Energy efficiency evaluation method based on multi-model fusion strategy

With the raise of “The Green Industrial Revolution” and the growing demand for low-carbon energy, determining the method for assessing energy usage has become an important problem. In this paper, an assessment method of energy is proposed based on the combination of several models. The study of energy efficiency in China is conducted. First, the data related to the energy efficiency in 24 provinces for the last 9 years is gathered. Meanwhile the key factors for ensuring effective energy utilization in two provinces is determined through feature recognition. Then, the comparative analysis on the categories-fusion model’s goodness of fit is performed, which was also used to predict the energy efficiency. Subsequently, the provinces with high and low energy efficiency based on the clustering strategies with multiple models merged are differentiated. Finally, corresponding recommendations for the development problem in China are presented based on the summary of the experimental results. The experimental results show that in comparison with the single-model approach, the merged multiple models has better performance than other methods. Therefore, this approach has a good engineering value.

[1]  Fuli Wang,et al.  Nonlinear process monitoring based on kernel dissimilarity analysis , 2009 .

[2]  Jordi Guitart,et al.  Assessing and forecasting energy efficiency on Cloud computing platforms , 2015, Future Gener. Comput. Syst..

[3]  Qingshan Jiang,et al.  Feature selection via maximizing global information gain for text classification , 2013, Knowl. Based Syst..

[4]  Wen-Shing Lee,et al.  Benchmarking the energy efficiency of government buildings with data envelopment analysis , 2008 .

[5]  Li Yang,et al.  Regional differences of environmental efficiency of China's energy utilization and environmental regulation cost based on provincial panel data and DEA method , 2013, Math. Comput. Model..

[6]  J. Ross Quinlan,et al.  Decision trees and decision-making , 1990, IEEE Trans. Syst. Man Cybern..

[7]  Kemal Polat,et al.  A novel hybrid intelligent method based on C4.5 decision tree classifier and one-against-all approach for multi-class classification problems , 2009, Expert Syst. Appl..

[8]  W. Guan,et al.  Study of spatial patterns and spatial effects of energy eco-efficiency in China , 2016, Journal of Geographical Sciences.

[9]  Qunwei Wang,et al.  Energy efficiency and production technology heterogeneity in China: A meta-frontier DEA approach , 2013 .

[10]  Wen-Jie Zou,et al.  Energy Efficiency Measures and Convergence in China, Taking into Account the Effects of Environmental and Random Factors , 2015 .

[11]  Yongjun Shen,et al.  Evaluation of energy transfer and utilization efficiency of azo dye removal by different pulsed electrical discharge modes , 2008 .

[12]  Wei Liu,et al.  Measurement and evaluation of Chinese regional energy efficiency based on provincial panel data , 2013, Math. Comput. Model..

[13]  Jin-Li Hu,et al.  Total-factor energy efficiency of regions in China , 2006 .

[14]  Yang Fuxia On Influencing Factors Affecting China’s Energy Efficiency: An Empirical Test Based on the VEC Model , 2011 .

[15]  Eyke Hüllermeier,et al.  FURIA: an algorithm for unordered fuzzy rule induction , 2009, Data Mining and Knowledge Discovery.

[16]  Saurabh Kumar,et al.  Energy Efficient Utilization of Resources in Cloud Computing Systems , 2016 .

[17]  Marc A Rosen,et al.  Assessing global resource utilization efficiency in the industrial sector. , 2013, The Science of the total environment.

[18]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.