Decentralized and Privacy-Preserving Learning of Approximate Stackelberg Solutions in Energy Trading Games with Demand Response Aggregators

TL;DR

This paper introduces a decentralized, privacy-preserving game-theoretic framework for energy trading between demand-response aggregators and prosumers, enabling flexible arbitrage and rewards while ensuring demand satisfaction.

Contribution

It proposes a scalable, decentralized algorithm for approximate equilibrium computation in energy trading games with privacy preservation and online learning capabilities.

Findings

Effective real-world validation using California market data.

Algorithm achieves scalable and privacy-preserving equilibrium approximation.

Provides cost bounds on solution quality.

Abstract

In this work, a novel Stackelberg game theoretic framework is proposed for trading energy bidirectionally between the demand-response (DR) aggregator and the prosumers. This formulation allows for flexible energy arbitrage and additional monetary rewards while ensuring that the prosumers' desired daily energy demand is met. Then, a scalable (linear with the number of prosumers), decentralized, privacy-preserving algorithm is proposed to find approximate equilibria with online sampling and learning of the prosumers' cumulative best response, which finds applications beyond this energy game. Moreover, cost bounds are provided on the quality of the approximate equilibrium solution. Finally, real data from the California day-ahead market and the UC Davis campus building energy demands are utilized to demonstrate the efficacy of the proposed framework and algorithm.