A quantum particle swarm optimization driven urban traffic light scheduling model

Urban traffic congestion becomes a severe problem for many cities all around the world. How to alleviate traffic congestions in real cities is a challenging problem. Benefited from concise and efficient evolution rules, the Biham, Middleton and Levine (BML) model has a great potential to provide favorable results in the dynamic and uncertain traffic flows within an urban network. In this paper, an enhanced BML model (EBML) is proposed to effectively simulate the urban traffic where the timing scheduling optimization algorithm (TSO) based on the quantum particle swarm optimization is creatively introduced to optimize the timing scheduling of traffic light. The main contributions include that: (1) The actual urban road network with different two-way multi-lane roads is firstly mapped into the theoretical lattice space of BML. And the corresponding updating rules of each lattice site are proposed to control vehicle dynamics; (2) compared with BML, a much deeper insight into the phase transition and traffic congestions is provided in EBML. And the interference among different road capacities on forming traffic congestions is elaborated; (3) based on the scheduling simulation of EBML, TSO optimizes the timing scheduling of traffic lights to alleviate traffic congestions. Extensive comparative experiments reveal that TSO can achieve excellent optimization performances in real cases.

     

柔性制造系统的改进粒子群无死锁调度算法

基于柔性制造系统的Petri网模型,以制造期最小为优化目标,将死锁避免策略嵌入粒子群算法中,提出一种无死锁改进粒子群调度算法.该算法将粒子与工件的工序序列相对应,以位置数值的大小表示对应工件工序在执行顺序中的优先级.采用一步向前看的死锁避免策略方法对序列的可行性进行验证,提出一种跳出局部极值的策略.实例仿真结果表明了粒子群调度算法的可行性和有效性,以及改进粒子群调度算法的优越性.     

基于自适应参数与混沌搜索的PSO算法求解柔性作业车间调度问题

针对传统粒子群优化(PSO)算法在求解柔性作业车间调度问题中的不足,提出了基于自适应参数与混沌搜索的粒子群优化算法。对粒子群算法中的惯性系数等参数采用基于迭代搜索而自适应调整的方式,使粒子在初期以较大惯性进行大范围搜索,后期逐渐减小惯性而转入精细搜索。这种方法改变了传统粒子群算法在求解过程中的盲目随机与求解精度不高的问题;同时,通过在局部搜索过程中引入混沌技术,扩大对最优解的寻找范围,以此避免算法陷入局部最优,有效提高算法的全局寻优能力。实验结果表明,基于自适应参数与混沌搜索的粒子群优化算法在求解柔性作业车间调度问题(FJSP)时能够获得更优粒子适应度平均值及更好的优化目标。所提算法对求解柔性作业车间调度问题可行,有效。     

粒子置换的双种群综合学习PSO算法

针对粒子群算法(PSO)种群多样性低和易于陷入局部最优等问题,提出一种粒子置换的双种群综合学习PSO算法(PP-CLPSO)。根据PSO算法的收敛特性和Logistic映射的混沌思想,设计并行进化的PSO种群和混沌化种群,结合粒子编号机制,形成双种群系统中粒子的同号结构和同位结构,其中粒子的惯性权重根据适应度值自适应调节;当搜索过程陷入局部最优时,PSO种群同位结构下适应度值较差的粒子,根据与混沌化种群间的同号结构执行粒子置换操作,实现了双种群系统资源的合理调度,增加了种群的多样性;进而综合双向搜索的同位粒子学习策略和线性递减搜索步长的局部学习策略,进行全局探勘和局部搜索,提高了算法的求解精度。实验选取9个基准测试函数,同时与4个改进的粒子群算法和4个群智能算法进行对比验证,实验结果表明,PP-CLPSO算法在求解精度和收敛速度等方面具备较好的综合性能。     

人工鱼群—粒子群混合算法优化进港航班排序

针对空中交通管理中的进港航班排序问题, 提出了人工鱼群—粒子群混合算法(AFPSO)这一航班排序算法来优化进港航班排序, 使时段内进港航班队列总延误时间最少。算法结合了基本人工鱼群算法(AFSA)和基本粒子群算法(PSO)各自的优点, 先以AFSA在全局寻找满意的解域, 再以PSO算法在这些解域中进行快速的局部搜索获得精确解, 最终使算法提高收敛速度和搜索精度。仿真结果表明, 在单跑道和双跑道情况下, AFPSO算法使得航班队列总延误时间比FCFS调度方法减少了20. 9%和34. 4%, 比基本AFSA减少了3. 2%和3. 5%。算法得到的满意解能够为自动化空中交通管理提供实时支持。     

An improved particle swarm optimization algorithm for flowshop scheduling problem

The flowshop scheduling problem has been widely studied and many techniques have been applied to it, but few algorithms based on particle swarm optimization (PSO) have been proposed to solve it. In this paper, an improved PSO algorithm (IPSO) based on the “alldifferent” constraint is proposed to solve the flow shop scheduling problem with the objective of minimizing makespan. It combines the particle swarm optimization algorithm with genetic operators together effectively. When a particle is going to stagnate, the mutation operator is used to search its neighborhood. The proposed algorithm is tested on different scale benchmarks and compared with the recently proposed efficient algorithms. The results show that the proposed IPSO algorithm is more effective and better than the other compared algorithms. It can be used to solve large scale flow shop scheduling problem effectively.     

基于粒子群优化的多用户MIMO下行链路调度算法

将多用户MIMO下行链路调度问题描述为一优化问题,并引入粒子群优化(particle swarm optimization,PSO)算法进行求解.针对容量和复杂度有不同要求的应用场合,给出了两类采用不同目标函数PSO调度算法:基于容量PSO(C-PSO)调度算法和基于特征值下界PSO(LBE-PSO)调度算法.C-PSO算法目标是获得接近最优容量的性能;而LBE-PSO算法旨在有效降低算法复杂度的同时尽可能获得高的容量增益.进一步,从粒子和速度两方面对PSO算法的收敛性进行分析并得出收敛条件,然后通过不同参数值的实例对其进行验证.仿真结果表明,C-PSO算法能够以较低的复杂度获得接近穷搜索算法的容量,而LBE-PSO调度算法则提供了一种能够在容量和复杂度之间很好折中的调度方案.     

一种适用于多任务多资源移动边缘计算环境下的改进粒子群算力卸载算法

为了研究移动设备在多资源复杂环境下的能量消耗问题,提出一种针对移动边缘设备计算卸载的改进粒子群算法。首先基于多环境的移动设备能耗提出一种移动设备能量消耗的计算模型;其次针对计算资源分配问题设计一种可以用于衡量分配方案优劣的适应度算法;最后提出一种改进的粒子群算法,用于求解进一步降低移动边缘设备能耗分配方案的最优解。通过使用模拟仿真软件对多种卸载策略下移动设备能耗、系统响应时间等关键指标对比表明,本文算法在满足用户响应时间的前提下,在求解降低移动设备能耗调度分配方案最优解的过程中具有更优的表现。     

Cellular particle swarm optimization

This paper proposes a cellular particle swarm optimization (CPSO), hybridizing cellular automata (CA) and particle swarm optimization (PSO) for function optimization. In the proposed CPSO, a mechanism of CA is integrated in the velocity update to modify the trajectories of particles to avoid being trapped in the local optimum. With two different ways of integration of CA and PSO, two versions of CPSO, i.e. CPSO-inner and CPSO-outer, have been discussed. For the former, we devised three typical lattice structures of CA used as neighborhood, enabling particles to interact inside the swarm; and for the latter, a novel CA strategy based on “smart-cell” is designed, and particles employ the information from outside the swarm. Theoretical studies are made to analyze the convergence of CPSO, and numerical experiments are conducted to compare the proposed algorithm with different variants of PSO. According to the experimental results, the proposed method performs better than other variants of PSO on benchmark test functions.     

A novel intelligent particle swarm optimization algorithm for solving cell formation problem

The formation of manufacturing cells forms the backbone of designing a cellular manufacturing system. In this paper, we present a novel intelligent particle swarm optimization algorithm for the cell formation problem. The proposed solution method benefits from the advantages of particle swarm optimization algorithm (PSO) and self-organization map neural networks by combining artificial individual intelligence and swarm intelligence. Numerical examples demonstrate that the proposed intelligent particle swarm optimization algorithm significantly outperforms PSO and yields better solutions than the best solutions existed in the literature of cell formation. The application of the proposed approach is examined in a case problem where real data is utilized for cell reconfiguration of an actual company involved in agricultural manufacturing sector.

     

基于双向并行灾变粒子群算法的区域交通控制

针对基本粒子群优化算法易陷入局部极值点、搜索精度低等缺点,引入灾变模型,采用双向并行策略,提出一种双向并行灾变粒子群优化算法（BPC-PSO）,并将其成功应用于城市区域交通控制信号参数配时优化。仿真结果表明：双向并行灾变粒子群算法相对于基本粒子群算法大大提高了寻找全局最优解的能力,使车辆平均延误和平均停车率都比基本粒子群算法有明显地降低。     

Automatically extracting T–S fuzzy models using cooperative random learning particle swarm optimization

This paper proposes a methodology for automatically extracting T–S fuzzy models from data using particle swarm optimization (PSO). In the proposed method, the structures and parameters of the fuzzy models are encoded into a particle and evolve together so that the optimal structure and parameters can be achieved simultaneously. An improved version of the original PSO algorithm, the cooperative random learning particle swarm optimization (CRPSO), is put forward to enhance the performance of PSO. CRPSO employs several sub-swarms to search the space and the useful information is exchanged among them during the iteration process. Simulation results indicate that CRPSO outperforms the standard PSO algorithm, genetic algorithm (GA) and differential evolution (DE) on the functions optimization and benchmark modeling problems. Moreover, the proposed CRPSO-based method can extract accurate T–S fuzzy model with appropriate number of rules.     

析因-粒子群算法及其在海上运动目标搜寻中的应用

针对粒子群算法在处理多峰复杂函数优化问题时容易陷入局部极值,难以满足海上运动目标搜寻问题的需要,提出一种基于析因思想的改进粒子群算法.所提算法结合种群智能思想与析因实验设计思想,利用随机化及区组化策略,设计参数在不同水平的组合,并得到相应的适应度值,获取各个参数的适应度曲线;分析各参数变化对适应度值的影响以及参数间的交互作用,基于此获取解空间形态;针对不同参数采用不同策略,利用种群迭代寻找全局最优解,使种群针对交互作用明显的参数侧重于全局搜索,针对交互作用不明显的参数侧重于局部搜索;最后将所提算法应用于海上运动目标搜寻问题,实验结果表明,相较其他几种对比算法,所提出的算法能够有效制定更优的搜寻计划.     

基于烟花算法的云计算多目标任务调度

为了更好地满足云计算中用户的服务质量(Quality of Service, QoS)需求,合理利用云数据中心的资源,以任务的执行时间和虚拟机的负载均衡作为优化的目标对象,提出了一种基于烟花算法(Fireworks Algorithm, FWA)的多目标优化调度模型。烟花算法是一种启发式算法,利用爆炸算子、高斯变异和选择策略能较快地寻找到全局最优解。通过在Cloudsim上与粒子群优化算法(PSO)和遗传算法(GA)进行有效性和执行时间上的对比,结果表明烟花算法在不同实验次数下可持续得到最优适应度值,而且在种群规模不断扩大时,烟花算法的执行时间没有陡然增加,明显优于PSO算法和GA算法。     

基于质心和自适应指数惯性权重改进的粒子群算法

针对粒子群优化(PSO)算法易出现早熟收敛及寻优精度低等问题,为提高粒子群优化算法寻优能力,提出了一种基于质心和自适应指数惯性权重改进的粒子群优化算法(CEPSO)。首先,使用各粒子的适应度计算权重系数;然后,分别使用各粒子当前位置和迄今为止最优位置构造了加权的种群质心和最优个体质心,使用平均粒距来度量群体状态,并依据群体状态设计了分段指数惯性权重;最后,结合使用分段指数惯性权重和双质心调整了粒子速度更新公式。仿真结果表明,CEPSO能增强寻优能力,并具有较强的稳定性。     

差分进化粒子群算法求解发电资源调度问题

为了有效地解决水火电力系统资源短期优化调度问题,提出了一种基于差分进化粒子群的调度算法。设计了水火电力系统资源调度问题的数学模型,给出了差分进化粒子群优化算法的框架,通过PSO种群和DE种群之间的信息交流机制以寻求全局最优位置,从而使算法具有动态自适应性,能够较容易地跳出局部最优。实验结果表明,该算法能有效解决水火发电资源调度问题,具有较好的应用价值。     

基于模拟退火算法的粒子群优化算法在容器调度中的应用

随着互联网产业的发展,虚拟机创建速度慢、不易扩展、灵活性不足等缺点越来越凸显,容器技术的出现为这些问题提出了一种新的解决思路;而现有的调度算法仅考虑容器云集群中工作节点的内存、CPU等物理资源,没有考虑对容器云调度后的镜像分发过程有明显影响的网络负载率,导致容器调度任务等待时间过长,造成数据中心的资源浪费;鉴于粒子群优化算法在局部开采能力和全局探测方面有较强的优势,提出了一种基于模拟退火算法的粒子群优化算法(SA-PSO,simulated annealing particle swarm optimization algorithm)的容器调度算法,通过使用模拟退火优化粒子群算法使其在算法初期跳出局部最优情况,提升算法性能;在Kubernetes平台实验过程中,SA-PSO调度算法相比Kubernetes的BalancedQosPriority算法,提升了整体节点资源利用率,显著减少任务最少等待时间;同时与标准PSO算法以及动态惯性权重PSO算法进行对比,不仅收敛能力有显著提升,并且相较标准PSO算法全局最优节点命中率提升近60％.     

一种免疫粒子群优化算法及在小波神经网络学习中的应用

粒子群优化算法是一类简单有效的随机全局优化技术。受生物体免疫系统抗体多样性保持机制的启发,将抗体多样性保持机制引入到粒子群优化算法中,并给出了一种免疫粒子群优化算法。该算法在保留高适应度粒子的同时,确保了粒子的多样性,从而改善了粒子群优化算法摆脱局部极值点的能力,提高了算法的收敛速度和精度。该算法应用于函数优化和小波神经网络学习的计算机仿真,结果表明该算法有良好的收敛性能。     

模拟退火PSO的神经网络的网络流量预测模型

为解决网络流量时间序列的预测问题,针对传统BP神经网络的网络流量时间序列预测模型容易陷入局部极小值的不足,提出一种基于模拟退火的微粒群算法训练神经网络的网络流量时间序列预测模型.将模拟退火算法和基本粒子微粒群算法相结合,设计出一种基于模拟退火的微粒群算法.利用基于模拟退火微粒群算法优化BP神经网络的权值和阀值,对实际采集的网络流量时间序列进行建模.实验结果表明,基于模拟退火的微粒群算法训练的神经网络具有较高的预测效果,相对于传统的神经网络模型具有更高的预测精度和良好的自适应性.     

Novel scheduling strategy for downlink multiuser MIMO system: Particle swarm optimization

In this paper the scheduling problem in downlink multiuser MIMO system is described as an optimization problem and particle swarm optimization (PSO) algorithm is introduced to address such problem. Two PSO scheduling methods with different objective functions applicable to different requirements on capacity and complexity are investigated. One is the capacity based PSO(C-PSO) scheduling method aiming at achieving the near optimal capacity; and the other is the lower bound of eigenvalue based PSO (LBE-PSO) scheduling method with the purpose of reducing computational complexity and at the same time achieving as large as possible capacity gain. Furthermore, convergence analysis of PSO from both the particle and the velocity aspects is also presented to derive the convergent condition, which is validated by several examples of different parameter values. Simulation results reveal that the C-PSO can obtain nearly the same capacity as the exhaustive search method with lower complexity, while the LBE-PSO provides a viable approach by striking a better tradeoff between capacity and computational complexity.