Hybridizing Multi-Objective Interactive Techniques - Some Applications to the Electricity Generation Industry

Presented on 12 Jan at ICORES 2015

Keynote Lecturer: Francisco Ruiz

Abstract: Interactive methods have proved to be extremely useful multi-objective techniques, when it comes to solve real complex decision making problems. Their iterative schemes are especially suitable for the necessary learning process that has to be present in very decision making process. Many different interactive methods exist, and they vary both in the type of information that the decision maker (DM) has to provide at each iteration, and in the way the different solutions are obtained along the process. These two aspects have leaded us to develop several hybrid models:- With respect to the information required from the DM, this can take many different forms (just choosing one solution among a set of possible solutions, giving local tradeoffs, giving reference or target values, classifying the objectives…). But in many cases, the interactive method is chosen without taking into account the cognitive burden that it implies for the DM. In this sense, we have developed a hybrid interactive multi-objective system (PROMOIN), where the DM can decide at each step the type of information (s)he prefers to give, and the system internally switches to the most appropriated method. The idea is to adapt the resolution process to the necessities of the DM, and not vice versa. PROMOIN was applied to an empirical study, founded by the Regional Ministry of Environment of Andalucía, about the determination of the optimal electricity mix, taking into account economical and environmental criteria. - With respect to the inner methodology, interactive methods imply the sequential resolution of single objective optimization problems, which, depending on the specific features of the model, can be very complex and time consuming. In many of these cases, traditional solvers are no longer applicable. For these reason, we have studied several hybridizations of interactive methods with Evolutionary Multi-Objective techniques, which have proved to be very useful, not only to solve the individual optimization problems, but to extract many useful information during a preliminary learning phase. We have applied these hybrid methodologies to two real decision problems of one of the main Spanish electricity generation firms. In one of them, we studied the optimal dimensions of a solar thermal generation plant. In another one, we aimed in the decision of the actions to take in a coal thermal plant, in order to improve the efficiency of the auxiliary systems.