A New Technique for Investigating Wind Power Prediction Error in the Multi-Objective Environmental Economics Problem

Abstract

This paper develops a novel multi-objective evolutionary algorithm (MOEA), namely an enhanced multi-objective exchange market algorithm (EMEMA), to solve the multi-objective problems in the presence of uncertainty. In this paper, Quasi-Monte Carlo (QMC) simulation is implemented for the first time to address the overestimation and underestimation caused by the uncertain wind power generation. In QMC, instead of pseudorandom numbers, some samples are generated to reduce the computational burden using the Sobol sequences. In addition, a new procedure is introduced to increase the spread and maintain the diversity of solutions. The effectiveness of the EMEMA is tested on two well-known benchmark functions and Taiwan's well-known 40-unit test system in two different scenarios, with and without considering the uncertainty. Also, four different measurements are employed to scrutinize the algorithm performance. The results prove the superiority of the proposed method compared to the state-of-art algorithms. Finally, the robustness of the EMEMA is studied using parametric and non-parametric statistical tests. The statistical analysis corroborates the robustness of the proposed method.