基于LSTM神经网络的短期高压负荷电流预测方法

详细信息    查看全文 | 推荐本文 |

英文篇名：Short-term High Voltage Load Current Prediction Method Based on LSTM Neural Network 作者：张洋 ; 姬波 ; 卢红星 ; 娄铮铮 英文作者：ZHANG Yang;JI Bo;LU Hong-xing;LOU Zheng-zheng;School of Information Engineering,Zhengzhou University;The Fourth Generation of Industry Research Institute,Zhengzhou University,Industrial Technology Research Institute; 关键词：短期负荷电流预测 ; LSTM ; 回归预测 ; SHCP-LSTM 英文关键词：Short-termload current prediction;;LSTM;;Regression prediction;;SHCP-LSTM 中文刊名：JSJA 英文刊名：Computer Science 机构：郑州大学信息工程学院;郑州大学产业技术研究院第四代工业研究所; 出版日期：2019-06-15 出版单位：计算机科学 年：2019 期：v.46 基金：国家自然科学青年基金(61502434);; 国家重点研发计划(2018YFB1201403)资助 语种：中文; 页：JSJA201906006 页数：6 CN：06 ISSN：50-1075/TP 分类号：55-60

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。
        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.

引文

[1] ZHOU M,YAN Z,NI Y X,et al.A novel RIMA approach on electricity price forecasting ith theimprovement of predicted error [J].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[J].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[J].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.