Optimal Siting and Sizing of Distributed Generation Using a Hybrid Jellyfish Search Optimizer and Machine Learning Predictive Model: An Overview

Abstract

The rapid transition toward decentralized and renewable energy-based power systems has significantly increased the adoption of distributed generation (DG) within electrical distribution networks. Distributed generation offers several technical, economic, and environmental benefits, including reduced transmission losses, improved voltage regulation, enhanced system reliability, increased energy efficiency, and lower greenhouse gas emissions. However, these benefits can only be fully realized when DG units are optimally located and appropriately sized. Improper placement or sizing may lead to excessive power losses, voltage violations, reverse power flow, feeder overloading, and compromised system stability. Consequently, the optimal siting and sizing of DG has become one of the most important optimization problems in modern power system planning. This review presents a comprehensive overview of recent developments in intelligent optimization techniques for DG planning, with particular emphasis on the integration of the Jellyfish Search Optimizer and machine learning (ML) predictive models. The paper examines the evolution of optimization methods from conventional mathematical techniques to nature-inspired metaheuristic algorithms and advanced artificial intelligence approaches. It critically reviews the operating principles, strengths, limitations, and applications of JSO and explores how machine learning can enhance optimization accuracy, convergence speed, computational efficiency, and solution robustness through predictive guidance. The review further discusses current research trends, implementation challenges, and opportunities associated with integrating renewable energy resources, battery energy storage systems, electric vehicles, and smart grid technologies into intelligent DG planning frameworks. Finally, the paper identifies existing research gaps and proposes future research directions for the development of adaptive, scalable, and data-driven optimization techniques capable of addressing the increasing complexity of modern electrical distribution systems. The findings provide researchers, utility engineers, and policymakers with a comprehensive understanding of emerging hybrid optimization strategies for achieving efficient, reliable, and sustainable distributed generation planning. IJEMT

Keywords

References