Development of a domestic hot water demand prediction model based on a bottom-up approach for residential energy management systems

Abstract An energy management system (EMS) that controls energy equipment in residential dwellings contributes to energy conservation and cost reduction. A hot energy demand prediction method is necessary for the EMS to provide the best possible performance. A prediction method using a bottom-up approach based on end-use analysis with detailed energy consumption measurement was developed. One of the advantages of the proposed prediction method is that it provides good accuracy without needing large computational resources. Since the method is based on end-use analysis, the EMS can revise the prediction and controls when necessary. The performance of the developed prediction method was evaluated by comparing it with results produced by support vector regression. An operational simulation was performed to evaluate performance in a more practical environment. The simulation indicated that the proposed method showed the best performance.

[1]  Rodney Anthony Stewart,et al.  Residential water heaters in Brisbane, Australia: thinking beyond technology selection to enhance energy efficiency and level of service , 2014 .

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

[3]  Hongbo Ren,et al.  Economic and environmental evaluation of micro CHP systems with different operating modes for residential buildings in Japan , 2010 .

[4]  S. Hokoi,et al.  Energy efficiency and energy savings in Japanese residential buildings : research methodology and surveyed results , 2005 .

[5]  Wil L. Kling,et al.  Support Vector Machine in Prediction of Building Energy Demand Using Pseudo Dynamic Approach , 2015, ArXiv.

[6]  Joseph Virgone,et al.  Development and validation of regression models to predict monthly heating demand for residential buildings , 2008 .

[7]  Aya Hagishima,et al.  Validation of probabilistic methodology for generating actual inhabitants' behavior schedules for accurate prediction of maximum energy requirements , 2008 .

[8]  Hiroto Takaguchi,et al.  Detailed research for energy consumption of residences in Northern Kyushu, Japan , 2006 .

[9]  Christina J. Hopfe,et al.  A critical software review - how is hot water modelled in current building simulation ? , 2015 .

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

[11]  Rodney Anthony Stewart,et al.  Alarming visual display monitors affecting shower end use water and energy conservation in Australian residential households. , 2010 .

[12]  Hong Zhang,et al.  An intelligent pattern recognition model to automate the categorisation of residential water end-use events , 2013, Environ. Model. Softw..

[13]  Nicola Bianco,et al.  Economic optimization of a residential micro-CHP system considering different operation strategies , 2016 .

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

[15]  Ryohei Yokoyama,et al.  Suitable operational strategy for power interchange operation using multiple residential SOFC (solid oxide fuel cell) cogeneration systems , 2010 .

[16]  Abbas Khosravi,et al.  A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings , 2015 .

[17]  Jiejin Cai,et al.  Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks , 2009 .