Abstract—Designing fair compensation mechanisms for demand response (DR) is challenging. This paper models the problem in a game theoretic setting and designs a payment distribution mechanism based on the Shapley value (SV). As exact computation of the SV is in general intractable, we pro-pose estimating it using a reinforcement learning algorithm that approximates optimal stratified sampling. We apply this algo-rithm to a DR program that utilizes the SV for payments and quantify the accuracy of the resulting estimates. Index Terms—Economics, power system economics. I.

Designing fair compensation mechanisms for demand response (DR) is challenging. This paper models the problem in a game theoretic setting and designs a payment distribution mechanism based on the Shapley value (SV). As exact computation of the SV is in general intractable, we pro-pose estimating it using a reinforcement learning algorithm that approximates optimal stratified sampling. We apply this algorithm to a DR program that utilizes the SV for payments and quantify the accuracy of the resulting estimates.

We draw inspirations from real-world applications that present an opportunity for making breakthroughs, discover practical research problems through experimental studies and inter-disciplinary collaborations, develop fundamental theory principles and algorithms and implement real-world protocols and systems. 2 RESEARCH VISION AND THRUST Our research primarily focuses on Cyber-Physical Systems and Security for geophysical imaging, smart grid and smart health, where sensing, computing, communication and security play a critical role and need a transformative study. It greatly impacts the society on environment, energy and health issues. 2.1 Real-time In-situ Geophysical Imaging A sensor web system is often used in environment monitoring application to provide a high degree of visibility into environmental physical processes- capture the spatial and temporal environmental changes, essentially like a “video camera”. One of the niche is geophysical imaging, that use a network of geophysical sensors to image the subsurface and has critical application in hazard mitigation and oil/gas exploration. We are the leader of real-time in-situ geophysical imaging and have enormous collaborations with geophysics community, such as top researchers from U.S. Geological Survey, Jet

Abstract—Selecting customers for demand response programs is challenging and existing methodologies are hard to scale and poor in performance. The existing methods were limited by lack of temporal consumption information at the individual customer level. We propose a scalable methodology for demand response targeting utilizing novel data available from smart meters. The approach relies on formulating the problem as a stochastic integer program involving predicted customer responses. A novel approximation is developed algorithm so it can scale to problems involving millions of customers. The methodology is tested experimentally using real utility data. Index Terms—smart meter data, targeting, demand response, big data, algorithms, stochastic knapsack problem. I.