Review of Short-Term Load Forecasting for Smart Grids Using Deep Neural Networks and Metaheuristic Methods

Forecasting electricity load demand is critical for power system planning and energy management. In particular, accurate short-term forecasting (STLF), which focuses on the lead time horizon of few minutes to one week ahead, can help in better scheduling, unit commitment, cost-effective operation smart grids. last decade, different artificial intelligence (AI)-based techniques metaheuristic algorithms have been utilized STLF by researchers scientists with varying degrees accuracy efficacy. Despite benefits implemented methods STLF, many drawbacks associated problems also observed reported researchers. This paper provides a comprehensive review hybrid deep learning models based nature-inspired respect analysis results accuracy. Moreover, it research findings gaps that will assist an early awareness all important these integrated scientifically systematically. Especially, forecast using intelligence-based grids are focused. Several performance indices used compare report including mean absolute percentage error (MAPE). Multiple other parametric exogenous variable details focused figure out potential intelligent from perspective