Hybrid Artificial Neural Network and Genetic Algorithm-Based Model for Energy Management in Solar Smart Lighting Systems

Abstract

A hybrid Artificial Neural Network (ANN) and Genetic Algorithm (GA) model for effective energy management in solar smart lighting systems is presented in this paper. To improve system performance, the suggested model combines the optimization power of GA with the prediction power of ANN. Accuracy, precision, recall, F1-score, and energy efficiency are used to assess a variety of machine learning models, such as ANN, GA, Random Forest, and Support Vector Machine (SVM). With an accuracy of 96.8% and an energy efficiency of 97.5%, the hybrid ANN-GA model performs quite well. In order to minimize waste and increase sustainability, the system efficiently forecasts energy demand and optimizes power use in real time. This method works especially well for smart city applications when using renewable energy is essential. The findings show that decision-making and operational efficiency in solar-powered lighting systems are greatly improved by integrating learning and optimization approaches.