Forecasting energy consumption in Anhui province of China through two Box-Cox transformation quantile regression probability density methods

Abstract Energy consumption can be taken as one of crucial indicators for economic development in any regions. Rapid development of economic, population and urbanization in Anhui province of China has led energy consumption to grow rapidly. The considerable demand for energy has become an issue of great concern. For proper policy formulation, it is necessary to have reliable forecasts for energy consumption. However, energy consumption forecasting is affected by some potential factors, including historical energy consumption, economic activities, population and weather. These uncertain factors put forward higher requirements for energy consumption forecasting methods. Considering these problems, a reasonable feature selection method called stepwise regression is adopted to extract important variables before prediction. Historical energy consumption, average annual GDP growth rate, and total GDP are identified as key factors on annual energy consumption. Then, two probability density forecasting methods based on Box-Cox transformation quantile regression via normal distribution (N-BCQR) and gamma distribution(G-BCQR) are proposed to measure the uncertainty and estimate the future demand of energy in Anhui province of China. The comparatives results show that the N-BCQR outperforms G-BCQR and other existing methods in terms of point forecasts and interval predictions. In addition, on the strength of predefined assumptions regarding the average annual gross domestic product (GDP) growth rate, the energy consumption of Anhui province through 2023 is forecasted. The results indicate that total energy consumption of Anhui is an important component determining local economic growth.

[1]  Xiping Wang,et al.  A Hybrid Neural Network and ARIMA Model for Energy Consumption Forcasting , 2012, J. Comput..

[2]  Yanpeng Cai,et al.  An Integrated Modeling Approach for Forecasting Long-Term Energy Demand in Pakistan , 2017 .

[3]  Omid Nematollahi,et al.  Experimental investigation of energy consumption and environmental impact of adaptive defrost in domestic refrigerators , 2016 .

[4]  Andreas Svensson,et al.  Probabilistic forecasting of electricity consumption, photovoltaic power generation and net demand of an individual building using Gaussian Processes , 2018 .

[5]  Derek W. Bunn,et al.  Modeling the UK electricity price distributions using quantile regression , 2016 .

[6]  R. Koenker,et al.  Robust Tests for Heteroscedasticity Based on Regression Quantiles , 1982 .

[7]  Xiantao Liu,et al.  Prediction of long-term gas load based on particle swarm optimization and gray neural network model , 2017 .

[8]  Haiyan Li,et al.  Probability density forecasting of wind power using quantile regression neural network and kernel density estimation , 2018 .

[9]  Harun Kemal Ozturk,et al.  Estimating energy demand of Turkey based on economic indicators using genetic algorithm approach , 2004 .

[10]  H. Ozturk,et al.  Application of genetic algorithm (GA) technique on demand estimation of fossil fuels in Turkey , 2008 .

[11]  Joakim Widén,et al.  Review on probabilistic forecasting of photovoltaic power production and electricity consumption , 2018 .

[12]  B. Moreno,et al.  A grey neural network and input-output combined forecasting model. Primary energy consumption forecasts in Spanish economic sectors , 2016 .

[13]  James W. Taylor.  A Quantile Regression Neural Network Approach to Estimating the Conditional Density of Multiperiod Returns , 2000 .

[14]  Eduardo Gomes Salgado,et al.  Forecasting number of ISO 14001 certifications in the Americas using ARIMA models , 2017 .

[15]  Shanlin Yang,et al.  Short-term power load probability density forecasting based on quantile regression neural network and triangle kernel function , 2016 .

[16]  Parag Sen,et al.  Application of ARIMA for forecasting energy consumption and GHG emission: A case study of an Indian pig iron manufacturing organization , 2016 .

[17]  Zheng-Xin Wang,et al.  Forecasting Chinese carbon emissions from fossil energy consumption using non-linear grey multivariable models , 2017 .

[18]  T. Yee.  Quantile regression via vector generalized additive models , 2004, Statistics in medicine.

[19]  Z. Yumurtacı,et al.  Electric Energy Demand of Turkey for the Year 2050 , 2004 .

[20]  Alex J. Cannon.  Quantile regression neural networks: Implementation in R and application to precipitation downscaling , 2011, Comput. Geosci..

[21]  Serhat Kucukali,et al.  Turkey’s short-term gross annual electricity demand forecast by fuzzy logic approach , 2010 .

[22]  R. Koenker,et al.  Regression Quantiles , 2007 .

[23]  Mohan Liu,et al.  Prediction and analysis of the three major industries and residential consumption CO2 emissions based on least squares support vector machine in China , 2016 .

[24]  G. Aydin.  Modeling of energy consumption based on economic and demographic factors: The case of Turkey with projections , 2014 .

[25]  A. Hussain,et al.  Forecasting electricity consumption in Pakistan: the way forward , 2016 .

[26]  Fernando Luiz Cyrino Oliveira,et al.  Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods , 2018 .

[27]  Tao Lu,et al.  Modeling and forecasting energy consumption for heterogeneous buildings using a physical -statistical approach , 2015 .

[28]  S. Fan,et al.  Short-term load forecasting based on an adaptive hybrid method , 2006, IEEE Transactions on Power Systems.

[29]  Abbas Khosravi,et al.  Uncertainty handling using neural network-based prediction intervals for electrical load forecasting , 2014 .

[30]  Abbas Rohani,et al.  Assessment of energy consumption and modeling of output energy for wheat production by neural network (MLP and RBF) and Gaussian process regression (GPR) models , 2018 .

[31]  Carlo Renno,et al.  ANN model for predicting the direct normal irradiance and the global radiation for a solar application to a residential building , 2016 .

[32]  Chuanglin Fang,et al.  Urbanisation, energy consumption, and carbon dioxide emissions in China: A panel data analysis of China’s provinces , 2014 .

[33]  Tian Xia,et al.  Estimation of demand response to energy price signals in energy consumption behaviour in Beijing, China , 2014 .

[34]  Jolanta Szoplik,et al.  Forecasting of natural gas consumption with artificial neural networks , 2015 .

[35]  Jinxing Che,et al.  An incremental electric load forecasting model based on support vector regression , 2016 .

[36]  Tze Ling Ng,et al.  Equivalent full-load hours for assessing climate change impact on building cooling and heating energy consumption in large Asian cities , 2017 .

[37]  Shuo Wang,et al.  Short-term power load probability density forecasting method using kernel-based support vector quantile regression and Copula theory , 2017 .

[38]  Derek W. Bunn,et al.  Analysis and Forecasting of Electricty Price Risks with Quantile Factor Models , 2016 .

[39]  M. Hadi Amini,et al.  A novel multi-time-scale modeling for electric power demand forecasting: From short-term to medium-term horizon , 2017 .

[40]  Saeed-Reza Sabbagh-Yazdi,et al.  Evaluating the effect of particulate matter pollution on estimation of daily global solar radiation using artificial neural network modeling based on meteorological data , 2017 .

[41]  Chun-Ping Chang,et al.  The impact of energy consumption on economic growth: Evidence from linear and nonlinear models in Taiwan , 2007 .

[42]  Guohua Cao,et al.  Support vector regression with fruit fly optimization algorithm for seasonal electricity consumption forecasting , 2016 .

[43]  Yu Bengong.  A Power Load Probability Density Forecasting Method Based on RBF Neural Network Quantile Regression , 2013 .

[44]  Mahendran Shitan,et al.  Forecasting with univariate time series models : a case of export demand for Peninsular Malaysia’s moulding and chipboard. , 2010 .

[45]  Jeyraj Selvaraj,et al.  Long-term electrical energy consumption formulating and forecasting via optimized gene expression programming , 2017 .

[46]  Amir H. Gandomi,et al.  Building energy consumption forecast using multi-objective genetic programming , 2018 .

[47]  M. Saberi,et al.  Improved Estimation of Electricity Demand Function by Integration of Fuzzy System and Data Mining Approach , 2006, 2006 IEEE International Conference on Industrial Technology.

[48]  Coşkun Hamzaçebi,et al.  Forecasting the annual electricity consumption of Turkey using an optimized grey model , 2014 .

[49]  A. Bennouna,et al.  Energy needs for Morocco 2030, as obtained from GDP-energy and GDP-energy intensity correlations , 2016 .

[50]  M. A. Rafe Biswas,et al.  Regression analysis for prediction of residential energy consumption , 2015 .

[51]  Nadia S. Ouedraogo.  Africa energy future: Alternative scenarios and their implications for sustainable development strategies , 2017 .

[52]  Feng Liu,et al.  A hybrid forecasting model based on date-framework strategy and improved feature selection technology for short-term load forecasting , 2017 .

[53]  Yi Zeng,et al.  Multifactor-influenced energy consumption forecasting using enhanced back-propagation neural network , 2017 .

[54]  T J Cole,et al.  Smoothing reference centile curves: the LMS method and penalized likelihood. , 1992, Statistics in medicine.