Evaluation of Machine Learning Models for Smart Grid Parameters: Performance Analysis of ARIMA and Bi-LSTM

The integration of renewable energy resources into smart grids has become increasingly important to address the challenges managing and forecasting production in fourth revolution. To this end, artificial intelligence (AI) emerged as a powerful tool for improving control management. This study investigates application machine learning techniques, specifically ARIMA (auto-regressive integrated moving average) Bi-LSTM (bidirectional long short-term memory) models, predicting solar power next year. Using one year real-time data, trains tests these models on performance measures such mean absolute error (MAE) root squared (RMSE). results demonstrate that model outperforms terms accuracy is able successfully identify intricate patterns long-term relationships real-time-series data. findings suggest techniques can optimize grids, leading more efficient sustainable systems.