# Feature-driven reinforcement learning for photovoltaic in continuous intraday trading

arXiv: https://arxiv.org/abs/2510.16021 · HTML: https://mlsanity.com/paper/2510.16021/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 7 of 7)

- [A Deep Reinforcement Learning Framework for Continuous Intraday Market Bidding](https://mlsanity.com/paper/2004.05940/) (2020)
- [Feature-driven Improvement of Renewable Energy Forecasting and Trading](https://mlsanity.com/paper/1907.07580/) (2019)
- [Learning from Past Bids to Participate Strategically in Day-Ahead Electricity Markets](https://mlsanity.com/paper/1811.06113/) (2018)
- [A Reinforcement Learning Approach for the Continuous Electricity Market of Germany: Trading from the Perspective of a Wind Park Operator](https://mlsanity.com/paper/2111.13609/) (2021)
- [Online Decision Making for Trading Wind Energy](https://mlsanity.com/paper/2209.02009/) (2022)
- [Learning to Bid in Forward Electricity Markets Using a No-Regret Algorithm](https://mlsanity.com/paper/2404.03314/) (2024)
- [Feature-Driven Strategies for Trading Wind Power and Hydrogen](https://mlsanity.com/paper/2310.01385/) (2023)

## Abstract (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.