PV-grid performance improvement through integrated intelligent water drop optimization with neural network for maximum power point tracking

• Published in: I-Manager's Journal on Electrical Engineering Vol. 18; no. 1; p. 1
• Main Authors: Abhishek, Kumar Sahu, Durga, Sharma, Anup, Mishra
• Format: Journal Article
• Language: English
• Published: Nagercoil iManager Publications 01.09.2024
• Subjects: Adaptation; Alternative energy sources; Artificial intelligence; Efficiency; Electrical engineering; Fuzzy logic; Genetic algorithms; Incremental conductance; Machine learning; Maximum power tracking; Neural networks; Optimization algorithms; Particle swarm optimization; Performance evaluation; Photovoltaic cells; Renewable resources; Simulation; Solar energy; Water; Water drops
• ISSN: 0973-8835; 2230-7176
• DOI: 10.26634/jee.18.1.21181

This paper presents an optimized model that combines the Intelligent Water Drop (IWD) optimization algorithm and a neural network (NN) for maximum power point tracking (MPPT) in photovoltaic (PV) applications. The proposed approach demonstrates superior performance compared to conventional methods, including Fuzzy Logic Control, Perturb and Observe (P&O), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Incremental Conductance (INC) control. The enhanced model improves adaptability and convergence due to the optimization capabilities of the IWD algorithm and leverages the predictive characteristics of the NN for faster and more accurate tracking. The results indicate that this model offers significant potential for future-generation PV systems, particularly in solar energy applications.