LSTM-Based Deep Learning Long Term Electric Demand Prediction for Karnataka

Long Short-Term Memory (LSTM) simulations offer a robust time series-based electric demand forecasting framework. By leveraging the memory capabilities of LSTM networks, accurate predictions can be made for future demand, aiding in efficient resource allocation. LSTM networks have emerged as powerful tools for time series forecasting. Their ability to capture long-range dependencies and handle temporal patterns makes them particularly effective in predicting future values of sequential data. The input data is required for the LSTM, the power demand of Karnataka state has been taken as a study model. It explores the application of LSTM models in time series forecasting, highlighting their strengths in capturing complex temporal dynamics and achieving accurate predictions across various domains. Historical demand data has been collected from 1975 to 2023. Electric demand is forecasted till 2029. The effectiveness of the proposed algorithm has captured long-range dependencies and outperformed traditional methods.