State-Space Models for Online Post-Covid Electricity Load Forecasting Competition

Abstract

We present the winning strategy for the IEEE DataPort Competition on Day-Ahead Electricity Load Forecasting: Post-Covid Paradigm. This competition was organized to design new forecasting methods for unstable periods such as the one starting in Spring 2020. First, we pre-process the data with a statistical correction of the meteorological variables. Second, we apply standard statistical and machine learning models. Third, we rely on state-space models to adapt the aforementioned forecasters. It achieves the right compromise between two extremes. Indeed, machine learning methods allow to learn complex dependence to explanatory variables on a historical data set but fail to forecast non-stationary data accurately. Conversely, purely time-series models such as autoregressives are adaptive in essence but fail to capture dependence to exogenous variables. Finally, we use aggregation of experts, and we leverage the diversity of the set of obtained forecasters to improve our final predictions. The evaluation period of the competition was the occasion of trial and error and we put the focus on the final procedure.

Keywords

• Covid-19
• electricity load
• Kalman filter
• forecast
• state-space model
• time series