Lab Home | Phone | Search
Center for Nonlinear Studies  Center for Nonlinear Studies
 Home 
 People 
 Current 
 Affiliates 
 Visitors 
 Students 
 Research 
 ICAM-LANL 
 Publications 
 Conferences 
 Workshops 
 Sponsorship 
 Talks 
 Colloquia 
 Colloquia Archive 
 Seminars 
 Postdoc Seminars Archive 
 Quantum Lunch 
 Quantum Lunch Archive 
 CMS Colloquia 
 Q-Mat Seminars 
 Q-Mat Seminars Archive 
 P/T Colloquia 
 Archive 
 Kac Lectures 
 Kac Fellows 
 Dist. Quant. Lecture 
 Ulam Scholar 
 Colloquia 
 
 Jobs 
 Postdocs 
 CNLS Fellowship Application 
 Students 
 Student Program 
 Visitors 
 Description 
 Past Visitors 
 Services 
 General 
 
 History of CNLS 
 
 Maps, Directions 
 CNLS Office 
 T-Division 
 LANL 
 
Wednesday, June 21, 2017
1:00 PM - 2:00 PM
CNLS Conference Room (TA-3, Bldg 1690)

Seminar

The foundations of Data Predictive Control for Cyber-Physical Systems

Madhur Behl
University of Pennsylvania

Control-oriented predictive models of a cyber-physical system’s dynamics are needed for understanding and improving the system operation. In many applications such as building energy management and process control, model identification using first principles is very cost and time prohibitive, thus limiting the use of model-based predictive controllers like MPC. The alternative is to use black-box, or completely data-driven modeling approaches, based on machine learning algorithms. The primary advantage of using machine learning methods for the system’s model is that it has the potential to eliminate the time and effort required to build first principles based models. Listening to real-time data, from existing systems and interfaces, is far cheaper than unleashing hoards of on-site engineers to physically measure and model the physical system. However, data-driven models are not well suited for receding horizon closed-loop control synthesis, which can provide performance and stability guarantees for plant operations. This talk is about Data Predictive Control (DPC), a framework designed to combine the simplicity of data-driven methods with the predicitve capability of model-based control. With DPC we bridge the modeling incompatibility gap between machine learning models and control synthesis by building control-oriented and interpretable regression trees based models. In this talk, I will show how we use DPC for demand response (DR) and peak power management in large commercial buildings. Demand response is becoming increasingly important as the volatility on the grid continues to increase and yet current DR approaches are predominantly completely manual or rule-based. Our data-driven control synthesis algorithm outperforms rule-based DR by 17% for a large DoE commercial reference building and leads to a curtailment of up to 380 kW and over $45,000 in savings. Our methods have been integrated into a tool called DR-Advisor, which acts as a recommender system for the building’s facilities manager and provides suitable control actions to meet the desired load curtailment while maintaining operations and maximizing the economic reward. DR-Advisor achieves 92.8–98.9% prediction accuracy for 8 buildings on a university campus. We also compare DR-Advisor with other data driven methods and rank 2nd on ASHRAE’s benchmarking data-set for energy prediction.

Host: Michael Chertkov