Electrical Load Forecasting: A Parallel Seasonal Approach

Abstract

The electrical load forecast is an important aspect for the electrical distribution companies. It is important to determine the future demand for power in the short, medium, and long term. In the aim of making sure that the prediction remains relevant, different parameters are taking into account such as gross domestic product (GDP) and weather. This contribution covers the forecasting of medium and long terms of Algerian electrical load, using information contained in past consumption in a parallel approach where each season is forecasted separately and using dynamic load profile in order to deduct daily and hourly load values. Three models are implemented in this work. Multy variables linear regression (MLRs), artificial neural network (ANN) multi-layer perceptron (MLP), support vector machines regression (SVR) with grid search algorithm for hyperparameter optimization, and we use real energy consumption records. The proposed approach can be useful in the elaboration of energy policies, although accurate predictions of energy consumption positively affect the capital investment, while conserving at the same time the supply security. In addition it can be a precise tool for the Algerian mid-long term energy consumption prediction problem, which up today has not been faced effectively. The results are very encouraging and were accepted by the local electricity company.