Price-Sensitive Machine Learning for Electricity Virtual Bidding

Summary

The paper presents a risk-constrained portfolio optimization approach for virtual bidding in U.S. wholesale electricity markets. It forecasts inter-hour locational marginal price spreads with a recurrent neural network, using dependencies created by market clearing. A constrained gradient boosting tree models how those spreads respond to net virtual bids, allowing the strategy to account for the effect its own positions may have on prices.

Empirical analysis across PJM, ISO-NE, and CAISO finds that portfolios explicitly modeling price sensitivity outperform portfolios that ignore it. The paper also reports Sharpe ratios for all three markets above the S&P 500’s, and finds lower efficiency in CAISO’s two-settlement system than in PJM and ISO-NE. These results connect strategy design with market-efficiency assessment. The supplied summary does not give sample dates, transaction-cost assumptions, risk constraint details, or out-of-sample validation, so it is insufficient to judge whether reported performance would persist in live trading.

Key ideas

• Virtual bidding is framed as risk-constrained portfolio optimization for a proprietary trading firm.
• A recurrent neural network forecasts inter-hour locational marginal price spreads.
• A constrained gradient boosting model estimates how net virtual bids affect spread prices.
• Explicitly modeling price sensitivity improves reported portfolio performance across PJM, ISO-NE, and CAISO.
• The analysis reports lower two-settlement efficiency in CAISO than in PJM and ISO-NE.

Tags

# Machine Learning-Driven Virtual Bidding with Electricity Market Efficiency Analysis


# Machine Learning-Driven Virtual Bidding with Electricity Market Efficiency Analysis









This paper develops a machine learning-driven portfolio optimization framework for virtual bidding in electricity markets considering both risk constraint and price sensitivity. The algorithmic trading strategy is developed from the perspective of a proprietary trading firm to maximize profit. A recurrent neural network-based Locational Marginal Price (LMP) spread forecast model is developed by leveraging the inter-hour dependencies of the market clearing algorithm. The LMP spread sensitivity with respect to net virtual bids is modeled as a monotonic function with the proposed constrained gradient boosting tree. We leverage the proposed algorithmic virtual bid trading strategy to evaluate both the profitability of the virtual bid portfolio and the efficiency of U.S. wholesale electricity markets. The comprehensive empirical analysis on PJM, ISO-NE, and CAISO indicates that the proposed virtual bid portfolio optimization strategy considering the price sensitivity explicitly outperforms the one that neglects the price sensitivity. The Sharpe ratio of virtual bid portfolios for all three electricity markets are much higher than that of the S&P 500 index. It was also shown that the efficiency of CAISO's two-settlement system is lower than that of PJM and ISO-NE.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.