News and Load: Social and Economic Drivers of Regional Multi-horizon Electricity Demand Forecasting

TL;DR

This study integrates social and economic variables derived from news analysis into multi-horizon electricity demand forecasting, revealing their significant influence and improving forecast accuracy in UK regions.

Contribution

It introduces a novel approach using NLP on news data to incorporate social factors into electricity demand models, enhancing forecasting performance.

Findings

Textual features relate to conflicts, pandemic, and energy markets.

Causal links between news content and demand validated.

Economic and social factors influence demand differently across regions.

Abstract

The relationship between electricity demand and variables such as economic activity and weather patterns is well established. However, this paper explores the connection between electricity demand and social aspects. It further embeds dynamic information about the state of society into energy demand modelling and forecasting approaches. Through the use of natural language processing on a large news corpus, we highlight this important link. This study is conducted in five regions of the UK and Ireland and considers multiple time horizons from 1 to 30 days. It also considers economic variables such as GDP, unemployment and inflation. The textual features used in this study represent central constructs from the word frequencies, topics, word embeddings extracted from the news. The findings indicate that: 1) the textual features are related to various contents, such as military conflicts, transportation, the global pandemic, regional economics, and the international energy market. They exhibit causal relationships with regional electricity demand, which are validated using Granger causality and Double Machine Learning methods. 2) Economic indicators play a more important role in the East Midlands and Northern Ireland, while social indicators are more influential in the West Midlands and the South West of England. 3) The use of these factors improves deterministic forecasting by around 6%.