his paper examines planning management problems in a Multiagentbased Distributed Open Computing Environment Model (MDOCEM). First the meaning of planning management in MDOCEM is introduced, and then a formal method to...his paper examines planning management problems in a Multiagentbased Distributed Open Computing Environment Model (MDOCEM). First the meaning of planning management in MDOCEM is introduced, and then a formal method to describe the associated task partition problems is presented, and a heuristic algorithm which gives an approximate optimum solution is given. Finally the task coordination and integration of execution results are discussed.展开更多
提出了一种基于M u lti-A gen t的虚拟维修训练系统(VM TS)结构框架,整个系统分别由主控A gen t、仿真A gen t、和接口A gen t3个具有交互作用的A gen t组成,从而将虚拟维修训练系统的开发转化为一个多A gen t系统的设计与开发。基于多A...提出了一种基于M u lti-A gen t的虚拟维修训练系统(VM TS)结构框架,整个系统分别由主控A gen t、仿真A gen t、和接口A gen t3个具有交互作用的A gen t组成,从而将虚拟维修训练系统的开发转化为一个多A gen t系统的设计与开发。基于多A gen t的框架结构可实现受训者的智能模型及虚拟训练场景中虚拟物体的行为模型,从而可以提高VM TS的健壮性和可重用性。基于A gen t的概念模型实现了A gen t之间的交互和协作,并介绍了主控A gen t和仿真A gen t的具体实现方法。展开更多
车间调度作为车间制造系统的重要组成部分,影响着整个车间制造系统的敏捷性和智能性.但是,由于资源和工艺约束的并存,使得车间调度成为一类NP-hard问题.基于静态的智能算法与动态的多Agent思想,提出了一种结合通用部分全局规划(generali...车间调度作为车间制造系统的重要组成部分,影响着整个车间制造系统的敏捷性和智能性.但是,由于资源和工艺约束的并存,使得车间调度成为一类NP-hard问题.基于静态的智能算法与动态的多Agent思想,提出了一种结合通用部分全局规划(generalized partial global planning,GPGP)机制与多种智能算法的多Agent车间调度模型,设计了从"初始宏观调度"到"微观再调度"的大规模复杂问题的调度步骤,并构建了一个柔性强且Agent可自我动态调度的仿真系统.同时,从理论上总结了GPGP基本协同机制的策略,实现了二级多目标优化调度.最后使用DECAF仿真Agent软件模拟了车间调度的GPGP协同机制,并与CNP,NONE机制进行了比较.结果表明,所提出的模型不仅提高了调度的效率,而且降低了资源的损耗.展开更多
Traditionally, heuristic re-planning algorithms are used to tackle the problem of dynamic task planning for multiple satellites. However, the traditional heuristic strategies depend on the concrete tasks, which often ...Traditionally, heuristic re-planning algorithms are used to tackle the problem of dynamic task planning for multiple satellites. However, the traditional heuristic strategies depend on the concrete tasks, which often affect the result’s optimality. Noticing that the historical information of cooperative task planning will impact the latter planning results, we propose a hybrid learning algorithm for dynamic multi-satellite task planning, which is based on the multi-agent reinforcement learning of policy iteration and the transfer learning. The reinforcement learning strategy of each satellite is described with neural networks. The policy neural network individuals with the best topological structure and weights are found by applying co-evolutionary search iteratively. To avoid the failure of the historical learning caused by the randomly occurring observation requests, a novel approach is proposed to balance the quality and efficiency of the task planning, which converts the historical learning strategy to the current initial learning strategy by applying the transfer learning algorithm. The simulations and analysis show the feasibility and adaptability of the proposed approach especially for the situation with randomly occurring observation requests.展开更多
文摘his paper examines planning management problems in a Multiagentbased Distributed Open Computing Environment Model (MDOCEM). First the meaning of planning management in MDOCEM is introduced, and then a formal method to describe the associated task partition problems is presented, and a heuristic algorithm which gives an approximate optimum solution is given. Finally the task coordination and integration of execution results are discussed.
文摘提出了一种基于M u lti-A gen t的虚拟维修训练系统(VM TS)结构框架,整个系统分别由主控A gen t、仿真A gen t、和接口A gen t3个具有交互作用的A gen t组成,从而将虚拟维修训练系统的开发转化为一个多A gen t系统的设计与开发。基于多A gen t的框架结构可实现受训者的智能模型及虚拟训练场景中虚拟物体的行为模型,从而可以提高VM TS的健壮性和可重用性。基于A gen t的概念模型实现了A gen t之间的交互和协作,并介绍了主控A gen t和仿真A gen t的具体实现方法。
文摘车间调度作为车间制造系统的重要组成部分,影响着整个车间制造系统的敏捷性和智能性.但是,由于资源和工艺约束的并存,使得车间调度成为一类NP-hard问题.基于静态的智能算法与动态的多Agent思想,提出了一种结合通用部分全局规划(generalized partial global planning,GPGP)机制与多种智能算法的多Agent车间调度模型,设计了从"初始宏观调度"到"微观再调度"的大规模复杂问题的调度步骤,并构建了一个柔性强且Agent可自我动态调度的仿真系统.同时,从理论上总结了GPGP基本协同机制的策略,实现了二级多目标优化调度.最后使用DECAF仿真Agent软件模拟了车间调度的GPGP协同机制,并与CNP,NONE机制进行了比较.结果表明,所提出的模型不仅提高了调度的效率,而且降低了资源的损耗.
文摘Traditionally, heuristic re-planning algorithms are used to tackle the problem of dynamic task planning for multiple satellites. However, the traditional heuristic strategies depend on the concrete tasks, which often affect the result’s optimality. Noticing that the historical information of cooperative task planning will impact the latter planning results, we propose a hybrid learning algorithm for dynamic multi-satellite task planning, which is based on the multi-agent reinforcement learning of policy iteration and the transfer learning. The reinforcement learning strategy of each satellite is described with neural networks. The policy neural network individuals with the best topological structure and weights are found by applying co-evolutionary search iteratively. To avoid the failure of the historical learning caused by the randomly occurring observation requests, a novel approach is proposed to balance the quality and efficiency of the task planning, which converts the historical learning strategy to the current initial learning strategy by applying the transfer learning algorithm. The simulations and analysis show the feasibility and adaptability of the proposed approach especially for the situation with randomly occurring observation requests.
