Wild Horse Optimization with Deep Learning-Driven Short-Term Load Forecasting Scheme for Smart Grids

Energy is a major driver of human activity. Demand response the utmost importance to maintain efficient and reliable operation smart grid systems. The short-term load forecasting (STLF) method particularly significant for electric fields in trade energy. This model has several applications everyday operations utilities, namely switching, energy-generation planning, contract evaluation, energy purchasing, infrastructure maintenance. A considerable number STLF algorithms have introduced tradeoff between convergence rate forecast accuracy. study presents new wild horse optimization with deep learning-based scheme (WHODL-STLFS) SGs. presented WHODL-STLFS technique was initially used design WHO algorithm optimal selection features from electricity data. In addition, attention-based long memory (ALSTM) exploited learning consumption behaviors load. Finally, an artificial algae (AAO) applied as hyperparameter optimizer ALSTM model. experimental validation process carried out on FE Dayton obtained results indicated that achieved accurate load-prediction performance