Document Type

Conference Paper

Subject Area

CPS Efficient Buildings, CPS Real-Time

Date of this Version


Publication Source

Data Predictive Control for Peak Power Reduction



Decisions on how best to optimize today's energy systems operations are becoming ever so complex and conflicting such that model-based predictive control algorithms must play a key role. However, learning dynamical models of energy consuming systems such as buildings, using grey/white box approaches is very cost and time prohibitive due to its complexity. This paper presents data-driven methods for making control-oriented model for peak power reduction in buildings. Specifically, a data predictive control with regression trees (DPCRT) algorithm, is presented. DPCRT is a finite receding horizon method, using which the building operator can optimally trade off peak power reduction against thermal comfort without having to learn white/grey box models of the systems dynamics. We evaluate the performance of our method using a DoE commercial reference virtual test-bed and show how it can be used for learning predictive models with 90% accuracy, and for achieving 8.6% reduction in peak power and costs.


Machine learning, Predictive control, Building control, Peak power reduction

Bib Tex

@InProceedings{Jain2016, author = {Jain, Achin and Mangharam, Rahul and Behl, Madhur}, title = {Data Predictive Control for Peak Power Reduction}, booktitle = {Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments}, year = {2016}, series = {BuildSys '16}, pages = {109--118}, publisher = {ACM}, acmid = {2993582}, doi = {10.1145/2993422.2993582}, isbn = {978-1-4503-4264-3}, location = {Palo Alto, CA, USA}, numpages = {10}, url = {}, }



Date Posted: 17 September 2016

This document has been peer reviewed.