基于优化灰色傅里叶残差修正的中长期负荷预测

doi:10.16180/j.cnki.issn1007-7820.2021.12.009

摘要/Abstract

摘要：

针对电力系统中长期负荷预测精度不高的问题,文中提出改进粒子群优化的灰色傅里叶残差修正的中长期电力负荷预测模型。该模型利用三点平滑法对原始负荷数据进行预处理,削弱了异常值的影响。采用改进粒子群优化的灰色模型对原始负荷进行预测,解决了预测数据不足和预测精度不高的问题。通过傅里叶变换对预测误差进行修正,提高了预测精度。浙江某地区2013~2018年年度负荷预测结果显示,采用该方法后,平均负荷预测精度提高了1.94%,证明该模型在中长期负荷预测中具有较高的精度和可行性。

关键词: 负荷预测, 灰色模型, 粒子群, 傅里叶, 残差修正, 三点平滑法, 预处理, 傅里叶变换

Abstract:

In view of the problem of low accuracy of mid- and long-term load forecasting in power systems, a gray Fourier residual correction modified particle swarm optimization model for mid- and long-term power load forecasting is proposed. The model uses a three-point smoothing method to preprocess the original load data to weaken the influence of outliers. The gray model of improved particle swarm optimization is adopted to predict the original load, which solves the problems of insufficient forecast data and low forecast accuracy. Fourier transform corrects the prediction error and greatly improves the prediction accuracy. The results of the annual load forecasting in a certain area of Zhejiang from 2013 to 2018 show that the average load forecasting accuracy has increased by 1.94%, which indicates that the model has high accuracy and feasibility in medium and long-term load forecasting.

Key words: load forecasting, gray model, particle swarm, Fourier, residual correction, three-point smoothing method, preprocessing, Fourier transfor

中图分类号:

TM715

朱健安,魏云冰,朱鹏杰,蒋成成,朱成名. 基于优化灰色傅里叶残差修正的中长期负荷预测[J]. 电子科技, 2021, 34(12): 49-55.

ZHU Jian'an,WEI Yunbing,ZHU Pengjie,JIANG Chengcheng,ZHU Chengming. Medium and Long-Term Load Forecasting Based on Optimized Grey Fourier Residual Correction[J]. Electronic Science and Technology, 2021, 34(12): 49-55.

图/表 8

图1

图2

表1

图3

表2

图4

表3

图5

参考文献 18

[1]	邓永生, 焦丰顺, 张瑞锋, 等. 配电网规划中电力负荷预测方法研究综述[J]. 电器与能效管理技术, 2019(14):1-7.
	Deng Yongsheng, Jiao Fengshun, Zhang Ruifeng, et al. Research review on power load forecasting methods in distribution network planning[J]. Electrical & Energy Management Technology, 2019(14):1-7.
[2]	陆兴华, 郑永涛. 基于非线性时间序列分析的电力系统负荷预测模型[J]. 电力与能源, 2015, 37(2):197-201.
	Lu Xinghua, Zheng Yongtao. Power system load forecasting model based on nonlinear time series analysis[J]. Power & Energy, 2015, 37(2):197-201.
[3]	黄元生, 方伟. 基于灰色傅里叶变换残差修正的电力负荷预测模型[J]. 电力自动化设备, 2013, 33(9):105-107.
	Huang Yuansheng, Fang Wei. Power load forecasting model with residual error correction based on grey Fourier transform[J]. Electric Power Automation Equipment, 2013, 33(9):105-107.
[4]	樊一娜. 基于粒子群优化算法的灰色模型在电力负荷预测中的应用[J]. 青海大学学报, 2013, 31(1):19-23.
	Fan Yina. An application of grey model based on particle swarm optimization in power load forecasting[J]. Journal of Qinghai University, 2013, 31(1):19-23.
[5]	刘帅. 基于粒子群优化的GM(1,1)幂模型电力负荷预测研究[D]. 北京:华北电力大学, 2013.
	Liu Shuai. Electricity load forecasting based on GM (1,1) power model optimized by particle swarm algorithm[D]. Beijing:North China Electric Power University, 2013.
[6]	Deng Z F, Wang B B, Xu Y L, et al. Multi-scale convolutional neural network with time-cognition for multi-step short-term load forecasting[J]. IEEE Access, 2019(7):88058-88071.
[7]	李若晨, 朱帆, 朱永利, 等. 结合受限玻尔兹曼机的递归神经网络电力系统短期负荷预测[J]. 电力系统保护与控制, 2018, 46(17):83-88.
	Li Ruochen, Zhu Fan, Zhu Yongli, et al. Short-term power load forecasting using recurrent neural network with restricted Boltzmann machine[J]. Power System Protection and Control, 2019, 46(17):83-88.
[8]	王瑞, 周晨曦, 逯静. 改进粒子群优化BP神经网络短期负荷预测研究[J]. 制造业自动化, 2019, 41(6):39-42.
	Wang Rui, Zou Chenxi, Lu Jing. Improved particle swarm optimization BP neural network for short-term load forecasting[J]. Manufacturing Automation, 2019, 41(6):39-42.
[9]	周英, 尹邦德, 任铃, 等. 基于BP神经网络的电网短期负荷预测模型研究[J]. 电测与仪表, 2011, 48(2):68-71.
	Zhou Ying, Yin Bangde, Ren Ling, et al. Study of Electricity Short-term Load Forecast Based on BP Neural Network[J]. Electrical Measurement & Instrumentation, 2011, 48(2):68-71.
[10]	吴倩红, 高军, 候广松, 等. 实现影响因素多源异构融合的短期负荷预测支持向量机算法[J]. 电力自动化设备, 2016, 40(15):67-72.
	Wu Qianhong, Gao Jun, Hou Guangsong, et al. Short-term load forecasting support vector machine algorithm to realize multi-source heterogeneous fusion of influencing factors[J]. Electric Power Automation Equipment, 2016, 40(15):67-72.
[11]	Chen Y H, Yang Y, Liu C Q, et al. A hybrid application algorithm based on the support vector machine and artificial intelligence:An example of electric load forecasting[J]. Applied Mathematical Modelling. 2015, 39(9):2617-2632. doi: 10.1016/j.apm.2014.10.065
[12]	郭艳飞, 程林, 李洪涛, 等. 基于支持向量机和互联网信息修正的空间负荷预测方法[J]. 中国电力, 2019, 52(4):80-88.
	Guo Yanfei, Cheng Lin, Li Hongtao, et al. Spatial load forecasting method based on support vector machine and internet information correction[J]. Electric China Power, 2019, 52(4):80-88.
[13]	高昆仑, 刘建明, 徐茹枝, 等. 基于支持向量机和粒子群算法的信息网络安全态势复合预测模型[J]. 电网技术, 2011, 35(4):176-182.
	Gao Kunlun, Liu Jianming, Xu Ruzhi, et al. A hybrid security situation prediction model for information network based on support vector machine and particle swarm algorithm optimization[J]. Power System Technology, 2011, 35(4):176-182.
[14]	邓聚龙. 灰色预测与决策[M]. 武汉: 华中科技大学出版社, 1986.
	Deng Julong. Grey prediction and decision-making[M]. Wuhan: Huazhong University of Science and Technology Press, 1986.
[15]	陈昊. 采用现代时间序列分析方法的电力负荷预测[M]. 北京: 中国电力出版社, 2015.
	Chen Hao. Power load forecasting using modern time series analysis method[M]. Beijing: China Electric Power Press, 2015.
[16]	康重庆, 夏清, 刘梅. 电力系统负荷预测[M]. 北京: 中国电力出版社, 2007.
	Kang Chongqing, Xia Qing, Liu Mei. Power system load forecasting[M]. Beijing: China Electric Power Press, 2007.
[17]	刘思峰, 谢乃明. 灰色系统理论及其应用[M]. 4版.北京: 科学出版社, 2008.
	Liu Sifeng, Xie Naiming. Grey system theory and its application[M].4th ed. Beijing: Science Press, 2008.
[18]	杨胡萍, 毕志鹏. 粒子群优化的灰色模型在中长期负荷预测中的应用[J]. 电测与仪表, 2011, 48(2):40-43.
	Yang Huping, Bi Zhipeng. Particle swarm optimization-based grey model for long-term load forecasting[J]. Electrical Measurement & Instrumentation, 2011, 48(2):40-43.

年份	负荷/TW·h	年份	负荷/TW·h	年份	负荷/TW·h
2001	27.36	2007	50.46	2013	81.88
2002	32.58	2008	55.69	2014	87.71
2003	36.78	2009	61.35	2015	91.21
2004	38.47	2010	64.58	2016	98.31
2005	42.76	2011	67.63	2017	104.07
2006	46.25	2012	75.25	2018	108.95

年份	负荷/TW·h	年份	负荷/TW·h
2001	28.67	2007	50.72
2002	32.33	2008	55.78
2003	36.15	2009	60.74
2004	39.12	2010	64.54
2005	42.56	2011	68.77
2006	46.43	2012	73.35

年份	原始负荷 /TW·h	GM(1,1)	Error /%	平滑 GM(1,1)	Error /%	RWPSO- GM(1,1)	Error /%	FR-RWPSO- GM(1.1)	Error /%
2013	81.88	81.82	-0.07	81.27	-0.74	80.35	-1.87	80.16	-2.10
2014	87.71	88.73	1.20	88.04	0.38	86.65	-1.21	86.77	-1.07
2015	91.21	96.22	5.50	95.38	4.57	93.44	2.44	90.39	-0.9
2016	98.31	104.34	6.10	103.33	5.12	100.77	2.50	99.84	1.56
2017	104.07	113.14	8.72	111.95	7.57	108.66	4.41	106.54	2.37
2018	108.95	122.69	11.90	120.28	10.4	117.18	7.55	112.92	3.64
平均精度			5.58		4.80		3.52		1.94