A novel oppositional learning-based chaotic sine cosine algorithm for the dynamic thermal–wind economic dispatch problem

Abstract

Wind power generation is efficiently utilized with traditional thermal power generation in the dynamic economic emission dispatch (DEED) problem to achieve the demand power of scheduled periods with minimum generation cost and emission of pollutants. This study uses a novel oppositional learning-based chaotic sine cosine algorithm (SCA) (OL-CSCA) to solve a new model of wind energy-based DEED, called dynamic thermal–wind economic emission dispatch (DTWEED). The concepts of oppositional learning and chaos are introduced into the SCA to strengthen its optimization performance. The effectiveness of the proposed model is tested by solving four cases (generation cost, spinning reserve based generation cost, emission and combined cost–emission) using OL-CSCA. The novelty of DTWEED is shown by comparing the results of different cases with the traditional DEED model. Comparison of the results of OL-CSCA for different cases of DEED and DTWEED with the results of SCA and other algorithms demonstrated its robustness and proficiency.