A data-characteristic-driven decomposition ensemble forecasting model for thermal power overcapacity

WANG Delu, MAO Jinqi, SONG Xuefeng, WANG Yadong

Systems Engineering - Theory & Practice ›› 2021, Vol. 41 ›› Issue (3) : 727-743.

PDF(1501 KB)
PDF(1501 KB)
Systems Engineering - Theory & Practice ›› 2021, Vol. 41 ›› Issue (3) : 727-743. DOI: 10.12011/SETP2020-0001

A data-characteristic-driven decomposition ensemble forecasting model for thermal power overcapacity

  • WANG Delu, MAO Jinqi, SONG Xuefeng, WANG Yadong
Author information +
History +

Abstract

By organically integrating data-characteristic-driven modeling idea with multi-modal information ensemble modeling idea, a combination forecasting method and model for overcapacity in China's thermal power industry is constructed. Firstly, the nature and pattern characteristics of thermal power overcapacity scale data are identified and it is found that the data not only has non-stationary and non-linear characteristics, but also has high complexity and mutability characteristics. Secondly, variational mode decomposition method which matches the data characteristics is used to decompose the time series data to obtain multiple components. Then the data characteristics of obtained components are identified, and then a triple exponential smoothing-least square support vector machine model is selected for prediction. Finally the forecasting results of each component are integrated to obtain the final forecasting result of the scale of thermal power overcapacity. Empirical tests show that the forecasting performance of the constructed model is better than the single and other combined prediction models currently widely used in terms of level accuracy, directional accuracy, and stability. The forecast results show that the scale of China's thermal power overcapacity will be still at a relatively high level showing a trend of falling first and then rising. And the institutional distortion will still be the decisive factor for thermal power overcapacity.

Key words

data characteristics / decomposition and ensemble / combined forecasting / overcapacity / thermal power industry

Cite this article

Download Citations
WANG Delu , MAO Jinqi , SONG Xuefeng , WANG Yadong. A data-characteristic-driven decomposition ensemble forecasting model for thermal power overcapacity. Systems Engineering - Theory & Practice, 2021, 41(3): 727-743 https://doi.org/10.12011/SETP2020-0001

References

[1] Shi X, Wang K, Shen Y, et al. A permit trading scheme for facilitating energy transition:A case study of coal capacity control in China[J]. Journal of Cleaner Production, 2020, 256:1-11.
[2] Yang Q, Hou X, Zhang L. Measurement of natural and cyclical excess capacity in China's coal industry[J]. Energy Policy, 2018, 118:270-278.
[3] Corwin S, Johnson T L. The role of local governments in the development of China's solar photovoltaic industry[J]. Energy Policy, 2019, 130:283-293.
[4] Yuan J, Wang Y, Zhang W, et al. Will recent boom in coal power lead to a bust in China? A micro-economic analysis[J]. Energy Policy, 2017, 108:645-656.
[5] Yuan J. Wind energy in China:Estimating the potential[J]. Nature Energy, 2016, 1(7):16095.
[6] Wang D, Wan K, Song X. Quota allocation of coal overcapacity reduction among provinces in China[J]. Energy Policy, 2018, 116:170-181.
[7] Lei H, Yao X, Zhang J. The competitiveness of provincial electric power supply in China:Based on a bottom-up perspective[J]. International Journal of Electrical Power and Energy Systems, 2020, 116:105557.
[8] Wang D, Wan K, Song X, et al. Provincial allocation of coal de-capacity targets in China in terms of cost, efficiency, and fairness[J]. Energy Economics, 2019, 78:109-128.
[9] Feng Y, Wang S, Sha Y, et al. Coal power overcapacity in China:Province-Level estimates and policy implications[J]. Resources, Conservation and Recycling, 2018, 137:89-100.
[10] 林文达. 对我国煤炭行业去产能问题的预测与建议[J]. 经济研究参考, 2017(23):119-123.Lin W D. Prediction and suggestions on the problem of coal industry's capacity reduction in China[J]. Review of Economic Research, 2017(23):119-123.
[11] 孙涵, 杨普容, 成金华. 基于Matlab支持向量回归机的能源需求预测模型[J]. 系统工程理论与实践, 2011, 31(10):2001-2007.Sun H, Yang P R, Cheng J H. Forecasting model of energy demand based on Matlab support vector regression[J]. Systems Engineering-Theory & Practice, 2011, 31(10):2001-2007.
[12] 谷建伟, 隋顾磊, 李志涛, 等. 基于ARIMA-Kalman滤波器数据挖掘模型的油井产量预测[J]. 深圳大学学报(理工版), 2018, 35(6):29-35.Gu J W, Sui G L, Li Z T, et al. Oil well production forecasting method based on ARIMA-Kalman filter data mining model[J]. Journal of Shenzhen University Science and Engineering, 2018, 35(6):29-35.
[13] Wang D, Wang Y, Song X, et al. Coal overcapacity in China:Multiscale analysis and prediction[J]. Energy Economics, 2018, 70:244-257.
[14] Lukas E, Spengler T S, Kupfer S, et al. When and how much to invest? Investment and capacity choice under product life cycle uncertainty[J]. European Journal of Operational Research, 2017, 260(3):1105-1114.
[15] Mathis S, Koscianski J. Excess capacity as a barrier to entry in the US titanium industry[J]. International Journal of Industrial Organization, 1997, 15(2):263-281.
[16] 林毅夫, 巫和懋, 邢亦青. "潮涌现象"与产能过剩的形成机制[J]. 经济研究, 2010, 45(10):4-19.Lin Y F, Wu H M, Xing Y Q. "Wave phenomena" and formation of excess capacity[J]. Economic Research Journal, 2010, 45(10):4-19.
[17] 席鹏辉, 梁若冰, 谢贞发, 等. 财政压力, 产能过剩与供给侧改革[J]. 经济研究, 2017(9):88-104.Xi P H, Liang R B, Xie Z F, et al. Fiscal stress, excess capacity and supply-side reform[J]. Economic Research Journal, 2017(9):88-104.
[18] Lin J, Kahrl F, Liu X. A regional analysis of excess capacity in China's power systems[J]. Resources, Conservation and Recycling, 2018, 129:93-101.
[19] Ming Z, Ping Z, Shunkun Y, et al. Overall review of the overcapacity situation of China's thermal power industry:Status quo, policy analysis and suggestions[J]. Renewable and Sustainable Energy Reviews, 2017, 76:768-774.
[20] Qin Q, Jiao Y, Gan X, et al. Environmental efficiency and market segmentation:An empirical analysis of China's thermal power industry[J]. Journal of Cleaner Production, 2020, 242:118560.
[21] Liu H H, Zhang Z X, Chen Z M, et al. The impact of China's electricity price deregulation on coal and power industries:Two-stage game modeling[J]. Energy Policy, 2019, 134:110957.
[22] Yuan J, Li P, Wang Y, et al. Coal power overcapacity and investment bubble in China during 2015-2020[J]. Energy Policy, 2016, 97:136-144.
[23] Zhao C, Zhang W, Wang Y, et al. The economics of coal power generation in China[J]. Energy Policy, 2017, 105:1-9.
[24] Del Río P, Janeiro L. Overcapacity as a barrier to renewable energy deployment:The Spanish case[J]. Journal of Energy, 2016, 2016:1-10.
[25] Laleman R, Albrecht J. Belgian blackout? Estimations of the reserve margin during the nuclear phase-out[J]. International Journal of Electrical Power and Energy Systems, 2016, 81:416-426.
[26] Taylor J W. An evaluation of methods for very short-term load forecasting using minute-by-minute British data[J]. International Journal of Forecasting, 2008, 24(4):645-658.
[27] de Assis Cabral J, Legey L F L, de Freitas Cabral M V. Electricity consumption forecasting in Brazil:A spatial econometrics approach[J]. Energy, 2017, 126:124-131.
[28] 刘秋华, 徐杨. 基于改进灰色预测法的连云港市电力需求与对策研究[J]. 南京工程学院学报(社会科学版), 2019, 19(3):32-39.Liu Q H, Xu Y. Research into power demand and countermeasures of Lianyungang city based on improved grey prediction method[J]. Journal of Nanjing Institute of Technology (Social Science), 2019, 19(3):32-39.
[29] Zhang Y, Chen B, Pan G, et al. A novel hybrid model based on VMD-WT and PCA-BP-RBF neural network for short-term wind speed forecasting[J]. Energy Conversion and Management, 2019, 195:180-197.
[30] Wu C, Wang J, Chen X, et al. A novel hybrid system based on multi-objective optimization for wind speed forecasting[J]. Renewable Energy, 2020, 146:149-165.
[31] Al-Musaylh M S, Deo R C, Adamowski J F, et al. Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia[J]. Advanced Engineering Informatics, 2018, 35:1-16.
[32] Khwaja A S, Zhang X, Anpalagan A, et al. Boosted neural networks for improved short-term electric load forecasting[J]. Electric Power Systems Research, 2017, 143:431-437.
[33] Yu C, Li Y, Zhang M. Comparative study on three new hybrid models using Elman neural network and empirical mode decomposition based technologies improved by singular spectrum analysis for hour-ahead wind speed forecasting[J]. Energy Conversion and Management, 2017, 147:75-85.
[34] De Oliveira E M, Oliveira F L C. Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods[J]. Energy, 2018, 144:776-788.
[35] Han L, Jing H, Zhang R, et al. Wind power forecast based on improved long short term memory network[J]. Energy, 2019, 189:116300.
[36] Xie G, Zhang N, Wang S. Data characteristic analysis and model selection for container throughput forecasting within a decomposition-ensemble methodology[J]. Transportation Research Part E:Logistics and Transportation Review, 2017, 108:160-178.
[37] Yu L, Wang Z, Tang L. A decomposition-ensemble model with data-characteristic-driven reconstruction for crude oil price forecasting[J]. Applied Energy, 2015, 156:251-267.
[38] Tang L, Yu L, He K. A novel data-characteristic-driven modeling methodology for nuclear energy consumption forecasting[J]. Applied Energy, 2014, 128:1-14.
[39] Guclu Y S. Multiple sen-innovative trend analyses and partial Mann-Kendall test[J]. Journal of Hydrology, 2018, 566:685-704.
[40] Lahmiri S. A variational mode decompoisition approach for analysis and forecasting of economic and financial time series[J]. Expert Systems with Applications, 2016, 55:268-273.
[41] 凌立文, 陈善盈, 张大斌. 考虑层级特性的第一产业总产值预测及修正[J]. 系统工程学报, 2019(3):289-300.Ling L W, Chen S Y, Zhang D B. Forecast and reconciliation of the gross output value of primary industry considering hierarchy characteristics[J]. Journal of Systems Engineering, 2019(3):289-300.
[42] 张华强, 张晓燕. 基于混沌理论和LSSVM的蒸汽负荷预测[J]. 系统工程理论与实践, 2013, 33(4):244-252.Zhang H Q, Zhang X Y. Steam load forecasting based on chaos theory and LSSVM[J]. Systems Engineering-Theory & Practice, 2013, 33(4):244-252.
[43] Vaninsky A. Efficiency of electric power generation in the United States:Analysis and forecast based on data envelopment analysis[J]. Energy Economics, 2006, 28(3):326-338.
[44] 袁家海, 张文华. 中国煤电过剩规模量化及去产能路径研究[J]. 中国能源, 2017, 39(8):14-20.Yuan J H, Zhang W H. Quantification of China's coal power surplus and research on capacity reduction path[J]. Energy of China, 2017, 39(8):14-20.
[45] Zhou K, Yang S. Demand side management in China:The context of China's power industry reform[J]. Renewable and Sustainable Energy Reviews, 2015, 47:954-965.
[46] Zhang Y, Zhang M, Liu Y, et al. Enterprise investment, local government intervention and coal overcapacity:The case of China[J]. Energy Policy, 2017, 101:162-169.
[47] 杨晓光, 程建华. 经济预测的认知与定量方法[J]. 系统科学与数学, 2019, 39(10):1553-1582.Yang X G, Cheng J H. Economic forecasting:Characterisitics and quantitative methods[J]. Journal of Systems Science and Mathematical Sciences, 2019, 39(10):1553-1582.
[48] Lin J, Kahrl F, Yuan J, et al. Challenges and strategies for electricity market transition in China[J]. Energy Policy, 2019, 133:110899.

Funding

National Natural Science Foundation of China (72074210, 71573252); China University of Mining and Technology "Two First-Class" Special Construction Procurement Projects (2018WHCC01)
PDF(1501 KB)

1201

Accesses

0

Citation

Detail

Sections
Recommended

/