摘要
含有大规模决策变量的优化问题是当前多目标进化算法领域中的研究热点和难点之一.为有效解决大变量优化问题,设计了关联变量识别和分组策略,并结合MOEA/D算法,提出一种关联变量分组的分解多目标进化算法(MOEAD/IVG).该算法通过识别决策变量间内在的关联信息来把关联变量分配到同组中,从而将复杂高维变量的优化问题分解为简单低维的子问题来分组优化.算法通过增加关联变量分配到同组中的概率以尽可能地保留变量间的关联性,减少分组后子问题间的依赖性,从而提高子问题最优解的质量并最终获得最佳的Pareto最优解集.将该算法应用于通信系统中用户功率优化控制的工程问题,仿真实验结果表明了MOEAD/IVG算法的有效性,无论是求解精度还是运行效率,整体上都优于其他的多目标进化算法RVEA、MOEA/D、MOPSO和NSGA-Ⅱ.
Optimization problem with large-scale decision variable is one of the hot and difficult points in the multi-objective evolutionary algorithm research field.In order to solve the optimization problem of large variable effectively,this paper designs the interacting variable identification and grouping strategy,and combines with MOEA/D algorithm.Thus a multi-objective evolutionary algorithm based on decomposition using interacting variables grouping （MOEAD/IVG） is proposed.This algorithm can identify the internal relation among the decision variables and allocate the interacting variables to the same group.So it can decompose a difficult high-dimensional problem into a set of simpler and low-dimensional subproblems that can be grouping optimized easily.In order to make the algorithm as far as possible to retain the relationship between variables and keep the interdependencies among different subproblems minimal,the algorithm increases the probability of assigning the interacting variables to the same group so as to improve the quality of the optimal solution of the subproblems and ultimately gets the best Pareto optimal solution set.This algorithm is applied to the engineering problem of user power optimal control in communication system.The simulation results show the effectiveness of MOEAD/IVG.The algorithm is superior to RVEA,MOEA/D,MOPSO and NSGA-II on a whole,no matter the accuracy of obtained solutions or the efficiency of algorithm.
作者
邱飞岳
胡烜
王丽萍
QIU Fei-yue1,2, HU Xuan1 ,WANG Li-ping3(1 College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China; 2 （ Institute of Modem Educational Technology, Zhejiang University of Technology, Hangzhou 310023, China; 3 Institute of Information Intelligence and Decision Optimization . Zhejiang University of Technology, Hangzhou 310023, China)
出处
《小型微型计算机系统》
CSCD
北大核心
2018年第4期644-650,共7页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(61472366
61379077)资助
浙江省自然科学基金项目(LY13F030010
LY17F020022)资助
关键词
大规模优化
关联变量
变量识别
功率控制
large-scale optimization
interacting variables
variable identification
power control
