# Algorithmic Bidding for Virtual Trading in Electricity Markets

arXiv: https://arxiv.org/abs/1802.03010 · HTML: https://mlsanity.com/paper/1802.03010/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2018.

## Built on by (most cited first, 9 of 9)

- [Machine Learning-Driven Virtual Bidding with Electricity Market Efficiency Analysis](https://mlsanity.com/paper/2104.02754/) (2021)
- [Massively Digitized Power Grid: Opportunities and Challenges of Use-inspired AI](https://mlsanity.com/paper/2205.05180/) (2022)
- [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)
- [A Data-Driven Convergence Bidding Strategy Based on Reverse Engineering of Market Participants' Performance: A Case of California ISO](https://mlsanity.com/paper/2109.09238/) (2021)
- [Energy Storage Arbitrage in Two-settlement Markets: A Transformer-Based Approach](https://mlsanity.com/paper/2404.17683/) (2024)
- [AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusion](https://mlsanity.com/paper/2608.26896/) (2026)
- [A General Stochastic Optimization Framework for Convergence Bidding](https://mlsanity.com/paper/2210.06543/) (2022)
- [How to Use Reinforcement Learning to Facilitate Future Electricity Market Design? Part 2: Method and Applications](https://mlsanity.com/paper/2305.06921/) (2023)
- [Learn to Bid as a Price-Maker Wind Power Producer](https://mlsanity.com/paper/2503.16107/) (2025)

## Abstract (arXiv)

We consider the problem of optimal bidding for virtual trading in two-settlement electricity markets. A virtual trader aims to arbitrage on the differences between day-ahead and real-time market prices; both prices, however, are random and unknown to market participants. An online learning algorithm is proposed to maximize the cumulative payoff over a finite number of trading sessions by allocating the trader's budget among his bids for K options in each session. It is shown that the proposed algorithm converges, with an almost optimal convergence rate, to the global optimal corresponding to the case when the underlying price distribution is known. The proposed algorithm is also generalized for trading strategies with a risk measure. By using both cumulative payoff and Sharpe ratio as performance metrics, evaluations were performed based on historical data spanning ten year period of NYISO and PJM markets. It was shown that the proposed strategy outperforms standard benchmarks and the S&P 500 index over the same period.