Energy Demand Forecasting Method Based on Shapley Value Theory

doi:10.3969/j.issn.1000-7229.2016.01.003

Abstract

Abstract:

The reasonable and accurate prediction of energy consumption is of great significance for scientifically making energy plan and optimizing the structure of energy and industry. Aiming at the shortcomings of the traditional energy forecasting method, which has low prediction accuracy and not be fully accounted for the influence of environmental policies, this paper presents a combined forecasting and scene correction model based on the Shapley value theory. Firstly, according to the requirements and characteristics of energy consumption forecasting, we select three single forecasting models, and determine the weight of the single model in the combined model through the Shapley value theory to obtain the basic forecasting result. Then, three main aspects of technological progress, economic development and policy change are quantified as the correction term and coefficient to further improve the model function and obtain the modified prediction results under different scenes. Finally, the case of life energy consumption in T City is studied. The results show that the forecasted value curve and actual value curve are highly fitted in the proposed method, which can improve the accuracy of energy forecasting based on the full consideration of environmental policy influence and provide decision basis for the energy planning of related departments.

Key words: combined model, energy consumption forecasting, Shapley value, scene correlation

CLC Number:

LI Na, LIU Shuyong, ZENG Ming, LIU Lixia, LI Yuanfei, HAN Xu. Energy Demand Forecasting Method Based on Shapley Value Theory[J]. Electric Power Construction, 2016, 37(1): 15-22.

References

［1］王祥. 中国能耗强度影响因素分析与节能目标实现［D］. 沈阳：东北财经大学, 2012.
WANG Xiang. The research for influencing factors of China energy consumption intensity and achieve of target to saving energy［D］. Shenyang：Dongbei University of Finance and Economics, 2012.
［2］邬亮, 赵小凡, 齐晔. 改革开放以来中国能源供需特征与治理模式［J］. 中国人口SymbolWC@资源与环境, 2014(12): 147-152.
WU Liang, ZHAO Xiaofan, QI Ye. Demand, supply and governance of energy in reform-era China［J］. China Population Resources and Environment, 2014(12): 147-152.
［3］王刚, 徐园, 叶承晋. 浙江省终端能源结构演化进程分析［J］. 能源工程, 2015(1): 26-30, 36.
WANG Gang, XU Yuan, YE Chengjin. Analysis of the terminal energy structure evolution process in Zhejiang province［J］. Energy Engineering, 2015(1): 26-30, 36.
［4］付立东, 张金锁, 冯雪. GA-SA模型预测中国能源需求［J］. 系统工程理论与实践, 2015,35(3):780-789.
FU Lidong, ZHANG Jinsuo, FENG Xue. GA-SA model forecasting Chinas energy demand［J］.Systems Engineering-Theory & Practice,2015,35(3):780-789.
［5］陶然, 蔡云泽, 楼振飞, 等. 国内外能源预测模型和能源安全评价体系研究综述［J］. 上海节能, 2012(1):16-21.
TAO Ran, CAI Yunze, LOU Zhenfei, et al. Comprehensive research of domestic and foreign energy forecast model and energy safety appraisal systems ［J］.Shanghai Energy Conservation, 2012(1):16-21.
［6］韩睿. 能源需求预测误差成因研究及启示——基于IEA和EIA中长期预测数据［D］. 北京：北京理工大学, 2015.
HAN Rui. Study on energy demand medium-and long forecast error causes of world major energy agencies——IEA&EIA［D］. Beijing：Beijing Institute of Technology, 2015.
［7］张旭超. 北京市终端能源预测模型及发展对策研究［D］. 北京：华北电力大学, 2009.
ZHANG Xuchao. Research on end-use energy forecasting model and strategy of sustainable development in Beijing［D］. Beijing：North China Electric Power University, 2009.
［8］刘殿海, 杨勇平, 杨昆, 等. 基于马尔科夫链的能源结构与污染物排放预测模型及其应用［J］. 中国电力,2006,39(3):8-13
LIU Dianhai, YANG Yongping, YANG Kun, et al. Forecasting model and its application of energy structure and pollutant emission based on Markov chain［J］.Electric Power,2006,39(3):8-13.
［9］叶彬, 秦丹丹, 杨欣, 等. 电力占终端能源消费比重分析预测方法及应用［J］. 电力与能源, 2014(2): 156-161.
YE Bin, QIN Dandan,YANG Xin, et al. Analysis ＆ forecasting method and application of electric energy proportion in final energy consumption［J］.Power & Energy,2014(2):156-161.
［10］柴岩, 刘翔. 改进的GM(1,1)-LSSVM模型及其在能源消耗预测中的应用［J］. 统计与决策, 2014(17): 84-87.
［11］王明刚, 廖为鲲,许华, 等. 政府调控下的能源供需系统动力学分析［J］. 数学的实践与认识,2013,43(8) : 50-61.
WANG Minggang, LIAO Weikun, XU Hua, et al. Energy demand-supply model with government regulation and its dynamical analysis［J］.Mathematics in Practice and Theory,2013,43(8) : 50-61.
［12］陈卫东, 朱红杰. 基于粒子群优化算法的中国能源需求预测［J］. 中国人口SymbolWC@资源与环境, 2013(3): 39-43.
CHEN Weidong, ZHU Hongjie. Energy demand forecast in China based on particle swarm optimization algorithm［J］. China Population Resources and Environment, 2013(3): 39-43.
［13］秦国真. 云南能源需求影响因素分析及预测［D］. 昆明：云南财经大学, 2012.
QIN Guozhen. Energy demand impact factors analysis and forecasts of Yunnan province［D］. Kunming：Yunnan University of Finance and Economics, 2012.
［14］张志启. 我国能源消费总量预测建模分析［D］.包头：内蒙古科技大学, 2012.
ZHANG Zhiqi. Modeling analysis of China’s total energy consumption predictive［D］.Baotou：Inner Mongolia University of Science and Technology, 2012.
［15］谭显东, 胡兆光, 彭谦. 考虑能效电厂的供需资源组合优化模型［J］. 电网技术,2009, 33(20):108-112.
TAN Xiandong, HU Zhaoguang, PENG Qian. A resource combination optimization model considering efficiency power plant［J］. Power System Technology, 2009, 33(20):108-112.
［16］陈玉金, 刘建永, 李凌, 等. 基于神经网络回归分析组合模型的能源消耗预测研究［J］. 兵工自动化,2008,27(11): 59-60.
CHEN Yujin, LIU Jianyong, LI Ling, et al. Forecast and research on energy consumption based on analytical and combined model of BP neural network and regression［J］.Ordnance Industry Automation,2008,27(11): 59-60.
［17］尹航. 节能减排环境下电能替代其他能源评价方法研究［D］. 北京：华北电力大学, 2013.
YIN Hang. Energy conservation and emission reduction environment power to substitute other energy evaluation method research［D］. Beijing：North China Electric Power University, 2013.
［18］万磊, 郑季良. 基于情景分析法的云南省能源消耗预测［C］//第三届（2008）中国管理学年会——金融分会场论文集. 长沙：中国管理现代化研究会, 2008: 5.
［19］KUMAR U, JAIN V K. Time series models (grey-markov, grey model with rolling mechanism and singular spectrum analysis) to forecast energy consumption in India［J］. Energy, 2010, 35(4): 354-362
［20］JUNGHANS A . Decision support model for energy-efficient improvement of entire building stocks ［J］. Facilities, 2013, 31(3): 173-184.
［21］王舒容. 天津市人口发展趋势预测［D］. 天津：天津理工大学, 2013.
WANG Shurong. Prediction of the trend of population development in Tianjin［D］. Tianjin：Tianjin University of Technology, 2013.