Analysis method of electric energy substitution potential based on time series and BP neural network

doi:10.3969/j.issn.2097-0706.2022.03.006

Abstract

Abstract:

A prediction method based on time series and BP neural network is proposed.The time series model based on cubic exponential smoothing method is used to predict the electric energy substitution,and the prediction results are corrected by BP neural network.The prediction and comparative analysis on energy consumption are made according to the data from National Bureau of Statistics.The results of a case study show that the combination forecast method based on time series and BP neural network can make a more accurate prediction on electric energy substitution than a single prediction method,which provides certain guidance for the analysis on electric energy substitution potential.

Key words: electric energy substitution potential, time series forecast, BP neural network, combination forecast

CLC Number:

TK01

LIAO Minle, HUANG Chongyang, DAI Chengcheng, LI Hualin, FAN Gaosong. Analysis method of electric energy substitution potential based on time series and BP neural network[J]. Integrated Intelligent Energy, 2022, 44(3): 38-43.

Figures/Tables 8

Fig.1

Fig.2

Fig.3

Table 1

Fig.4

Table 2

Fig.5

Table 3

References 21

[1]	杨博文. 习近平新发展理念下碳达峰、碳中和目标战略实现的系统思维、经济理路与科学路径[J]. 经济学家, 2021(9):5-12.
	YANG Bowen. The systematic thinking,economic logic and scientific path for the realization of carbon summit and carbon neutral target strategy under Xi Jinping's new development concept[J]. Economist, 2021(9):5-12.
[2]	刘振亚. 电能替代是实现碳达峰碳中和的重要途径[J]. 记者观察, 2021(13):41-45.
[3]	孙伟卿, 谈一鸣, 曾平良, 等. 考虑电能替代的全球负荷变化趋势分析[J]. 电网技术, 2019, 43(2):678-687.
	SUN Weiqing, TAN Yiming, ZENG Pingliang, et al. Analysis on variation trend of global load considering electricity substitution[J]. Power System Technology, 2019, 43(2):678-687.
[4]	国家能源局. 关于推进电能替代的指导意见[Z]. 发改能源〔2016〕1054号. 2016.
[5]	刘可真, 王骞, 赵明, 等. 基于多方合作博弈及梯级化的电能替代效益分析[J]. 电网技术, 2020, 44(2):711-718.
	LIU Kezhen, WANG Qian, ZHAO Min, et al. Benefit analysis of electric energy substitution based on multi-player cooperative game and cascade model[J]. Power System Technology, 2020, 44(2):711-718.
[6]	陈增. 区域电能替代潜力评估体系及模型研究[D]. 北京:华北电力大学, 2019.
[7]	李艳梅, 陈增. 基于联系度优化TOPSIS法的区域电能替代潜力评估研究[J]. 电网技术, 2019, 43(2):687-695.
	LI Yanmei, CHEN Zeng. Study on regional electric energy substitution potential evaluation based on TOPSIS method of optimized connection degree[J]. Power System Technology, 2019, 43(2):687-695.
[8]	孙毅, 周爽, 单葆国, 等. 多情景下的电能替代潜力分析[J]. 电网技术, 2017, 41(1):118-123.
	SUN Yi, ZHOU Shuang, SHAN Baoguo, et al. Analysis of electric power alternative potential under multi-scenario[J]. Power System Technology, 2017, 41(1):118-123.
[9]	孙毅, 石墨, 单葆国, 等. 基于粒子群优化支持向量机的电能替代潜力分析方法[J]. 电网技术, 2017, 41(6):1767-1771.
	SUN Yi, SHI Mo, SHAN Baoguo, et al. Electric energy substitution potential analysis method based on particle swarm optimization support vector machine[J]. Electric Power System Technology, 2017, 41(6):1767-1771.
[10]	陈涛, 吕松, 任廷林, 等. 基于最小二乘支持向量机的周用电量预测方法[J]. 华电技术, 2020, 42(1):35-40.
	CHEN Tao, LYU Song, REN Tinglin, et al. Prediction method for weekly electricity consumption based on LSSVM algorithm[J]. Huadian Technology, 2020, 42(1):35-40.
[11]	刘国静, 谈健, 李琥, 等. 基于Logistic模型的电能替代电量预测[J]. 电力工程技术, 2018, 37(6):39-43.
	LIU Guojing, TAN Jian, LI Hu, et al. Forecast of electric energy substitution based on logistic model[J]. Power System Technology, 2018, 37(6):39-43.
[12]	WAGENA M B, GOERING D, COLLICK A S, et al. Comparison of short-term streamflow forecasting using stochastic time series,neural networks,process-based,and Bayesian models[J/OL]. Environmental Modelling and Software, 2020.(2020-04-08)[2021-10-09]. https://doi.org/10.1016/j.envsoft.2020.104669.
[13]	WU Y Q, GAO R L, YANG J Z. Prediction of coal and gas outburst:A method based on the BP neural network optimized by GASA[J]. Process Safety and Environmental Protection, 2020(133):64-72.
[14]	YANG S M, CHEN D J, LI S L, et al. Carbon price forecasting based on modified ensemble empirical mode decomposition and long short-term memory optimized by improved whale optimization algorithm[J/OL]. Science of the Total Environment,2020.(2020-05-10)[2021-10-09]. https://doi.org/10.1016/j.scitotenv.2020.137117.
[15]	吴佳懋, 李艳, 符一健. 基于粗糙集-混沌时间序列Elman神经网络的短期用电量预测[J]. 电力系统保护与控制, 2019, 47(3):23-30.
	WU Jiamao, LI Yan, FU Yijian. Short-term power consumption prediction based on rough set chaotic time series Elman neural network[J]. Power System Protection and Control, 2019, 47(3):23-30.
[16]	胡倩, 孙志达, 江坷滕, 等. 基于短期负荷打捆预测的售电公司偏差考核控制方法[J]. 华电技术, 2021, 43(4):47-55.
	HU Qian, SUN Zhida, JIANG Keteng, et al. Deviation assessment and control method for electricity sales companies based on short-term load bundling forecast[J]. Huadian Technology, 2021, 43(4):47-55.
[17]	ZHANG J H, MENG H, GU B, et al. Research on short-term wind power combined forecasting and its Gaussian could uncertainty to support the integration of renewables and EVs[J]. Renewable Energy, 2020(153):884-899.
[18]	于群, 张铮, 屈玉清, 等. 基于ARMA-GABP组合模型的电网大停电事故损失负荷预测[J]. 中国电力, 2018, 51(11):38-44.
	YU Qun, ZHANG Zheng, QU Yuqing, et al. Power loss prediction of large blackouts in power grid based on ARMA-GABP combined model[J]. Electric Power, 2018, 51(11):38-44.
[19]	王瑞, 周晨曦, 逯静. 基于一种组合模型的短期电力负荷预测[J]. 计算机仿真, 2018, 35(12):396-400.
	WANG Rui, ZHOU Chenxi, LU Jing. Short-term load prediction based on a combination model[J]. Computer Simulation, 2018, 35(12):396-400.
[20]	彭维珂, 聂椿明, 陈衡, 等. 基于智能算法的空冷火电机组负荷预测研究[J]. 华电技术, 2021, 43(3):57-64.
	PENG Weike, NIE Chunming, CHEN Heng, et al. Study on load forecasting for air cooling thermal power units based on intelligent algorithm[J]. Huadian Technology, 2021, 43(3):57-64.
[21]	刘瑞叶, 黄磊. 基于动态神经网络的风电场输出功率预测[J]. 电力系统自动化, 2012, 36(11):19-22,37.
	LIU Ruiye, HUANG Lei. Wind power forecasting based on dynamic neural networks[J]. Automation of Electric Power Systems, 2012, 36(11):19-22,37.

年份	标准煤使用量/万t	电能使用量/（TW·h）	电能使用量占能源使用量比例/%	电能替代量/（TW·h）
2000	146 964	1 347.238	11.266 40	84.902
2001	155 547	1 472.346	11.633 22	46.427
2002	169 577	1 646.545	11.933 24	41.397
2003	197 083	1 903.160	11.868 01	-10.461
2004	230 281	2 197.137	11.726 03	-26.604
2005	261 369	2 494.032	11.727 35	0.281
2006	286 467	2 858.797	12.264 80	125.275
2007	311 442	3 271.181	12.908 60	163.146
2008	320 611	3 454.135	13.240 76	86.649
2009	336 126	3 703.214	13.540 31	81.927
2010	360 648	4 193.449	14.290 25	220.068
2011	387 043	4 700.088	14.924 46	199.730
2012	402 138	4 976.264	15.208 28	92.869
2013	416 913	5 420.341	15.978 39	261.244
2014	425 806	5 638.369	16.273 97	102.409
2015	429 905	5 801.997	16.586 58	109.351
2016	435 819	6 129.709	17.285 64	247.897
2017	448 529	6 482.097	17.761 39	173.624
2018	464 000	7 033.075	18.628 55	327.393
2019	486 000	7 649.563	19.344 27	283.023

年份	真实值/（TW·h）	预测值/（TW·h）	相对误差/%
2013	261.243	292.339	11.90
2014	102.408	73.703	28.03
2015	109.350	60.589	44.59
2016	247.896	287.563	16.00
2017	173.622	193.463	11.42
2018	327.394	399.448	22.01
2019	283.023	329.835	16.54