A Combination of Variational Mode Decomposition with Neural Networks on Household Electricity Consumption Forecast

International audienceRecently, there has been a significant emphasis on the forecasting of the electricity demand due to the increase in the power consumption. This paper presents the computational modeling of electricity consumption based on Neural Network (NN) training algorithms. The noise in signals, which are caused by various external factors, often corrupt demand series and influence consequently on the model performance. For accurate electricity demand forecasting, we propose a novel approach that combines a NN MLP (multilayer perceptron) with VMD (variational mode decomposition)-based signal filtering. Using the daily electricity demand series of EDF (Electricté De France) obtained from the UCI machine learning repository, this paper demonstrates that the proposed VMD-NN model greatly improves the forecasting error comparing to existing stationary stochastic process such as the autoregressive moving average (ARMA) model. 1 Introduction Domestic energy consumption [1] is the total amount of energy used in a house for household work. The amount of energy used per household varies widely depending on the standard of living of the country, the climate, and the age and type of residence. Energy demand forecasting is a very important task in the electric power distribution system to enable appropriate planning for future power generation. Quantitative and qualitative methods have been utilized previously for the electricity demand forecasting. These methods fail to provide effective results. With the development of the advanced tools, these methods are replaced by efficient forecasting techniques. According to common classifications [2], demand forecasting models are classified based on two different criteria: the forecasting horizon and the aim of the forecast, also we can divide them into linear and nonlinear models and a third group consists of models that use a combination of both