analiza aiqbench
This study evaluates whether foundation models can universally supersede specialized benchmarks for electricity price forecasting across multiple European markets. While TabPFN variants demonstrated superior statistical accuracy in zero-shot mode, their economic viability in battery arbitrage depends heavily on risk tolerance and bidding strategies rather than offering a one-size-fits-all solution. The findings suggest that general-purpose foundation models remain complementary tools rather than complete replacements for domain-specific forecasting architectures in energy trading contexts.
Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models?
arXiv:2609.00089v1 Announce Type: new Abstract: Foundation models promise accurate forecasts with little or no task-specific training, but whether they can replace models designed specifically for electricity price forecasting remains unclear. We compare nine variants from five foundation model families, evaluated in zero-shot mode, with two state-of-the-art electricity price forecasting benchmarks in Germany, Poland, and Spain over 2021-2025. Their performance is assessed in terms of point and probabilistic forecasting accuracy, as well as economic value in battery energy storage arbitrage. Only the TabPFN models consistently and significantly outperform the benchmarks across all three markets and all statistical measures. However, this statistical dominance does not translate directly into economic dominance: TabPFN performs best under unlimited bids and riskier quantile-based strategies, whereas the Distributional Deep Neural Network benchmark is more profitable when risk tolerance is lower. Thus, foundation models cannot universally replace market-specific models, and their value depends on both model architecture and the decision problem.
Title:Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models?
Abstract:Foundation models promise accurate forecasts with little or no task-specific training, but whether they can replace models designed specifically for electricity price forecasting remains unclear. We compare nine variants from five foundation model families, evaluated in zero-shot mode, with two state-of-the-art electricity price forecasting benchmarks in Germany, Poland, and Spain over 2021-2025. Their performance is assessed in terms of point and probabilistic forecasting accuracy, as well as economic value in battery energy storage arbitrage. Only the TabPFN models consistently and significantly outperform the benchmarks across all three markets and all statistical measures. However, this statistical dominance does not translate directly into economic dominance: TabPFN performs best under unlimited bids and riskier quantile-based strategies, whereas the Distributional Deep Neural Network benchmark is more profitable when risk tolerance is lower. Thus, foundation models cannot universally replace market-specific models, and their value depends on both model architecture and the decision problem.
Machine Learning (cs.LG); Econometrics (econ.EM)
arXiv:2609.00089 [cs.LG]
(or arXiv:2609.00089v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.00089 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 257 cuvinte
