Adversarially and Distributionally Robust Virtual Energy Storage Systems via the Scenario Approach

2025-11-12

AI Summary

Parking lot managers (PLMs) face significant challenges in robustly aggregating electric vehicle (EV) batteries for virtual energy storage services under high uncertainty in EV departure times and charging limits. Method: We propose a data-driven distributionally robust optimization (DRO) framework that integrates scenario-based modeling with a Wasserstein ambiguity set to characterize uncertainty. A tunable scenario relaxation mechanism enables precise profit–risk trade-offs, while convex reformulation ensures computational efficiency. Contribution/Results: This work is the first to embed Wasserstein DRO into coordinated EV cluster scheduling, providing tight finite-sample guarantees on constraint satisfaction. Extensive experiments demonstrate that the proposed model strictly satisfies both physical (e.g., battery dynamics, power limits) and operational constraints—both out-of-sample and under distributional shifts—while significantly improving robustness and economic performance. The approach exhibits strong practical deployability for real-world PLM applications.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

We propose an optimization model where a parking lot manager (PLM) can aggregate parked EV batteries to provide virtual energy storage services that are provably robust under uncertain EV departures and state-of-charge caps. Our formulation yields a data-driven convex optimization problem where a prosumer community agrees on a contract with the PLM for the provision of storage services over a finite horizon. Leveraging recent results in the scenario approach, we certify out-of-sample constraint safety. Furthermore, we enable a tunable profit-risk trade-off through scenario relaxation and extend our model to account for robustness to adversarial perturbations and distributional shifts over Wasserstein-based ambiguity sets. All the approaches are accompanied by tight finite-sample certificates. Numerical studies demonstrate the out-of-sample and out-of-distribution constraint satisfaction of our proposed model compared to the developed theoretical guarantees, showing their effectiveness and potential in robust and efficient virtual energy services.

Problem

• Aggregating EV batteries for robust virtual energy storage
• Providing certified safety under uncertain EV departures
• Enabling tunable profit-risk trade-offs via scenario optimization

Innovation

• Aggregating EV batteries for virtual energy storage
• Using scenario approach for constraint safety certification
• Enabling tunable profit-risk trade-off via scenario relaxation