A Hybrid Simplex Multi-Objective Evolutionary Algorithm Based on A New Fitness Assignment Strategy

نویسندگان

  • Xiaofang Guo
  • Yuping Wang
چکیده

In multi-objective evolutionary algorithms (MOEAs), the traditional fitness assignment strategy based on Pareto dominance is ineffective in sorting out the highquality solutions when the number of the objective is large. Recently, many scholars have used preference order (PO) ranking approach as an optimality criterion in the ranking stage of MOEAs. The experiment shows that the algorithms equipped with the PO ranking procedures can have a better convergence to the true Pareto surface, but are ineffective to maintain a set of well-distributed solutions over the Pareto surface. In order to overcome above shortcomings, a new algorithm is proposed which adopts a new fitness assignment strategy using the information of the individual preference order ranking and the individual density. In this way, it is helpful to guide the individuals to more sparse areas in the Pareto Front. At the same time, the proposed algorithm effectively combines multi-objective evolutionary algorithm with the Nelder-Mead simplex search to get a balance between the exploration and exploitation abilities. In each generation, the algorithm adopts a parallel hybrid way to evolve two subsets simultaneously, and the population will be improved by both evolution algorithm and simplex search. The proposed algorithm has been compared with other MOEAs on some many-objective problems by experiments. The experimental results indicate that the proposed algorithm achieves a better performance in convergence and diversity.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A New Multi-objective Job Shop Scheduling with Setup Times Using a Hybrid Genetic Algorithm

This paper  presents a new multi objective job shop scheduling with sequence-dependent setup times. The objectives are to minimize the makespan and sum of the earliness and tardiness of jobs in a time window. A mixed integer programming model is developed for the given problem that belongs to NP-hard class. In this case, traditional approaches cannot reach to an optimal solution in a reasonable...

متن کامل

A Novel Intelligent Energy Management Strategy Based on Combination of Multi Methods for a Hybrid Electric Vehicle

Based on the problems caused by today conventional vehicles, much attention has been put on the fuel cell vehicles researches. However, using a fuel cell system is not adequate alone in transportation applications, because the load power profile includes transient that is not compatible with the fuel cell dynamic. To resolve this problem, hybridization of the fuel cell and energy storage device...

متن کامل

A Hybrid MOEA/D-TS for Solving Multi-Objective Problems

In many real-world applications, various optimization problems with conflicting objectives are very common. In this paper we employ Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D), a newly developed method, beside Tabu Search (TS) accompaniment to achieve a new manner for solving multi-objective optimization problems (MOPs) with two or three conflicting objectives. This i...

متن کامل

Design Methodology of the Heterogeneous Multi-core Processor With the Combination of Parallelized Multi-core Simulator and Common Register File-Based Instruction Set Extension Architecture

SPECIAL ISSUE PAPERS The Synchronization Problem for a Class of Supply Chain Complex Networks Xiaobing Gan and Jingyi Wang A Hybrid Genetic Algorithm for Constrained Optimization Problems Da-lian Liu, Xiao-hua Chen, and Jin-ling Du New Heuristic Algorithm of RNA Structure Prediction including Pseudoknots Zhendong Liu and Daming Zhu A Hybrid Simplex Multi-Objective Evolutionary Algorithm Based o...

متن کامل

An Evolutionary Algorithm Based on a Hybrid Multi-Attribute Decision Making Method for the Multi-Mode Multi-Skilled Resource-constrained Project Scheduling Problem

This paper addresses the multi-mode multi-skilled resource-constrained project scheduling problem. Activities of real world projects often require more than one skill to be accomplished. Besides, in many real-world situations, the resources are multi-skilled workforces. In presence of multi-skilled resources, it is required to determine the combination of workforces assigned to each activity. H...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • JCP

دوره 8  شماره 

صفحات  -

تاریخ انتشار 2013