High Dimensional Models for Forecasting Power Electricity Consumption

We use machine learning techniques to forecast Brazilian power electricity consumption (PEC) for short and medium terms. We compare our models to benchmark specifications such as Random Walk and autoregressive integrated moving average (ARIMA). Our results show that machine learning methods, especially Random Forest and Lasso Lars, give more accurate forecasts for all horizons. Random Forest and Lasso Lars managed to keep up with the trend and the seasonality in various time horizons. The gain in predicting PEC using machine learning models relative to the benchmarks is much higher for the very short-term. Machine learning variable selection further shows that lagged consumption values are extremely important for very short-term forecasting due to the series high autocorrelation. Other variables are important for longer time horizons.Code's folder contains the Python's 3.7 script that wu use to load, exchange, model and analyze our work. Data's folder contains the raw, results and auxiliar of our work's data