Data Predictive Control for building energy management

Simple item page
dc.bibliographic.citation<p>@InProceedings{JainACC2017, author = {Jain, Achin and Behl, Madhur and Mangharam, Rahul}, title = {Data Predictive Control for building energy management}, booktitle = {Proceedings of the 2017 American Control Conference}, year = {2017}, organization = {IEEE}}</p>
dc.contributor.authorJain, Achin
dc.contributor.authorJain, Achin
dc.contributor.authorBehl, Madhur
dc.contributor.authorMangharam, Rahul
dc.date2023-05-17T16:29:42.000
dc.date.accessioned2023-05-22T23:59:58Z
dc.date.available2023-05-22T23:59:58Z
dc.date.issued2017-02-01
dc.date.submitted2017-01-27T21:54:58-08:00
dc.description.abstractDecisions on how to best optimize energy systems operations are becoming ever so complex and conflicting, that model-based predictive control (MPC) algorithms must play an important role. However, a key factor prohibiting the widespread adoption of MPC in buildings, is the cost, time, and effort associated with learning first-principles based dynamical models of the underlying physical system. This paper introduces an alternative approach for implementing finite-time receding horizon control using control-oriented data-driven models. We call this approach Data Predictive Control (DPC). Specifically, by utilizing separation of variables, two novel algorithms for implementing DPC using a single regression tree and with regression trees ensembles (random forest) are presented. The data predictive controller enables the building operator to trade off energy consumption against thermal comfort without having to learn white/grey box models of the systems dynamics. We present a comprehensive numerical study which compares the performance of DPC with an MPC based energy management strategy, using a single zone building model. Our results demonstrate that performance of DPC is comparable to an MPC controller, with only 3.8% additional cost in terms of optimal objective function and within 95% in terms of R2 score, thereby making it an alluring alternative to MPC, whenever the associated cost of learning the model is high.
dc.identifier.citationAchin Jain, Madhur Behl, and Rahul Mangharam. In Proceedings of the 2017 American Control Conference. IEEE, May 2017.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/40711
dc.legacy.articleid1115
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1115&amp;context=mlab_papers&amp;unstamped=1
dc.source.issue96
dc.source.journalReal-Time and Embedded Systems Lab (mLAB)
dc.source.peerreviewedtrue
dc.source.statuspublished
dc.subject.otherCPS Efficient Buildings
dc.subject.otherCPS Real-Time
dc.subject.othermachine learning
dc.subject.otherpredictive control
dc.subject.otherbuilding control
dc.subject.otherenergy management
dc.subject.otherComputer Engineering
dc.subject.otherControl Theory
dc.subject.otherDynamical Systems
dc.subject.otherElectrical and Computer Engineering
dc.subject.otherStatistical Models
dc.titleData Predictive Control for building energy management
dc.typePresentation
digcom.contributor.authorisAuthorOfPublication|email:achinj@seas.upenn.edu|institution:University of Pennsylvania|Jain, Achin
digcom.contributor.authorBehl, Madhur
digcom.contributor.authorMangharam, Rahul
digcom.identifiermlab_papers/96
digcom.identifier.contextkey9593705
digcom.identifier.submissionpathmlab_papers/96
digcom.typeconference
dspace.entity.typePublication
relation.isAuthorOfPublicationfd44b26f-0c9c-452b-8cd1-62b1f796b6f4
relation.isAuthorOfPublication.latestForDiscoveryfd44b26f-0c9c-452b-8cd1-62b1f796b6f4
upenn.schoolDepartmentCenterReal-Time and Embedded Systems Lab (mLAB)
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
root.pdf
Size:
1.5 MB
Format:
Adobe Portable Document Format
Download
Collection
Presentations