Renewable Energy Management Using Action Dependent Heuristic Dynamic Programming

With increases in global energy demand and the rapid consumption of fossil fuels, the use of green energy and more efficient energy management approaches are receiving serious attention. Our focus is on improving energy resource scheduling in smart buildings and homes to minimize cost, while meeting energy demand. Here, we present an approach using Action Dependent Heuristic Dynamic Programming (ADHDP) optimization for a smart home set-up using solar panels, wind turbines, and a storage battery. In this work, we trained and evaluated our ADHDP approach using different simulation scenarios with various amounts of available renewable energy. We then demonstrated via computer simulation that our approach is more effective in cost minimization compared to a standard rule-based method. A correlation between optimization improvement and available renewable energy was also confirmed by computer simulation in all scenarios.