考虑电力经济相关性的全社会电量预测算法

胡怡霜, 丁一

分布式能源 ›› 2018, Vol. 3 ›› Issue (5) : 16-21.

PDF(859 KB)
PDF(859 KB)
分布式能源 ›› 2018, Vol. 3 ›› Issue (5) : 16-21. DOI: 10.16513/j.cnki.10-1427/tk.2018.05.003

考虑电力经济相关性的全社会电量预测算法

作者信息 +

Algorithm of Societal Electricity Consumption Forecasting Based on Society-Electricity-Economy Production Function

Author information +
文章历史 +

摘要

在社会经济发展过程中,产业用电量与经济之间存在较强的相关性,而传统算法并未合理考虑两者的相关性特征,也没有从全社会的角度量化分析产业经济与电力之间的相关性,故传统的电量预测算法无法表征其经济特性,不适用于全社会产业电量的高效预测。基于电力-经济生产函数,提出了一种全社会电量预测算法。首先,本文将全社会用电量分为三个产业和居民用电。其次,通过电力-经济生产函数法量化三个产业产值与电量之间的关联性;利用专家分析法对三个产业的未来经济数据和居民用电进行预测;基于三个产业的电力-经济生产函数法和未来经济数据,利用生产函数法预测三个产业的未来电量,从而得到全社会未来用电量。最后,综合考虑三个产业的产业结构调整趋势和电力-经济生产函数的特征,提出产业经济和电力发展规划意见。以浙江省为例,预测2018—2020年的全社会用电量并基于其未来经济、电力发展趋势,提出9条产业经济、电力结构调整意见。通过案例发现,产值的改变都会相应改变产业用电量以及用电量增速,可以通过提高用电量增速来提高或者降低相应产业的比重,从而有效调整产业结构。基于电力-经济生产函数的全社会电量预测算法从宏观的角度分析电量和经济的相关性,从而可以更加全面地预测全社会用电量。

Abstract

In the process of social and economic development, there is a strong correlation between industrial electricity consumption and economy. However, the traditional algorithm does not consider this correlation, and is incapable of quantifying the relationship between societal electricity consumption and industrial output value. Therefore, the traditional electricity prediction algorithm can not characterize its economic characteristics, and is not suitable for efficient prediction of industrial electricity in the whole society. Based on the power-economic production function, this paper proposes a electricity consumption prediction algorithm for the whole society. Firstly, we divides the societal electricity into four level: three major industries and residential electricity. Then, we quantify the correlation between the output value of the three industries and the power supply through the power-economic production function. With the help of development tendency of three major industries economy and residential electricity capacity obtained by expert analysis, and the future electric quantity of the three industries forecasted by the production function method, the future societal electricity consumption can be calculated, based on the power-economic production function method and future economic data of the three industries. Finally, comprehensively considering the trend of industrial structure adjustment in three industries and the characteristics of power-economic production function, we proposes some opinions on the industrial economy and power development planning. Taking Zhejiang province as an example, we forecast its societal electricity consumption during 2018-2020 and propose 9 suggestions on industrial economy and power structure adjustment based on its future economic and power development trend. In the case, it is found that changes in output value will correspondingly change the industrial electricity consumption and electricity consumption growth. The proportion of the corresponding industries can be increased or reduced by increasing the growth rate of electricity consumption, so as to effectively adjust the industrial structure. The whole society electricity forecasting algorithm based on power-economic production function analyses the correlation between electricity and economy from a macro perspective, which can predict the whole social electricity consumption more comprehensively.

关键词

用电量预测 / 电力经济相关性 / 生产函数 / 产业结构调整

Key words

electric consumption forecasting / economic relevance / production function / adjustment of industrial structure

引用本文

导出引用
怡霜, . 考虑电力经济相关性的全社会电量预测算法[J]. 分布式能源. 2018, 3(5): 16-21 https://doi.org/10.16513/j.cnki.10-1427/tk.2018.05.003
Yishuang HU, Yi DING. Algorithm of Societal Electricity Consumption Forecasting Based on Society-Electricity-Economy Production Function[J]. Distributed Energy Resources. 2018, 3(5): 16-21 https://doi.org/10.16513/j.cnki.10-1427/tk.2018.05.003
中图分类号: TK 6   

参考文献

[1]
中华人民共和国国家统计局. 浙江省全省生产总值[EB/OL]. (2014)[2018-04-18].
[2]
韩丹张宏波贾勇. 经济因素对电量的影响分析与预测[J]. 吉林电力2009, 37(3): 16-19.
HAN Dan, ZHANG Hongbo, JIA Yong. Analysis and forecasting for effect of economic factor on electricity consumption[J]. Jilin Electric Power, 2009, 37(3): 16-19.
[3]
吴奎忠. 吉林省经济社会发展对电力公司的电量需求影响分析[D]. 长春:吉林大学,2013.
WU Kuizhong. Impact analysis of Jilin province's economic and social development on the power company's electricity demand[D]. Changchun: Jilin University, 2013.
[4]
KAYTEZ F, TAPLAMACIOGLU M C, CAM E, et al. Forecasting electricity consumption: a comparison of regression analysis, neural networks and least squares support vector machines[J]. International Journal of Electrical Power & Energy Systems, 2015, 67(67): 431-438.
[5]
ANGELOPOULOS D, PSARRAS J, SISKOS Y. Long-term electricity demand forecasting via ordinal regression analysis: the case of Greece[C]//PowerTech, 2017 IEEE. Manchester, England: The University of Manchester, 2017: 1-6.
[6]
LIU Shuang, TIAN Lixia. The study of long-term electricity load forecasting based on improved grey prediction model[C]//ICMLC. Tianjin, China: The University of Tianjin, 2013: 653-656.
[7]
JIANG Ping, ZHOU Qingping, JIANG Haiyan, et al. An optimized forecasting approach based on grey theory and cuckoo search algorithm: a case study for electricity consumption in new south wales[J]. Abstract & Applied Analysis, 2014(9): 1-13.
[8]
WIBOWO W, DWIJANTARI S, HARTATI A. Time series machine learning: implementing ARIMA and hybrid ARIMA-ANN for electricity forecasting modeling[C]//SCD2017. Yogyakarta, Singapore: Springer, 2017: 126-139.
[9]
王奕萱. 基于统计特征量和支持向量机的短期售电量预测研究[J]. 华北电力技术2013(12): 17-19.
WANG Yixuan. Research on short term electricity sales forecasting based on statistical characteristics and support vector machine [J]. North China Electric Power, 2013(12): 17-19.
[10]
BIKCORA C, VERHEIJEN L, WEILAND S. Density forecasting of daily electricity demand with ARMA-GARCH, CAViaR, and CARE econometric models[J]. Sustainable Energy Grids & Networks, 2018, 13: 148-156.
[11]
OHTSUKA Y, OGA T, KAKAMU K. Forecasting electricity demand in Japan: A bayesian spatial autoregressive ARMA approach[J]. Computational Statistics & Data Analysis, 2010, 54(11): 2721-2735.
[12]
吴杰宋国堂卢志刚,等. 基于偏最小二乘回归与比重法的月售电量预测[J]. 电力系统及其自动化学报2008, 20(3): 66-69.
WU Jie, SONG Guotang, LU Zhigang, et al. Forecasting for monthly electricity consumption using partial least-square regressive and proportion model[J]. Proceedings of the CSU-EPSA, 2008, 20(3): 66-69.
[13]
朱国华吕华珍王林. 一种改进的月电量灰色预测模型[J].湖北电力2007, 31(2): 4-6.
ZHU Guohua, Huazheng, WANG Lin. Improved grey prediction model for monthly electric power demand[J]. Hubei Electric Power, 2007, 31(2): 4-6.
[14]
袁吉伟. 基于生产函数法的我国潜在经济增速分析及预测[J]. 金融理论探索2012(5): 31-35.
YUAN Jiwei. Forecasting and analysis of economic growth in China based on production function[J]. Discovery in Economy, 2012(5): 31-35.
[15]
谢保嵩雷进贤. 基于生产函数法的中国潜在产出及经济增长前景研究[J]. 金融监管研究2013(12): 53-76.
XIE Baosong, LEI Jinxian. The research of potential output and economic growth in China based on production function [J]. Financial Regulation Research, 2013(12): 53-76.
[16]
胡兆光. 电力经济学引论[M]. 北京:清华大学出版社,2013.

编辑: 毅恒
PDF(859 KB)

Accesses

Citation

Detail

段落导航
相关文章

/