Load Forecasting for Households and Energy Communities: Are Deep Learning Models Worth the Effort?

2025-01-09

AI Summary

Accurate and cost-effective short-term load forecasting (STLF) remains challenging for households and energy communities, particularly under data-scarce conditions. Method: This study systematically evaluates LSTM, xLSTM, Transformer, k-Nearest Neighbors (k-NN), and persistence models on real-world measurements from a 50-household community. It introduces a synthetic-load-based pretraining strategy and quantifies the relationship between aggregation level and economic benefit in storage-integrated community settings. Contribution/Results: Under small-sample regimes (≤6 months), the simple persistence model significantly outperforms deep learning models—challenging the assumption that higher model complexity implies superior accuracy. The proposed pretraining reduces average normalized mean absolute error (nMAE) by 1.28 percentage points over the first nine months. Aggregation-aware optimization yields an additional 1.1-percentage-point nMAE reduction and ~€600 annual savings per community. These findings provide empirical guidance and methodological support for lightweight, edge-deployable STLF and model selection under limited data.

Technology Category

Machine Learning: Learning on the Edge & Model CompressionSearch and Optimization: Learning to SearchPlanning, Routing, and Scheduling: Planning with Language Models

Application Category

Web Mining and Content Analysis: Large pretrained models with web dataEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systemsGraph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Accurate load forecasting is crucial for predictive control in many energy domain applications, with significant economic and ecological implications. To address these implications, this study provides an extensive benchmark of state-of-the-art deep learning models for short-term load forecasting in energy communities. Namely, LSTM, xLSTM, and Transformers are compared with benchmarks such as KNNs, synthetic load models, and persistence forecasting models. This comparison considers different scales of aggregation (e.g., number of household loads) and varying training data availability (e.g., training data time spans). Further, the impact of transfer learning from synthetic (standard) load profiles and the deep learning model size (i.e., parameter count) is investigated in terms of forecasting error. Implementations are publicly available and other researchers are encouraged to benchmark models using this framework. Additionally, a comprehensive case study, comprising an energy community of 50 households and a battery storage demonstrates the beneficial financial implications of accurate predictions. Key findings of this research include: (1) Simple persistence benchmarks outperform deep learning models for short-term load forecasting when the available training data is limited to six months or less; (2) Pretraining with publicly available synthetic load profiles improves the normalized Mean Absolute Error (nMAE) by an average of 1.28%pt during the first nine months of training data; (3) Increased aggregation significantly enhances the performance of deep learning models relative to persistence benchmarks; (4) Improved load forecasting, with an nMAE reduction of 1.1%pt, translates to an economic benefit of approximately 600EUR per year in an energy community comprising 50 households.

Problem

• Energy Prediction
• Model Complexity
• Energy Management

Innovation

• Predictive Accuracy
• Pre-training
• Economic Benefits