Paper author list:
Feixiang Ni 1,2,Yunjuan Zang1,2, Zhiyong Feng3
1.Shanghai Inst. ofMicrosyst. & Inf. Technol., Chinese Acad. of Sci., Shanghai, China
2.School of InformationScience and Technology, ShanghaiTech University, Shanghai, China
3.Beijing University ofPosts and Telecommunications, Beijing, China
A Study on CellularWireless Traffic Modeling and Prediction Using Elman Neural Networks
Modern cellular resourcemanagement for dynamic control of channel resources and energy efficiencyimprovement relies largely on early and accurate monitoring and prediction ofcellular base station traffic volumes. Analysis of network traffic volume over spaceand time plays an important role in traffic prediction. In this paper, weexamine both the temporal and spatial characteristics of cellular traffic datagenerated by users in a large population city in China. We analyze and clusterbase-stations of similar characteristics. We determine the sliding window sizesand integrate the Elman Neural Network (ENN) after applying wavelet transformin order to realize traffic volume prediction. We present numerical results toillustrate the accuracy of wireless traffic volume prediction, and we test theperformance of our method to demonstrate improvement over some existingmethods.
Conference or journal’s name and website：
2015 4th InternationalConference on Computer Science and Network Technology (ICCSNT2015)
A short description of theconference or the journal:
It is the forth forum forthe presentation of new advances and research results in a wide variety ofscientific areas with a common interest in improving Future Computer Science,Network Technology and Communication related techniques. It is sponsoredby Heilongjiang University, co-sponsored by Dalian Jiaotong University andNortheast Normal University and technical co-sponsored by IEEE Harbin Section.The proceedings of ICCSNT2015 will be included in IEEE Xplore after the reviewtaken by IEEE conference publication group and then submitted to EI Compendexindex.