Daily Middle-Term Probabilistic Forecasting of Power Consumption in North-East England

TL;DR

This paper introduces a Gaussian Process-based model for probabilistic daily power consumption forecasting over a middle-term horizon, effectively incorporating trend, seasonality, and weather variables, with promising results on real data.

Contribution

It presents a novel machine learning approach combining time-series features and weather data for probabilistic power consumption forecasting in a middle-term horizon.

Findings

Effective density forecasts up to one year

Good performance with only two years of data

Validated with sector-standard probabilistic measures

Abstract

Probabilistic forecasting of power consumption in a middle-term horizon (months to a year) is a main challenge in the energy sector. It plays a key role in planning future generation plants and transmission grid. We propose a new model that incorporates trend and seasonality features as in traditional time-series analysis and weather conditions as explicative variables in a parsimonious machine learning approach, known as Gaussian Process. Applying to a daily power consumption dataset in North East England provided by one of the largest energy suppliers, we obtain promising results in Out-of-Sample density forecasts up to one year, even using a small dataset, with only a two-year In-Sample data. In order to verify the quality of the achieved power consumption probabilistic forecast we consider measures that are common in the energy sector as pinball loss and Winkler score and backtesting conditional and unconditional tests, standard in the banking sector after the introduction of Basel II Accords.