IRA-EMO: Interactive Method Using Reservation and Aspiration Levels for Evolutionary Multiobjective Optimization

We propose a new interactive evolutionary multiobjective optimization method, IRA-EMO. At each iteration, the decision maker (DM) expresses her/his preferences as an interesting interval for objective function values. The DM also specifies the number of representative Pareto optimal solutions in these intervals referred to as regions of interest one wants to study. Finally, a real-life engineering three-objective optimization problem is used to demonstrate how IRA-EMO works in practice for finding the most preferred solution.

[1]  Kalyanmoy Deb,et al.  Toward an Estimation of Nadir Objective Vector Using a Hybrid of Evolutionary and Local Search Approaches , 2010, IEEE Transactions on Evolutionary Computation.

[2]  Rubén Saborido,et al.  A combined interactive procedure using preference-based evolutionary multiobjective optimization. Application to the efficiency improvement of the auxiliary services of power plants , 2015, Expert Syst. Appl..

[3]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

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

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

[6]  Dmitry Podkopaev,et al.  Interactive Multiple Criteria Decision Making based on preference driven Evolutionary Multiobjective Optimization with controllable accuracy , 2012, Eur. J. Oper. Res..

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

[8]  Eckart Zitzler,et al.  Indicator-Based Selection in Multiobjective Search , 2004, PPSN.

[9]  Rubén Saborido,et al.  A preference-based evolutionary algorithm for multiobjective optimization: the weighting achievement scalarizing function genetic algorithm , 2015, J. Glob. Optim..

[10]  Kaisa Miettinen,et al.  An Interactive Evolutionary Multiobjective Optimization Method: Interactive WASF-GA , 2015, EMO.

[11]  Antonio J. Nebro,et al.  jMetal: A Java framework for multi-objective optimization , 2011, Adv. Eng. Softw..

[12]  Bernhard Sendhoff,et al.  A Reference Vector Guided Evolutionary Algorithm for Many-Objective Optimization , 2016, IEEE Transactions on Evolutionary Computation.

[13]  Rubén Saborido,et al.  Global WASF-GA: An Evolutionary Algorithm in Multiobjective Optimization to Approximate the Whole Pareto Optimal Front , 2017, Evolutionary Computation.

[14]  A.G. Martins,et al.  A Multiple Objective Approach to Direct Load Control Using an Interactive Evolutionary Algorithm , 2007, IEEE Transactions on Power Systems.

[15]  Qingfu Zhang,et al.  Interactive MOEA/D for multi-objective decision making , 2011, GECCO '11.

[16]  Kalyanmoy Deb,et al.  Multiobjective optimization , 1997 .

[17]  Lothar Thiele,et al.  A Preference-Based Evolutionary Algorithm for Multi-Objective Optimization , 2009, Evolutionary Computation.

[18]  Kaisa Miettinen,et al.  Connections of reference vectors and different types of preference information in interactive multiobjective evolutionary algorithms , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

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

[20]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .