Forecasting of Chinese Primary Energy Consumption in 2021 with GRU Artificial Neural Network

The forecasting of energy consumption in China is a key requirement for achieving national energy security and energy planning. In this study, multi-variable linear regression (MLR) and support vector regression (SVR) were utilized with a gated recurrent unit (GRU) artificial neural network of Chinese energy to establish a forecasting model. The derived model was validated through four economic variables; the gross domestic product (GDP), population, imports, and exports. The performance of various forecasting models was assessed via MAPE and RMSE, and three scenarios were configured based on different sources of variable data. In predicting Chinese energy consumption from 2015 to 2021, results from the established GRU model of the highest predictive accuracy showed that Chinese energy consumption would be likely to fluctuate from 2954.04 Mtoe to 5618.67 Mtoe in 2021.

[1]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.

[2]  Fuat Egelioğlu,et al.  Economic variables and electricity consumption in Northern Cyprus , 2001 .

[3]  Shaoyan Zhang,et al.  Face recognition with support vector machine , 2003, IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, 2003. Proceedings. 2003.

[4]  B. O’Neill,et al.  Accuracy of past projections of US energy consumption , 2005 .

[5]  S. Iniyan,et al.  Energy models for commercial energy prediction and substitution of renewable energy sources , 2006 .

[6]  Adnan Sözen,et al.  Forecasting Net Energy Consumption Using Artificial Neural Network , 2006 .

[7]  Seyed Farid Ghaderi,et al.  Improved Estimation of Electricity Demand Function by Integration of Fuzzy System and Data Mining Approach , 2006 .

[8]  M. D. Earle,et al.  Application of multiple linear regression to analysis of data from factory energy surveys , 2007 .

[9]  C.S. Ozveren,et al.  Short term load forecasting using Multiple Linear Regression , 2007, 2007 42nd International Universities Power Engineering Conference.

[10]  Xindong Wu,et al.  The Top Ten Algorithms in Data Mining , 2009 .

[11]  M. Duran Toksarı,et al.  Estimating the net electricity energy generation and demand using the ant colony optimization approach: Case of Turkey , 2009 .

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

[13]  William E. Roper,et al.  Energy demand estimation of South Korea using artificial neural network , 2009 .

[14]  Zhiwei Lian,et al.  An Application of Support Vector Machines in Cooling Load Prediction , 2009, 2009 International Workshop on Intelligent Systems and Applications.

[15]  Lambros Ekonomou,et al.  Greek long-term energy consumption prediction using artificial neural networks , 2010 .

[16]  Ujjaini Mukhopadhyay,et al.  Identifying the major players behind increasing global carbon dioxide emissions: a decomposition analysis , 2010 .

[17]  M. R. AlRashidi,et al.  LONG TERM ELECTRIC LOAD FORECASTING BASED ON PARTICLE SWARM OPTIMIZATION , 2010 .

[18]  Murat Kankal,et al.  Modeling and forecasting of Turkey's energy consumption using socio-economic and demographic variables , 2011 .

[19]  Jaume Rosselló,et al.  Estimation of tourism-induced electricity consumption: The case study of Balearics Islands, Spain , 2011 .

[20]  Alun Gu,et al.  Recent development of energy supply and demand in China, and energy sector prospects through 2030 , 2011 .

[21]  J. Mata,et al.  Interpretation of concrete dam behaviour with artificial neural network and multiple linear regression models , 2011 .

[22]  Nazih M. Abu-Shikhah,et al.  Medium-Term Electric Load Forecasting Using Multivariable Linear and Non-Linear Regression , 2011 .

[23]  Hsiao-Tien Pao,et al.  Forecasting of CO2 emissions, energy consumption and economic growth in China using an improved grey model , 2012 .

[24]  P. K. Adom,et al.  Conditional dynamic forecast of electrical energy consumption requirements in Ghana by 2020: A comparison of ARDL and PAM , 2012 .

[25]  J. Armstrong.  Illusions in regression analysis , 2012 .

[26]  Firas M. Tuaimah,et al.  Short-Term Electrical Load Forecasting for Iraqi Power System based on Multiple Linear Regression Method , 2014 .

[27]  Xiang Yin,et al.  A bottom-up analysis of China’s iron and steel industrial energy consumption and CO2 emissions , 2014 .

[28]  Kevin M. Smith,et al.  Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy , 2014 .

[29]  Roozbeh Torkzadeh,et al.  Medium term load forecasting in distribution systems based on multi linear regression & principal component analysis: A novel approach , 2014, 2014 19th Conference on Electrical Power Distribution Networks (EPDC).

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

[31]  Stan Matwin,et al.  Applying instance-weighted support vector machines to class imbalanced datasets , 2014, 2014 IEEE International Conference on Big Data (Big Data).

[32]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

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

[34]  Mohammad Pezeshki,et al.  Sequence Modeling using Gated Recurrent Neural Networks , 2015, ArXiv.

[35]  Chaoqing Yuan,et al.  Forecasting China’s energy demand and self-sufficiency rate by grey forecasting model and Markov model , 2015 .

[36]  Yi-Ming Wei,et al.  China's Farewell to Coal: A Forecast of Coal Consumption through 2020 , 2015 .

[37]  Guglielmina Mutani,et al.  Chinese residential energy demand: Scenarios to 2030 and policies implication , 2015 .

[38]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

[39]  D. Khummongkol,et al.  Electricity Consumption Forecasting in Thailand Using an Artificial Neural Network and Multiple Linear Regression , 2015 .

[40]  Nima Hamta,et al.  Predictive Modeling Techniques to Forecast Energy Demand in the United States: A Focus on Economic and Demographic Factors , 2015 .

[41]  Mohamed Abuella,et al.  Solar power probabilistic forecasting by using multiple linear regression analysis , 2015, SoutheastCon 2015.

[42]  Ting Liu,et al.  Document Modeling with Gated Recurrent Neural Network for Sentiment Classification , 2015, EMNLP.

[43]  Fabiano Castro Torrini,et al.  Long term electricity consumption forecast in Brazil: A fuzzy logic approach , 2016 .

[44]  Lianhong Cai,et al.  Question detection from acoustic features using recurrent neural network with gated recurrent unit , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[45]  Rajib Rana,et al.  Gated Recurrent Unit (GRU) for Emotion Classification from Noisy Speech , 2016, ArXiv.

[46]  Jianxin Wu,et al.  Minimal gated unit for recurrent neural networks , 2016, International Journal of Automation and Computing.

[47]  Howon Kim,et al.  Classification performance using gated recurrent unit recurrent neural network on energy disaggregation , 2016, 2016 International Conference on Machine Learning and Cybernetics (ICMLC).

[48]  Suya You,et al.  Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning , 2016 .

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