Online Learning and Distributed Control for Residential Demand Response

TL;DR

This paper introduces an online, distributed control algorithm for residential air conditioner loads during demand response events, using machine learning to adapt to uncertain customer behaviors and thermal dynamics.

Contribution

It develops a novel Thompson sampling-based online control method that learns customer responses and thermal models in real-time, ensuring privacy and improved demand response performance.

Findings

Demonstrates control optimality through simulations

Shows efficient learning of customer behaviors

Validates distributed implementation benefits

Abstract

This paper studies the automated control method for regulating air conditioner (AC) loads in incentive-based residential demand response (DR). The critical challenge is that the customer responses to load adjustment are uncertain and unknown in practice. In this paper, we formulate the AC control problem in a DR event as a multi-period stochastic optimization that integrates the indoor thermal dynamics and customer opt-out status transition. Specifically, machine learning techniques including Gaussian process and logistic regression are employed to learn the unknown thermal dynamics model and customer opt-out behavior model, respectively. We consider two typical DR objectives for AC load control: 1) minimizing the total demand, 2) closely tracking a regulated power trajectory. Based on the Thompson sampling framework, we propose an online DR control algorithm to learn customer behaviors and make real-time AC control schemes. This algorithm considers the influence of various environmental factors on customer behaviors and is implemented in a distributed fashion to preserve the privacy of customers. Numerical simulations demonstrate the control optimality and learning efficiency of the proposed algorithm.