A hybrid model approach for forecasting future residential electricity consumption

Abstract Urban energy management nowadays has put more focus on residential houses energy consumption. Lots of machine learning based data-driven approaches have the abilities to characterize and forecast total energy consumption of commercial data. However, a paucity of research applying data-driven methods have been tested on the hour ahead energy consumption forecast for typical single family houses in the US. With the advances in smart metering, sub meter usages forecast in household-level is also getting more and more popular on smart building control and demand response program. The situation here inspires us to develop a hybrid model to address the problem of residential hour and day ahead load forecasting through the integration of data-driven techniques with a physics-based model. In this article, we report on the evaluations of five different machine learning algorithms, artificial neural network (ANN), support vector regression (SVR), least-square support vector machine (LS-SVM), Gaussian process regression (GPR) and Gaussian mixture model (GMM), applied to four residential data set that contains smart meters. Both total and non-air conditioning (AC) power consumption are forecasted for hour ahead and 24-h ahead. The variation of patterns captured from non-AC part is further input as internal heat gain to a physics-based model. The model uses a 2R-1C thermal network and an AC regression model. By utilizing this hybrid approach, we get AC load prediction and non-AC energy forecast simultaneously. Total energy consumption is further produced by summing up the two sub meters forecast for hybrid model. The results from new modeling are compared with those from pure data-driven techniques. The final result showing improvements of coefficient of variance between the best data-driven model and hybrid model are 6–10% and 2–15% for hour ahead and 24-h ahead, respectively.

[1]  D.J. Leith,et al.  Gaussian process prior models for electrical load forecasting , 2004, 2004 International Conference on Probabilistic Methods Applied to Power Systems.

[2]  Abhishek Srivastav,et al.  Integrated energy performance modeling for a retail store building , 2013 .

[3]  Kevin M. Smith,et al.  Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy , 2014 .

[4]  Graeme Burt,et al.  Enhanced Load Profiling for Residential Network Customers , 2014, IEEE Transactions on Power Delivery.

[5]  Henrik Madsen,et al.  Identification of the main thermal characteristics of building components using MATLAB , 2008 .

[6]  James E. Braun,et al.  An Inverse Gray-Box Model for Transient Building Load Prediction , 2002 .

[7]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[8]  Abhishek Srivastav,et al.  Baseline building energy modeling and localized uncertainty quantification using Gaussian mixture models , 2013 .

[9]  Merih Aydinalp,et al.  Modeling of the space and domestic hot-water heating energy-consumption in the residential sector using neural networks , 2004 .

[10]  Sylvain Calino,et al.  Robot programming by demonstration : a probabilistic approach , 2009 .

[11]  Qian Ding,et al.  Application of LS-SVM in the Short-term Power Load Forecasting Based on QPSO , 2014 .

[12]  Xindong Wu,et al.  The Top Ten Algorithms in Data Mining , 2009 .

[13]  M. Etezadi-Amoli,et al.  Smart meter based short-term load forecasting for residential customers , 2011, 2011 North American Power Symposium.

[14]  H. Mori,et al.  Probabilistic short-term load forecasting with Gaussian processes , 2005, Proceedings of the 13th International Conference on, Intelligent Systems Application to Power Systems.

[15]  Tony N.T. Lam,et al.  Artificial neural networks for energy analysis of office buildings with daylighting , 2010 .

[16]  Lino Guzzella,et al.  EKF based self-adaptive thermal model for a passive house , 2014 .

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

[18]  Eric Monmasson,et al.  Thermal parameter identification of simplified building model with electric appliance , 2011, 11th International Conference on Electrical Power Quality and Utilisation.

[19]  Philip Haves,et al.  A Modular Building Controls Virtual Test Bed for the Integrations of Heterogeneous Systems , 2008 .

[20]  Lynne E. Parker,et al.  Predicting future hourly residential electrical consumption: A machine learning case study , 2012 .

[21]  Refrigerating ASHRAE handbook of fundamentals , 1967 .

[22]  Jesús M. Zamarreño,et al.  Prediction of hourly energy consumption in buildings based on a feedback artificial neural network , 2005 .

[23]  Xinhua Xu,et al.  A grey‐box model of next‐day building thermal load prediction for energy‐efficient control , 2008 .

[24]  S. Fan,et al.  Short-term load forecasting based on an adaptive hybrid method , 2006, IEEE Transactions on Power Systems.

[25]  Mohammad Yusri Hassan,et al.  A review on applications of ANN and SVM for building electrical energy consumption forecasting , 2014 .

[26]  Abdullatif Ben-Nakhi,et al.  Cooling load prediction for buildings using general regression neural networks , 2004 .

[27]  Xueming Yang,et al.  Comparison of the LS-SVM based load forecasting models , 2011, Proceedings of 2011 International Conference on Electronic & Mechanical Engineering and Information Technology.

[28]  Guido Smits,et al.  Improved SVM regression using mixtures of kernels , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[29]  Yu Erkeng,et al.  Short-term electrical load forecasting using least squares support vector machines , 2002, Proceedings. International Conference on Power System Technology.

[30]  Zheng O'Neill,et al.  TESTING AND VALIDATING AN EQUATION-BASED DYNAMIC BUILDING PROGRAM WITH ASHRAE STANDARD METHOD OF TEST , 2008 .

[31]  Prashant G. Mehta,et al.  Structure-preserving model reduction of nonlinear building thermal models , 2014, Autom..

[32]  Benedikt Gregor Eric Schenker,et al.  Prediction and control using feedback neural networks and partial models , 1996 .

[33]  Victor M. Zavala,et al.  On-line economic optimization of energy systems using weather forecast information. , 2009 .

[34]  Desheng Dash Wu,et al.  Power load forecasting using support vector machine and ant colony optimization , 2010, Expert Syst. Appl..

[35]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[36]  Christian Ghiaus,et al.  Optimal temperature control of intermittently heated buildings using Model Predictive Control: Part I – Building modeling , 2012 .

[37]  Bing Dong,et al.  An investigation on energy-related occupancy behavior for low-income residential buildings , 2015 .

[38]  Kenneth Levenberg A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[39]  Ali Azadeh,et al.  Annual electricity consumption forecasting by neural network in high energy consuming industrial sectors , 2008 .

[40]  Stéphane Bertagnolio,et al.  Building and HVAC system simulation with the help of an engineering equation solver , 2008 .

[41]  Yasuhiro Hayashi,et al.  A Versatile Clustering Method for Electricity Consumption Pattern Analysis in Households , 2013, IEEE Transactions on Smart Grid.

[42]  Johan A. K. Suykens,et al.  Fixed-size Least Squares Support Vector Machines: A Large Scale Application in Electrical Load Forecasting , 2006, Comput. Manag. Sci..

[43]  Zheng O'Neill,et al.  MODEL-BASED THERMAL LOAD ESTIMATION IN BUILDINGS , 2010 .

[44]  James E. Braun,et al.  Evaluating the Performance of Building Thermal Mass Control Strategies , 2001 .