507 results about "Multi-agent system" patented technology

A system, methods and apparatus are described involving the self-organizing dynamics of networks of distributed computers. The system is comprised of complex networks of databases. The system presents a novel database architecture called the distributed transformational spatio-temporal object relational (T-STOR) database management system (dbms). Data is continuously input, analyzed, organized, reorganized and used for specific commercial and industrial applications. The system uses intelligent mobile software agents in a multi-agent system in order to learn, anticipate, and adapt and to perform numerous functions, including search, analysis, collaboration, negotiation, decision making and structural transformation. The system links together numerous complex systems involving distributed networks to present a novel model for dynamic adaptive computing systems, which includes plasticity of collective behavior and self-organizing behavior in intelligent system structures.

A system and method of interacting with a multi-agent distributed control system employing a plurality of controllers on which are programmed a plurality of agents in which the controllers are coupled by a network are disclosed. The method includes providing a computer program capable of operating a user interface, where the computer program is in communication with the agents via the network. The method further includes displaying agent-related information on the user interface by way of a plurality of windows, where within a first of the windows is further displayed a workflow among at least some of the agents, and within a second of the windows is further displayed at least one of a plurality of messages communicated among at least some of the agents, a work unit requested by at least one of the agents, and message content associated with at least one of the messages.

A system, methods and apparatus are described involving the self-organizing dynamics of networks of distributed computers. The system uses intelligent mobile software agents in a multi-agent system to perform numerous functions, including search, analysis, collaboration, negotiation, decision making and structural transformation. Data are continuously input, analyzed, organized, reorganized, used and output for specific commercial and industrial applications. The system uses combinations of AI techniques, including evolutionary computation, genetic programming and evolving artificial neural networks; consequently, the system learns, anticipates and adapts. The numerous categories of applications of the system include optimizing network dynamics, collective robotics systems, automated commercial systems and molecular modeling systems. Given the application of complexity theory and modal and temporal logics to self-organizing dynamic networks, a novel model of intelligent systems is presented.

The invention provides a cooperative control method for multi-intersection signal lamp based on Q value migration depth reinforcement learning, and belongs to the crossing field of machine learning and intelligent traffic. A multi-intersection traffic network of an area is modeled into a multi-Agent system firstly. Each Agent simultaneously considers the influence of adjacent Agent actions at themost recent moment in the learning strategy process, so that multiple Agents can cooperatively conduct signal lamp control of multi-intersection. Each Agent adaptively controls one intersection through a deep Q network, and a network input is a discrete traffic state code of the original state information of the corresponding intersection. An optimal action Q value of the adjacent Agent at the most recent moment is transferred to the loss function of the network in the process of learning. The cooperative control method for multi-intersection signal lamp based on the Q value migration depth reinforcement learning can improve the traffic flow of the regional road network and the utilization rate of the road and can reduce the queuing length of the vehicle to relieve the traffic jam, and hasno limitation on the structure of each intersection.

Computerized scheduling methods and computerized scheduling systems according to exemplary embodiments. A computerized scheduling method may be stored in a memory and executed on one or more processors. The method may include defining a main multi-machine scheduling problem as a plurality of single machine scheduling problems; independently solving the plurality of single machine scheduling problems thereby calculating a plurality of near optimal single machine scheduling problem solutions; integrating the plurality of near optimal single machine scheduling problem solutions into a main multi-machine scheduling problem solution; and outputting the main multi-machine scheduling problem solution.

The present invention provides a real estate information management and data analysis system, and relates to the field of real estates. The system is provided with a client service system, an agent system, a developer system and a data analysis system, each sub system of the client service system, the agent system, the developer system and the data analysis system has concrete sub systems, and thesub systems with rich functions can achieve integrated service for clients and can improve the client experience.

The invention discloses an active fault-tolerant control method for a lienar multi-agent tracking system on the basis of slip form control. A distributed fault-tolerant control strategy is put forwardby a distributed observer and a slip form control method by considering the executor faults, the sensor faults, the inherent nonlinearity and the leader unknown control input of a general linear multi-agent tracking system. Firstly, a state tracking error system is established by aiming at each follower, and a sensor fault signal is taken as an auxiliary state amount to establish an augmented tracking error system. In order to simultaneously estimate various faults and the leader unknown control input, an intermediate variable is imported. On the basis of neighbor set output information, a distributed observer is designed for the augmented tracking error system and the intermediate variable, and a global estimation error system is proved to be finally uniformly bounded. According to the obtained observation information, a nonlinear slip form surface is designed for the tracking error system of each follower agent, system robustness is enhanced, and the stability of a sliding mode is proved. According to the fault observation information and the neighbor set output information, a distributed slip form controller is put forward, the state of the error system is guaranteed to reach and be kept at the slip form surface within limited time, and therefore, the fault-tolerant tracking stability of the multi-agent system is realized. The method is used for the fault-tolerant control of the linear multi-agent tracking system with executor faults and sensor faults.

A hybrid router for dynamical control systems is described. The mobile hybrid software router (MHSR) combines distinctive computational and mathematical techniques, including evolutionary computation (EC), probabilistic simulations (PS), machine learning and artificial neural networks (A-NNs), in order to solve unique problems encountered in an unknown environment in real time. Embodied in intelligent mobile software agents (IMSAs), the MHSR operates within a multi-agent system (MAS) to continually optimize system operation. The MHSR is applied to several major complex system categories. In one embodiment of the system, the MHSR is implemented in hardware, including continuously programmable field programmable gate arrays (CP-FPGAs), for perpetually reconfigurable evolvable hardware operation. Whether in application-specific or multi-functional mode, the MHSR is useful to groups of agents in intelligent systems for adaptation to uncertain environments in order to perform self-organization capabilities.

The invention discloses the optimal consistency control method and system of a nonlinear multi-agent system. The method is characterized by establishing a reference behavior model according to the individual dynamic characteristic of a heterogeneous multi-agent system, and using a leader-follower control model to form a multi-agent system formed by reference behavior models; then, constructing a dynamic graph game global error dynamical model according to the network topology structure of multiple agents, defining a multi-agent local performance index function, and according to the global Nashequilibrium, acquiring a Bellman optimal equation; and then, under the condition of only using local agent information, using an execution-evaluation execution network framework mode based on value function approximation to carry out online iterative learning, and acquiring an optimal consistency protocol to achieve the consistency of each reference model behavior. Compared with the prior art, byusing the method and the system of the invention, under the condition of guaranteeing optimal control performance, the consistency problem of the complex multi-agent system can be high-efficiently solved, and an actual application value and high scalability are achieved.

The invention discloses an intelligent storage and distribution system optimization scheduling method based on a polychromatic sets theory. The method belongs to a centralized and distributive combined mixed scheduling control method based on a multi-AGENT system. Under the condition of not influencing the normal work of other modules, the system has the advantages that a parallel processing effect and the robustness can be achieved, the modification and the extension are easy, and the like. The adaptability, the flexibility and the intellectuality of the system are enhanced. Through optimizing the system physical layer operating flow process and designing a reasonable system control layer decision algorithm, the real-time and dynamic scheduling of a storage and distribution system is realized. An RFID (Radio Frequency Identification) technology is utilized for collecting and processing system information, and the state of a material flow system is monitored in real time; the reference is provided for the management layer scheduling decision; the automation, the intelligence and the informatization of the information management and the control scheduling of the intelligent storage and distribution system are realized; and powerful technical support is provided for building the intelligent storage and distribution system based on Internet of Things.

The invention discloses a tracking fault-tolerant control method for a linear multi-agent system based on sliding mode control. A fault-tolerant control method based on the sliding mode control methodand adaptive control is proposed for the actuator fault of the linear multi-agent tracking system with external disturbance. Aiming at the actuator partial failure fault that may occur in the agent,the state error variable is defined according to the communication topology between multi-agents, the integral sliding mode surface is designed based on the error variable and sufficient conditions for sliding mode asymptotic stability are given. Then the unknown upper bound of the actuator fault is estimated by the adaptive method, and a sliding mode fault-tolerant controller is proposed to guarantee the tracking stability of the multi-agent system. The integral sliding mode surface is designed according to the state error variable between the multi-agents and the robustness of the system isenhanced, and the fault-tolerant control law having good fault-tolerant ability when the system has partial actuator failure fault and external disturbance is put forward and the tracking stability ofthe multi-agent system is improved. The fault-tolerant control method is used for fault tolerant control of the linear multi-agent system with the actuator failure fault and the external disturbance.

The invention discloses a distributed multi-intelligent-agent real time fault detection method based on neighbor associated condition. By converting node models having faults, a new fault detection model is built, fault signals and system condition variables are decoupled, fault detection difficulty is lowered, and only associated condition information of neighbors can be obtained via nodes. According to the distributed multi-intelligent-agent real time fault detection method, by setting fault detection sub-networks and subjecting sub-network models to corresponding linear conversion, node associated condition information can be converted into condition variables in the above fault detection model, and fault detection tasks can be done via the model. The invention provides a new fault detection solution to observe whether faults occur. The invention provides a neighbor associated condition solution for fault detection results. According to the distributed multi-intelligent-agent real time fault detection method, groupment advantages of a multi-intelligent-agent system are fully used, reliability of detection results is increased without system hardware performance improvement, and the distributed multi-intelligent-agent real time fault detection method is high in application value.

The invention provides a leader-follower ratio consistency control method of a two-order multi-agent system. Following agents and leaders are determined according to a network topological structure; adirected generation tree structure using leaders as root nodes is determined; secondarily, the multi-agent state ratio relationship is realized according to the expectation; the proportional parameter is selected for the following agents, so that the two-order multi-agent state reaches the expected specified proportion relationship; finally, under the condition that one or a plurality of following agents can obtain the leader information, a leader-follower ratio consistency protocol is designed; the goal of strictly following the state of a leader according to a certain ratio in a way of following the agent state is achieved, so that the state of all following agents realizes the ratio consistency.

A self-adaptive intelligent coordination protection and control system for power grids based on WANs (Wide Area Network) and multiple agents has the design scheme that according to the characters of hierarchical structure and geograhical distribution of a power system, a developing and modeling method of the software Agent is used to establish a divisional and hierarchical system. The system realizes coordination of protection actions by the capacity of a multi-agent system for solving distributed on-line questions. Through the plan to protect setting tasks, each agent is responsible for a specific task, and thus, the multi-agent system can establish knowledge libraries of all agents rightly and obtain high search efficiency. Each agent improves performance per se by exchanging information and learning from others, and then improves the capacity of the whole self-adaptive coordination protection system for solving questions. Because of the loose coupling relationship among the agents, the whole system has a more flexible structure and has real-time response to environmental changes.

The invention discloses a finite time robust fault diagnosis design method for a leader-follower multi-agent system. The method includes the steps: firstly, building a multi-agent system connection diagram with a leader and showing the multi-agent system connection diagram by a directed graph to obtain a Laplacian matrix L of a follower and an adjacent matrix G of the leader; building a state equation and an output equation of each node flight control system and augmenting a state vector and a fault vector into new vectors; constructing a distributed error equation and a global error equation based on the directed graph for each node according to the built directed graph, constructing a finite time fault diagnosis observer of a flight control system based on finite time robust control, and performing finite time fault diagnosis for faults of a multi-agent executor based on the directed graph. Faults of an optional node of the control system or simultaneously occurring faults of a plurality of nodes are effectively and accurately diagnosed and estimated on line in finite time.

The invention discloses an energy local area network distributed cooperative control method based on a multi-intelligent-agent system. The method comprises the following steps: (1) constructing a three-level control framework of the energy local area network, namely a control framework of local droop control-secondary power optimization control-centralized optimization and area autonomous control;(2) designing a dispatching decision function module, in the processes of fault generator tripping and connection and disconnection switching in the energy local area network, coordinating the controllable resources with different control response rates, responding to the internal and external energy requirements of the local area network, and rapidly stabilizing the power fluctuation of the interconnection line; (3) constructing a distributed sparse communication network based on a multi-intelligent-agent system, communicating through the adjacent intelligent agents, estimating the average voltage of the whole net based on the consistency algorithm, and correcting the voltage and the frequency of the local droop controller to simulate the behavior of the synchronous generator. The control method provided realizes the energy management optimization, flexible interaction of multiple users, and coordinate operation of distributed resources.

The invention discloses a distributed optimal cooperative fault-tolerant control method based on self-adaptive dynamic planning. The distributed optimal cooperative fault-tolerant control method comprises the steps of: firstly, constructing a communication topology of a multi-agent system by means of communication links among agents, and representing the communication topology by a directed graphG=(V, E, A); secondly, establishing a local domain consistency error equation, and defining a failure-free cooperative control input quantity of the agent vi as ui based on an optimal control theory and a minimum value principle, so as to obtain a distributed optimal cooperative control law; thirdly, executing the distributed optimal cooperative control law; and finally, designing a distributed optimal cooperative fault-tolerant control law of the agents. The distributed optimal cooperative fault-tolerant control method can overcome the shortcomings of the existing nonlinear multi-agent systemfault-tolerant control method, and has a good application prospect in the fault-tolerant control of UAV formation.

The invention provides a cooperated tracking control method of time-lag non-linear multi-agent systems. The method aims at the time-lag non-linear multi-agent systems having uncertain communication. In a practical environment, the local information exchange among the time-lag non-linear multi-agent systems is frequently influenced by uncertainty such as unreliable communication caused by switching of network topologies and interrupt of communication links. According to the invention, an effective distributed control protocol is designed, and the cooperated tracking consistency under the environment that network topology exchange and unreliable communication exist at the same time is well realized, so that design guidance is provided for complex systems having uncertain communication in the practically complex civil and military fields.

A scheduling system (DPS) for planning and scheduling production in an industrial production system (CL), which scheduled production is to be executed by the production system (CL) under the control of a manufacturing execution system (MES), wherein: —said scheduling system is a multi-agent scheduling system (DPS); —at least a part of the behavior of the agents in said multi-agent system (DPS) is customizable by means of visually defined scheduling rules; —said scheduling system (DPS) and manufacturing execution system environment comprising: —editor means (CI) for visually defining both said manufacturing execution system (MES), and—an execution engine for executing said scheduling rules and control rules and making scheduling decisions on the basis of the execution of said scheduling rules and control rules.

The invention relates to a method and a system for restoring power after fault of a power distribution network containing DGs. According to the method, the DGs integrated in the power distribution network are processed in a classified manner according to the control method of the DGs and are divided into main power supplies and ordinary power supplies, wherein the main power supplies are controllable DGs, and the ordinary power supplies are random and uncontrollable DGs; and meanwhile, a standby contact wire is used as a main power supply, then, a multi-agent system for power restoration after fault of the power distribution network containing the DGs is established, and the optimum power supply scheme of a power-losing area is planned in a master-slave control mode. Compared with the prior art, the standby contact wire and the DGs integrated in the power distribution network are fully utilized in the restoration process, the power outage load is restored to the maximum, and the isolated island operation capacity of the DGs and randomness and volatility of output power are given full consideration, so that a restoration scheme can continuously and stably operate.

The invention relates to a fixed time cooperative tracking control method of a second-order nonlinear multi-agent system, which comprises the steps of: designing a fixed time convergence nonsingular terminal sliding mode surface; designing an RBF neural network approximation system dynamics nonlinear term; designing a multi-agent system fixed time cooperative tracking controller; and enabling thedesigned controller to act on the system to realize the control of a multi-agent system for cooperatively tracking a target agent within fixed time. The fixed time cooperative tracking control methodhas strong robustness to external disturbance, has strong adaptability to unknown nonlinearity of a model, and can ensure the convergence of the system within fixed time, and enables the convergence time to be irrelevant to the initial state of the system. The fixed time cooperative tracking control method has wide application range and can be applied to systems with high requirement on convergence time.

The invention discloses a multi-intelligent-agent system collaborative fault-tolerant control method based on finite time control. The method comprises the steps of firstly, selecting an intelligent agent as a leader node in all the intelligent agents, constructing a multi-intelligent-agent system communication topology and expressing by an undirected graph through communication links among the multiple intelligent agents, calculating a weighted adjacent matrix, establishing a finite time controller based on the state error based on a finite time theory for the established multi-intelligent-agent system with the leader nodes, establishing different finite time controllers for each intelligent agent, and obtaining a global dynamic equation of the multi-intelligent-agent system, so that thesystem can achieve cooperative fault-tolerant control within a specified time from the time a fault occurs. The defects of a non-finite-time closed-loop control system are overcome, and the robustnessand the disturbance resistance of a multi-intelligent-agent system are improved.

A method and apparatus is described for insuring coherency between memories in a multi-agent system where the agents are interconnected by one or more fabrics. A global arbiter is used to segment coherency into three phases: request; snoop; and response, and to apply global ordering to the requests. A bus interface having request, snoop, and response logic is provided for each agent. A bus interface having request, snoop and response logic is provided for the global arbiter, and a bus interface is provided to couple the global arbiter to each type of fabric it is responsible for. Global ordering and arbitration logic tags incoming requests from the multiple agents and insures that snoops are responded to according to the global order, without regard to latency differences in the fabrics.

The invention, which belongs to the crossing field of artificial intelligence and intelligent transportation, provides a multi-intersection cooperative traffic light control method based on Q-value migration of a multi-task deep Q network. Multiple intersections are modeled into a multi-agent system; a multi-task network that is suitable for controlling of each intersection traffic light is trained at multiple intersections; knowledge learned at the multiple intersections is applied to a target problem, so that the multi-task network have much more knowledge than the single network and the single intersection feature extraction capacity is enhanced; and then on the basis of a cooperative algorithm, traffic lights of all intersections in a target area are controlled cooperatively. Therefore, the traffic flows of all intersections can be balanced to a certain degree; the road utilization rate in the regional traffic can be increased; the vehicle queuing length can be reduced; and the traffic congestion can be alleviated. The method has the high scalability to the traffic network.

The invention discloses a distribution network expansion planning method considering the optimized operation of a regional integrated energy system. Firstly, a regional integrated energy system modelis established and the internal energy flow relationship is analyzed. Secondly, based on the multi-agent system, a three-layer interactive structure including the main layer, the regional layer and the device layer is built to realize the interaction of different entities on the spatial scale. Then, a bi-level optimization model is established for the distribution network with residential, commercial and industrial regional integrated energy systems. The upper level is used for the expansion planning of distribution network, and the lower level is used for the optimization operation of regional integrated energy systems. Genetic membrane algorithm and sequential quadratic programming are used to solve the upper and lower level models nested nested. Finally, the simulation example shows that the distribution network planning considering the optimal operation of regional integrated energy system can reduce the total cost of planning, improve energy efficiency and new energy consumption rate.

The invention discloses an active formation fault-tolerant control method based on a fast adaptive technology. The active formation fault-tolerant control method comprises the steps that a laplacian matrix and a leader-following connection matrix of distributed multi-agent systems are achieved by constructing a connection diagram of multi-agent systems; according to a four-rotor aircraft model ofan existing nonlinear term, a corresponding observer and a fast adaptive fault estimator are constructed to predict the actual size of faults;alocal augmented system error dynamic equation and a wholeaugmented system error dynamic equation are constructed; Lyapunov function is constructed, the method that parameters in a computational controller and the fault estimator are calculated is derived and achieved through corresponding theories, and the requirements of formation control are finished under the action of actuator failure of the system and external interference. According to the activeformation fault-tolerant control method, adverse influence of the external interference on fault-tolerant control is completely eliminated at the theoretical level, performance of fault estimation isimproved, and the fault-tolerant control when the actuator fault occurs at any node of four-rotor aircraft formation or when the actuator fault occurs at multiple nodes at the same time is achieved.

The invention provides a distributed multi-agent system-based combat simulation engine. According to the combat simulation engine, a hierarchical blackboard structure is constructed on the basis of a blackboard mechanism; and by applying a distributed parallel computing theory, the reasonable distribution and full utilization of the computing resources of simulation nodes in the distributed simulation are realized, and the multi-process parallel computing management and scheduling of a large number of intelligent agent models in the simulation nodes are realized. The combat simulation engine comprises a universal blackboard frame, a blackboard manager, a serial network communication component, a blackboard browser, a recording / playback component, a CGF behavior modeling frame, a graphical CGF behavior modeling tool, an equipment performance parameter library component and a behavior knowledge base.

A distributed swarm intelligence system comprises an underlying protocol layer used for adapting to a network protocol; a core software platform layer, used for calling computing resources of an external system platform and supporting a distributed system, a consistency algorithm and a computing model; an open software layer, used for providing an open source system framework. The distributed system at least comprises one or more of an HLA system, a DDS system and a Multi-Agent system. According to the system, the problems of large-scale calculation, calculation model splitting, cooperation of multiple intelligent expert systems, swarm intelligence decision making, intelligent system decision making flexible organization and the like are solved.

The invention discloses a fault tolerant control method for a multi-agent system based on adaptive sliding mode control. The failure of the actuator in the second-order nonlinear multi-agent system isconsidered, combined with adaptive control and sliding mode control, a fault-tolerant control method is proposed. The consistency error variable is defined according to the relative state informationbetween the agents, and the sliding mode surface is designed based on the consistency error variable, and the sufficient conditions for the asymptotic stability are given. The method based on adaptive boundary estimation estimates the upper bound of the fault, which ultimately constitutes a complete sliding mode fault-tolerant controller. The method simplifies the complexity of the problem by designing a sliding surface based on the consistency error variable; combined with the advantages of adaptive control and sliding mode control, the designed fault-tolerant control law has good fault tolerance. The method is used for fault tolerant control of a multi-agent system with actuator partial failure.

The invention discloses a multi-intelligent-agent coordination control method based on an evolutionary game theory. By constructing an evolution system having a natural selection attribute, the gaming conflict among the intelligent agents and the coordination control of the intelligent agents can be realized. The proposed method includes S1 establishing a multi-intelligent-agent theory framework; S2 establishing the topological relationship between agents through a communication topological graph: setting up the communication topological graph; S3 determining the gaming type according to the controlled target; S4 calculating returns according to the gaming relationship between agents, defining the state of a multi-intelligent-agent system based on the gaming matrix, expressing the variation of each group of component in the system by means of the replication kinetic equation, analyzing the balance point of the replication kinetic equation, and determining the evolutionary stability strategy of the system; S5 evaluating the fitness of the intelligent agents; and S6 evaluating the returns of the intelligent agents in the evolution of the system and updating the strategy.