基于前景理论的CGF Agent决策建模研究

前景理论(Prospect Theory,PT)描述了个体在不确定条件下的决策规律,较好地刻画了决策者的风险偏好。分析表明,PT在作战决策建模中具有一定的适用性和可行性。提出了一种基于PT的计算机生成兵力(Computer Generated Forces,CGF)Agent决策建模方法,给出了CGF Agent的建模框架,对CGF Agent决策过程中方案选择的具体步骤和算法进行了详细阐述。实验表明,所提出的方法在一定程度上提高了CGF Agent决策行为的真实性,证明了所提出方法的有效性。     

Information security: Designing a stochastic‐network for throughput and reliability

Todas information and communication network requires a design that is secure to tampering. Traditional performance measures of reliability and throughput must be supplemented with measures of security. Recognition of an adversary who can inflict damage leads toward a game‐theoretic model. Through such a formulation, guidelines for network designs and improvements are derived. We opt for a design that is most robust to withstand both natural degradation and adversarial attacks. Extensive computational experience with such a model suggests that a Nash‐equilibrium design exists that can withstand the worst possible damage. Most important, the equilibrium is value‐free in that it is stable irrespective of the unit costs associated with reliability vs. capacity improvement and how one wishes to trade between throughput and reliability. This finding helps to pinpoint the most critical components in network design. From a policy standpoint, the model also allows the monetary value of information‐security to be imputed. © 2009 Wiley Periodicals, Inc. Naval Research Logistics, 2009     

Oligopolistic contracting: Channel coordination under competition

We study contracts between a single retailer and multiple suppliers of two substitutable products, where suppliers have fixed capacities and present the retailer cost contracts for their supplies. After observing the contracts, the retailer decides how much capacity to purchase from each supplier, to maximize profits from the purchased capacity from the suppliers plus his possessed inventory (endowment). This is modeled as a noncooperative, nonzero‐sum game, where suppliers, or principals, move simultaneously as leaders and the retailer, the common agent, is the sole follower. We are interested in the form of the contracts in equilibrium, their effect on the total supply chain profit, and how the profit is split between the suppliers and the retailer. Under mild assumptions, we characterize the set of all equilibrium contracts and discuss all‐unit and marginal‐unit quantity discounts as special cases. We also show that the supply chain is coordinated in equilibrium with a unique profit split between the retailer and the suppliers. Each supplier's profit is equal to the marginal contribution of her capacity to supply chain profits in equilibrium. The retailer's profit is equal to the total revenue collected from the market minus the payments to the suppliers and the associated sales costs.     

舰炮目标毁伤判定与毁伤效果仿真研究

舰炮对目标毁伤的判定与毁伤效果仿真是舰载作战系统仿真训练的重要组成部分,作为连接舰炮射击与目标毁伤的中间环节,它实现了对目标毁伤状态的判定,以及目标毁伤效果的仿真反馈,从而仿真训练系统中其他仿真成员,以及各型侦察模拟设备可以发现并判定目标毁伤状态,为作战指挥人员进行作战指挥决策提供目标毁伤信息,为参训职手提供更为实战化的仿真训练环境。在简述舰载作战系统仿真训练系统的基础上,重点探讨了基于毁伤概率表和弹目交会的舰炮毁伤判定方法,并简述了目标毁伤效果仿真方法。     

基于效果的装备保障合同商选择方法

基于效果的合同商装备保障是将基于效果的维修理念应用于合同商装备保障领域提出的一种装备保障策略,更加关注装备的作战效能,同时对合同商提出了更高要求,因此,选择恰当的合同商对于实现预期结果显得更为重要。而合同商选择是一个多准则决策问题,很大程度上依赖于决策者和决策条件状态的不确定性和模糊性。构建了一个基于效果的合同商选择系统流程,并提出了基于相似度的模糊TOPSIS法,简化了计算流程,最后通过一个具体案例来验证该方法的有效性。     

合成分队双层主从决策模型研究

针对合成分队不同指挥层级之间的决策交互优化问题,提出了基于主从决策的双层武器目标分配模型。该模型能够体现上下指挥层级之间交互式决策协调优化的特点:上层目标为主攻方向我方遭受威胁最小,下层目标为对敌打击最大。结合合成分队作战决策的特点和要求,提出了一种求解该模型的改进型粒子群优化算法。仿真结果表明,该模型合理有效,改进的求解算法能够获得满意解。     

基于Epsilon-Nash策略的动态武器-目标分配方法

在大型任务规划软件的作战单元任务分配中,搜索零和博弈问题的纳什均衡点是求解任务分配的一种有效的方法。然而,纳什均衡点在决策中并不一定总是存在且唯一,这造成了纳什均衡策略在实际使用时具有较大的局限。通过采用Epsilon-Nash策略克服这种局限,并将其应用于自主空战任务规划系统中,通过仿真实验,证实Epsilon-Nash策略具有近似于纳什策略的效果。     

基于系统动力学的协同决策模型性能分析

为探索信息化作战中指挥控制关键因素,提出改进作战指挥体制的对策措施,采用系统动力学理论,对协同决策的结构、参与者和信息反馈关系等关键因素进行了分析,在此基础上构建了基于系统动力学的协同决策模型并进行了模拟仿真。结果表明,增加指挥控制机构之间的信息共享可以有效提升协同决策的效率,为建立协同决策指挥控制体制提供了借鉴意义。     

Dynamic server assignment policies for assembly‐type queues with flexible servers

We seek dynamic server assignment policies in finite‐capacity queueing systems with flexible and collaborative servers, which involve an assembly and/or a disassembly operation. The objective is to maximize the steady‐state throughput. We completely characterize the optimal policy for a Markovian system with two servers, two feeder stations, and instantaneous assembly and disassembly operations. This optimal policy allocates one server per station unless one of the stations is blocked, in which case both servers work at the unblocked station. For Markovian systems with three stations and instantaneous assembly and/or disassembly operations, we consider similar policies that move a server away from his/her “primary” station only when that station is blocked or starving. We determine the optimal assignment of each server whose primary station is blocked or starving in systems with three stations and zero buffers, by formulating the problem as a Markov decision process. Using this optimal assignment, we develop heuristic policies for systems with three or more stations and positive buffers, and show by means of a numerical study that these policies provide near‐optimal throughput. Furthermore, our numerical study shows that these policies developed for assembly‐type systems also work well in tandem systems. © 2008 Wiley Periodicals, Inc. Naval Research Logistics, 2008     

信息化战场中基于智能体聚类的信息处理

研究了信息战条件下信息的处理问题,通过分析信息化战场条件下战场环境和人员的特点,提出了一种基于智能体聚类的信息处理方法,通过该方法来实现战场信息的通信、传输、交换从而协助指挥员决策。该方法的特点是可以根据战场的环境进行聚类,降低了信息的复杂度从而保证及时有效地传递消息。该方法通过智能体平台实现,具有一定智能性并减少了指挥员的决策难度,对指挥自动化而言是一个很好的实例。