Study on A Simple Model to Forecast the Electricity Demand under China’s New Normal Situation

A simple model was built to predict the national and regional electricity demand by sectors under China’s new normal situation. In the model, the data dimensionality reduction method and the Grey model (GM(1,1)) were combined and adopted to disaggregate the national economic growth rate into regional levels and forecast each region’s contribution rate to the national economic growth and regional industrial structure. Then, a bottom–up accounting model that considered the impacts of regional industrial structure transformation, regional energy efficiency, and regional household electric consumption was built to predict national and regional electric demand. Based on the predicted values, this paper analyzed the spatial changes in electric demand, and our results indicate the following. Firstly, the proposed model has high accuracy in national electricity demand prediction: the relative error in 2017 and 2018 was 2.90% and 2.60%, respectively. Secondly, China’s electric demand will not peak before 2025, and it is estimated to be between 7772.16 and 8458.85 billion kW·h in 2025, which is an increase of 31.28–42.88% compared with the total electricity consumption in 2016. The proportion of electricity demand in the mid-west regions will increase, while the eastern region will continue to be the country’s load center. Thirdly, under China’s new normal, households and the tertiary industry will be the main driving forces behind the increases in electric demand. Lastly, the drop in China’s economy under the new normal will lead to a decline in the total electricity demand, but it will not evidently change the electricity consumption share of the primary industry, secondary industry, tertiary industry, and household sector.

[1]  Paola Zuccolotto,et al.  Pricing strategies for Italian red wine , 2011 .

[2]  Randall Spalding-fecher,et al.  Electricity supply and demand scenarios for the Southern African power pool , 2017 .

[3]  Christian A. Gueymard,et al.  Minimum redundancy – Maximum relevance with extreme learning machines for global solar radiation forecasting: Toward an optimized dimensionality reduction for solar time series , 2017 .

[4]  C. Kang,et al.  Input-output table of electricity demand and its application , 2010 .

[5]  Yongxiu He,et al.  Urban long term electricity demand forecast method based on system dynamics of the new economic normal: The case of Tianjin , 2017 .

[6]  Usman Zia,et al.  The long-term forecast of Pakistan's electricity supply and demand: An application of long range energy alternatives planning , 2015 .

[7]  Nicholas F. Marshall,et al.  Extracting geography from trade data , 2016, 1607.05235.

[8]  Hyojoo Son,et al.  Short-term forecasting of electricity demand for the residential sector using weather and social variables , 2017 .

[9]  H. Zha,et al.  Principal manifolds and nonlinear dimensionality reduction via tangent space alignment , 2004, SIAM J. Sci. Comput..

[10]  Shian-Chang Huang,et al.  Integrating nonlinear graph based dimensionality reduction schemes with SVMs for credit rating forecasting , 2009, Expert Syst. Appl..

[11]  Xiao Zhong,et al.  Forecasting daily stock market return using dimensionality reduction , 2017, Expert Syst. Appl..

[12]  Hai-ying He,et al.  Electricity demand price elasticity in China based on computable general equilibrium model analysis , 2011 .

[13]  Zhengyan Shao,et al.  On electricity consumption and economic growth in China , 2017 .

[14]  张振跃,et al.  Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment , 2004 .

[15]  W. Nuttall,et al.  A dynamic simulation of low-carbon policy influences on endogenous electricity demand in an isolated island system , 2017 .

[16]  Shaolong Sun,et al.  A new dynamic integrated approach for wind speed forecasting , 2017 .

[17]  A. Torres,et al.  A multi-agent system providing demand response services from residential consumers , 2015 .

[18]  Luiz Fernando Loureiro Legey,et al.  Electricity consumption forecasting in Brazil: A spatial econometrics approach , 2017 .

[19]  Bin Chen,et al.  Can equalization of public services narrow the regional disparities in China? A spatial econometrics approach , 2017 .

[20]  Qian Ma,et al.  Factors influencing CO2 emissions in China's power industry: Co-integration analysis , 2013 .

[21]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[22]  Humberto Verdejo,et al.  Statistic linear parametric techniques for residential electric energy demand forecasting. A review and an implementation to Chile , 2017 .

[23]  Julián Pérez-García,et al.  Analysis and long term forecasting of electricity demand trough a decomposition model: A case study for Spain , 2016 .

[24]  V. Bianco,et al.  Electricity consumption forecasting in Italy using linear regression models , 2009 .

[25]  Suhonoa.  Long-term electricity demand forecasting of Sumatera system based on electricity consumption intensity and Indonesia population projection 2010-2035 , 2015 .

[26]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[27]  Rosalie L. Tung.  Opportunities and Challenges Ahead of China's “New Normal” , 2016 .

[28]  Jiang Lin,et al.  Economic rebalancing and electricity demand in China , 2016 .

[29]  Eva González Romera,et al.  Forecasting of the electric energy demand trend and monthly fluctuation with neural networks , 2007, Comput. Ind. Eng..

[30]  Radu Zmeureanu,et al.  Forecasting electric demand of supply fan using data mining techniques , 2016 .

[31]  José Francisco Moreira Pessanha,et al.  ScienceDirect Information Technology and Quantitative Management ( ITQM 2015 ) Forecasting long-term electricity demand in the residential sector , 2015 .

[32]  Lei Zhu,et al.  Emission path planning based on dynamic abatement cost curve , 2016, Eur. J. Oper. Res..

[33]  Diana Domanska,et al.  Handling high-dimensional data in air pollution forecasting tasks , 2016, Ecol. Informatics.

[34]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[35]  Georgios Sermpinis,et al.  Reverse adaptive krill herd locally weighted support vector regression for forecasting and trading exchange traded funds , 2017, Eur. J. Oper. Res..

[36]  V. Bianco,et al.  Linear Regression Models to Forecast Electricity Consumption in Italy , 2013 .

[37]  Chi-Keung Woo,et al.  How much have electricity shortages hampered China's GDP growth? , 2013 .

[38]  Carlos Maté,et al.  Electric power demand forecasting using interval time series: A comparison between VAR and iMLP , 2010 .

[39]  Eva Gonzalez-Romera,et al.  Monthly electric demand forecasting with neural filters , 2013 .

[40]  B. Zhang,et al.  Energy implications of China's regional development: New insights from multi-regional input-output analysis , 2017 .

[41]  Lu Zongxiang,et al.  Multiple Data Source Dimensionality Reduction Pretreatment Used in Ultra-Short Term Wind Resource Forecast , 2015 .

[42]  Dongxiao Niu,et al.  Incorporating the influence of China's industrial capacity elimination policies in electricity demand forecasting , 2017 .

[43]  Zhen Liu,et al.  Multi-agent based experimental analysis on bidding mechanism in electricity auction markets , 2012 .

[44]  Maria Grazia De Giorgi,et al.  Photovoltaic forecast based on hybrid PCA-LSSVM using dimensionality reducted data , 2016, Neurocomputing.

[45]  Tanveer Ahmad,et al.  Utility companies strategy for short-term energy demand forecasting using machine learning based models , 2018 .