Coal consumption prediction model of space heating with feature selection for rural residences in severe cold area in China

Abstract Identification of optimal subsets of input variables is a primary task in data-driven prediction modeling for the coal consumption for space heating (CCSH) of rural residences. However, most related predictive models of CCSH in rural residences ignore the nonlinear relationship between the factors and CCSH, and are short of feature selection process. This paper proposed an enhanced CCSH prediction model with learning-based optimized feature selection based on the measured weekly CCSH during real operation in Chifeng, Inner Mongolia, China. Partial least squares regression and random forest were employed to rank the features, and ten models with various input subsets were established by support vector regression. The prediction accuracy of the ten models was compared and the optimal features were examined based on the coefficient of variation of the root mean square error (CVRMSE), coefficient of determination (R2) and model generalization ability. Furthermore, the residual errors between predicted and measured CCSH are distributed around zero evenly and extracted from the normal distribution for the optimized model. Particularly, we employed the best model to predict the aggregate CCSH at the district level. The prediction model with the optimal inputs was verified to be reasonable and accurate at the individual and district scales.

[1]  Wei Tian,et al.  A review of sensitivity analysis methods in building energy analysis , 2013 .

[2]  L. Duanmu,et al.  Heat transfer model of hot-wall Kang based on the non-uniform Kang surface temperature in Chinese rural residences , 2017 .

[3]  Jiejin Cai,et al.  Applying support vector machine to predict hourly cooling load in the building , 2009 .

[4]  Li Yang,et al.  Building energy efficiency in China rural areas: Situation, drawbacks, challenges, corresponding measures and policies , 2014 .

[5]  Joaquim Melendez,et al.  Short-term load forecasting in a non-residential building contrasting models and attributes , 2015 .

[6]  Chunsheng Yao,et al.  Analysis of rural residential energy consumption and corresponding carbon emissions in China , 2012 .

[7]  Jie Deng,et al.  A new Chinese solar kang and its dynamic heat transfer model , 2013 .

[8]  Jack Chin Pang Cheng,et al.  Identifying the influential features on the regional energy use intensity of residential buildings based on Random Forests , 2016 .

[9]  Zhiqiang John Zhai,et al.  An evaluation and model of the Chinese Kang system to improve indoor thermal comfort in northeast rural China – Part-2: Result analysis , 2015 .

[10]  Shuwen Niu,et al.  Energy demand for rural household heating to suitable levels in the Loess Hilly Region, Gansu Province, China , 2010 .

[11]  Sancho Salcedo-Sanz,et al.  Feature selection in machine learning prediction systems for renewable energy applications , 2018, Renewable and Sustainable Energy Reviews.

[12]  Eleni Mangina,et al.  Input variable selection for thermal load predictive models of commercial buildings , 2017 .

[13]  Shuyuan Li,et al.  Village energy survey reveals missing rural raw coal in northern China: Significance in science and policy. , 2017, Environmental pollution.

[14]  Wil L. Kling,et al.  Pseudo Dynamic Transitional Modeling of Building Heating Energy Demand Using Artificial Neural Network , 2014, ArXiv.

[15]  David Hsu.  Identifying key variables and interactions in statistical models of building energy consumption using regularization , 2015 .

[16]  B. Walczak,et al.  Particle swarm optimization (PSO). A tutorial , 2015 .

[17]  Xudong Yang,et al.  Energy and environment in Chinese rural buildings: Situations, challenges, and intervention strategies , 2015 .

[18]  Manuel R. Arahal,et al.  A prediction model based on neural networks for the energy consumption of a bioclimatic building , 2014 .

[19]  Mohammad Mottahedi,et al.  On the development of multi-linear regression analysis to assess energy consumption in the early stages of building design , 2014 .

[20]  Zhiqiang John Zhai,et al.  Comprehensive evaluation of the influence of meta-models on Bayesian calibration , 2017 .

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

[22]  Tiberiu Catalina,et al.  Multiple regression model for fast prediction of the heating energy demand , 2013 .

[23]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[24]  Zhujun Jiang,et al.  Energy consumption in China's rural areas: A study based on the village energy survey , 2017 .

[25]  B. W. Yap,et al.  Comparisons of various types of normality tests , 2011 .

[26]  Lv Jinhu,et al.  A Novel Hybrid Approach of KPCA and SVM for Building Cooling Load Prediction , 2010, 2010 Third International Conference on Knowledge Discovery and Data Mining.

[27]  Fan Yang,et al.  Effect of input variables on cooling load prediction accuracy of an office building , 2018 .

[28]  Qiang Zhang,et al.  Underreported coal in statistics: A survey-based solid fuel consumption and emission inventory for the rural residential sector in China , 2019, Applied Energy.

[29]  Zeyu Wang,et al.  Random Forest based hourly building energy prediction , 2018, Energy and Buildings.

[30]  Wang Xiaomei.  An Investigation of Envelope Situation and Simulation of Heating/Cooling Energy Consumption for Rural Residential Buildings in Shanghai , 2011 .

[31]  S. Tsakovski,et al.  Comparison of the variable importance in projection (VIP) and of the selectivity ratio (SR) methods for variable selection and interpretation , 2015 .

[32]  Daisuke Sumiyoshi,et al.  A simplified model for dynamic analysis of the indoor thermal environment of rooms with a Chinese kang , 2017 .

[33]  Lv Jinhu,et al.  Applying principal component analysis and weighted support vector machine in building cooling load forecasting , 2010, 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering.

[34]  Juha Jokisalo,et al.  Simulation of the heating performance of the Kang system in one Chinese detached house using biomass , 2011 .

[35]  Bin Chen,et al.  Chinese kang as a domestic heating system in rural northern China—A review , 2009 .

[36]  David Fischer,et al.  A stochastic bottom-up model for space heating and domestic hot water load profiles for German households , 2016 .

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

[38]  Jesús Ariel Carrasco-Ochoa,et al.  A new hybrid filter-wrapper feature selection method for clustering based on ranking , 2016, Neurocomputing.

[39]  Zhiqiang Zhai,et al.  An evaluation and model of the Chinese Kang system to improve indoor thermal comfort in northeast rural China – Part-1: Model development , 2015 .

[40]  Xudong Yang,et al.  Thermal performance of a traditional Chinese heated wall with the in-series flow pass: Experiment and modeling , 2014 .

[41]  David R. Riley,et al.  Multi-linear Regression Models to Predict the Annual Energy Consumption of an Office Building with Different Shapes , 2015 .

[42]  Y. Shimoda,et al.  Residential end-use energy simulation at city scale , 2004 .

[43]  Jin Wen,et al.  A systematic feature selection procedure for short-term data-driven building energy forecasting model development , 2019, Energy and Buildings.

[44]  Kadir Kavaklioglu,et al.  Modeling and prediction of Turkey’s electricity consumption using Support Vector Regression , 2011 .

[45]  Qiong Li,et al.  Prediction model of annual energy consumption of residential buildings , 2010, 2010 International Conference on Advances in Energy Engineering.

[46]  Koen Steemers,et al.  Modelling domestic energy consumption at district scale: A tool to support national and local energy policies , 2011, Environ. Model. Softw..

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

[48]  Li Zhen.  Energy Consumption Simulation and Analysis on Energy Saving Reconstruction of Rural House in China Extreme Cold Areas , 2012 .

[49]  F. W. Yu,et al.  Critique of operating variables importance on chiller energy performance using random forest , 2017 .

[50]  Juan D. Gomez,et al.  Predicting future monthly residential energy consumption using building characteristics and climate data: A statistical learning approach , 2016 .

[51]  Hyeun Jun Moon,et al.  Energy consumption model with energy use factors of tenants in commercial buildings using Gaussian process regression , 2018, Energy and Buildings.

[52]  T. Hacib,et al.  Predictors Generation by Partial Least Square Regression for microwave characterization of dielectric materials , 2018, Physica B: Condensed Matter.

[53]  Zhang Su-jua.  Variance Analysis in the Research of Heating Energy Consumption of Rural Buildings , 2013 .