离散系统仿真技术在装备作战仿真中的应用

装备作战仿真系统是一个复杂的交互型混合动态系统,该文描述了一种基于离散事件系统仿真技术,即通过确定离散系统仿真的基本要素：随机离散事件、仿真时钟及其推进方式、未来时间表、随机数发生器等,并增加对连续系统的等技术,来实现装备作战仿真中连续及离散随机事件的仿真。通过试验,仿真效果满足需求,其成果对从事作战模拟开发研究工作者具有一定的借鉴作用。     

需求随机依赖库存环境下的订货仿真优化模型

需求的随机性和依赖库存性是库存问题的特点之一,在需求以泊松分布的形式随机依赖库存的条件下讨论了（Q,T）型库存控制问题。为了评估库存控制策略的平均盈利水平,建立了该库存问题的离散事件系统仿真模型,设计了一种基于仿真的种群重叠、遗传操作非重叠的进化算法,用以优化库存控制策略,类似设计了基于仿真的模拟退火和粒子群优化算法进行比较。通过实例分析了不同参数的变化对模型最优解的影响,灵敏度分析表明需求依赖库存效应越明显时,利润水平越高,最优订货策略越倾向于高库存、短周期和现货销售。仿真实例说明了基于仿真的优化算法的可行性、有效性。     

一类不确定脉冲型混杂系统的保代价控制

针对混合代价函数,研究了参数不确定脉冲型混杂系统的保代价控制问题,给出了混杂状态反馈保代价控制律的设计方法,由此得到的控制律既能使系统闭环鲁棒渐近稳定,又可使系统的闭环混合代价指标在对象参数摄动的范围内不超过确定的上界.本文提出的控制律不仅包含连续时间动态,也包含离散事件动态,而且其离散事件动态行为不需要与被控系统的离散事件动态行为一致,因此设计时不要求被控系统的每个连续时间子系统都具有可控性.仿真结果表明所提设计方法是可行有效的.     

基于仿真的飞行模拟器优化配置研究

随着飞行模拟训练的比重不断加大,模拟器优化配置已成为重点研究问题。以离散事件系统仿真理论为基础,使用统一建模语言（UML）,依据面向对象分析设计的方法,建立了飞行模拟训练系统的仿真模型。通过仿真,得到能够反映系统性能的指标参数。最后运用层次分析法（AHP）对各方案的仿真结果进行综合评价,从而得到模拟器最佳配置方案。     

离线仿真与在线控制相结合的DEDS控制方法

本文在对离散事件动态系统(DEDS)进行仿真研究的基础上,提出了一种基于仿真优化的DEDS控制方法。它首先通过离线仿真优化建立DEDS控制数据库,然后在系统的运行过程中,不断地检测系统的状态,并根据状态值,检索控制数据库,实施控制.以得到对离散事件动态系统进行控制的目的。     

观测永久丢失下随机离散事件系统故障预测的验证算法

针对随机离散事件系统在故障预测时可能出现系统观测永久丢失,导致预测不准确的问题,提出一种观测永久丢失下故障预测验证的算法。首先对观测永久丢失的随机离散事件系统的U-可预测性进行了形式化。其次使用随机预测器构造了一个随机离散事件系统的U-预测器,实现了系统的故障预测。基于U-预测器,提出了随机离散事件系统U-可预测性的充分必要条件及验证算法,并且引入成对的方式,明显地改进了该验证算法的复杂度。仿真结果表明,该验证算法使得观测永久丢失下系统故障预测准确。最后,实例说明观测永久丢失下故障预测验证算法的应用。结果表明,该验证算法相比现有同类验证算法应用范围更广,验证结果更精确。     

仿真优化研究进展

仿真优化研究基于仿真的目标优化问题，具有很强的工程背景，但存在随机性、计算费时和NP—hard等难点。目前，仿真优化已成为国际上系统仿真和运筹学等领域共同关注的热点和前沿课题，尤其是在离散事件动态系统领域。因此在分析仿真优化特点的基础上，对仿真优化算法进行了综述，介绍了仿真优化的若干改进、应用和软件，并指出了仿真优化的进一步研究内容和方向。     

并行离散事件仿真及其应用研究

并行离散事件仿真是一种非常有用的分析求解大规模复杂问题的工具,近年来成为住址界研究热点之一。本文首先指出并行离散事件仿真研究和应用中的不中足,在分析离散事件仿真机制和并行平台引入方式的基础上,结合实际应用现状阐述了并行离散事件仿真机制难以实现和应用的原因,然后针对这种不足提出了一种实现框架,并以通信系统仿真为例说明了所提框架的优越性。     

离散事件系统规范DEVS研究

离散事件系统是一类常见的系统,如何对这类系统进行描述与建模是离散事件系统仿真研究的核心内容。离散事件系统规范DEVS是一种离散事件系统形式化描述方法,它具有层次化和模块化的特点,利用该方法可对复杂的离散事件系统进行建模、设计、分析和仿真。该文详细介绍了DEVS基本模型和耦合模型,给出了DEVS在耦合运算下的封闭性构造证明,并提出了一种具有嵌套层次结构的DEVS耦合模型实现算法,该算法对基于DEVS描述的离散事件系统的仿真实现具有一定参考价值。     

通信网络随机模拟的快速方法研究

引入现代控制科学离散事件动态系统摄动分析思想，提出通信网络随机模拟的快速并行算法。在一台个人计算机上根据被模拟网络在一组参数下的仿真样本轨迹，同时构造一簇不同参数集合的网络系统样本轨迹。     

基于罚函数内点法的泄露积分型回声状态网的参数优化

为了提升泄露积分型回声状态网（Leaky integrator echo state network,Leaky-ESN）的性能,提出利用罚函数内点法优化Leaky-ESN的全局参数,如泄漏率、内部连接权矩阵谱半径、输入比例因子等,这克服了通过反复试验法选取参数值而降低了Leaky-ESN模型的优越性和性能.Leaky-ESN的全局参数必须保障回声状态网满足回声状态特性,因此它们之间存在不等式约束条件.有学者提出利用随机梯度下降法来优化内部连接权矩阵谱半径、输入比例因子、泄露率三个全局参数,一定程度上提高了Leaky-ESN的逼近精度.然而,随机梯度下降法是解决无约束优化问题的基本算法,在利用随机梯度下降法优化参数时,没有考虑参数必须满足回声特性的约束条件（不等式约束条件）,致使得到的参数值不是最优解.由于罚函数内点法可以求解具有不等式约束的最优化问题,应用范围广,收敛速度较快,具有很强的全局寻优能力.因此,本文提出利用罚函数内点法优化Leaky-ESN的全局参数,并以时间序列预测为例,检验优化后的Leaky-ESN的预测性能,仿真结果表明了本文提出方法的有效性.     

Adaptive simulation budget allocation in Simulation assisted Differential Evolution algorithm

Recently, the literature on simulation assisted optimization for solving stochastic optimization problems has been considerably growing. In the optimization context, the population based meta-heuristics algorithms, such as, Differential Evolutionary (DE), has shown tremendous success in solving continuous optimization problems. While in the simulation context, Monte-Carlo Simulation for sample average approximation is one of the successful approaches in handling the stochastic parameters of such problems. However, the intertwined computational burden, when combining these two approaches is amplified, and that encourages new research in this topic. In this problem, the challenge is to maintain high quality stochastic solutions by minimizing the computational cost to a reasonable level. To deal with this challenge, we propose a novel Adaptive Segment Based Scheme (ASBS) algorithm, for allocating the MCS budget in a Simulation assisted Differential Evolution (Sim-DE) Algorithm. This allows the algorithm to adaptively control the simulation budget based on a performance measure. The performance of the proposed ASBS algorithm is compared with other simulation budget allocation techniques while using the same base algorithm. The experimental study has been conducted by solving a modified set of IEEE-CEC’2006 test problems and a wind-thermal power systems application. The experimental results reveal that the ASBS algorithm is able to substantially reduce the simulation budget, with an insignificant effect in solution quality.     

An operator allocation optimization model for balancing control of the hybrid assembly lines using Pareto utility discrete differential evolution algorithm

This paper investigates the operator allocation problems (OAP) with jobs sharing and operator revisiting for balance control of a complicated hybrid assembly line which appears in the apparel sewing manufacturing system. Multiple objectives and constraints for the problem are formulated. The utility function is employed to deal with the difficulty of combining several conflicting and incommensurable objectives into one overall measure. An optimization model combining the Pareto utility discrete differential evolution (PUDDE) algorithm and the embedded discrete event simulation (DES) model is proposed to solve the OAPs. The PUDDE algorithm is an improved discrete differential evolution approach used with the Pareto utility selection strategy, which extends the real-value differential evolution to handle the discrete-value vector by introducing two modified operators, namely the subtraction and addition operators. During the optimization process, the embedded DES model is used to evaluate the performance objectives by analyzing the dynamic behaviors of the hybrid assembly lines, which tackles the problem of having no closed-form mathematical expressions for the evaluation of performance objectives owing to the existence of jobs sharing and operator revisiting. Extensive experiments are conducted to validate the proposed optimization model. The experimental results demonstrate that the proposed PUDDE-based optimization model can effectively solve the OAPs for the hybrid assembly lines with the consideration of jobs sharing and operator revisiting. It was also found that the proposed PUDDE algorithm evidently outperforms the general differential evolution algorithm. Compared with the collected industrial results, the solution generated by the proposed optimization model has much better performance objectives for the hybrid assembly lines.     

无线多媒体通信网适应带宽配置在线优化算法

基于强化学习的方法,提出一种无线多媒体通信网适应带宽配置在线优化算法,在满足多类业务不同QoS(quality of service)要求的同时,提高网络资源的利用率.建立事件驱动的随机切换分析模型,将无线多媒体通信网中的适应带宽配置问题转化为带约束的连续时间Markov决策问题.利用此模型的动态结构特性,结合在线学习估计梯度与随机逼近改进策略,提出适应带宽配置在线优化算法.该算法不依赖于系统参数,如呼叫到达率、呼叫持续时间等,自适应性强,计算量小,能够收敛到全局最优,适用于复杂应用环境中无线多媒体通信网适应带宽配置的在线优化.仿真实验结果验证了算法的有效性.     

Almost Asymptotic Regulation of Markovian Jumping Linear Systems in Discrete Time

This paper considers the problems of almost asymptotic output regulation for discrete‐time Markovian jumping linear systems. Based on a stochastic Lyapunov‐Krasovskii functional framework, sufficient conditions for the extension of the regulation scheme to such stochastic systems are obtained via state feedback and via error feedback. Relying on a characterization of the feedback controllers, the almost asymptotic regulation is accomplished. The problem of guaranteeing stochastic stability and almost asymptotic tracking is achieved by solving linear matrix inequalities subject to a set of linear equality constraints. In order to ensure relaxed solutions of the regulation equations, a semi‐definite optimization approach via disciplined convex programming is outlined. Simulation results also are given to illustrate the effectiveness of the proposed design approach.     

Reducing Two-Stage Probabilistic Optimization Problems with Discrete Distribution of Random Data to Mixed-Integer Programming Problems*

We consider two-stage stochastic programming models with quantile criterion as well as models with a probabilistic constraint on the random values of the objective function of the second stage. These models allow us to formalize the requirements for the reliability and safety of the system being optimized and to optimize system’s performance under extreme conditions. We propose a method of equivalent transformation of these models under discrete distribution of random parameters to mixed-integer programming problems. The number of additional integer (Boolean) variables in these problems equals to the number of possible values of the vector of random parameters. The obtained mixed optimization problems can be solved by powerful standard discrete optimization software. To illustrate the approach, the results of numerical experiment for the problem of small dimension are presented.     

Discrete Event System Framework for Fault Diagnosis with Measurement Inconsistency: Case Study of Rogue DHCP Attack

Fault detection and diagnosis (FDD) facilitates reliable operation of systems. Various approaches have been proposed for FDD like Analytical redundancy (AR), Principal component analysis (PCA), Discrete event system (DES) model etc., in the literature. Performance of FDD schemes greatly depends on accuracy of the sensors which measure the system parameters. Due to various reasons like faults, communication errors etc., sensors may occasionally miss or report erroneous values of some system parameters to FDD engine, resulting in measurement inconsistency of these parameters. Schemes like AR, PCA etc., have mechanisms to handle measurement inconsistency, however, they are computationally heavy. DES based FDD techniques are widely used because of computational simplicity, but they cannot handle measurement inconsistency efficiently. Existing DES based schemes do not use Measurement inconsistent (MI) parameters for FDD. These parameters are not permanently unmeasurable or erroneous, so ignoring them may lead to weak diagnosis. To address this issue, we propose a Measurement inconsistent discrete event system (MIDES) framework, which uses MI parameters for FDD at the instances they are measured by the sensors. Otherwise, when they are unmeasurable or erroneously reported, the MIDES invokes an estimator diagnoser that predicts the state(s) the system is expected to be in, using the subsequent parameters measured by the other sensors. The efficacy of the proposed method is illustrated using a pumpvalve system. In addition, an MIDES based intrusion detection system has been developed for detection of rogue dynamic host configuration protocol (DHCP) server attack by mapping the attack to a fault in the DES framework.      

仿真优化:理论与应用综述

对于现实中的复杂系统, 仿真优化是一种非常强大的分析和优化工具. 本文对仿真优化领域的相关理论与方法进行了介绍与回顾. 根据系统中决策变量的性质的不同(连续或者离散变量), 我们对仿真优化问题进行了分类. 而且我们对仿真优化领域中的重要技术进行了详细地讨论, 包括它们的原理、使用方法、优势和劣势以及应用等. 关于仿真优化领域未来的研究方向, 我们也进行了相关论述.     

用于测试用例最小化问题的改进PSO算法

针对回归测试中测试用例最小化问题,将粒子群优化算法和随机算法相结合,提出一种二维随机粒子群优化算法,用来解决测试用例最小化的问题。该算法采用二维适应值评价函数,一维是覆盖度,另一维是冗余度。利用各个测试用例的覆盖率为概率随机产生下一代个体位置。实验结果表明该算法性能优良且具有较好的稳定性。     

动态电源管理的随机切换模型与在线优化

考虑系统参数未知情况下的动态电源管理问题,提出一种基于强化学习的在线策略优化算法. 通过建立事件驱动的随机切换分析模型,将动态电源管理问题转化为带约束的Markov 决策过程的策略优化问题. 利用此模型的动态结构特性,结合在线学习估计梯度与随机逼近改进策略,提出动态电源管理策略的在线优化算法．随机切换模型对电源管理系统的动态特性描述精确,在线优化算法自适应性强,运算量小,精度高,具有较高的实际应用价值．