Short-term load forecasting method based on fusion of multiple neural networks

被引：0

作者：

Pang H. ^{[1
]}

Gao J. ^{[1
]}

Du Y. ^{[2
]}

机构：

[1] Industrial Technology Research Institute, Zhengzhou University, Zhengzhou

[2] Yantai Power Supply Company of State Grid Shandong Electric Power Company, Yantai

来源：

Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2020年 / 40卷 / 06期

关键词：

Attention mechanism network; Convolutional neural network; Fusion of multiple neural networks; Gated recurrent unit network; Maxout network; Short-term load forecasting;

D O I：

10.16081/j.epae.202005021

中图分类号：

学科分类号：

摘要：

In order to make use of the advantages of different deep neural networks and improve the ability of deep learning algorithm for short-term load forecasting, a short-term load forecasting method based on multiple neural networks fusion is proposed. The historical active power load, season, date type and weather data of power system are taken as input characteristics, while the deep neural network and attention mechanism network of parallel architecture are taken as core network. The static features are extracted by the convolutional neural network channel in the parallel architecture, the dynamic time series features are mined by the gated recurrent unit network channel, and the attention mechanism network is adopted to fuse the extracted features and dynamically adjust the dependent degree of network on different features. Maxout network is used to enhance the non-linear mapping ability of the whole network, and the forecasting results are output through the fully connected network. Compared with the results of support vector machine and long- and short-term memory network, the proposed method has higher forecasting stability and accuracy. © 2020, Electric Power Automation Equipment Press. All right reserved.

引用

页码：37 / 42

页数：5

共 22 条

[1]

CHEN Hao, WANG Yurong, Short-term load forecasting based on SV model, Electric Power Automation Equipment, 30, 11, pp. 86-89, (2010)

[2]

HOR C L, WATSON S J, MAJITHIA S., Daily load forecasting and maximum demand estimation using ARIMA and GARCH, (2006)

[3]

MAHMUD M A., Isolated area load forecasting using linear regression analysis: practical approach, Energy and Power Engineering, 3, 4, pp. 547-550, (2011)

[4]

WAN Kun, LIU Ruiyu, Application of interval time-series vector autoregressive model in short-term load forecasting, Po-wer System Technology, 36, 11, pp. 77-81, (2012)

[5]

ZHANG Ping, PAN Xueping, XUE Wenchao, Short-term load forecasting based on wavelet decomposition, fuzzy gray correlation clustering and BP neural network, Electric Power Automation Equipment, 32, 11, pp. 121-125, (2012)

[6]

WANG Baoyi, WANG Dongyang, ZHANG Shaomin, Distributed short-term load forecasting algorithm based on Spark and IPPSO_SSVM, Electric Power Automation Equipment, 36, 1, pp. 117-122, (2016)

[7]

ZHANG Zhisheng, YU Daolin, RBF-NN based short-term load forecasting model considering comprehensive factors affecting demand response, Proceedings of the CSEE, 38, 6, pp. 1631-1638, (2018)

[8]

JU Ping, ZHOU Xiaoxin, CHEN Weijiang, Et al., Smart Grid Plus" research overview, Electric Power Automation Equipment, 38, 5, pp. 2-11, (2018)

[9]

SCOTT D, SIMPSON T, DERVILIS N, Et al., Machine learning for energy load forecasting, Journal of Physics: Conference Series, 11, 1, pp. 12-25, (2018)

[10]

KONG Xiangyu, ZHENG Feng, E Zhijun, Et al., Short-term load forecasting based on deep belief network, Automation of Electric Power Systems, 42, 5, pp. 133-139, (2018)

← 1 2 3 →