基于CatBoost算法的电力短期负荷预测研究 *

doi:10.11985/2020.01.011

电气工程学报 ›› 2020, Vol. 15 ›› Issue (1): 76-82.doi: 10.11985/2020.01.011

• 特邀专栏: 微电网功率变换与稳定控制 • 上一篇下一篇

扫码分享

基于CatBoost算法的电力短期负荷预测研究 ^*

党存禄^1,^2,³,武文成¹(),李超锋¹,李永强¹

^1. 兰州理工大学电气工程与信息工程学院兰州 730050
^2. 甘肃省工业过程先进控制重点实验室兰州 730050
^3. 兰州理工大学电气与控制工程国家级实验教学示范中心兰州 730050

收稿日期:2019-12-23 出版日期:2020-03-25 发布日期:2020-05-13
通讯作者: 武文成 E-mail:huanghepijiu@vip.qq.com
作者简介:党存禄,男,1964年生,教授。主要研究方向为新能源发电技术,电力电子与电力传动。E-mail：dcl_1964@163.com
基金资助:
* 国家自然科学基金(51767017);国网甘肃省电力科学研究院(SGGSKY00DJJS1900216);甘肃省住房和城乡建设厅2018年建设科技基金项目[A1](JK2018-21)

Short-term Load Forecasting Based on CatBoost Algorithm

DANG Cunlu^1,^2,³,WU Wencheng¹(),LI Chaofeng¹,LI Yongqiang¹

^1. College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050 China
^2. Key Laboratory of Gansu Province Advanced Control for Industrial Processes, Lanzhou University of Technology, Lanzhou 730050 China
^3. National Experimental Teaching Demonstration Center of Electrical and Control Engineering of Lanzhou University of Technology, Lanzhou 730050 China

Received:2019-12-23 Online:2020-03-25 Published:2020-05-13
Contact: WU Wencheng E-mail:huanghepijiu@vip.qq.com

摘要/Abstract

摘要：

针对传统电力系统负荷预测算法数据预处理过程中大量的超参数调节以及数值强行代替标签时容易发生条件偏移的问题,为进一步提高电力系统短期负荷预测的精度,将CatBoost算法应用于电力短期负荷预测,较传统负荷预测深度神经网络算法而言,CatBoost算法在数据预处理过程当中无需进行数值强行代替标签,同时减小对超参数依赖的情况下得到较优的预测结果。首先选取了两地区20天的数据用于训练CatBoost模型,其次将预测结果与其他常见智能算法进行分析和对比,最后仿真结果表明CatBoost算法具备预测电力系统短期负荷的能力。

关键词: CatBoost, 短期负荷预测, 条件偏移, 超参数调整, 数据预处理

Abstract:

In order to improve the accuracy of short-term load forecasting in power systems, CatBoost algorithm is applied to short-term power load for prediction. Compared with the traditional load prediction deep neural network algorithm, the CatBoost algorithm does not need to perform numerical forced substitution in the data preprocessing process, and at the same time reduces the dependence on hyperparameters to obtain better prediction results. Firstly, 20 days of data from two regions are used to train the CatBoost model. Secondly, analyze the prediction results and compared with other common intelligent algorithms. Finally, the simulation results showed that the CatBoost algorithm has the ability to predict short-term load of the power system.

Key words: CatBoost, short-term load forecasting, conditional offset, hyperparameters adjustment, data preprocessing

中图分类号:

TM74

党存禄,武文成,李超锋,李永强. 基于CatBoost算法的电力短期负荷预测研究 ^*[J]. 电气工程学报, 2020, 15(1): 76-82.

DANG Cunlu,WU Wencheng,LI Chaofeng,LI Yongqiang. Short-term Load Forecasting Based on CatBoost Algorithm[J]. Journal of Electrical Engineering, 2020, 15(1): 76-82.

图/表 5

图1

图2

图3

图4

表1

参考文献 23

[1]	靳现林, 赵迎春, 吴刚 . 考虑分布式光伏和电动汽车接入的配电网空间负荷预测方法[J]. 电力系统保护与控制, 2019,47(14):10-19.
	Jin Xianlin, Zhao Yingchun, Wu Gang . Distribution network spatial load forecasting method considering distributed photovoltaic and electric vehicle access[J]. Power System Protection and Control, 2019,47(14):10-19.
[2]	张丽, 张涛, 王福忠 , 等. 基于柔性负荷响应特性的超短期预测方法[J]. 电力系统保护与控制, 2019,47(9):27-34.
	Zhang Li, Zhang Tao, Wang Fuzhong , et al. Ultra-short term prediction method based on flexible load response characteristics[J]. Power System Protection and Control, 2019,47(9):27-34.
[3]	史文博, 王健, 沈添福 , 等. 基于改进倍比平滑法的节假日短期负荷预测方法[J]. 电力建设, 2014,35(10):21-25. doi: 10.3969/j.issn.1000-7229.2014.10.005
	Shi Wenbo, Wang Jian, Shen Tianfu , et al. Prediction method of short term load in holidays based on improved multiple proportions smoothing method[J]. Electric Power Construction, 2014,35(10):21-25. doi: 10.3969/j.issn.1000-7229.2014.10.005
[4]	康重庆, 夏清, 张伯明 . 电力系统负荷预测研究综述与发展方向的探讨[J]. 电力系统自动化, 2004,28(17):1-11.
	Kang Chongqing, Xia Qing, Zhang Boming . Review of power system load forecasting and its development[J]. Automation of Electric Power Systems, 2004,28(17):1-11.
[5]	赵云, 高泽璞, 肖勇 , 等. 基于多层聚类和改进BP神经网络的短期负荷预测[J]. 武汉大学学报, 2019,52(7):622-629.
	Zhao Yun, Gao Zepu, Xiao Yong , et al. Short term load forecasting based on multi-layer clustering and improved BP neural network[J]. Engineering Journal of Wuhan University, 2019,52(7):622-629.
[6]	王程斯, 赵少东 . 区分待预测日的城市电网短期负荷预测方法研究[J]. 自动化与仪器仪表, 2019(6):114-117.
	Wang Chengsi, Zhao Shaodong . Research on short term load forecasting method for urban power grid on the forecast day[J]. Automation & Instrumentation, 2019(6):114-117.
[7]	闫云凤 . 基于决策森林的回归模型方法研究及应用[D]. 杭州:浙江大学, 2019.
[8]	吴云, 雷建文, 鲍丽山 , 等. 基于改进灰色关联分析与蝙蝠优化神经网络的短期负荷预测[J]. 电力系统自动化, 2018,42(20):67-74.
	Wu Yun, Lei Jianwen, Bao Lishan , et al. Short term load forecasting based on improved grey correlation analysis and bat optimization neural network[J]. Automation of Electric Power Systems, 2018,42(20):67-74.
[9]	王帅, 王文爽, 孙伟 , 等. 基于粗糙集和BP网络的微网短期负荷预测[J]. 控制工程, 2018,25(8):1528-1533.
	Wang Shuai, Wang Wenshuang, Sun Wei , et al. Short term load forecasting of microgrid based on rough set and BP network[J]. Control Engineering of China, 2018,25(8):1528-1533.
[10]	张刚, 刘福潮, 王维洲 , 等. 电网短期负荷预测的BP-ANN方法及应用[J]. 电力建设, 2014,35(3):54-58. doi: 10.3969/j.issn.1000－7229.2014.03.010
	Zhang Gang, Liu Fuchao, Wang Weizhou , et al. BP-ANN method for power grid short term load forecasting and its application[J]. Electric Power Construction, 2014,35(3):54-58. doi: 10.3969/j.issn.1000－7229.2014.03.010
[11]	李香龙, 张宝群, 张宇 , 等. 基于EEMD-BP神经网络的含电采暖的配电变压器短期负荷预测[J]. 电测与仪表, 2018,55(10):101-107.
	Li Xianglong, Zhang Baoqun, Zhang Yu , et al. Short term load forecasting of distribution transformer with electric heating based on EEMD-BP neural network[J]. Electrical Measurement & Instrumentation, 2018,55(10):101-107.
[12]	张蕾, 章毅 . 大数据分析的无限深度神经网络方法[J]. 计算机研究与发展, 2016,53(1):68-79. doi: DOI:10.7544/issn1000-1239.2016.20150663
	Zhang Lei, Zhang Yi . Infinite depth neural network method for big data analysis[J]. Journal of Computer Research and Development, 2016,53(1):68-79. doi: DOI:10.7544/issn1000-1239.2016.20150663
[13]	李龙, 魏靖, 黎灿兵 , 等. 基于人工神经网络的负荷模型预测[J]. 电工技术学报, 2015,30(8):225-230.
	Li Long, Wei Jing, Li Canbing , et al. Prediction of load model based on artificial neural network[J]. Transactions of China Electrotechnical Society, 2015,30(8):225-230.
[14]	邵亚洁 . 基于复合CatBoost模型的P2P网贷违约分类预测[D]. 兰州:兰州大学, 2019.
[15]	鲁迪, 王星华, 刘升伟 , 等. 加权多分位鲁棒ELM的短期负荷预测方法[J/OL]. 电力系统及其自动化学报:1-7[2019-06-17]. https://doi.org/10.19635/j.cnki.csu-epsa. 000266.
	Lu Di, Wang Xinghua, Liu Shengwei , et al. Weighted multi-component robust ELM short term load forecasting method[J/OL]. Proceedings of the CSU-EPSA:1-7 [2019-06-17]. https://doi.org/10.19635/j.cnki.csu-epsa. 000266.
[16]	黄小庆, 陈颉, 陈永新 , 等. 大数据背景下的充电站负荷预测方法[J]. 电力系统自动化, 2016,40(12):68-74.
	Huang Xiaoqing, Chen Jie, Chen Yongxin , et al. Load forecasting method for electric vehicle charging station based on big data[J]. Automation of Electric Power Systems, 2016,40(12):68-74.
[17]	杨甲甲, 刘国龙, 赵俊华 , 等. 采用长短期记忆深度学习模型的工业负荷短期预测方法[J]. 电力建设, 2018,39(10):20-27.
	Yang Jiajia, Liu Guolong, Zhao Junhua , et al. A long short term memory based deep learning method for industrial load forecasting[J]. Electric Power Construction, 2018,39(10):20-27.
[18]	廖旎焕, 胡智宏, 马莹莹 , 等. 电力系统短期负荷预测方法综述[J]. 电力系统保护与控制, 2011,39(1):147-152. doi: 10.7667/j.issn.1674-3415.2011.01.028
	Liao Nihuan, Hu Zhihong, Ma Yingying , et al. Review of the short term load forecasting methods of electric power system[J]. Power System Protection and Control, 2011,39(1):147-152 doi: 10.7667/j.issn.1674-3415.2011.01.028
[19]	刘思捷, 张海鹏, 林舜江 , 等. 夏季日最大降温负荷的估算和预测方法[J]. 电力系统保护与控制, 2016,44(5):75-81. doi: 10.7667/PSPC150822
	Liu Sijie, Zhang Haipeng, Lin Shunjiang , et al. An estimating and forecasting method for daily maximum cooling load in summer[J]. Power System Protection and Control, 2016,44(5):75-81. doi: 10.7667/PSPC150822
[20]	周志华 . 机器学习[M]. 北京: 清华大学出版社, 2016.
[21]	谢从珍, 王江储, 谢心昊 , 等. 基于细粒度特征的BOA- GBDT光伏出力预测[J/OL]. 电网技术:1-9 [2019-07-04]. https://doi.org/10.13335/j.1000-3673.pst.2019.0447.
	Xie Congzhen, Wang Jiangchu, Xie Xinhao , et al. Prediction of PVoutput based on fine-grained features of BOA-GBDT [J/OL]. Power System Technology:1-9 [2019-07-04]. https://doi.org/10.13335/j.1000-3673.pst.2019.0447.
[22]	Dorogush A V, Ershov V, Gulin A . CatBoost:Gradient boosting with categorical features support[M]. New York:Cornell University, 2018.
[23]	Wu Lifeng, Huang Guomin, Fan Junliang , et al. Potential of kernel-based nonlinear extension of ARPS decline model and gradient boosting with categorical features support for predicting daily global solar radiation in humid regions[J]. Energy Conversion and Management, 2019(183):280-295.

算法	地区1负荷预测误差指标			地区2负荷预测误差指标
算法	RMSE	MAE	MAPE	RMSE	MAE	MAPE
KNN算法	348.12	293.90	3.679	517.88	485.69	6.51
BP神经网络	423.30	322.44	5.650	497.51	466.21	6.77
决策树算法	510.52	452.72	5.860	403.65	348.12	4.37
GBDT算法	436.62	285.12	5.330	996.94	879.56	11.29
CatBoost算法	308.02	199.56	2.880	321.56	274.97	4.14

基于CatBoost算法的电力短期负荷预测研究 ^*

Short-term Load Forecasting Based on CatBoost Algorithm

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 23

相关文章 11

编辑推荐

Metrics

本文评价

[1]	丁宇劼. 基于可再生能源与储能系统的微电网模型及其优化运行仿真研究[J]. 电气工程学报, 2020, 15(1): 36-40.
[2]	钟开成. 时变时滞电力系统鲁棒稳定性新判据[J]. 电气工程学报, 2019, 14(1): 79-82.
[3]	牟建伟,尚亚男,刘文刚,戴思源,江澎,王保力,王延勃. 基于改进Prony法的电力系统低频振荡快衰分量辨识[J]. 电气工程学报, 2018, 13(12): 36-41.
[4]	杨永前,陈曦. 基于PSASP程序的TCPST潮流建模与仿真[J]. 电气工程学报, 2018, 13(8): 37-42.
[5]	周生海,尹航,顾颖,王翀,柏峰. 基于POP NSGA-Ⅱ的配电网故障恢复重构[J]. 电气工程学报, 2018, 13(6): 28-35.
[6]	谷天聪,范兴明,张鑫. 基于Matlab的小电流接地系统故障特征仿真分析[J]. 电气工程学报, 2017, 12(2): 20-25.
[7]	王瑶. 恒定导通时间控制单电感双输出CCM Buck变换器[J]. 电气工程学报, 2016, 11(9): 48-54.
[8]	张建新,吴盛刚,赵建沛,王卫东,高杨. 近区故障试验人工链路的选型及其参数计算[J]. 电气工程学报, 2016, 11(2): 33-39.
[9]	刘晓飞,崔淑梅,李锦瑭,高唯峰,徐石明. 停车场电动汽车用户侧最优V2G控制策略研究[J]. 电气工程学报, 2015, 10(10): 44-51.
[10]	王磊,骆玮,曹现峰. 基于改进EMD算法的小电流接地故障选线[J]. 电气工程学报, 2015, 10(8): 29-34.
[11]	卢志刚,陈月敏. 基于改进聚类的输电线路参数多代理辨识与估计[J]. 电气工程学报, 2015, 10(4): 70-81.