Short-Term Electricity Load Forecasting Using the Temporal Fusion Transformer: Effect of Grid Hierarchies and Data Sources

TL;DR

This study evaluates the Temporal Fusion Transformer (TFT) for short-term electricity load forecasting across different grid levels and horizons, finding notable improvements at substation and week-ahead levels compared to LSTM models.

Contribution

It demonstrates the application of TFT to multi-level, multi-horizon load forecasting and compares its performance to LSTM models, highlighting its strengths and limitations.

Findings

TFT performs similarly to LSTM for day-ahead grid forecasting.

TFT significantly improves accuracy at substation level with aggregation.

TFT outperforms LSTM in week-ahead load forecasting.

Abstract

Recent developments related to the energy transition pose particular challenges for distribution grids. Hence, precise load forecasts become more and more important for effective grid management. Novel modeling approaches such as the Transformer architecture, in particular the Temporal Fusion Transformer (TFT), have emerged as promising methods for time series forecasting. To date, just a handful of studies apply TFTs to electricity load forecasting problems, mostly considering only single datasets and a few covariates. Therefore, we examine the potential of the TFT architecture for hourly short-term load forecasting across different time horizons (day-ahead and week-ahead) and network levels (grid and substation level). We find that the TFT architecture does not offer higher predictive performance than a state-of-the-art LSTM model for day-ahead forecasting on the entire grid. However, the results display significant improvements for the TFT when applied at the substation level with a subsequent aggregation to the upper grid-level, resulting in a prediction error of 2.43% (MAPE) for the best-performing scenario. In addition, the TFT appears to offer remarkable improvements over the LSTM approach for week-ahead forecasting (yielding a predictive error of 2.52% (MAPE) at the lowest). We outline avenues for future research using the TFT approach for load forecasting, including the exploration of various grid levels (e.g., grid, substation, and household level).