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

arXiv: https://arxiv.org/abs/2305.10559 · HTML: https://mlsanity.com/paper/2305.10559/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 46 references that are in the map.
- First posted on arXiv 17 May 2023.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Darts: User-Friendly Modern Machine Learning for Time Series](https://mlsanity.com/paper/2110.03224/) (2021)
- [Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges](https://mlsanity.com/paper/1802.04117/) (2018)
- [Augmented cross-selling through explainable AI -- a case from energy retailing](https://mlsanity.com/paper/2208.11404/) (2022)

## Built on by (most cited first, 13 of 13)

- [Kolmogorov-Arnold Recurrent Network for Short Term Load Forecasting Across Diverse Consumers](https://mlsanity.com/paper/2501.06965/) (2025)
- [Transformer Training Strategies for Forecasting Multiple Load Time Series](https://mlsanity.com/paper/2306.10891/) (2023)
- [Short-Term Electricity-Load Forecasting by Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2408.16202/) (2024)
- [Transfer learning for day-ahead load forecasting: a case study on European national electricity demand time series](https://mlsanity.com/paper/2310.15555/) (2023)
- [Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models](https://mlsanity.com/paper/2604.28149/) (2026)
- [Transfer Learning in Transformer-Based Demand Forecasting For Home Energy Management System](https://mlsanity.com/paper/2310.19159/) (2023)
- [Overcoming Anchoring Bias: The Potential of AI and XAI-based Decision Support](https://mlsanity.com/paper/2405.04972/) (2024)
- [Transfer Learning on Transformers for Building Energy Consumption Forecasting -- A Comparative Study](https://mlsanity.com/paper/2410.14107/) (2024)
- [Electricity Demand Forecasting in Future Grid States: A Digital Twin-Based Simulation Study](https://mlsanity.com/paper/2503.04757/) (2025)
- [Explainable time-series forecasting with sampling-free SHAP for Transformers](https://mlsanity.com/paper/2512.20514/) (2025)
- [Meta-Regression Analysis of Errors in Short-Term Electricity Load Forecasting](https://mlsanity.com/paper/2305.18550/) (2023)
- [AutoPQ: Automating Quantile estimation from Point forecasts in the context of sustainability](https://mlsanity.com/paper/2412.00419/) (2024)
- [Benchmarking Transformer and xLSTM for Time-Series Forecasting of Heat Consumption](https://mlsanity.com/paper/2605.09722/) (2026)

## Abstract (arXiv)

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).