Feature-driven reinforcement learning for photovoltaic in continuous intraday trading

2025-10-15 · Arega Getaneh Abate, Xiao-Bing Zhang, Xiufeng Liu, Ruyu Liu arxiv

Sequential intraday electricity trading allows photovoltaic (PV) operators to reduce imbalance settlement costs as forecasts improve throughout the day. Yet deployable trading policies must jointly handle forecast uncertainty, intraday prices, liquidity, and the asymmetric economics of PV imbalance exposure. This paper proposes a feature-driven reinforcement learning (FDRL) framework for intraday PV trading in the Nordic market. Its main methodological contribution is a corrected reward that evaluates performance relative to a no-trade baseline, removing policy-independent noise that can otherwise push reinforcement learning toward inactive policies in high-price regimes. The framework combines this objective with a predominantly linear policy and a closed-form execution surrogate for efficient, interpretable training. In a strict walk-forward evaluation over 2021-2024 across four Nordic bidding zones (DK1, DK2, SE3, SE4), the method delivers statistically significant profit improvements over the spot-only baseline in every zone. Portfolio experiments show that a pooled cross-zone policy can match zone-specific models, while transfer-learning results indicate a two-cluster market structure and effective deployment in new zones with limited local data. The proposed framework offers an interpretable and computationally practical way to reduce imbalance costs, while the transfer results provide guidance for scaling strategies across bidding zones with different market designs.

📄 PDF Abstract BibTeX arXiv:2510.16021

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

A Reinforcement Learning Approach for the Continuous Electricity Market of Germany: Trading from the Perspective of a Wind Park Operator

2021-11-26 · Malte Lehna, Björn Hoppmann, René Heinrich, Christoph Scholz

With the rising extension of renewable energies, the intraday electricity markets have recorded a growing popularity amongst traders as well as electric utilities to cope with the induced volatility of the energy supply.…

Deep Reinforcement Learning

Deep reinforcement learning with positional context for intraday trading

2024-06-12 · Sven Goluža, Tomislav Kovačević, Tessa Bauman, Zvonko Kostanjčar

Deep reinforcement learning (DRL) is a well-suited approach to financial decision-making, where an agent makes decisions based on its trading strategy developed from market observations. Existing DRL intraday trading str…

Decision Making Deep Reinforcement Learning Feature Importance reinforcement-learning+1

Feature-driven reinforcement learning for photovoltaic in continuous intraday trading

Code (0)

Tasks

Similar Papers 제목 키워드 기반

A Reinforcement Learning Approach for the Continuous Electricity Market of Germany: Trading from the Perspective of a Wind Park Operator

Deep reinforcement learning with positional context for intraday trading

The Living Forecast: Evolving Day-Ahead Predictions into Intraday Reality

Forecasting Intraday Power Output by a Set of PV Systems using Recurrent Neural Networks and Physical Covariates

Intra-day Solar and Power Forecast for Optimization of Intraday Market Participation