TY - JOUR
T1 - Online Learning and Distributed Control for Residential Demand Response
AU - Chen, Xin
AU - Li, Yingying
AU - Shimada, Jun
AU - Li, Na
N1 - Funding Information:
This work was supported in part by the National Science Fund CAREER under Grant ECCS-1553407, and in part by the National Science Fund EAGER under Grant ECCS-1839632.
Publisher Copyright:
© 2010-2012 IEEE.
PY - 2021/11/1
Y1 - 2021/11/1
N2 - 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.
AB - 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.
KW - distributed algorithm
KW - incentive-based demand response
KW - Online learning
KW - uncertain customer behavior
UR - http://www.scopus.com/inward/record.url?scp=85112153786&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112153786&partnerID=8YFLogxK
U2 - 10.1109/TSG.2021.3090039
DO - 10.1109/TSG.2021.3090039
M3 - Article
AN - SCOPUS:85112153786
SN - 1949-3053
VL - 12
SP - 4843
EP - 4853
JO - IEEE Transactions on Smart Grid
JF - IEEE Transactions on Smart Grid
IS - 6
ER -