基于双阶段搜索的约束进化多任务优化算法  

Two-stage search-based constrained evolutionary multitasking optimization algorithm

作　　者：赵楷文 王鹏 童向荣 ZHAO Kaiwen;WANG Peng;TONG Xiangrong(School of Computer and Control Engineering,Yantai University,Yantai Shandong 264005,China)

机构地区：[1]烟台大学计算机与控制工程学院,山东烟台264005

出　　处：《计算机应用》2024年第5期1415-1422,共8页journal of Computer Applications

基　　金：收国家自然科学基金资助项目(62072392,61972360);山东省重大科技创新工程项目(2019522Y020131);山东省自然科学基金资助项目(ZR2020QF113);烟台市重点实验室项目。

摘　　要：高效地平衡算法的多样性、收敛性和可行性是求解约束多目标优化问题(CMOP)的关键;然而,复杂约束的出现给该类问题的求解带来了更大的挑战。因此,提出一种基于双阶段搜索的约束进化多任务优化算法(TEMA),通过完成两个协同进化的任务实现多样性、收敛性和可行性之间的平衡。首先,进化过程由探索和利用两个阶段组成,分别致力于加强算法在目标空间的广泛探索能力和高效搜索能力;其次,设计一种动态约束处理策略以平衡种群中可行解的比例,从而增强算法在可行区域的探索能力;再次,提出一种回退搜索策略,利用无约束Pareto前沿所包含的信息指导算法向约束Pareto前沿快速收敛;最后,在两个基准测试集中的23个问题上进行对比实验。实验结果表明,TEMA分别在14个和13个测试问题上取得最优反世代距离(IGD)值和超体积(HV)值,体现出明显优势。It is crucial in solving Constrained Multi-objective Optimization Problems(CMOPs)to efficiently balance the relationship between diversity,convergence and feasibility.However,the emergence of complex constraints poses a greater challenge in solving CMOPs.Therefore,a Two-stage search-based constrained Evolutionary Multitasking optimization Algorithm(TEMA)was proposed to achieve the balance between diversity,convergence and feasibility by completing the two cooperatively evolutionary tasks together.At first,the whole evolutionary process was divided into two stages,exploration stage and utilization stage,which were dedicated to enhance the extensive exploration capability and efficient search capability of the algorithm in the target space,respectively.Second,a dynamic constraint handling strategy was designed to balance the proportions of the feasible solutions in the population to enhance the exploration capability of the algorithm in the feasible region.Then,a backward search strategy was proposed to utilize the information contained in the unconstrained Pareto front to guide the algorithm to converge quickly to the constrained Pareto front.Finally,comparative experiments were performed on 23 problems in two benchmark test suites to verify the performance of the proposed algorithm.Experimental results indicate that the proposed algorithm achieves optimal IGD(Inverted Generational Distance)and HV(HyperVolume)values on 14 and 13 test problems,respectively,which reflects its significant advantages.

关 键 词：约束多目标优化问题 进化多任务优化算法 双阶段进化机制 进化算法 约束处理技术 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]