Data-Driven Models in Power Systems

Increase in supply-side variability due to increases in renewable generation requires integrating new resources utilizing improved models of the power system to reduce electricity delivery costs. Data from consumers and markets has become broadly available and represent an opportunity to learn better models of market dynamics, consumer behavior, and resource valuation. In this talk, we introduce two problems in statistical learning from data in power networks: learning virtual bidding dynamics and optimal storage placement in networks. In the first part of the talk, we focus on models of wholesale electricity markets developed to understand virtual bidding.  We demonstrate that data can be utilized to test market efficiency and to characterize competitive equilibrium conditions in the presence of virtual bidding utilizing more tractable models. In the second part of the talk, we utilize consumer data to infer customer profiles and quantify the benefits of distributed storage and their coordination. We then analyze an optimal placement strategy for storage that can account for capital and operations costs and is simple to implement in practice.