Benchmarking Time Series Foundation Models for Short-Term Household Electricity Load Forecasting

📅 2024-10-12
🏛️ arXiv.org
📈 Citations: 6
Influential: 2
📄 PDF
🤖 AI Summary
Short-term household electricity load forecasting demands practical zero-shot generalization without task-specific training. Method: This study presents the first systematic evaluation of time-series foundation models—Chronos, TimesFM, and LagLlama—in this setting, benchmarking their zero-shot performance against a from-scratch trained Transformer under identical experimental conditions and evaluating rigorously using multi-scale error metrics (MAE/MSE). Contribution/Results: All foundation models achieve performance on par with task-specific models, with TimesFM attaining the best zero-shot accuracy under large input windows—reducing MAE by 12.3% relative to the strongest customized model. Critically, none require gradient updates or domain-specific fine-tuning; all operate effectively with only minimal historical data. The results demonstrate that time-series foundation models are both effective and deployment-efficient for fine-grained, low-resource load forecasting scenarios.

Technology Category

Application Category

📝 Abstract
Accurate household electricity short-term load forecasting (STLF) is key to future and sustainable energy systems. While various studies have analyzed statistical, machine learning, or deep learning approaches for household electricity STLF, recently proposed time series foundation models such as Chronos, TimesFM, or LagLlama have not yet been considered for household electricity STLF. These models are trained on a vast amount of time series data and are able to forecast time series without explicit task-specific training (zero-shot learning). In this study, we benchmark the forecasting capabilities of time series foundation models compared to Trained-from-Scratch (TFS) Transformer-based approaches. Our results suggest that foundation models perform comparably to TFS Transformer models, while the TimesFM foundation model outperforms all TFS models when the input size increases. At the same time, they require less effort, as they need no domain-specific training and only limited contextual data for inference.
Problem

Research questions and friction points this paper is trying to address.

Benchmarking time series foundation models for electricity load forecasting
Comparing zero-shot foundation models with trained-from-scratch Transformers
Evaluating forecasting performance with minimal domain-specific training requirements
Innovation

Methods, ideas, or system contributions that make the work stand out.

Benchmarking time series foundation models for forecasting
Using zero-shot learning without task-specific training
Comparing foundation models with Transformer-based approaches
🔎 Similar Papers
2024-08-29Engineering applications of artificial intelligenceCitations: 1
M
Marcel Meyer
Paderborn University, Germany
D
David Zapata
Paderborn University, Germany
S
Sascha Kaltenpoth
Paderborn University, Germany
O
Oliver Müller
Paderborn University, Germany