Kernel regression for real-time building energy analysis

This study proposes a new technique for real-time building energy modelling and event detection using kernel regression. We show that this technique can exceed the performance of conventional neural network algorithms, and do so by a large margin when the available training dataset is small. Furthermore, unlike the synapse weights in a neural network, the parameters of our kernel regression models are amenable to human interpretation and can give useful information about the building being studied. We extensively test our proposed algorithms using a new dataset consisting of 1.5 years of power and environmental measurements for four buildings, in addition to benchmarking against the ASHRAE Predictor Shootout dataset. On the new dataset, our kernel regression algorithm gave the best prediction performance in three of four cases and significantly outperformed neural networks (the nearest competitor) with training sets of 1/2 a year or less.

[1]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[2]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Ardeshir Mahdavi,et al.  Reflections on computational building models , 2004 .

[4]  L. H. Hansen,et al.  Modelling the heat dynamics of a building using stochastic differential equations , 2000 .

[5]  Ardeshir Mahdavi.  Simulation-based control of building systems operation , 2001 .

[6]  Daniel E. Fisher,et al.  ENERGYPLUS: AN UPDATE , 2004 .

[7]  D. Claridge,et al.  A Fourier Series Model to Predict Hourly Heating and Cooling Energy Use in Commercial Buildings With Outdoor Temperature as the Only Weather Variable , 1999 .

[8]  Peter J. Huber,et al.  Robust Statistics , 2005, Wiley Series in Probability and Statistics.

[9]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[10]  Jeff Haberl,et al.  The Great Energy Predictor Shootout II : Measuring Retriofit Savings-Overview and Discussion of Results , 1996 .

[11]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[12]  Vladislav Kantchev Shunturov,et al.  Dormitory residents reduce electricity consumption when exposed to real‐time visual feedback and incentives , 2007 .

[13]  J. F. Kreider.  Prediction Hourly Building Energy Use : The Great Energy Predictor Shootout - Overview and Discussion of Results , 1994 .

[14]  Aravaipa Canyon Basin,et al.  Volume 3 , 2012, Journal of Diabetes Investigation.

[15]  E. Nadaraya.  On Estimating Regression , 1964 .

[16]  Drury B. Crawley,et al.  EnergyPlus: Energy simulation program , 2000 .

[17]  Shyh-Jier Huang,et al.  Short-term load forecasting via ARMA model identification including non-Gaussian process considerations , 2003 .

[18]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .

[19]  V. Geros,et al.  Modeling and predicting building's energy use with artificial neural networks: Methods and results , 2006 .

[20]  Jessica Granderson.  Building Energy Information Systems: State of the Technology and User Case Studies , 2010 .

[21]  Evan Mills,et al.  Monitoring Based Commissioning: Benchmarking Analysis of 24 UC/CSU/IOU Projects , 2009 .

[22]  Jeff Haberl,et al.  The great energy predictor shootout. II : Measuring retrofit savings , 1998 .

[23]  Moncef Krarti,et al.  Development of a Predictive Optimal Controller for Thermal Energy Storage Systems , 1997 .

[24]  A. Richards.  Energy and buildings , 2012 .

[25]  Jeff Haberl,et al.  Procedures for Calibrating Hourly Simulation Models to Measured Building Energy and Environmental Data , 1998 .

[26]  B. Ripley,et al.  Robust Statistics , 2018, Encyclopedia of Mathematical Geosciences.

[27]  Jin Yang,et al.  On-line building energy prediction using adaptive artificial neural networks , 2005 .

[28]  Gregor P. Henze,et al.  Statistical Analysis of Neural Networks as Applied to Building Energy Prediction , 2004 .

[29]  G. Bornard,et al.  Optimal adaptive predictive control and fault detection of residential building heating systems , 1994, 1994 Proceedings of IEEE International Conference on Control and Applications.

[30]  David J. C. MacKay,et al.  BAYESIAN NON-LINEAR MODELING FOR THE PREDICTION COMPETITION , 1996 .

[31]  Thomas Weng,et al.  The energy dashboard: improving the visibility of energy consumption at a campus-wide scale , 2009, BuildSys '09.

[32]  Zerouak Hamza.  Applications of artificial neural-networks for energy systems , 2000 .

[33]  C. E. Dorgan,et al.  Optimizing system control with load prediction by neural networks for an ice-storage system , 1996 .