Medium and Long-term Load Forecasting Method Considering Multi-time Scale Data

被引：0

作者：

Luo S. ^{[1
]}

Ma M. ^{[1
]}

Jiang L. ^{[2
]}

Jin B. ^{[1
]}

Lin Y. ^{[1
]}

Diao X. ^{[3
]}

Li C. ^{[2
]}

Yang B. ^{[4
]}

机构：

[1] Grid Planning Research Center, Guangdong Power Grid Co., Ltd., Guangzhou

[2] Hunan Key Laboratory of Intelligent Information Analysis and Integrated Optimization for Energy Internet (Hunan University), Changsha

[3] School of Mathematical Sciences, Peking University, Haidian District, Beijing

[4] Guangzhou Operation Power Technology Co., Ltd., Guangzhou

来源：

Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2020年 / 40卷

关键词：

Big data; Medium and long-term load forecasting; Multiple time scale; Neural network; Power system;

D O I：

10.13334/j.0258-8013.pcsee.190550

中图分类号：

学科分类号：

摘要：

Accurately load forecasting is critical to power system. Massive smart grid data with complex structures is collected from different electrical installations. The factors affecting the load are complicated. Most of them are distributed on different time scales. It is necessary to consider the dependence between multi-scale data and make full use of data from different time scales in order to make accurate, stable and reliable medium and long-term predictions. This paper proposed a stacked long-term and short-term memory (LSTM) network model, which integrated three different time scales data of monthly historical load, annual regional economic and daily climate information. In the model, in order to avoid the algorithm is overfitting, all the parameters excepted the offset parameters which in the circulatory neural network were regularized. An example of Guangdong load forecasting proved that compared to the method using the support vector machine (SVM) and deep neural networks (DNN) method, the accuracy of load forecasting is effectively improved. © 2020 Chin. Soc. for Elec. Eng.

引用

页码：11 / 19

页数：8

共 24 条

[1] Zhong Qing, Sun Wen, Yu Nanhua, Et al., Load and power forecasting in active distribution network planning, Proceedings of the CSEE, 34, 19, pp. 3050-3056, (2014)
[2] Zhao Teng, Wang Lintong, Zhang Yan, Et al., Relation factor identification of electricity consumption behavior of users and electricity demand forecasting based on mutual information and random forests, Proceedings of the CSEE, 36, 3, pp. 604-614, (2016)
[3] Yao Min, Zhao Min, Xiao Hui, Et al., Research on mid-long term load forecasting based on combination forecasting mode, 2015 IEEE/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing(SNPD), pp. 1-5, (2015)
[4] Wang Peng, Chen Qixin, Xia Qing, Et al., Correlation analysis and forecasting method on industrial electricity demand based on vector error correction model, Proceedings of the CSEE, 32, 4, pp. 100-107, (2012)
[5] Kang Chongqing, Xia Qing, Liu Mei, Power system load forecasting, (2017)
[6] Li Jin, Liu Jinpeng, Wang Jianjun, Mid-long term load forecasting based on simulated annealing and SVM algorithm, Proceedings of the CSEE, 31, 16, pp. 63-66, (2011)
[7] Zhou Quan, Ren Haijun, Li Jian, Et al., Variable weight combination method for mid-long term power load forecasting based on hierarchical structure, Proceedings of the CSEE, 30, 16, pp. 47-52, (2010)
[8] 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, Power System Protection and Control, 44, 3, pp. 92-97, (2016)
[9] Wu Yaowu, Lou Suhua, Lu Siyu, Et al., The medium and long-term load forecasting based on improved D-S evidential theory, Transactions of China Electrotechnical Society, 27, 8, pp. 157-162, (2012)
[10] Zhang Qian, Lai K K, Niu Dongxiao, Optimization combination forecast method of SVM and WNN for power load forecasting, 2011 Fourth International Joint Conference on Computational Sciences and Optimization, pp. 249-253, (2011)

← 1 2 3 →