Technology Category
Reasoning under Uncertainty: Stochastic OptimizationSearch and Optimization: Mixed Discrete/Continuous SearchPlanning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
Optimal Trading of a Charging-Station Company in Auction Markets for Electricity
🤖 AI Summary
This study addresses the day-ahead and intra-day stochastic optimal trading decision-making problem for electric-hydrogen dual-mode charging stations (Chargcos), jointly considering electricity price uncertainty, load responsiveness, and multi-energy arbitrage. Methodologically, it proposes: (1) a GAN-based scenario generation and clustering approach to enhance joint modeling accuracy of price–demand uncertainties; (2) an RF–linear regression hybrid modeling framework to capture the nonlinear dependence between charging/hydrogen-production loads and electricity prices; and (3) an improved L-shaped algorithm incorporating infeasibility handling mechanisms and multiple acceleration strategies to significantly reduce computational complexity of stochastic mixed-integer linear programming (MILP). Numerical experiments demonstrate that the proposed method improves trading revenue across diverse scenarios while maintaining risk control, and achieves substantial gains in computational efficiency. The framework provides a scalable, market-ready decision-support paradigm for integrated energy stations participating in electricity markets.
Technology Category
Application Category
📝 Abstract
This paper addresses a charging-station company (Chargco) for electric and hydrogen vehicles. The optimal trading of the Chargco in day-ahead and intraday auction markets for electricity is modeled as a stochastic Mixed-Integer Quadratic Program (MIQP). We propose a series of linearization and reformulation techniques to reformulate the stochastic MIQP as a mixed-integer linear program (MILP). To model stochasticity, we utilize generative adversarial networks to cluster electricity market price scenarios. Additionally, a combination of random forests and linear regression is employed to model the relationship between Chargco electricity and hydrogen loads and their selling prices. Finally, we propose an Improved L-Shaped Decomposition (ILSD) algorithm to solve our stochastic MILP. Our ILSD algorithm not only addresses infeasibilities through an innovative approach but also incorporates warm starts, valid inequalities and multiple generation cuts, thereby reducing computational complexity. Numerical experiments illustrate the Chargco trading using our proposed stochastic MILP and its solution algorithm.
Problem
Research questions and friction points this paper is trying to address.
Electric Vehicle Charging Stations
Optimal Trading Strategy
Demand Prediction
Innovation
Methods, ideas, or system contributions that make the work stand out.
Generative Adversarial Networks
Improved L-shaped Decomposition
Predictive Modeling
🔎 Similar Papers
No similar papers found.
