I-MODE: An Interactive Multi-objective Optimization and Decision-Making Using Evolutionary Methods

With the popularity of efficient multi-objective evolutionary optimization (EMO) techniques and the need for such problem-solving activities in practice, EMO methodologies and EMO research and application have received a great deal of attention in the recent past. The first decade of research in EMO area has been spent on developing efficient algorithms for finding a well-converged and well-distributed set of Pareto-optimal solutions, although EMO researchers were always aware of the importance of procedures which would help choose one particular solution from the Pareto-optimal set for implementation. In this paper, we address this long-standing issue and suggest an interactive EMO procedure by collating most salient research in EMO and putting together a step-by-step EMO and decision-making procedure. The idea is implemented in a GUI-based, user-friendly software which allows a user to supply the problem mathematically or by using user-defined macros and enables the user to evaluate solutions directly or by calling an executable software, such as popularly-used MATLAB software for a local search or ANSYS software for finite element analysis, etc. Starting with standard EMO applications, continuing to finding robust, partial, and user-defined preferred frontiers through standard MCDM procedures, the well-coordinated software allows the user to first have an idea of the complete trade-off frontier, then systematically focus in preferred regions, and finally choose a single solution for implementation.

[1]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[2]  Wolfgang Kröger.  Critical infrastructures at risk: securing electric power supply , 2006, Int. J. Crit. Infrastructures.

[3]  Tong Heng Lee,et al.  A multiobjective evolutionary algorithm toolbox for computer-aided multiobjective optimization , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[4]  J. Branke,et al.  Guidance in evolutionary multi-objective optimization , 2001 .

[5]  A. Ravindran,et al.  Engineering Optimization: Methods and Applications , 2006 .

[6]  Kalyanmoy Deb,et al.  Searching for Robust Pareto-Optimal Solutions in Multi-objective Optimization , 2005, EMO.

[7]  Kalyanmoy Deb,et al.  A Hybrid Multi-objective Evolutionary Approach to Engineering Shape Design , 2001, EMO.

[8]  Kalyanmoy Deb,et al.  Running performance metrics for evolutionary multi-objective optimizations , 2002 .

[9]  Kalyanmoy Deb,et al.  Reference point based multi-objective optimization using evolutionary algorithms , 2006, GECCO.

[10]  Andrzej P. Wierzbicki,et al.  The Use of Reference Objectives in Multiobjective Optimization , 1979 .

[11]  Simon French,et al.  Multiple Criteria Decision Making: Theory and Application , 1981 .

[12]  Marco Laumanns,et al.  A Tutorial on Evolutionary Multiobjective Optimization , 2004, Metaheuristics for Multiobjective Optimisation.

[13]  K. Deb,et al.  I-EMO: An Interactive Evolutionary Multi-objective Optimization Tool , 2005, PReMI.

[14]  Yacov Y. Haimes,et al.  Multiobjective Decision Making: Theory and Methodology , 1983 .

[15]  Kaisa Miettinen,et al.  Nonlinear multiobjective optimization , 1998, International series in operations research and management science.

[16]  Peter J. Fleming,et al.  Multiobjective optimization and multiple constraint handling with evolutionary algorithms. II. Application example , 1998, IEEE Trans. Syst. Man Cybern. Part A.