Assessing the Performance-Efficiency Trade-off of Foundation Models in Probabilistic Electricity Price Forecasting

• URL: http://arxiv.org/abs/2604.14739v1
• Date: Thu, 16 Apr 2026 07:53:38 GMT
• Title: Assessing the Performance-Efficiency Trade-off of Foundation Models in Probabilistic Electricity Price Forecasting
• Abstract summary: Large-scale renewable energy deployment introduces pronounced volatility into the electricity system, turning grid operation into a complex optimization problem.<n> Accurate electricity price forecasting (EPF) is essential not only to support operational decisions, but also to reduce economic risk and improve market efficiency.<n>It remains an open question which models to employ to produce accurate forecasts. Should these be task-specific machine learning (ML) models or Time Series Foundation Models (TSFMs)?
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale renewable energy deployment introduces pronounced volatility into the electricity system, turning grid operation into a complex stochastic optimization problem. Accurate electricity price forecasting (EPF) is essential not only to support operational decisions, such as optimal bidding strategies and balancing power preparation, but also to reduce economic risk and improve market efficiency. Probabilistic forecasts are particularly valuable because they quantify uncertainty stemming from renewable intermittency, market coupling, and regulatory changes, enabling market participants to make informed decisions that minimize losses and optimize expected revenues. However, it remains an open question which models to employ to produce accurate forecasts. Should these be task-specific machine learning (ML) models or Time Series Foundation Models (TSFMs)? In this work, we compare four models for day-ahead probabilistic EPF (PEPF) in European bidding zones: a deterministic NHITS backbone with Quantile-Regression Averaging (NHITS+QRA) and a conditional Normalizing-Flow forecaster (NF) are compared with two TSFMs, namely Moirai and ChronosX. On the one hand, we find that TSFMs outperform task-specific deep learning models trained from scratch in terms of CRPS, Energy Score, and predictive interval calibration across market conditions. On the other hand, we find that well-configured task-specific models, particularly NHITS combined with QRA, achieve performance very close to TSFMs, and in some scenarios, such as when supplied with additional informative feature groups or adapted via few-shot learning from other European markets, they can even surpass TSFMs. Overall, our findings show that while TSFMs offer expressive modeling capabilities, conventional models remain highly competitive, emphasizing the need to weigh computational expense against marginal performance improvements in PEPF.

Related papers

• Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models? [1.9336815376402718]
  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.<n>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.<n>Only the TabPFN models consistently and significantly outperform the benchmarks across all three markets.
  arXiv  Detail & Related papers  (2026-08-31T12:43:04Z)
• LEAF: A Living Benchmark for Event-Augmented Forecasting [78.94019460534442]
  LEAF is the first living benchmark for event-augmented forecasting tasks.<n>We evaluate state-of-the-art proprietary and open-weight LLMs.<n>We find that LLMs achieve better performance on equities they confidently identify as more predictable.
  arXiv  Detail & Related papers  (2026-05-09T03:17:59Z)
• Regression Models Meet Foundation Models: A Hybrid-AI Approach to Practical Electricity Price Forecasting [39.91788164419845]
  We propose FutureBoosting, a novel paradigm that enhances regression-based forecasts.<n>We instantiate this paradigm into a lightweight, plug-and-play framework for electricity price forecasting.<n>Our framework consistently outperforms state-of-the-art TSFMs and regression baselines.
  arXiv  Detail & Related papers  (2026-03-06T02:06:46Z)
• Day-Ahead Electricity Price Forecasting for Volatile Markets Using Foundation Models with Regularization Strategy [2.6110235246137328]
  Time series foundation models (TSFMs) have shown strong performance in general time series forecasting tasks.<n>This paper presents a spike regularization strategy and evaluates a wide range of TSFMs against traditional statistical and DL models.<n>Results demonstrate that TSFMs consistently outperform traditional approaches, achieving up to 37.4% improvement in MAPE.
  arXiv  Detail & Related papers  (2026-02-05T08:20:50Z)
• Exploring the Interpretability of Forecasting Models for Energy Balancing Market [43.548887305614585]
  The balancing market in the energy sector plays a critical role in physically and financially balancing the supply and demand.<n>While complex machine learning models can achieve high accuracy, their black-box nature severely limits the model interpretability.<n>This paper explores the trade-off between model accuracy and interpretability for the energy balancing market.
  arXiv  Detail & Related papers  (2026-01-19T12:56:41Z)
• Optimization of Deep Learning Models for Dynamic Market Behavior Prediction [4.594360512414794]
  We study multi-horizon demand forecasting on e-commerce transactions using the UCI Online Retail II dataset.<n>We present a hybrid sequence model that combines multi-scale temporal convolutions, a gated recurrent module, and time-aware self-attention.<n>Results show consistent accuracy gains and improved on peak/holiday periods.
  arXiv  Detail & Related papers  (2025-11-24T13:30:52Z)
• Bayesian Neural Networks with Monte Carlo Dropout for Probabilistic Electricity Price Forecasting [0.0]
  This work presents a framework for probabilistic electricity price forecasting using Bayesian neural networks (BNNs) with Monte Carlo (MC) dropouts.<n>A critical assessment and comparison with the benchmark model, namely: generalized autoregressive conditional heteroskedasticity with a variable (GARCHX) and the LASSO estimated auto-regressive model (LEAR)
  arXiv  Detail & Related papers  (2025-11-12T13:33:28Z)
• Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models [50.877082340479085]
  We study how different Time Series Foundational Models (TSFMs) exhibit specialized performance profiles across various forecasting settings.<n>We propose Synapse, a novel arbitration framework for TSFMs.<n>Results demonstrate that Synapse consistently outperforms other popular ensembling techniques as well as individual TSFMs.
  arXiv  Detail & Related papers  (2025-11-07T18:01:51Z)
• Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models [20.57107693396709]
  Building energy systems critically depend on the predictive accuracy of relevant time-series models.<n>This paper investigates the applicability and fine-tuning strategies of time-series foundation models (TSFMs) in building energy forecasting.
  arXiv  Detail & Related papers  (2025-05-31T16:38:29Z)
• BreakGPT: Leveraging Large Language Models for Predicting Asset Price Surges [55.2480439325792]
  This paper introduces BreakGPT, a novel large language model (LLM) architecture adapted specifically for time series forecasting and the prediction of sharp upward movements in asset prices. We showcase BreakGPT as a promising solution for financial forecasting with minimal training and as a strong competitor for capturing both local and global temporal dependencies.
  arXiv  Detail & Related papers  (2024-11-09T05:40:32Z)
• F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data [65.6499834212641]
  We formulate the demand prediction as a meta-learning problem and develop the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm. By considering domain similarities through task-specific metadata, our model improved generalization, where the excess risk decreases as the number of training tasks increases. Compared to existing state-of-the-art models, our method demonstrates a notable improvement in demand prediction accuracy, reducing the Mean Absolute Error by 26.24% on an internal vending machine dataset and by 1.04% on the publicly accessible JD.com dataset.
  arXiv  Detail & Related papers  (2024-06-23T21:28:50Z)
• Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction [54.21695754082441]
  Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility. Current solutions to multi-step stock price prediction are mostly designed for single-step, classification-based predictions. We combine a deep hierarchical variational-autoencoder (VAE) and diffusion probabilistic techniques to do seq2seq stock prediction. Our model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance.
  arXiv  Detail & Related papers  (2023-08-18T16:21:15Z)
• Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models [48.87381259980254]
  We document the capability of large language models (LLMs) like ChatGPT to predict stock market reactions from news headlines without direct financial training.<n>Using post-knowledge-cutoff headlines, GPT-4 captures initial market responses, achieving approximately 90% portfolio-day hit rates for the non-tradable initial reaction.
  arXiv  Detail & Related papers  (2023-04-15T19:22:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.