Efficient mid-term forecasting of hourly electricity load using generalized additive models

TL;DR

This paper introduces a novel, interpretable GAM-based model for mid-term hourly electricity load forecasting, capturing complex seasonal, weather, and socio-economic effects, achieving high accuracy and fast computation over extensive European data.

Contribution

The paper presents a new GAM-based approach with autoregressive post-processing for mid-term load forecasting, combining interpretability with high accuracy and efficiency.

Findings

Significantly improved forecasting accuracy over state-of-the-art methods

Model achieves day-ahead forecast accuracy with minimal computation time

Provides detailed insights into factors influencing electricity load

Abstract

Accurate mid-term (weeks to one year) hourly electricity load forecasts are essential for strategic decision-making in power plant operation, ensuring supply security and grid stability, planning and building energy storage systems, and energy trading. While numerous models effectively predict short-term (hours to a few days) hourly load, mid-term forecasting solutions remain scarce. In mid-term load forecasting, capturing the multifaceted characteristics of load, including daily, weekly and annual seasonal patterns, as well as autoregressive effects, weather and holiday impacts, and socio-economic non-stationarities, presents significant modeling challenges. To address these challenges, we propose a novel forecasting method using Generalized Additive Models (GAMs) built from interpretable P-splines that is enhanced with autoregressive post-processing. This model incorporates smoothed temperatures, Error-Trend-Seasonal (ETS) modeled and persistently forecasted non-stationary socio-economic states, a nuanced representation of effects from vacation periods, fixed date and weekday holidays, and seasonal information as inputs. The proposed model is evaluated using load data from 24 European countries over more than 9 years (2015-2024). This analysis demonstrates that the model not only has significantly enhanced forecasting accuracy compared to state-of-the-art methods but also offers valuable insights into the influence of individual components on predicted load, given its full interpretability. Achieving performance akin to day-ahead Transmission System Operator (TSO) forecasts, with computation times of just a few seconds for several years of hourly data, underscores the potential of the model for practical application in the power system industry.