ADMM-based distributed response quantity estimation: a probabilistic perspective.

With the wide deployment of smart meters in the end-user side, demand response (DR) is gaining prominence. Estimating the potential response is a preliminary step to the DR implementation. However, how to select proper features, how to protect privacy, and how to capture the response uncertainty remains three challenges to the customer response potential estimation. This study provides a detailed response quantity estimation for each customer. The authors proposed a probabilistic response quantity estimation framework and solved the problem by alternating direction method of multipliers (ADMM) in a fully-distributed way. In particular, by utilising a similar consumption pattern matching principle, the feature for each DR day of each customer is selected based on the matched DR participants. Then, the pinball loss-guided ridge regression is formulated, so the quantiles are obtained to cope with the uncertainty. The training process can be solved by each customer at the local site in a fully-distributed way, which protects the privacy and reduces the centralised processing burden. Finally, in the case study, the assumption behind a similar consumption pattern matching principle is validated empirically. Also, the proposed method is confirmed to have good convergence performance and can produce reasonable estimation results. [ABSTRACT FROM AUTHOR]