A Hybrid Sailfish Whale Optimization and Deep Long Short-Term Memory (SWO-DLSTM) Model for Energy Efficient Autonomy in India by 2048

In order to formulate the long-term and short-term development plans meet energy needs, there is a great demand for accurate forecasting. Energy autonomy helps decompose large-scale grid control into small sized decisions attain robustness scalability through independence level of country. Most existing forecasting models predict amount at regional or national scale failed forecast power generation small-scale decentralized systems, like micro grids, buildings, communities. A novel model called Sailfish Whale Optimization-based Deep Long Short- Term memory (SWO-based LSTM) electricity in distribution systems proposed. The proposed SWO designed by integrating Optimizer (SO) with Optimization Algorithm (WOA). Hilbert-Schmidt Independence Criterion (HSIC) applied on dataset, which collected from Central authority, Government India, selecting optimal features using technical indicators. algorithm implemented MATLAB software package study was done real-time data. are trained LSTM model. results terms install capacity prediction, village electrified length R & D lines hydro, coal, diesel, nuclear etc. compared models. achieves percentage improvements 10%, 9.5%,6%, 4% 3% Mean Squared Error (MSE) 26%, 21%, 16%, 12% 6% Root Square (RMSE) Bootstrap-based Extreme Learning Machine approach (BELM), Direct Quantile Regression (DQR), Temporally Local Gaussian Process (TLGP), Echo State Network (Deep ESN) respectively. hybrid optimization deep learning leads faster convergence rate during training process enables address challenges distributed resources. time series datasets different utilities temporal dependencies sequence data predicted point interval as 5 years-head. country till year 2048 assessed compared.