Sometimes, Money Does Grow on Trees: DR- Advisor, A Data Driven Demand Response Recommender System

Unprecedented amounts of information from millions of smart meters and thermostats installed in recent years has left the door open for better understanding, analyzing and using the insights that data can provide, about the power consumption patterns of a building. The challenge with using data-driven approaches, is to close the loop for near real-time control and decision making in large buildings. Furthermore, providing a technological solution alone is not enough, the solution must also be human centric. We consider the problem of end-user demand response for commercial buildings. Using historical data from the building, we build a family of regression trees based models for predicting the power consumption of the building in real-time. We have built DR-Advisor, a recommender system for the building's facilities manager, which provides optimal control actions to meet the required load curtailment while maintaining building operations and maximizing the economic reward.

[1]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[2]  Haimonti Dutta,et al.  Data Driven Energy Efficiency in Buildings , 2014, ArXiv.

[3]  C. Goldman.  Coordination of Energy Efficiency and Demand Response , 2010 .

[4]  J. Zhang,et al.  A model predictive control strategy for load shifting in a water pumping scheme with maximum demand charges , 2009, 2009 IEEE Bucharest PowerTech.

[5]  Bing Liu,et al.  U.S. Department of Energy Commercial Reference Building Models of the National Building Stock , 2011 .

[6]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[7]  Lynne E. Parker,et al.  Energy and Buildings , 2012 .

[8]  Viktor K. Prasanna,et al.  Scalable regression tree learning on Hadoop using OpenPlanet , 2012, MapReduce '12.

[9]  Manfred Morari,et al.  Model Predictive Climate Control of a Swiss Office Building: Implementation, Results, and Cost–Benefit Analysis , 2016, IEEE Transactions on Control Systems Technology.

[10]  Manfred Morari,et al.  Towards a standardized building assessment for demand response , 2013, 52nd IEEE Conference on Decision and Control.

[11]  R. Belmans,et al.  Impact of residential demand response on power system operation: A Belgian case study , 2014 .

[12]  M. Piette,et al.  Peak Demand Reduction from Pre-Cooling with Zone Temperature Reset in an Office Building , 2004 .

[13]  Carlos Silva,et al.  Demand response modeling: A comparison between tools , 2015 .

[14]  Tianzhen Hong,et al.  A fresh look at weather impact on peak electricity demand and energy use of buildings using 30-year actual weather data , 2013 .

[15]  Standard Ashrae.  Thermal Environmental Conditions for Human Occupancy , 1992 .

[16]  Yan Lu,et al.  Deep Demand Response: The Case Study of the CITRIS Building at the University of California-Berkeley , 2012 .

[17]  Eva Žáčeková,et al.  Towards the real-life implementation of MPC for an office building: Identification issues , 2014 .

[18]  J. Bryson,et al.  Energy price risk and the sustainability of demand side supply chains , 2014 .

[19]  Truong Nghiem,et al.  Model-IQ: Uncertainty propagation from sensing to modeling and control in buildings , 2014, 2014 ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS).

[20]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[21]  Yan Lu,et al.  Modeling and forecasting of cooling and electricity load demand , 2014 .

[22]  G. Yohe,et al.  Climate Change Impacts in the United States: The Third National Climate Assessment , 2014 .

[23]  A. Kialashaki,et al.  Modeling of the energy demand of the residential sector in the United States using regression models and artificial neural networks , 2013 .

[24]  Anastasios I. Dounis,et al.  Design of a fuzzy system for living space thermal-comfort regulation , 2001 .

[25]  Frauke Oldewurtel,et al.  Experimental analysis of model predictive control for an energy efficient building heating system , 2011 .

[26]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[27]  Daniel E. Fisher,et al.  EnergyPlus: creating a new-generation building energy simulation program , 2001 .

[28]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[29]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.

[30]  Burcin Becerik-Gerber,et al.  A model calibration framework for simultaneous multi-level building energy simulation , 2015 .

[31]  Karin Alvehag,et al.  Further exploring the potential of residential demand response programs in electricity distribution , 2014 .

[32]  Joshua Ryan New,et al.  AUTOTUNE E+ BUILDING ENERGY MODELS , 2012 .

[33]  G. Rizzoni,et al.  A highly resolved modeling technique to simulate residential power demand , 2013 .

[34]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .