Data-driven demand response modeling and control of buildings with Gaussian Processes

This paper presents an approach to provide demand response services with buildings. Each building receives a normalized signal that tells it to increase or decrease its power demand, and the building is free to implement any suitable strategy to follow the command, most likely by changing some of its setpoints. Due to this freedom, the proposed approach lowers the barrier for any buildings equipped with a reasonably functional building management system to participate in the scheme. The response of the buildings to the control signal is modeled by a Gaussian Process, which can predict the power demand of the buildings and also provide a measure of its confidence in the prediction. A battery is included in the system to compensate for this uncertainty and improve the demand response performance of the system. A model predictive controller is developed to optimally control the buildings and the battery, while ensuring their operational constraints with high probability. Our approach is validated by realistic co-simulations between Matlab and the building energy simulator EnergyPlus.

[1]  Sila Kiliccote,et al.  Strategies for Demand Response in Commercial Buildings , 2006 .

[2]  X Nghiem Truong,et al.  OpenBuildNet framework for distributed co-simulation of smart energy systems , 2016 .

[3]  Joel Andersson,et al.  A General-Purpose Software Framework for Dynamic Optimization (Een algemene softwareomgeving voor dynamische optimalisatie) , 2013 .

[4]  Michael Stadler,et al.  Quantifying Flexibility of Commercial and Residential Loads for Demand Response using Setpoint Changes , 2016 .

[5]  Alberto L. Sangiovanni-Vincentelli,et al.  Smart Connected Buildings Design Automation: Foundations and Trends , 2016, Found. Trends Electron. Des. Autom..

[6]  Miles Lubin,et al.  Two-sided linear chance constraints and extensions , 2015, 1507.01995.

[7]  Jan M. Maciejowski,et al.  Predictive control : with constraints , 2002 .

[8]  Pierluigi Siano,et al.  Demand response and smart grids—A survey , 2014 .

[9]  Juš Kocijan,et al.  Modelling and Control of Dynamic Systems Using Gaussian Process Models , 2015 .

[10]  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.

[11]  Hae Young Noh,et al.  Data-driven forecasting algorithms for building energy consumption , 2013, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[12]  Lorenz T. Biegler,et al.  On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming , 2006, Math. Program..

[13]  Madhur Behl,et al.  DR-Advisor: A data driven demand response recommender system , 2015 .

[14]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[15]  Colin N. Jones,et al.  Model Predictive Control for Market-Based Demand Response Participation , 2014 .

[16]  Zheng O'Neill,et al.  Comparisons of inverse modeling approaches for predicting building energy performance , 2015 .