Electricity Price Forecasting in Markets Considering Renewable and EV penetration using Machine Learning and DNN

The deregulation of the energy market increased rivalry, compelling many strategy creators to choose forecasting electricity prices because the more accurate the projection, the better the strategy they can devise. In this work, we have utilized both the renewable energy source (RES) generation data and Electric Vehicle (EVs) energy demand data along with the historical electricity price (EP) data to analyze and evaluate the impact of the integration of EV and RES on the Electricity Price Forecasting (EPF), for the forecasting purpose we used various machine learning (ML) models and DNN models out of which we got the best results from the Random Forest of 1.98 mean absolute error (MAE),0.686 percent of mean absolute percentage error (MAPE), 2.12 root mean square error (RMSE) and 0.864 of r2 score, these results are further compared with the past result, and it can be analyzed that addition of EV demand data helps in improvement in the forecasting accuracy.