Hybrid Deep Learning Enabled Load Prediction for Energy Storage Systems

Recent economic growth and development have considerably raised energy consumption over the globe. Electric load prediction approaches become essential for effective planning, decision-making, contract evaluation of power systems. In order to achieve forecasting outcomes with minimum computation time, this study develops an improved whale optimization deep learning enabled (IWO-DLELP) scheme storage systems (ESS) in smart grid platform. The major intention IWO-DLELP technique is effectually forecast electric SG environment designing proficient ESS. proposed model initially undergoes pre-processing two stages namely min-max normalization feature selection. Besides, partition clustering approach applied decomposition data into distinct clusters respect distance objective functions. Moreover, IWO bidirectional gated recurrent unit (BiGRU) hyperparameters are tuned by use algorithm. experiment analysis reported enhanced results recent methods interms measures.