Multiobjective multi verse optimization algorithm to solve dynamic economic emission dispatch problem with transmission loss prediction by an artificial neural network

Sundaram, Arunachalam

Abstract

To overcome the drawback of using only one B-loss coefficient for a widely varying demand pattern that occurs during the entire period of a dynamic economic emission dispatch model, this research work presents a new approach to integrating artificial neural network-based loss prediction into the dynamic economic emission dispatch model. The trained neural network will predict the transmission loss only once during each interval of the dispatch period. The novelty of the work lies in employing a trained neural network to replace the existing procedure of solving complex power flow equations or B-loss coefficients during every iteration. A potent multiobjective multiverse optimization algorithm along with an effective constraint handling mechanism is employed to solve the highly complicated dynamic economic emission dispatch model. A fuzzy membership-based approach is adopted to help the decision-maker select one optimal solution from the Pareto Optimal solutions during each hour of the dispatch period. The proposed algorithm is tested on four systems of varying complexity including a large-scale IEEE 118 bus power system with fifty-four thermal generators. The results obtained are compared with 16 state-of-the-art algorithms to prove the competitive behavior of the algorithm. For an IEEE 30 bus system, the proposed algorithm results in a saving of 92.92$ in fuel cost and a reduction of emission levels by 0.0375 tons per day. The total time taken by the algorithm is faster than the well-known non dominated sorted genetic algorithm II and multiobjective particle swarm optimization algorithm by 30 times and 7.6 times respectively.

Citation

Sundaram, A. (2022). Multiobjective multi verse optimization algorithm to solve dynamic economic emission dispatch problem with transmission loss prediction by an artificial neural network. Applied Soft Computing, 124, Article 109021. https://doi.org/10.1016/j.asoc.2022.109021

• Journal Article Type: Article
• Acceptance Date: May 11, 2022
• Publication Date: 2022-07
• Deposit Date: Jul 14, 2024
• Journal: Applied Soft Computing
• Print ISSN: 1568-4946
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 124
• Article Number: 109021
• DOI: https://doi.org/10.1016/j.asoc.2022.109021
• Keywords: Economic dispatch,Emission dispatch,Multiobjective optimization,Meta-heuristic algorithms,Artificial Neural Network,Transmission loss prediction.