A personalized load forecasting enhanced by activity information

In this paper, we propose an activity-enhanced load forecasting model at house-level. We focus on the impact of residents' daily activities on entire household's power consumption. The contribution of this paper is 3-fold: 1) a web-based system for collecting daily activity information in diary-style; 2) a correlation analysis between activities and power consumption and their information-theoretic relationship; 3) a personalized load forecasting study using different prediction algorithms and an activity recognition procedure as an enhancement. Both correlation and forecasting results show consistently that our collected activity information can contribute to estimate and predict the power consumption of individual households to varying degrees, in particular for 15 minutes ahead load forecasting. An extended forecasting model with an online activity recognition component can further reduce the forecasting error.

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

[2]  Fredrik Wallin,et al.  Forecasting for demand response in smart grids: An analysis on use of anthropologic and structural data and short term multiple loads forecasting , 2012 .

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

[4]  Michael Beigl,et al.  A framework for short-term activity-aware load forecasting , 2013, AIIP '13.

[5]  Claire Bergaentzlé,et al.  Demand-side management and European environmental and energy goals: an optimal complementary approach , 2014 .

[6]  Naonori Ueda,et al.  Mobile activity recognition for a whole day: recognizing real nursing activities with big dataset , 2015, UbiComp.

[7]  Hojung Cha,et al.  Personalized Energy Auditor: Estimating personal electricity usage , 2014, 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[8]  R. Larson,et al.  The Energy Box: Locally Automated Optimal Control of Residential Electricity Usage , 2009 .

[9]  A. Grandjean,et al.  A review and an analysis of the residential electric load curve models , 2012 .

[10]  Rob J Hyndman,et al.  Short-Term Load Forecasting Based on a Semi-Parametric Additive Model , 2012, IEEE Transactions on Power Systems.

[11]  H. Farhangi,et al.  The path of the smart grid , 2010, IEEE Power and Energy Magazine.

[12]  V. Ismet Ugursal,et al.  Modeling of end-use energy consumption in the residential sector: A review of modeling techniques , 2009 .

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

[14]  Stéphane Ploix,et al.  A prediction system for home appliance usage , 2013 .

[15]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[16]  Nilanjan Banerjee,et al.  Using rule mining to understand appliance energy consumption patterns , 2014, 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[17]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[18]  J. Widén,et al.  A high-resolution stochastic model of domestic activity patterns and electricity demand , 2010 .