This paper analyzes progresses and difficulties of subjects on computer network’s management and artificial intelligence, proposes AGIMA, a new model of network intelligent management, which is based on computer supp...This paper analyzes progresses and difficulties of subjects on computer network’s management and artificial intelligence, proposes AGIMA, a new model of network intelligent management, which is based on computer supported cooperative work (CSCW) and combining new technologies such as WWW, Java. AGIMA transfers from information distribution centered mode in traditional network management to computing distribution centered mode, providing intelligence capacity for network management by a whole intelligent agent group. The implementation of AGIMA takes much consideration of openess, scalability, proactive adaptability and friendliness of human computer interface. Authors present properties of intelligent agent in details, and conclude that network intelligence should be cooperation between human and computer.展开更多
Mission planning was thoroughly studied in the areas of multiple intelligent agent systems,such as multiple unmanned air vehicles,and multiple processor systems.However,it still faces challenges due to the system comp...Mission planning was thoroughly studied in the areas of multiple intelligent agent systems,such as multiple unmanned air vehicles,and multiple processor systems.However,it still faces challenges due to the system complexity,the execution order constraints,and the dynamic environment uncertainty.To address it,a coordinated dynamic mission planning scheme is proposed utilizing the method of the weighted AND/OR tree and the AOE-Network.In the scheme,the mission is decomposed into a time-constraint weighted AND/OR tree,which is converted into an AOE-Network for mission planning.Then,a dynamic planning algorithm is designed which uses task subcontracting and dynamic re-decomposition to coordinate conflicts.The scheme can reduce the task complexity and its execution time by implementing real-time dynamic re-planning.The simulation proves the effectiveness of this approach.展开更多
This paper presents a pooled-neighbor swarm intelligence approach (PNSIA) to optimal reactive power dispatch and voltage control of power systems. The proposed approach uses more particles’ information to control the...This paper presents a pooled-neighbor swarm intelligence approach (PNSIA) to optimal reactive power dispatch and voltage control of power systems. The proposed approach uses more particles’ information to control the mutation operation. The proposed PNSIA algorithm is also extended to handle mixed variables, such as transformer taps and reactive power source in- stallation, using a simple scheme. PNSIA applied for optimal power system reactive power dispatch is evaluated on an IEEE 30-bus power system and a practical 118-bus power system in which the control of bus voltages, tap position of transformers and reactive power sources are involved to minimize the transmission loss of the power system. Simulation results showed that the proposed approach is superior to current methods for finding the optimal solution, in terms of both solution quality and algorithm robustness.展开更多
During the development of the intellectual multi-agent investment management information system （designed for the formation of investor＇s investment decisions）, it was established that there is a lack of both neces...During the development of the intellectual multi-agent investment management information system （designed for the formation of investor＇s investment decisions）, it was established that there is a lack of both necessary comprehensive researches and analysis to invoke more than one decision-making aspect （argument） for the making of investment decision, and recommendations to combine these diverse parameters. It is possible to find a lot of articles and researches in which investment decisions or investment tactics are decided on the ground of either technical or fundamental analysis, or modeling and on the ground of intellectual calculating technique （for example, fuzzy logic, neural net, genetic programming）, whereas the issues of the coordination of different techniques are not decided at all. To fill this niche, the article offers the decision applied in multi-agent investment management information system which allows to provide rationale for investment decision taking into account four aspects （arguments）, i.e., to form the recommendation to purchase/hold/sell a security paper having evaluated the following four aspects （arguments）： （a） fundamental analysis, （b） technical analysis, （c） experts and analysts＇ recommendations and （d） risk assessment. These aspects （arguments） are chosen taking into account the real most commonly occurring process of investor＇s investment decision-making. The article gives the implementation of aspects （arguments） assessment by four corresponding software agents whose decisions are implemented with a help of fuzzy logic. Besides, the article offers the technique of the unification of these aspects （arguments）. The offered intellectual multi-agent investment management information system can be tested on the internet： www.sprendimutechnologijos.lt/webapp （MADSYS project）.展开更多
Machine learning has been widely applied to deal with problems in complex environment such as RoboCup, which is assumed as the ideal platform for research on AI and robotic. In RoboCup simulation league, software agen...Machine learning has been widely applied to deal with problems in complex environment such as RoboCup, which is assumed as the ideal platform for research on AI and robotic. In RoboCup simulation league, software agents play soccer games on an official soccer server over the network. When constructing these software agents, issues in area of agents learning techniques arise to satisfy the properties specified by agent theorists. This paper presented an overview of the agents learning used in the simulator teams. Many kinds of agents learning techniques were reported and compared. It also provided open questions for discussing and pointed out some possible answers to verify in near future.展开更多
A multi-agent evacuation model is proposed in this paper to simulate the pedestrian evacuation process in stadium with or without obstacles.The authors give a multi-agent individual decisionmaking framework,in which t...A multi-agent evacuation model is proposed in this paper to simulate the pedestrian evacuation process in stadium with or without obstacles.The authors give a multi-agent individual decisionmaking framework,in which the action direction of each pedestrian(called agent) is affected by the distance of the agent to the exits and the occupant number and density within the view field of the agent.Different from the existing results,the authors divide all the pedestrians in the stadium into four classes:Young male,young female,old male,and old female.In evacuation process,the weighting that affects individual decision-making between each class of agents is different.In the simulation,the authors present the effects of obstacles,crowd distribution and the exit position in evacuation process.Simulation results show that the proposed model can reproduce exactly the real evacuation process in stadium.Therefore,this method might be useful to assess public buildings design.展开更多
This paper investigates a consensus design problem for continuous-time first-order multiagent systems with uniform constant communication delay.Provided that the agent dynamic is unstable and the diagraph is undirecte...This paper investigates a consensus design problem for continuous-time first-order multiagent systems with uniform constant communication delay.Provided that the agent dynamic is unstable and the diagraph is undirected,sufficient conditions are derived to guarantee consensus.The key technique is the adoption of historical input information in the protocol.Especially,when agent's own historical input information is used in the protocol design,the consensus condition is constructed in terms of agent dynamic,communication delay,and the eigenratio of the network topology.Simulation result is presented to validate the effectiveness of the theoretical result.展开更多
To solve the dynamical consensus problem of second-order multi-agent systems with communication delay,delay-dependent compensations are added into the normal asynchronously-coupled consensus algorithm so as to make th...To solve the dynamical consensus problem of second-order multi-agent systems with communication delay,delay-dependent compensations are added into the normal asynchronously-coupled consensus algorithm so as to make the agents achieve a dynamical consensus. Based on frequency-domain analysis, sufficient conditions are gained for second-order multi-agent systems with communication delay under leaderless and leader-following consensus algorithms respectively. Simulation illustrates the correctness of the results.展开更多
This paper studies the consensus problem of multi-agent systems in which all agents are modeled by a general linear system. The authors consider the case where only the relative output feedback between the neighboring...This paper studies the consensus problem of multi-agent systems in which all agents are modeled by a general linear system. The authors consider the case where only the relative output feedback between the neighboring agents can be measured. To solve the consensus problem, the authors first construct a static relative output feedback control under some mild constraints on the system model. Then the authors use an observer based approach to design a dynamic relative output feedback control. If the adjacent graph of the system is undirected and connected or directed with a spanning tree, with the proposed control laws, the consensus can be achieved. The authors note that with the observer based approach, some information exchange between the agents is needed unless the associated adjacent graph is completely connected.展开更多
文摘This paper analyzes progresses and difficulties of subjects on computer network’s management and artificial intelligence, proposes AGIMA, a new model of network intelligent management, which is based on computer supported cooperative work (CSCW) and combining new technologies such as WWW, Java. AGIMA transfers from information distribution centered mode in traditional network management to computing distribution centered mode, providing intelligence capacity for network management by a whole intelligent agent group. The implementation of AGIMA takes much consideration of openess, scalability, proactive adaptability and friendliness of human computer interface. Authors present properties of intelligent agent in details, and conclude that network intelligence should be cooperation between human and computer.
基金Projects(61071096,61003233,61073103)supported by the National Natural Science Foundation of ChinaProjects(20100162110012,20110162110042)supported by the Research Fund for the Doctoral Program of Higher Education of China
文摘Mission planning was thoroughly studied in the areas of multiple intelligent agent systems,such as multiple unmanned air vehicles,and multiple processor systems.However,it still faces challenges due to the system complexity,the execution order constraints,and the dynamic environment uncertainty.To address it,a coordinated dynamic mission planning scheme is proposed utilizing the method of the weighted AND/OR tree and the AOE-Network.In the scheme,the mission is decomposed into a time-constraint weighted AND/OR tree,which is converted into an AOE-Network for mission planning.Then,a dynamic planning algorithm is designed which uses task subcontracting and dynamic re-decomposition to coordinate conflicts.The scheme can reduce the task complexity and its execution time by implementing real-time dynamic re-planning.The simulation proves the effectiveness of this approach.
基金Project supported by the National Natural Science Foundation ofChina (No. 60421002) and the Outstanding Young Research Inves-tigator Fund (No. 60225006), China
文摘This paper presents a pooled-neighbor swarm intelligence approach (PNSIA) to optimal reactive power dispatch and voltage control of power systems. The proposed approach uses more particles’ information to control the mutation operation. The proposed PNSIA algorithm is also extended to handle mixed variables, such as transformer taps and reactive power source in- stallation, using a simple scheme. PNSIA applied for optimal power system reactive power dispatch is evaluated on an IEEE 30-bus power system and a practical 118-bus power system in which the control of bus voltages, tap position of transformers and reactive power sources are involved to minimize the transmission loss of the power system. Simulation results showed that the proposed approach is superior to current methods for finding the optimal solution, in terms of both solution quality and algorithm robustness.
文摘During the development of the intellectual multi-agent investment management information system （designed for the formation of investor＇s investment decisions）, it was established that there is a lack of both necessary comprehensive researches and analysis to invoke more than one decision-making aspect （argument） for the making of investment decision, and recommendations to combine these diverse parameters. It is possible to find a lot of articles and researches in which investment decisions or investment tactics are decided on the ground of either technical or fundamental analysis, or modeling and on the ground of intellectual calculating technique （for example, fuzzy logic, neural net, genetic programming）, whereas the issues of the coordination of different techniques are not decided at all. To fill this niche, the article offers the decision applied in multi-agent investment management information system which allows to provide rationale for investment decision taking into account four aspects （arguments）, i.e., to form the recommendation to purchase/hold/sell a security paper having evaluated the following four aspects （arguments）： （a） fundamental analysis, （b） technical analysis, （c） experts and analysts＇ recommendations and （d） risk assessment. These aspects （arguments） are chosen taking into account the real most commonly occurring process of investor＇s investment decision-making. The article gives the implementation of aspects （arguments） assessment by four corresponding software agents whose decisions are implemented with a help of fuzzy logic. Besides, the article offers the technique of the unification of these aspects （arguments）. The offered intellectual multi-agent investment management information system can be tested on the internet： www.sprendimutechnologijos.lt/webapp （MADSYS project）.
文摘Machine learning has been widely applied to deal with problems in complex environment such as RoboCup, which is assumed as the ideal platform for research on AI and robotic. In RoboCup simulation league, software agents play soccer games on an official soccer server over the network. When constructing these software agents, issues in area of agents learning techniques arise to satisfy the properties specified by agent theorists. This paper presented an overview of the agents learning used in the simulator teams. Many kinds of agents learning techniques were reported and compared. It also provided open questions for discussing and pointed out some possible answers to verify in near future.
基金supported by the National Natural Science Foundation of China under Grant No.61203142the Natural Science Foundation of Hebei Province under Grant No.F2014202206the Project-Sponsored by SRF for ROCS,SEM
文摘A multi-agent evacuation model is proposed in this paper to simulate the pedestrian evacuation process in stadium with or without obstacles.The authors give a multi-agent individual decisionmaking framework,in which the action direction of each pedestrian(called agent) is affected by the distance of the agent to the exits and the occupant number and density within the view field of the agent.Different from the existing results,the authors divide all the pedestrians in the stadium into four classes:Young male,young female,old male,and old female.In evacuation process,the weighting that affects individual decision-making between each class of agents is different.In the simulation,the authors present the effects of obstacles,crowd distribution and the exit position in evacuation process.Simulation results show that the proposed model can reproduce exactly the real evacuation process in stadium.Therefore,this method might be useful to assess public buildings design.
基金supported by the Taishan Scholar Construction Engineering by Shandong Government,the National Natural Science Foundation of China under Grant Nos.61120106011 and 61203029
文摘This paper investigates a consensus design problem for continuous-time first-order multiagent systems with uniform constant communication delay.Provided that the agent dynamic is unstable and the diagraph is undirected,sufficient conditions are derived to guarantee consensus.The key technique is the adoption of historical input information in the protocol.Especially,when agent's own historical input information is used in the protocol design,the consensus condition is constructed in terms of agent dynamic,communication delay,and the eigenratio of the network topology.Simulation result is presented to validate the effectiveness of the theoretical result.
基金Supported by the National Natural Science Foundation of China under Grant Nos.61104092,61134007,and61203147the Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘To solve the dynamical consensus problem of second-order multi-agent systems with communication delay,delay-dependent compensations are added into the normal asynchronously-coupled consensus algorithm so as to make the agents achieve a dynamical consensus. Based on frequency-domain analysis, sufficient conditions are gained for second-order multi-agent systems with communication delay under leaderless and leader-following consensus algorithms respectively. Simulation illustrates the correctness of the results.
基金supported by the Swedish Research Council(VR)the Swedish Foundation for Strategic Research(SSF)+3 种基金the NNSF of China under Grant Nos.61203142 and 61273221the Excellent Young Technology Innovation Foundation of Hebei University of Technology under Grant No.2012005the Ministry of Education Innovation Team Development Plan under Grant No.IRT1232the Natural Science Foundation of Tianjin under Grant No.13JCQNJC03500
文摘This paper studies the consensus problem of multi-agent systems in which all agents are modeled by a general linear system. The authors consider the case where only the relative output feedback between the neighboring agents can be measured. To solve the consensus problem, the authors first construct a static relative output feedback control under some mild constraints on the system model. Then the authors use an observer based approach to design a dynamic relative output feedback control. If the adjacent graph of the system is undirected and connected or directed with a spanning tree, with the proposed control laws, the consensus can be achieved. The authors note that with the observer based approach, some information exchange between the agents is needed unless the associated adjacent graph is completely connected.
