of the power system; therefore, the prevention and control accuracy of the power system is improved.

The application relates to the technical field of intelligent computing centers, in particular to an agent context optimization method for an intelligent computing center, which comprises the following steps: step 1), system initialization; step 2), task receiving and disassembly; 3), intelligent routing and selective injection; step 4), subtask execution; step 5), result aggregation and feedback. Through MCP capability boundary binding and a selective injection mechanism, the MCP tool is changed from "full injection" to "precise injection", the Token occupation of a single agent is greatly reduced, the effective working space of the model is released, and the problem that Token resources are excessively squeezed is solved; the context of each expert agent only contains MCP tool definitions in the own field, MCP tool definitions under long context are avoided to accumulate, the problem of intermediate information loss caused by the U-shaped bias of the attention mechanism is solved, and the identification and execution accuracy of key business information is improved.

The invention discloses a multi-agent collaborative reasoning method and system, a terminal and a storage medium. According to the method, structural reasoning is firstly carried out on the user demand through the first-level intelligent agent, the first reasoning conclusion with the structural mark is output, the general user demand is divided into a plurality of clear structural intention bodies, each structural intention body has a respective reasoning result, confusion when a single intelligent agent processes complex information is avoided, and the user experience is improved. And understanding deviation is reduced. Secondly, secondary structured reasoning is conducted on the specific structured intention body through the secondary agent, and the primary agent is optimized through output of the secondary agent; in the optimization process, superposition correction is not carried out in original disordered dialogues, interference of historical deviation information is avoided, it is ensured that correction focuses on specific problems every time, deviation expansion cannot be caused, and therefore a reasoning conclusion meeting user requirements is updated step by step.