一种求解TSP问题的改进遗传蚁群算法

旅行商问题(TSP)是一种经典的组合优化问题.传统的蚁群算法运用正反馈和分布式计算机制,具有较强的鲁棒性.但是该算法搜索时间长、易出现早熟停滞现象.因此本文根据旅行商问题的模型特点,在蚁群算法的基础上针对TSP问题提出了一种新型的改进蚁群算法:即变参数选择城市策略,并且在交叉策略中选择PMX(Partially Matched Crossover)交叉策略.实验结果表明,与传统基本蚁群算法和遗传算法相比,能够较快地找到最优解,解的质量也相对较好,因此提高了蚁群算法对TSP问题的求解效率.     

基于遗传因子的自适应蚁群算法最优PID控制

蚁群算法是一种新型的模拟进化算法,重点始于组合优化问题的求解.作者运用该算法优化PID控制参数,但在基本蚁群算法中,存在收敛速度较慢,易出现停滞,以及全局搜索能力较低的缺陷.论文提出了一种具有遗传因子的自适应蚁群算法最优PID控制参数的方法,设计出参数优化图.该方法克服了基本蚁群算法的不足,能够满意地实现PID控制参数优化.仿真结果与Z-N法、遗传算法、基本蚁群算法相比较,优化效果明显得到改善.实验表明,该方法对于控制其他对象和过程也具有应用价值.     

基于蚁群算法的仿射变换参数求解

仿射变换参数估计是图像配准的基于蚁群算法的仿射变换参数估计方法,针对蚁群算法求解多维连续优化问题的不足,将仿射变换参数空间划分成若干子域,改进蚁群的搜索方法和信息素更新方法,快速搜索全局最优解,实验结果表明,该算法能够有效地估计仿射变换参数.     

一种求解连续对象优化问题的改进蚁群算法

蚁群算法在搜索过程中容易陷入局部最优解，且不适用于连续对象优化问题。文章针对这些问题．采用信息量变异、引入微粒群操作等方法进行改进，提出了一种引入微粒群操作的改进蚁群算法，并应用于求解连续对象优化问题。对几个典型复杂连续函数优化问题的测试研究表明，该改进算法不仅跳出局部最优解的能力更强．而且能较快地收敛到全局最优解，表明了算法的有效性。     

具有灾变的动态蚁群算法

尽管蚁群算法在优化计算中得到广泛应用,在求解大规模问题时它仍然存在的运行时间较长和容易产生过早收敛的缺点,本文在基本蚁群算法基础上,通过引入灾变、双向搜索、整段2-交换法、分段保存和对信息素等参数进行动态更新等策略改进算法,TSPLIB的一些实例求解结果均超过或达到记录的最好解,表明算法改进的效果是非常好的.     

3-状态并-串联设备网络单目标-单约束可靠性优化蚁群算法

3-状态设备网络系统单目标-单约束可靠性优化问题是NP-难问题,本文研究这类优化模型的快速算法。在对已有3-状态设备网络系统可靠性优化模型进行分类的基础上,采用蚁群算法为工具,给出了一个求解3-状态设备网络单目标-单约束并-串联网络系统可靠性优化问题最优解的蚁群算法。合理选择算法参数,进行计算机仿真。模拟仿真结果表明,在随机运行一定次数算法后,算法都能够有效给出模型的近似最优解。合理选择算法参数,蚁群算法能够成为有效求解3-状态设备网络可靠性优化问题有力工具。     

求解多目标资源分配问题的改进蚁群优化算法

多目标资源分配问题就是将有限资源分配到不同事件来获得预期目标.建立了多目标资源分配问题的数学模型,提出了一种有效求解该问题的改进蚁群优化算法：设计了一种多目标资源分配问题的可行方案构建机制,定义了蚁群优化算法中的信息素形式及其更新方式,提出了一种新的概率选择形式;通过以上改进有效地提高了蚁群优化方法的效率.为了验证此方法的有效性,将蚁群优化方法与混合遗传算法的实验结果进行了对比分析,证明此方法优于混合遗传算法.     

基于全局单位化的连续函数优化的改进蚁群算法

提出了一种基于空间全局单位化的解决连续空问优化问题的改进蚁群算法.该算法首先通过单位映射将优化空间映射到单位空间,然后蚂蚁在各变量的每个位数上在0到9十个数字中进行选择,以此来模拟蚁群觅食的过程,并阐述了此改进蚁群算法的主要改进操作.通过实例测试表明,改进蚁群算法具有较好的寻优能力.     

基于蚁群算法的面向服务软件的部署优化方法

面向服务软件的部署优化问题是典型的NP难题.本文构建了基于性能改善的软件部署优化模型,设计了一种蚁群优化算法ACO-DO进行近似最优解的快速求解.该算法通过设计基于部署优化问题的启发式、改进部署方案的构建顺序、增加局部搜索过程实现蚁群算法求解效率的提升.通过不同规模的实例实验,验证了ACO-DO算法能够取得比现有的混合整数线性规划算法、蚁群算法和遗传算法更好的性能.     

改进蚁群算法在交通系统最短路径问题的研究

求解交通路网中两点间的最短路径是智能交通系统中的一个重要功能,为了更为准确快速地找到最优解,这里分析Dijkstra算法处理动态车辆路径问题中的缺陷,提出一种改进的蚁群算法,即在基本蚁群算法中引入搜索方向和搜索热区机制提高算法的搜索性能.通过建立改进蚁群算法模型,用VC 6.0开发工具,以实际交通地图为例,求解交通网络两点间最短距离;并与基本蚁群算法进行对比.仿真实验表明,传统蚁群算法的平均迭代次数为71.06,改进蚁群算法平均迭代次数为55.82,比传统蚁群算法有了明显的提高.该方法能有效解决交通系统最短路径问题,具有一定的实际意义和参考价值和实际意义.     

基于蚁群算法的无人船平滑路径规划

为解决无人驾驶船舶在复杂环境中规划路径时存在的转向角度大、路径拐点多、航行能耗高等问题,文中提出一种基于改进蚁群算法的平滑路径规划方法。该方法采用栅格法进行环境建模,通过在启发函数中引入路径平滑度、距离启发因子以及在路径转移概率中引入障碍物启发因素,提高路径寻优和静态避障能力。结合启发因素改进信息素更新标准,设置可调节信息素挥发因子增加算法的自适应性。提取输出的最优路径关键节点并对其进行平滑处理,进一步保证路径平滑度和安全性。根据不同栅格环境下的避障仿真结果可知,与传统算法相比,文中改进蚁群算法的路径寻优速度提高了45%～62%,转向次数减少了25%～44%,平滑处理后的路径安全性和可行性得到了提升,较好地实现了不同环境下无人船自主路径规划。     

面向异构信号处理平台的负载均衡算法

针对当前异构信号处理平台中信号处理应用的调度算法优化目标单一且调度结果中处理器负载不均衡的问题，提出了一种基于蚁群优化算法的负载均衡算法。该算法结合蚁群优化算法的快速搜索能力和组合优化能力，以信号处理应用的调度长度和处理器负载均衡为优化目标，对初始信息素矩阵和蚂蚁的遍历顺序进行改进，提出调度长度启发因子和负载均衡启发因子对处理器选择公式进行改进，利用轮盘赌策略确定信号处理应用各子任务分配的处理器，完成信号处理应用的调度。仿真结果表明，该算法得到调度结果在调度长度和负载均衡方面均有改进，可以充分发挥各处理器性能，提高异构信号处理平台的整体效率。     

行为综合功能流水线中的负载平衡蚁群调度算法

在专用集成电路高层次综合中,功能流水线是提高算法描述执行速度的关键技术.针对时间约束和资源约束的两类行为综合功能流水线调度问题,提出了一种基于蚁群优化(ACO)的调度算法.LB-ACO算法将ACO算法与力向算法相结合,使用修改的力向公式定义局部试探因子,用个体调度结果的质量来更新全局试探因子.实验结果表明,LB-ACO算法在保证较低的时间复杂度O(cn2)的前提下,获得接近最优的调度结果.     

Structural health monitoring based on continuous ACO method

Structural damage detection remains as a challenging task in the field of structural health monitoring (SHM), which has occupied many scientific communities over the last two decades. As a new exploring attempt to the SHM problem, this paper proposes an ant colony optimization (ACO) based algorithm for continuous optimization problems on structural damage detection in the SHM field. First of all, the theoretical background of ACO is introduced for search of approximation best solution to discrete optimization problems and further to continuous optimization problems. Then four benchmark functions are used to evaluate the performance of continuous ACO (CnACO) algorithm. After that, the problem on the structural damage detection is mathematically converted into a constrained optimization problem, which is then hopefully solved by the CnACO algorithm. Meanwhile, effect of measurement noise on the algorithm is considered in all the damage scenarios. Upon extensive numerical simulations for single and multiple damages of a 2-storey rigid frame structure, the proposed method is extended to four damage patterns of a building model of 3-storey steel frame structure made in laboratory for further experimental verification of the proposed method. Illustrated results show that the proposed method is very effective for the structural damage detection. Regardless of weak damage or multiple damages, the identification accuracy is very high and the noise immunity is better, which shows that the proposed method is feasible and effective in the SHM field.     

Survey of research on application of heuristic algorithm in machine learning

Aiming at the problems existing in the application of machine learning algorithm,an optimization system of the machine learning model based on the heuristic algorithm was constructed.Firstly,the existing types of heuristic algorithms and the modeling process of heuristic algorithms were introduced.Then,the advantages of the heuristic algorithm were illustrated from its applications in machine learning,including the parameter and structure optimization of neural network and other machine learning algorithms,feature optimization,ensemble pruning,prototype optimization,weighted voting ensemble and kernel function learning.Finally,the heuristic algorithms and their development directions in the field of machine learning were given according to the actual needs.     

蚁群算法中系统初始化及系统参数的研究

蚁群算法作为近年来一种新的模拟进化算法具有较强的发现解的能力,但同时也有收敛慢、耗费时间的缺点.本文针对各种不同规模的TSP问题,通过实验对各参数的设置做了研究,并对蚂蚁初始化提出了新的算法,并进行了实验验证.     

多智能体系统中的任务分配蚁群优化算法

Task allocation is a key issue of agent cooperation mechanism in Multi-Agent Systems. The important features of an agent system such as the latency of the network infrastructure, dynamic topology, and node heterogeneity impose new challenges on the task allocation in Multi-Agent environments. Based on the traditional parallel computing task allocation method and Ant Colony Opti-mization (ACO), a novel task allocation method named Collection Path Ant Colony Optimization (CPACO) is proposed to achieve global optimization and reduce processing time. The existing problems of ACO are ana-lyzed; CPACO overcomes such problems by modifying the heuristic function and the up-date strategy in the Ant-Cycle Model and es-tablishing a three- dimensional path phero-mone storage space. The experimental results show that CPACO consumed only 10.3% of the time taken by the Global Search Algorithm and exhibited better performance than the Forward Optimal Heuristic Algorithm.     

An energy‐aware approach for resource managing in the fog‐based Internet of Things using a hybrid algorithm

Regarding the recent information technology improvement, the fog computing (FC) emergence increases the ability of computational equipment and supplies modern solutions for traditional industrial applications. In the fog environment, Internet of Things (IoT) applications are completed by computing nodes that are intermediate in the fog, and the physical servers in data centers of the cloud. From the other side, because of resource constraints, dynamic nature, resource heterogeneity, and volatility of fog environment, resource management problems must be considered as one of the challenging issues of fog. The resource managing problem is an NP‐hard issue, so, in the current article, a powerful hybrid algorithm for managing resources in FC‐based IoT is proposed using an ant colony optimization (ACO) and a genetic algorithm (GA). GAs are computationally costly because of some problems such as the lack of guarantee for obtaining optimal solutions. Then, the precision and speed of convergence can be optimized by the ACO algorithm. Therefore, the powerful affirmative feedback pros of ACO on the convergence rate is considered. The algorithm uses GA's universal investigation power, and then it is transformed into ACO primary pheromone. This algorithm outperforms ACO and GA under equal conditions, as the simulation experiments showed.     

Linear array synthesis using an ant-colony-optimization-based algorithm

The aim of this work is to show the use of a well-known type of evolutionary computational optimization technique, ant colony optimization (ACO), in a typical electromagnetic problem: linear array synthesis. To this aim, an algorithm based on the fundamentals of ant colony optimization has been developed. The algorithm uses real numbers. Some examples using different optimization criteria are presented. Also, some guidelines for the use of the algorithm, especially for creating the desirability function, are supplied. The algorithm has been demonstrated to be versatile and useful for this problem. The purpose of the work is to show (via this particular application) the flexibility and easy implementation of this algorithm family, which makes it suitable for use in other electromagnetic optimization problems.     

Adaptive subcarrier and bit allocation based on ant colony optimization

The problem of resource allocation in multiuser orthogonal frequency division multiplexing (OFDM) system is a combinatorial optimization problem, difficult to obtain optimal solutions in polynomial time. For the sake of reducing complexity, it can be solved either by relaxing constraints and making use of linear algorithms or by metaheuristic methods. In this paper, an algorithm based on ant colony optimization (ACO), which is a typical algorithm of metaheuristic methods, is proposed for the problem, utilizing excellent search performance of ACO to obtain good solutions. In addition, a parameter is applied to balance the efficiency and fairness of resource allocation. Performance analysis between algorithms based on ACO and genetic algorithm (GA) is carried out, indicating that the proposed algorithm based on ACO outperforms traditional linear algorithms as well as GA in the system throughput with assurance of fairness simultaneously, being as a promising technology for OFDM resource allocation.