Network Traffic Prediction Based on LSSVM Optimized by PSO

doi:10.1109/UIC-ATC-ScalCom.2014.100

IR > 计算机与通信学院

	Network Traffic Prediction Based on LSSVM Optimized by PSO
	Yang, Yi 1; Chen, Yanhua 1; Li, Caihong 1; Gui, Xiangquan2 ; Li, Lian 1
	2014
会议名称	11th IEEE International Conference on Ubiquitous Intelligence and Computing and 11th IEEE International Conference on Autonomic and Trusted Computing and 14th IEEE International Conference on Scalable Computing and Communications and Associated Symposia/Workshops, UIC-ATC-ScalCom 2014
会议录名称	Proceedings - 2014 IEEE International Conference on Ubiquitous Intelligence and Computing, 2014 IEEE International Conference on Autonomic and Trusted Computing, 2014 IEEE International Conference on Scalable Computing and Communications and Associated Symposia/Workshops, UIC-ATC-ScalCom 2014
页码	829-834
会议日期	December 9, 2014 - December 12, 2014
会议地点	Denpasar, Bali, Indonesia
出版者	Institute of Electrical and Electronics Engineers Inc.
摘要	Nowadays, artificial intelligence is frequently used to various fields including medicine, chemistry and forecasting. In this paper, artificial intelligence is applied to network traffic prediction. Due to that network traffic prediction plays an important role in network management, planning, traffic congestion control and traffic engineering. Seeking for more accurate network traffic prediction techniques, this paper proposed a new hybrid method (SPLSSVM) which based on seasonal adjustment (SA) and least squares support vector machine (LSSVM) optimized by particle swarm optimization (PSO) to predict network traffic. The proposed method is examined by using the network traffic data from Lanzhou University. Empirical testing indicates that the proposed method can provide more accurate and effective results than the other forecasting methods. © 2014 IEEE.
关键词	Artificial intelligence Computer networks Forecasting Least squares approximations Particle swarm optimization (PSO) Support vector machines Trusted computing Ubiquitous computing Empirical testing Forecasting methods In-network management Least square support vector machines Least squares support vector machines Network traffic predictions Seasonal adjustments Traffic Engineering
DOI	10.1109/UIC-ATC-ScalCom.2014.100
收录类别	EI
语种	英语
EI入藏号	20155101679374
EI主题词	Traffic congestion
来源库	Compendex
分类代码	723 Computer Software, Data Handling and Applications - 921.6 Numerical Methods
引用统计	被引频次：7[WOS] [WOS记录] [WOS相关记录]
文献类型	会议论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/117807
专题	计算机与通信学院
作者单位	1.School of Information Science and Engineering, Lanzhou University, Lanzhou; 730000, China; 2.College of Computer and Communication, Lanzhou University of Technology, Lanzhou; 730000, China
推荐引用方式 GB/T 7714	Yang, Yi,Chen, Yanhua,Li, Caihong,et al. Network Traffic Prediction Based on LSSVM Optimized by PSO[C]:Institute of Electrical and Electronics Engineers Inc.,2014:829-834.