Electricity Virtual Bidding Strategy Via Entropy-Regularized Stochastic Control Method

Paper: arXiv 2303.02303

Authors: Zhou Fang

Abstract

We propose a virtual bidding strategy by modeling the price differences between the day-ahead market and the real-time market as Brownian motion with drift, where the drift rate and volatility are functions of meteorological variables. We then transform the virtual bidding problem into a mean-variance portfolio management problem, where we approach the mean-variance portfolio management problem by using the exploratory mean-variance portfolio management framework

Complexity vs Empirical Score

• Math Complexity: 7.5/10
• Empirical Rigor: 5.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents a mathematically sophisticated approach by modeling electricity price differentials via stochastic control and entropy-regularized exploratory mean-variance frameworks incorporating meteorological covariates. While the theoretical formulation is strong and novel for energy markets, the empirical validation relies on basic backtesting assumptions that require deeper statistical rigor.

Research Flowchart

  flowchart TD
    A[Research Goal: Optimize Electricity Virtual Bidding Strategy] --> B[Data Inputs: Meteorological Variables & Market Prices]
    B --> C[Model Price Differences as Brownian Motion with Drift & Volatility]
    C --> D[Transform to Mean-Variance Portfolio Management Problem]
    D --> E[Apply Entropy-Regularized Exploratory Stochastic Control]
    E --> F[Outcomes: Optimal Bidding Policy balancing Profit & Risk]