OrderFusion: Encoding Orderbook for End-to-End Probabilistic Intraday Electricity Price Forecasting
This addresses the problem of managing market uncertainties for electricity traders by improving probabilistic price forecasting, though it appears incremental as it builds on existing time-series models with domain-specific adaptations.
The paper tackled probabilistic forecasting of intraday electricity prices by proposing OrderFusion, an end-to-end model that encodes orderbook data to handle market uncertainties, achieving consistent outperformance over baselines in German and Austrian markets with only 4,872 parameters.
Probabilistic forecasting of intraday electricity prices is essential to manage market uncertainties. However, current methods rely heavily on domain feature extraction, which breaks the end-to-end training pipeline and limits the model's ability to learn expressive representations from the raw orderbook. Moreover, these methods often require training separate models for different quantiles, further violating the end-to-end principle and introducing the quantile crossing issue. Recent advances in time-series models have demonstrated promising performance in general forecasting tasks. However, these models lack inductive biases arising from buy-sell interactions and are thus overparameterized. To address these challenges, we propose an end-to-end probabilistic model called OrderFusion, which produces interaction-aware representations of buy-sell dynamics, hierarchically estimates multiple quantiles, and remains parameter-efficient with only 4,872 parameters. We conduct extensive experiments and ablation studies on price indices (ID1, ID2, and ID3) using three years of orderbook in high-liquidity (German) and low-liquidity (Austrian) markets. The experimental results demonstrate that OrderFusion consistently outperforms multiple competitive baselines across markets, and ablation studies highlight the contribution of its individual components. The project page is at: https://runyao-yu.github.io/OrderFusion/.