Sustainable Energy Management in Educational Lighting Systems: A Fusion-Based Approach for Optimizing Solar-Powered LED Illumination

Reliable, sustainable electricity in educational facilities is crucial for effective learning, as power outages and reliance on nonrenewable energy disrupt activities and harm the environment. In this manuscript, a sustainable energy management approach is proposed to optimize solar-powered Light Emitting Diode (LED) illumination in educational lighting systems. The proposed technique combines the Hamiltonian Deep Neural Network (HDNN) and Electric Eel Foraging Optimization (EEFO), which is referred to as the HDNN-EEFO approach. The primary aim of the proposed technique is to enhance energy efficiency, minimize operational costs, and ensure stable illumination under varying weather conditions. The HDNN is used to predict load demand and adapt to environmental changes, while the EEFO is employed to optimize LED driver energy consumption and system cost. The proposed method was implemented on the MATLAB platform and compared with other existing methods, including Process Parameters Optimization (PPO), Artificial Neural Network (ANN), and Particle Swarm Optimization (PSO). Compared to existing approaches, the proposed method achieves the lowest prediction error 0.1% and a reduced implementation cost of 1.2 cents/kWh. These results demonstrate that the HDNN-EEFO system is suitable for deployment in energy-constrained and off-grid educational institutions, enabling cost-effective, reliable, and environmentally sustainable classroom lighting.