Research Based On Decomposition And Truncation For Dynamic Multi-objective Evolutionary Optimization Algorithm

Evolutionary Algorithms(EAs)are a kind of the random search Algorithm,which can solve multiple and conflicting multi-objective problems.In real-word,there are many application problems,such as individual scheduling and control design.However,the problems can change over time.This is a challenging problem for EAs.Thus,EAs are an important research topic.There are multiple and conflicting multiple-objective problems over time,which are called dynamic multi-objective optimization problems(DMOPs).However,EAs are not an efficient method to solve DMOPs.Maintaining a balance between convergence and diversity of the population in the objective space has been widely recognized as the main challenge when solving problems with two or more conflicting objectives.This is added by another difficulty of tracking the Pareto optimal solutions set(POS)and/or the Pareto optimal front(POF)in dynamic scenarios.In order to make EAs adapt the dynamic environment,we need to involve diversity or use prediction methods when a change is detected.Although the methods can improve performance of algorithms in some degree,some more effective methods need to be proposed to solve DMOPs.In order to handle the problems,this paper proposes a Pareto-based evolutionary algorithm using decomposition and truncation to address such dynamic multi-objective optimization problems(DMOPs).The proposed algorithm includes three contributions: a novel mating selection strategy,an efficient environmental selection technique and an effective dynamic response mechanism.The mating selection considers the decomposition-based method to select two promising mating parents with good diversity and convergence.The environmental selection presents a modified truncation method to preserve good diversity.The dynamic response mechanism is evoked to produce some solutions with good diversity and convergence whenever an environmental change is detected.In the experimental studies,a range of dynamic multi-objective benchmark problems with different characteristics were carried out to evaluate the performance of the proposed method.The experimental results demonstrate that the method is very competitive in terms of convergence and diversity,as well as in response speed to the changes,when compared with six other state-of-the-art methods such as DNSGA-II,PPS,SGEA.