并行多模型融合的混合神经网络超短期负荷预测

doi:10.12204/j.issn.1000-7229.2020.10.001

电力建设 ›› 2020, Vol. 41 ›› Issue (10): 1-8.doi: 10.12204/j.issn.1000-7229.2020.10.001

并行多模型融合的混合神经网络超短期负荷预测

庄家懿¹, 杨国华¹^,², 郑豪丰¹, 王煜东¹, 胡瑞琨¹, 丁旭¹

1.宁夏大学物理与电子电气工程学院,银川市 750021
2.宁夏电力能源安全自治区重点实验室,银川市 750021

收稿日期:2020-02-09 出版日期:2020-10-01 发布日期:2020-09-30
通讯作者: 杨国华
作者简介:庄家懿(1996),男,硕士研究生,主要研究方向为电力系统负荷预测;|郑豪丰(1996),男,硕士研究生,主要研究方向为综合能源系统调度;|王煜东(1994),男,硕士研究生,主要研究方向为综合能源系统调度;|胡瑞琨(1993),男,硕士研究生,主要研究方向为综合能源系统调度;|丁旭(1994),男,硕士研究生,主要研究方向为综合能源系统调度。
基金资助:
国家自然科学基金项目(61763040);宁夏自治区重点研发项目(2018BFH03004);宁夏自治区自然科学基金项目(NZ17022)

Ultra-short-term Load Forecasting Using Hybrid Neural Network Based on Parallel Multi-model Combination

ZHUANG Jiayi¹, YANG Guohua¹^,², ZHENG Haofeng¹, WANG Yudong¹, HU Ruikun¹, DING Xu¹

1. School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, China
2. Ningxia Key Laboratory of Electrical Energy Security, Yinchuan 750021,China

Received:2020-02-09 Online:2020-10-01 Published:2020-09-30
Contact: YANG Guohua
Supported by:
National Natural Science Foundation of China(61763040);Key Research & Development Projects of Ningxia(2018BFH03004);Natural Science Foundation of Ningxia(NZ17022)

摘要/Abstract

摘要：

针对输入数据特征多时负荷预测模型精度提升难的问题,文章提出一种并行多模型融合的混合神经网络超短期负荷预测方法。将卷积神经网络(convolutional neural network,CNN)与门控循环单元神经网络(gated recurrent unit neural network,GRU-NN)并行,分别提取局部特征与时序特征,将2个网络结构的输出拼接并输入深度神经网络(deep neural network,DNN),由DNN进行超短期负荷预测。最后应用负荷与温度数据进行预测实验,结果表明相比于GRU-NN网络结构、长短期记忆(long short term memory,LSTM)网络结构、串行CNN-LSTM网络结构与串行CNN-GRU网络结构,所提方法具有更好的预测性能。

关键词: 超短期负荷预测, 卷积神经网络(CNN), 门控循环单元(GRU), 深度神经网络(DNN), 特征提取

Abstract:

For the purpose of addressing the difficulty of improving load forecasting accuracy brought by enormous input data features, a method based on hybrid neural network using parallel multi-model combination is proposed. In order to respectively extract local features and time-series features, this paper places the convolutional neural network (CNN) in parallel with the gated recurrent unit (GRU) structure, then concatenates the output of two network structures and inputs to a deep neural network, uses deep neural network to perform load forecasting. Through a prediction experiment of load and temperature data by using the proposed method, the experiment results show that, compared with GRU-NN model, long short term memory (LSTM) model, serial CNN-LSTM network model and serial CNN-GRU network model, the proposed method shows better prediction performance.

Key words: ultra-short-term load forecasting, convolutional neural network (CNN), gated recurrent unit (GRU), deep neural network (DNN), feature extraction

中图分类号:

TM715

庄家懿, 杨国华, 郑豪丰, 王煜东, 胡瑞琨, 丁旭. 并行多模型融合的混合神经网络超短期负荷预测[J]. 电力建设, 2020, 41(10): 1-8.

ZHUANG Jiayi, YANG Guohua, ZHENG Haofeng, WANG Yudong, HU Ruikun, DING Xu. Ultra-short-term Load Forecasting Using Hybrid Neural Network Based on Parallel Multi-model Combination[J]. ELECTRIC POWER CONSTRUCTION, 2020, 41(10): 1-8.

图/表 12

图1 1月1日负荷与温度数据对比

Fig.1 Comparison of load and temperature on January 1st

图2 7月5日负荷与温度数据对比

Fig.2 Comparison of load and temperature on July 5th

图3 GRU基本结构

Fig.3 Basic structure of GRU

图4 并行多模型融合混合神经网络结构

Fig.4 Structure of hybrid neural network using parallel multi-model combination

图5 滑动窗口输入输出结构

Fig.5 Sliding window structure of input and output

表1 混合神经网络不同GRU结构预测指标对比

Table 1 Prediction metrics comparison of hybrid neural network under different GRU structure

表2 混合神经网络不同CNN结构预测指标对比

Table 2 Prediction metrics comparison of hybrid neural network under different CNN structure

表3 混合神经网络模型结构与参数

Table 3 Structure and parameters of hybrid neural network

表4 不同模型预测MAPE与RMSE对比

Table 4 Comparison of MAPE and RMSE under different model prediction

图6 单一、并行结构网络模型预测曲线与实际曲线对比

Fig.6 Comparison of single model and multi-model predicted and practical curves

表5 模型预测精确度对比

Table 5 Comparison of model prediction accuracy

图7 多种网络模型预测曲线与实际曲线对比

Fig.7 Comparison of multi-model predicted and practical curves

参考文献 23

[1]	HONG T, FAN S . Probabilistic electric load forecasting: A tutorial review[J]. International Journal of Forecasting, 2016,32(3):914-938. doi: 10.1016/j.ijforecast.2015.11.011 URL
[2]	苗键强, 童星, 康重庆 . 考虑相关因素统一修正的节假日负荷预测模型[J]. 电力建设, 2015,36(10):99-104. doi: 10.3969/j.issn.1000-7229.2015.10.015 URL
	MIAO Jianqiang, TONG Xing, KANG Chongqing . Holiday load forecasting model considering related factor with unified correction[J]. Electric Power Construction, 2015,36(10):99-104. doi: 10.3969/j.issn.1000-7229.2015.10.015 URL
[3]	KUSTER C, REZGUI Y, MOURSHED M . Electrical load forecasting models: A critical systematic review[J]. Sustainable Cities and Society, 2017,35:257-270. doi: 10.1016/j.scs.2017.08.009 URL
[4]	DUDEK G . Pattern-based local linear regression models for short-term load forecasting[J]. Electric Power Systems Research, 2016,130:139-147. doi: 10.1016/j.epsr.2015.09.001 URL
[5]	GOIA A, MAY C, FUSAI G . Functional clustering and linear regression for peak load forecasting[J]. International Journal of Forecasting, 2010,26(4):700-711. doi: 10.1016/j.ijforecast.2009.05.015 URL
[6]	艾欣, 周志宇, 魏妍萍 , 等. 基于自回归积分滑动平均模型的可转移负荷竞价策略[J]. 电力系统自动化, 2017,41(20):26-31, 104.
	AI Xin, ZHOU Zhiyu, WEI Yanping , et al. Bidding strategy for time-shiftable loads based on autoregressive integrated moving average model[J]. Automation of Electric Power Systems, 2017,41(20):26-31, 104.
[7]	麦鸿坤, 肖坚红, 吴熙辰 , 等. 基于R语言的负荷预测ARIMA模型并行化研究[J]. 电网技术, 2015,39(11):3216-3220. doi: 10.13335/j.1000-3673.pst.2015.11.030 URL
	MAI Hongkun, XIAO Jianhong, WU Xichen , et al. Research on ARIMA model parallelization in load prediction based on R language[J]. Power System Technology, 2015,39(11):3216-3220. doi: 10.13335/j.1000-3673.pst.2015.11.030 URL
[8]	ABBAS F, FENG D, HABIB S , et al. Short term residential load forecasting: An improved optimal nonlinear auto regressive (NARX) method with exponential weight decay function[J]. Electronics, 2018,7(12):432. doi: 10.3390/electronics7120432 URL
[9]	刘雨竹, 徐楠 . 基于混沌时间序列的IGA-WLSSVR短期负荷预测模型[J/OL]. 控制工程. ( 2019-12-20) [2020-02-07]. https://doi.org/10.14107/j.cnki.kzgc.20190495.
	LIU Yuzhu, XU Nan . Short-term load forecasting model using IGA-WLSSVR based on chaotic time series[J/OL]. Control Engineering of China. ( 2019-12-20) [2020-02-07]. https://doi.org/10.14107/j.cnki.kzgc.20190495 .
[10]	BALIYAN A, GAURAV K, MISHRA S K . A review of short term load forecasting using artificial neural network models[J]. Procedia Computer Science, 2015,48:121-125. doi: 10.1016/j.procs.2015.04.160 URL
[11]	BARBULESCU C, KILYENI S, DEACU A , et al. Artificial neural network based monthly load curves forecasting [C]// 2016 IEEE 11th International Symposium on Applied Computational Intelligence and Informatics (SACI). Timisoara, Romania: IEEE, 2016.
[12]	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 URL
	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 URL
[13]	BIANCHI F M, MAIORINO E, KAMPFFMEYER M C , et al. Recurrent neural networks for short-term load forecasting[M]. Cham: Springer International Publishing, 2017.
[14]	QING X Y, NIU Y G . Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM[J]. Energy, 2018,148:461-468. doi: 10.1016/j.energy.2018.01.177 URL
[15]	张宇帆, 艾芊, 林琳 , 等. 基于深度长短时记忆网络的区域级超短期负荷预测方法[J]. 电网技术, 2019,43(6):1884-1891.
	ZHANG Yufan, AI Qian, LIN Lin , et al. A very short-term load forecasting method based on deep LSTM RNN at zone level[J]. Power System Technology, 2019,43(6):1884-1891.
[16]	彭文, 王金睿, 尹山青 . 电力市场中基于Attention-LSTM的短期负荷预测模型[J]. 电网技术, 2019,43(5):1745-1751.
	PENG Wen, WANG Jinrui, YIN Shanqing . Short-term load forecasting model based on attention-LSTM in electricity market[J]. Power System Technology, 2019,43(5):1745-1751.
[17]	王增平, 赵兵, 纪维佳 , 等. 基于GRU-NN模型的短期负荷预测方法[J]. 电力系统自动化, 2019,43(5):53-58.
	WANG Zengping, ZHAO Bing, JI Weijia , et al. Short-term load forecasting method based on GRU-NN model[J]. Automation of Electric Power Systems, 2019,43(5):53-58.
[18]	HOSSEN T, PLATHOTTAM S J, ANGAMUTHU R K , et al. Short-term load forecasting using deep neural networks (DNN) [C]// 2017 North American Power Symposium (NAPS). IEEE, 2017.
[19]	MUTLU E C, OGHAZ T A , OGHAZ T A. Review on graph feature learning and feature extraction techniques for link prediction[J/OL]. ( 2019 -01-10)[2020-02-07].
[20]	XIE L, YUILLE A . Genetic CNN [C]// Proceedings of the IEEE International Conference on Computer Vision. IEEE, 2017: 1379-1388.
[21]	ABADI M, BARHAM P, CHEN J , et al. Tensorflow: A system for large-scale machine learning [C]//Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation. 2016: 265-283.
[22]	CHO K, VAN MERRIENBOER B, GULCEHRE C , et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J/OL]. ( 2014-09-03) [2020-02-07]. https://arxiv.org/abs/1406.1078.
[23]	LIU B, FU C, BIELEFIELD A , et al. Forecasting of Chinese primary energy consumption in 2021 with GRU artificial neural network[J]. Energies, 2017,10(10):1453. doi: 10.3390/en10101453 URL

并行多模型融合的混合神经网络超短期负荷预测

Ultra-short-term Load Forecasting Using Hybrid Neural Network Based on Parallel Multi-model Combination

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 23

相关文章 5

编辑推荐

Metrics

本文评价

[1]	李浩茹, 丁保迪, 季宇, 王永刚, 陈继开, 张利伟. 考虑光伏出力间歇性的微电网故障辨识方法[J]. 电力建设, 2020, 41(9): 76-85.
[2]	陈倩，齐林海，王红. 基于LSTM网络的谐波多标签分类[J]. 电力建设, 2019, 40(7): 101-106.
[3]	牛东晓，马天男，王海潮，刘鸿飞，黄雅莉. 基于KPCA和NSGAII优化CNN参数的电动汽车充电站短期负荷预测[J]. 电力建设, 2017, 38(3): 85-.
[4]	闾海庆，翁向阳，封加会，雷远华,刘佳明. 一种自适应的无人机影像角点特征提取方法[J]. 电力建设, 2013, 34(7): 104-107.
[5]	贾东梨，孟晓丽，宋晓辉. 基于超短期负荷预测的智能配电网状态估计[J]. 电力建设, 2013, 34(1): 31-35.