资源描述:
《bp神经网络误差修正的电力物资时间序列预测①》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库。
1、计算机系统应用 ISSN 1003-3254, CODEN CSAOBNE-mail: csa@iscas.ac.cnComputer Systems & Applications,2017,26(10):196−200 [doi: 10.15888/j.cnki.csa.006011]http://www.c-s-a.org.cn©中国科学院软件研究所版权所有.Tel: +86-10-62661041BP神经网络误差修正的电力物资时间序列预测①赵一鹏1,2, 丁云峰1, 姚恺丰31(中国科学院沈阳计算技术研究所, 沈阳 110168)2(中国科学院大学, 北京
2、100049)3(国家电网公司东北分部, 沈阳 110180)摘 要: 传统的ARIMA时间序列分析方法是基于线性技术来进行时序预测, 而对非线性数据的处理不尽合理, 效果欠佳; 而影响电力物资需求的因素非常多, 绝大多数的物资序列通常既包含了线性时序的部分, 又包含了非线性时序的成分. 本文提出在ARIMA对电力物资需求预测的基础上, 融合BP神经网络进行误差修正, 以全面提取物资序列中的复合特征, 提高电力物资的预测精度. 实验结果表明, 误差修正后的电力物资预测精度有了显著提高, 可以为制定物资采购计划提供重要的数据支持.关键词: 时间序列; ARIMA模型;
3、BP神经网络; 误差修正; 电力物资预测引用格式: 赵一鹏,丁云峰,姚恺丰.BP神经网络误差修正的电力物资时间序列预测.计算机系统应用,2017,26(10):196–200. http://www.c-s-a.org.cn/1003-3254/6011.htmlTimeSeriesPredictionofPowerSuppliesBasedonBPNeuralNetworkErrorCorrectionZHAO Yi-Peng1,2, DING Yun-Feng1, YAO Kai-Feng31(Shenyang Institute of Computer Tec
4、hnology, Chinese Academy of Sciences, Shenyang 110168, China)2(University of Chinese Academy of Sciences, Beijing 100049, China)3(Northeast Branch of State Grid Corporation of China, Shenyang 110180, China)Abstract: The traditional ARIMA time series analysis method is based on the linea
5、r technology to predict the time series,while its processing of nonlinear data is not reasonable with poor effect. There are many factors influencing the demand ofpower supply, and most of the material sequences usually contain both the linear time series and the nonlinear time series.I
6、n this paper, based on the ARIMA forecast, the BP neural network is combined with error correction to extract thecomposite features in the material sequence in order to improve the forecast precision of the electric power materials. Theexperimental results show that the accuracy of powe
7、r supply forecasting with error correction can be improvedsignificantly, which can provide important data support for material procurement plan.Keywords: time series; ARIMA model; BP neural network; error correction; electric power supplies forecasting随着电力企业的快速发展, 物资管理在企业精细需求规划