Causal Inference in Energy Demand Prediction

TL;DR

This paper introduces a structural causal model for energy demand prediction that incorporates causal relationships among weather and calendar factors, leading to improved accuracy and robustness over traditional methods.

Contribution

It presents a novel causal framework and Bayesian model that leverage causal insights to enhance energy demand forecasting performance.

Findings

Causal model reveals temperature's season-dependent impact on demand.

Demand variance is lower in winter due to decoupling of temperature and activity.

Achieves 3.84% MAPE, outperforming previous methods.

Abstract

Energy demand prediction is critical for grid operators, industrial energy consumers, and service providers. Energy demand is influenced by multiple factors, including weather conditions (e.g. temperature, humidity, wind speed, solar radiation), and calendar information (e.g. hour of day and month of year), which further affect daily work and life schedules. These factors are causally interdependent, making the problem more complex than simple correlation-based learning techniques satisfactorily allow for. We propose a structural causal model that explains the causal relationship between these variables. A full analysis is performed to validate our causal beliefs, also revealing important insights consistent with prior studies. For example, our causal model reveals that energy demand responds to temperature fluctuations with season-dependent sensitivity. Additionally, we find that energy demand exhibits lower variance in winter due to the decoupling effect between temperature changes and daily activity patterns. We then build a Bayesian model, which takes advantage of the causal insights we learned as prior knowledge. The model is trained and tested on unseen data and yields state-of-the-art performance in the form of a 3.84 percent MAPE on the test set. The model also demonstrates strong robustness, as the cross-validation across two years of data yields an average MAPE of 3.88 percent.