2014 Poster Sessions : Compensating Demand Response Participants Via Their Shapley Values

Student Name : Gearoid O'Brien
Advisor : Abbas El Gamal
Research Areas: Information Systems
Abstract:
Designing fair compensation mechanisms for demand response (DR) is challenging. Here, we model the problem in a game theoretic setting and design a payment distribution mechanism based on the Shapley Value. As exact computation of the Shapley Value is in general intractable, we propose estimating it using a reinforcement learning algorithm that approximates optimal stratified sampling. We apply this algorithm to two DR programs that utilize the Shapley Value for payments and quantify the accuracy of the resulting estimates.

Bio:
Gearoid is a Doctoral Candidate in Stanford's Electrical Engineering Department. He is working with Professors Abbas El Gamal and Ram Rajagopal on issues relating to the 'Smart Grid', including Demand Response and Renewable Integration. He received both his Bachelors and Masters Degrees from the National University of Ireland, Cork and his research in Stanford is supported by China EPRI.