计算机科学 ›› 2019, Vol. 46 ›› Issue (6): 49-54.doi: 10.11896/j.issn.1002-137X.2019.06.006

• 大数据与数据科学* • 上一篇    下一篇

基于LSTM神经网络的短期高压负荷电流预测方法

张洋1, 姬波1,2, 卢红星1,2, 娄铮铮1   

  1. (郑州大学信息工程学院 郑州450001)1
    (郑州大学产业技术研究院第四代工业研究所 郑州450001)2
  • 收稿日期:2018-06-13 发布日期:2019-06-24
  • 通讯作者: 卢红星(1965-),男,硕士,副教授,CCF高级会员,主要研究方向为模式识别、工控系统,E-mail:iehxlu@zzu.edu.cn
  • 作者简介:张 洋(1991-),男,硕士生,主要研究方向为数据挖掘、深度学习;姬 波(1973-),男,博士,教授,主要研究方向为数据分析、模式识别、工控系统;娄铮铮(1984-),男,博士,副教授,主要研究方向为机器学习、数据挖掘、模式识别。
  • 基金资助:
    国家自然科学青年基金(61502434),国家重点研发计划(2018YFB1201403)资助。

Short-term High Voltage Load Current Prediction Method Based on LSTM Neural Network

ZHANG Yang1, JI Bo1,2, LU Hong-xing1,2, LOU Zheng-zheng1   

  1. (School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China)1
    (The Fourth Generation of Industry Research Institute,Zhengzhou University,Industrial Technology Research Institute,Zhengzhou 450001,China)2
  • Received:2018-06-13 Published:2019-06-24

摘要: 传统模型在短期高压负荷电流预测中难以同时解决负荷电流数据的非线性和时间相关性问题。针对此问题,提出一种基于长短期记忆(LSTM)循环神经网络的短期高压负荷电流回归预测方法SHCP-LSTM。该方法引入自循环权重,使细胞彼此循环连接,可以动态改变累积的时间尺度,使其具有长短期记忆功能;使用遗忘门来控制输入和输出,从而使得门控单元具有sigmoid非线性。实验结果验证了该方法的可行性和有效性,与线性逻辑回归算法LR和机器学习算法ANN神经网络、BPNN神经网络预测相比,SHCP-LSTM收敛速度更快,且精确度更高。

关键词: LSTM, SHCP-LSTM, 短期负荷电流预测, 回归预测

Abstract: In the short-term load current prediction,the traditional model can’t solve the problems of nonlinearity and time dependence of load current data simultaneously.To solve this problem,this paper proposed a short-term high vol-tage load current regression prediction(SHCP) method based on a long short-term memory(LSTM) recurrent neural network,namely SHCP-LSTM.The proposed method introduces the weight of self-circulation,which can make cells connected with each other circularly and dynamically change the cumulative time scale in the prediction,thus having a long short memory function.Meanwhile,the method uses the forgetting gate to control the input and output,so that the gate control unit has the sigmoid nonlinearity.Experiments show that the method is feasible and effective.Compared with linear logistic regression algorithm(LR) and machine learning algorithm artificial neural network(ANN) and back propagation neural network(BPNN) prediction,SHCP-LSTM has fast convergence speed and high accuracy.

Key words: LSTM, Regression prediction, SHCP-LSTM, Short-termload current prediction

中图分类号: 

  • TP183
[1]ZHOU M,YAN Z,NI Y X,et al.A novel RIMA approach on electricity price forecasting ith theimprovement of predicted error .Proceedings of the CSEE,2017,24(12):63-68.(in Chinese)
周明,严正,倪以信,等.含误差预测校正的ARIMA电价预测新方法[J].中国电力工程学报,2017,24(12):63-68.
[2]AL-MUSAYLH M S,DEO R C,ADAMOWSKI J F,et al.Short-term electricity demand forecasting with MARS,SVR and ARIMA models using aggregated demand data in Queens-land,Australia[J].Advanced Engineering Informatics,2018,35:1-16.
[3]NEWSHAM G R,BIRT B J.Building-level Occupancy Data to Improve ARIMA-based Electricity Use Forecasts[C]∥ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Buildings.Texas:ACM Press,2010:13-18.
[4]SONG K B,BAEK Y S,HONG D H.Short-Term Load Forecasting for the Holidays Using Fuzzy Linear Regression Method[J].IEEE Transactions on Power Systems,2005,20(1):96-101.
[5]PATEL H,PANDYA M,AWARE M.Short Term Load Forecasting of Indian System Using Linear Regression and Artificial NeuralNetwork[C]∥N-UiCONE 2015-5th Nirma University International Conference on Engineering.NewYork:IEEE Press,2015:1-5.
[6]LV Z Y,QIAN Z M,GREEN T C.A predicted control scheme of shunt active power filter with artificial neural network.Proceedings of the CSEE,1999,19(12):22-26.(in Chinese)
吕征宇,钱照明,GREEN T C.并联有源电力滤波器的神经网络预测控制[J].中国电机工程学报,1999,19(12):22-26.
[7]VIEGAS J L,VIEIRA S M,MELICIO R,et al.GA-ANN Short-Term Electricity Load Forecasting[C]∥IFIP Advances in Information and Communication Technology.Berlin:Springer New York,2016:485-493.
[8]KOLHE M,LIN T C,MAUNUKSELA J.GA-ANN for Short-Term Wind Energy Prediction [C]∥Asia-Pacific Power and Energy Engineering Conference.NewYork:IEEE Press,2011:1-6.
[9]AKBAL B.Hybrid GSA-ANN Methods to Forecast Sheath Current of High Voltage Underground Cable Lines[J].Journal of Computers,2018,13(4):417-425.
[10]TANG C E.Short-term Load Forecasting of Power System Based on AIternating Particle Swarm BP Network.Computer Science,2017,44(S2):133-135,165.(in Chinese)
唐承娥.基于交变粒子群 BP 网络的电力系统短期负荷预测[J].计算机科学,2017,44(S2):133-135,165.
[11]CHEN P,ZHANG Q,LI Y J,et al.Short-Term Load Forecasting Model for Power System Based on Complementation of Fuzzy-Rough Set Theory and BP Neural Network[C]∥Proceedings of the IEEE International Conference on Automation and Logistics.NewYork:IEEE Press,2007:1373-1377.
[12]HOCHREITER S,SCHMIDHUBER J.LSTM Can Solve Hard Long Time Lag Problems[C]∥Advances in Neural Information Processing Systems.Canada:NIPS,1996:473-479.
[13]GRAVES A,ECK D,SCHMIDHUBER J,et al.Biologically plausible speech recognition with LSTM Neural Nets[M]∥Lecture Notes in Computer Science.Berlin:Springer Verlag,2004:127-136.
[1] 张源, 康乐, 宫朝辉, 张志鸿.
基于Bi-LSTM的期货市场关联交易行为检测方法
Related Transaction Behavior Detection in Futures Market Based on Bi-LSTM
计算机科学, 2022, 49(7): 31-39. https://doi.org/10.11896/jsjkx.210400304
[2] 于家畦, 康晓东, 白程程, 刘汉卿.
一种新的中文电子病历文本检索模型
New Text Retrieval Model of Chinese Electronic Medical Records
计算机科学, 2022, 49(6A): 32-38. https://doi.org/10.11896/jsjkx.210400198
[3] 林夕, 陈孜卓, 王中卿.
基于不平衡数据与集成学习的属性级情感分类
Aspect-level Sentiment Classification Based on Imbalanced Data and Ensemble Learning
计算机科学, 2022, 49(6A): 144-149. https://doi.org/10.11896/jsjkx.210500205
[4] 王杉, 徐楚怡, 师春香, 张瑛.
基于CNN-LSTM的卫星云图云分类方法研究
Study on Cloud Classification Method of Satellite Cloud Images Based on CNN-LSTM
计算机科学, 2022, 49(6A): 675-679. https://doi.org/10.11896/jsjkx.210300177
[5] 袁景凌, 丁远远, 盛德明, 李琳.
基于视觉方面注意力的图像文本情感分析模型
Image-Text Sentiment Analysis Model Based on Visual Aspect Attention
计算机科学, 2022, 49(1): 219-224. https://doi.org/10.11896/jsjkx.201000074
[6] 程思伟, 葛唯益, 王羽, 徐建.
BGCN:基于BERT和图卷积网络的触发词检测
BGCN:Trigger Detection Based on BERT and Graph Convolution Network
计算机科学, 2021, 48(7): 292-298. https://doi.org/10.11896/jsjkx.200500133
[7] 俞建业, 戚湧, 王宝茁.
基于Spark的车联网分布式组合深度学习入侵检测方法
Distributed Combination Deep Learning Intrusion Detection Method for Internet of Vehicles Based on Spark
计算机科学, 2021, 48(6A): 518-523. https://doi.org/10.11896/jsjkx.200700129
[8] 许明泽, 韦明辉, 邓霜, 蔡卫.
多模型集成学习在机械钻速预测中的新应用
Application of Multi-model Ensemble Learning in Prediction of Mechanical Drilling Rate
计算机科学, 2021, 48(6A): 619-622. https://doi.org/10.11896/jsjkx.201000070
[9] 胡聿文.
基于优化LSTM模型的股票预测
Stock Forecast Based on Optimized LSTM Model
计算机科学, 2021, 48(6A): 151-157. https://doi.org/10.11896/jsjkx.200400011
[10] 陈慧琴, 郭贯成, 秦朝轩, 李兆碧.
基于GM-LSTM模型的南京市老年人口预测研究
Research on Elderly Population Prediction Based on GM-LSTM Model in Nanjing City
计算机科学, 2021, 48(6A): 231-234. https://doi.org/10.11896/jsjkx.200900142
[11] 张争万, 吴迪, 张春炯.
基于多通道稀疏LSTM的蜂窝流量预测研究
Study of Cellular Traffic Prediction Based on Multi-channel Sparse LSTM
计算机科学, 2021, 48(6): 296-300. https://doi.org/10.11896/jsjkx.210400134
[12] 董哲, 邵若琦, 陈玉梁, 翟维枫.
基于BERT和对抗训练的食品领域命名实体识别
Named Entity Recognition in Food Field Based on BERT and Adversarial Training
计算机科学, 2021, 48(5): 247-253. https://doi.org/10.11896/jsjkx.200800181
[13] 陈明豪, 祝跃飞, 芦斌, 翟懿, 李玎.
基于Attention-CNN的加密流量应用类型识别
Classification of Application Type of Encrypted Traffic Based on Attention-CNN
计算机科学, 2021, 48(4): 325-332. https://doi.org/10.11896/jsjkx.200900155
[14] 李冰荣, 皮德常, 候梦如.
基于CNN和LSTM的移动对象目的地预测
Destination Prediction of Moving Objects Based on Convolutional Neural Networks and Long-Short Term Memory
计算机科学, 2021, 48(4): 70-77. https://doi.org/10.11896/jsjkx.200200024
[15] 王友卫, 朱晨, 朱建明, 李洋, 凤丽洲, 刘江淳.
基于用户兴趣词典和LSTM的个性化情感分类方法
User Interest Dictionary and LSTM Based Method for Personalized Emotion Classification
计算机科学, 2021, 48(11A): 251-257. https://doi.org/10.11896/jsjkx.201200202
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!