Load forecasting for households and energy communities: Are deep learning models worth the effort?

Energy communities (ECs) play a key role in enabling local demand shifting and enhancing self-sufficiency, as energy systems transition toward decentralized structures with high shares of renewable generation. To optimally operate them, accurate short-term load forecasting is essential, particularly for implementing demand-side management strategies. With the recent rise of deep learning methods, data-driven forecasting has gained significant attention, however, its role in optimizing energy communities remains insufficiently explored under varying conditions. Therefore, this study evaluates the effectiveness of state-of-the-art deep learning models—including Long Short-Term Memory (LSTM), extended LSTM (xLSTM), and Transformer architectures—compared to traditional benchmarks such as K-Nearest Neighbors (KNN) and persistence prediction, across different community sizes, historical data availability, and model complexity. Additionally, we assess the benefits of transfer learning using publicly available synthetic load profiles. On average, transfer learning improves the normalized mean absolute error by 1.97 percentage points when only two months of training data are available. Interestingly, for less than six months of training data, simple persistence predictions outperform deep learning architectures in forecast accuracy, indicating their suitability in data-scarce scenarios. The practical value of improved forecasting is demonstrated using model predictive control for ECs with a shared battery energy storage system. For an energy community with 50 households, the most accurate deep learning model achieves an average reduction in financial energy costs of 8.06%. Notably, the simple persistence and KNN approaches yield cost savings that are not statistically significantly different to deep learning methods (paired t-test, all p > 0.99). All implementations are publicly available to facilitate reproducibility. These findings offer actionable insights for ECs, and they highlight when the additional complexity of deep learning is warranted by performance gains.