融合LSTM和SVM的钢铁企业电力负荷短期预测

doi:10.6040/j.issn.1672-3961.0.2020.539

摘要/Abstract

摘要：

为了解决大型钢铁企业电力用电对地区负荷冲击大, 电力负荷短期预测准确率低的问题, 提出一种融合长短期记忆网络(long short-term memory, LSTM)和支持向量机(support vector machine, SVM)的负荷短期预测算法。对钢铁工业地区负荷特性进行分析, 根据系统负荷的组成部分将负荷细分为冲击性负荷和其他负荷, 采用协方差和皮尔逊算法分别对负荷影响因子进行相关性分析和差异化处理; 选取历史负荷、温度、日期类型、钢价、电价、铁矿石价格6个属性作为负荷预测影响因素, 通过模糊权值逻辑将LSTM和SVM融合, 得到最终负荷预测结果。仿真试验结果表明, 所提出的预测方法相对于单独的LSTM或SVM, 可以更准确地预测钢铁工业地区的短期负荷。

关键词: 钢铁企业, 短期负荷, 长短期记忆网络, 支持向量机, 冲击性负荷

Abstract:

A short-term load forecasting algorithm combining long short-term memory (LSTM) and support vector machine (SVM) was proposed to solve the low accuracy problem of short-term load forecasting due to the large-scale iron and steel enterprise power consumption impact on regional load. The research thoroughly analyzed the load characteristics of the selected region with predominant iron and steel mill load, which divided the load into the impulse load and others based on its various components.Covariance algorithm and Pearson algorithm were used to analyze the correlation and differentiation of load influence factors. Six attributes of historical load, temperature, date type, steel price, electricity price and iron ore price were selected as load forecasting. The fuzzy weight assignment was used to fuse LSTM and SVM which got the final load forecasting result. The simulation results showed that the proposed method could predict the short-term load more accurately than the single LSTM or SVM.

Key words: iron and steel industry, short-term load forecasting, LSTM, SVM, impulse load

中图分类号:

TM714

亓晓燕,刘恒杰,侯秋华,刘啸宇,谭延超,王连成. 融合LSTM和SVM的钢铁企业电力负荷短期预测[J]. 山东大学学报 (工学版), 2021, 51(4): 91-98.

Xiaoyan QI,Hengjie LIU,Qiuhua HOU,Xiaoyu LIU,Yanchao TAN,Liancheng WANG. Short-term load forecasting of iron and steel industry area based on combination model of SVM and LSTM[J]. Journal of Shandong University(Engineering Science), 2021, 51(4): 91-98.

图/表 15

图1

表1

表2

图2

表3

表4

图3

图4

图5

图6

表5

图7

图8

图9

图10

参考文献 27

1	康重庆, 夏清. 电力系统负荷预测[M]. 北京: 中国电力出版社, 2017.
2	LI B , ZHANG J , HE Y , et al. Short-term load forecasting method based on wavelet decomposition with second-order gray neural network model combined with ADF test[J]. IEEE Access, 2017, 5, 16324- 16331. doi: 10.1109/ACCESS.2017.2738029
3	NOSE-FILHO K , LOTUFO A D P , MINUSSI C R . Short-term multimodal load forecasting using a modified general regression neural network[J]. IEEE Transactions on Power Delivery, 2011, 26 (4): 2862- 2869. doi: 10.1109/TPWRD.2011.2166566
4	牛东晓, 谷志红, 邢棉, 等. 基于数据挖掘的SVM短期负荷预测方法研究[J]. 中国电机工程学报, 2006, 26 (18): 6- 12. doi: 10.3321/j.issn:0258-8013.2006.18.002
	NIU Xiaodong , GU Zhihong , XING Mian , et al. Study on forecasting approach to short-term load of SVM based on data mining[J]. Proceedings of the CSEE, 2006, 26 (18): 6- 12. doi: 10.3321/j.issn:0258-8013.2006.18.002
5	赵登福, 王蒙, 张讲社, 等. 基于支撑向量机方法的短期负荷预测[J]. 中国电机工程学报, 2002, 22 (4): 27- 31.
	ZHAO Dengfu , WANG Meng , ZHANG Jiangshe , et al. A support vector machine approach for short term load forecasting[J]. Proceedings of the CSEE, 2002, 22 (4): 27- 31.
6	王刚. 基于极限学习机的时间序列预测[D]. 沈阳: 沈阳工业大学, 2019.
	WANG Gang. Time series prediction based on extreme learning machine[D]. Shenyang: Shenyang University of Technology, 2019.
7	YU X, XU Z, ZHOU X, et al. Load forecasting based on smart meter data and gradient boosting decision tree[C]// Proceeding of 2019 Chinese Automation Congress (CAC). Hangzhou: IEEE, 2019: 4438-4442.
8	XIE Z, WANG R, WU Z, et al. Short-term power load forecasting model based on fuzzy neural network using improved decision tree[C]//Proceeding of 2019 IEEE Sustainable Power and Energy Conference (iSPEC). Beijing: IEEE, 2019: 482-486.
9	谭忠良. 基于BP神经网络实现钢铁厂电力系统负荷预[J]. 冶金自动化, 2015, S1 (增刊1): 370- 372.
10	梁青艳, 孙彦广. 钢铁企业电力负荷动态预测建模问题的应用研究[J]. 科学技术与工程, 2018, 18 (16): 44- 54. doi: 10.3969/j.issn.1671-1815.2018.16.008
	LIANG Qingyan , SUN Yanguang . Investigation on application of electricity load dynamic forecast modelling in iron and steel enterprises[J]. Science Technology and Engineering, 2018, 18 (16): 44- 54. doi: 10.3969/j.issn.1671-1815.2018.16.008
11	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. doi: 10.3969/j.issn.1000-7229.2018.10.003
	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. doi: 10.3969/j.issn.1000-7229.2018.10.003
12	李明, 王智灵, 杨晓宇, 等. 突变期电力负荷预测方法及其应用[J]. 电力系统自动化, 2006, (10): 93- 96. doi: 10.3321/j.issn:1000-1026.2006.10.019
	LI Ming , WANG Zhiling , YANG Xiaoyu , et al. Power load forecasting method and its application in abrupt change period[J]. Power System Automation, 2006, (10): 93- 96. doi: 10.3321/j.issn:1000-1026.2006.10.019
13	毛勇华, 桂小林, 李前, 等. 深度学习应用技术研究[J]. 计算机应用研究, 2016, 33 (11): 3201- 3205. doi: 10.3969/j.issn.1001-3695.2016.11.001
	MAO Yonghua , GUI Xiaolin , LI Qian , et al. Study on application technology of deep learning[J]. Application Research of Computers, 2016, 33 (11): 3201- 3205. doi: 10.3969/j.issn.1001-3695.2016.11.001
14	周林, 吕厚军. 人工神经网络应用于电力系统短期负荷预测的研究[J]. 四川电力技术, 2008, 31 (6): 68- 72. doi: 10.3969/j.issn.1003-6954.2008.06.021
	ZHOU Lin , LV Houjun . ANN application to short term load forecasting research of power system[J]. Sichuan Electric Power Technology, 2008, 31 (6): 68- 72. doi: 10.3969/j.issn.1003-6954.2008.06.021
15	王晨辉, 张晓亮, 梁晓传. 云计算架构下基于BP神经网络负载预测策略的研究[J]. 电力信息与通信技术, 2016, 14 (11): 46- 50.
	WANG Chenhui , ZHANG Xiaoliang , LIANG Xiaochuan . Research on load forecasting strategy based on BP neural network under cloud computing architectures[J]. Electric Power Information and Communication Technology, 2016, 14 (11): 46- 50.
16	谢伟, 赵琦, 郭乃网, 等. 改进的并行模糊核聚类算法在电力负荷预测的应用[J]. 电测与仪表, 2019, 56 (11): 49- 54.
	XIE Wei , ZHAO Qi , GUO Naiwang , et al. Powered big data clustering algorithm based on multi-kernel fuzzy C-means clustering[J]. Electrical Measurement & Instrumentation, 2019, 56 (11): 49- 54.
17	张冠英, 羡一鸣, 葛磊蛟, 等. 经济新常态下基于Verhulst-SVM的中长期负荷预测模型[J]. 电测与仪表, 2019, 56 (1): 102- 107.
	ZHANG Guanying , XIAN Yiming , GE Leijiao , et al. Medium and long term load forecasting model based on verhulst-svm under new normal economy[J]. Electrical Measurement & Instrumentation, 2019, 56 (1): 102- 107.
18	李永通, 陶顺, 赵蕾, 等. 基于短时间尺度相关性聚类的负荷预测[J]. 电测与仪表, 2019, 56 (16): 32- 38.
	LI Yongtong , TAO Shun , ZHAO Lei , et al. Load forecasting based on short-term correlation clustering[J]. Electrical Measurement & Instrumentation, 2019, 56 (16): 32- 38.
19	陈振宇, 刘金波, 李晨, 等. 基于LSTM与XGBoost组合模型的超短期电力负荷预测[J]. 电网技术, 2020, 44 (2): 614- 620.
	CHEN Zhenyu , LIU Jinbo , LI Chen , et al. Ultra short-term power load forecasting based on combined LSTM-XGBoost model[J]. Power System Technology, 2020, 44 (2): 614- 620.
20	王宁, 谢敏, 邓佳梁, 等. 基于支持向量机回归组合模型的中长期降温负荷预测[J]. 电力系统保护与控制, 2016, 44 (3): 92- 97.
	WANG Ning , XIE Min , DENG Jialiang , et al. Mid-long term temperature-lowering load forecasting based on combination of support vector machine and multiple regression[J]. Power System Protection and Control, 2016, 44 (3): 92- 97.
21	刘玉田, 孙润稼, 王洪涛, 等. 人工智能在电力系统恢复中的应用综述[J]. 山东大学学报(工学版), 2019, 49 (5): 1- 8.
	LIU Yutian , SUN Runjia , WANG Hongtao , et al. Review on application of artificial intelligence in power system restoration[J]. Journal of Shandong University (Engineering Science), 2019, 49 (5): 1- 8.
22	梁志祥, 刘晓明, 牟颖, 等. 基于深度学习的新能源爬坡事件预测方法[J]. 山东大学学报(工学版), 2019, 49 (5): 24- 28.
	LIANG Zhixiang , LIU Xiaoming , MU Ying , et al. Prediction method of wind power and PV ramp event based on deep learning[J]. Journal of Shandong University (Engineering Science), 2019, 49 (5): 24- 28.
23	黄任可, 罗谌持, 张明. 基于粒子滤波器的大容量冲击负荷短期预测方法[J]. 电力系统自动化, 2009, 33 (3): 40- 45.
	WANG Renke , LUO Chenchi , ZHANG Ming . Short-term forecasting of the high-capacity impact load based on particle filters[J]. Automation of Electric Power Systems, 2009, 33 (3): 40- 45.
24	李云飞, 张鹏, 程鹏飞, 等. 大数据挖掘下冲击性负荷特性电网短期负荷预测的探索与实践[J]. 电力大数据, 2019, 22 (4): 80- 86.
	LI Yunfei , ZHANG Peng , CHENG Pengfei , et al. Exploration and practice of short-term load forecasting of power grid with impact load characteristics under big data mining[J]. Power Systems and Big Data, 2019, 22 (4): 80- 86.
25	赵威. 基于大数据的短期负荷预测关键技术研究[D]. 山东大学, 2019, 22(4): 80-86.
	ZHAO Wei. Research on key technologies of short-term load forecasting based on big data[D]. Jinan: Shandong University, 2019, 22(4): 80-86.
26	张鑫. 基于支持向量机的能源管理系统短期负荷预测[D]. 长春: 长春工业大学, 2010.
	ZHANG Xin. Short term load forecasting of energy management system based on support vector machine[D]. Changchun: Changchun University of Technology, 2010.
27	郑静, 杜秀华, 史新祈. 大型钢铁企业电力负荷的短期预测研究[J]. 电力需求侧管理, 2004, 6 (1): 18- 21.
	ZHENG Jing , DU Xiuhua , SHI Xinqi . Research on short term load forecasting in steel enterprise[J]. Power Demand Management, 2004, 6 (1): 18- 21.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

冲击性负荷	影响因素名称
冲击性负荷	铁矿石期货价格	螺纹钢期货价格	气温	湿度	风向	负荷历史数据1	负荷历史数据2	周日期	风速	日类型
皮尔逊算法	0.356 7	0.335 6	0.301 0	0.453 7	0.167 8	0.612 0	0.534 0	0.109 1	0.100 8	0.556 1
协方差算法	0.400 0	0.350 0	0.320 0	0.510 2	0.058 9	0.699 8	0.467 8	0.110 0	0.088 1	0.410 0

输入量	描述
铁矿石期货价格	上一周铁矿石期货均价
螺纹钢期货价格	上一周铁螺纹钢期货均价
气温	t时刻的预测温度
湿度	t时刻的预测湿度
负荷历史数据1	预测日前30 d内的同时刻负荷
负荷历史数据2	预测时刻前24 h内各时刻负荷
日类型	工作日或者节假日, 以1/0表示

稳定性负荷	影响因素名称
稳定性负荷	钢价	日期类型	电价	气温
协方差算法	0.000 7	0.510 5	0.412 3	0.612 0
皮尔逊算法	0.000 2	0.489 0	0.453 4	0.587 4

输入量	描述
日类型	预测日前7 d的工作日或节假日类型, 以1/0表示
电价	预测日前7 d的电价
气温	预测日前7 d的温度
负荷历史	预测日前7 d的历史负荷

日期	平均相对误差
日期	LSTM	SVM	组合算法
5月1日	1.81	2.84	1.74
5月2日	2.20	3.53	2.00
5月3日	1.98	2.06	1.50
5月4日	2.10	3.64	2.00
5月5日	2.98	2.20	1.97
5月6日	3.36	3.88	2.42
5月7日	2.06	2.87	1.69