Wavelet Transform Processing for Cellular Traffic Prediction in Machine Learning Networks

发布者:系统管理员发布时间:2016-05-21浏览次数:859

Paper author list:

Yunjuan Zang 1, Feixiang Ni 1,Zhiyong Feng 2, Shuguang Cui1,3, and Zhi Ding 1,4

1. School of Information Science and Technology, ShanghaiTechUniversity, Shanghai, China

2. Beijing University of Posts and Telecommunications,Beijing, China

3. Dept. of ECE, Texas A&M University, College Station,TX, USA

4. Dept. of ECE, UC Davis, Davis, CA, USA

 

Published time

2015.07

 

Paper title

Wavelet TransformProcessing for Cellular Traffic Prediction in Machine Learning Networks

 

Paper abstract

The ability for cellularoperators to closely predict the network traffic volume at various locationscan be very important for their resource management and dynamic network controlincluding offloading. This work investigates the analysis of thespatial-temporal information of cellular traffic flow and the prediction ofcell-station traffic volumes. Based on the integration of K-means clustering,Elman Neural Network (Elman-NN), and wavelet decomposition methods, wecharacterize the performance comparison of traffic volume prediction. We testedour wavelet decomposition based machine learning approach using the realtraffic data recorded at a district in a big city and demonstrated the gainover traditional approaches.

 

Conference or journals name and website

The Third IEEE China Summitand International Conference on Signal and Information Processing (ChinaSIP2015)

http://www.chinasip2015.org/

 

A short description of theconference or the journal:

The Third IEEE China Summitand International Conference on Signal and Information Processing (ChinaSIP2015) was held in Chengdu, China from 12th to 15th July 2015. Sponsored by theIEEE Signal Processing Society (SPS), ChinaSIP is an annual summit andinternational conference held in China for domestic and internationalscientists, researchers, and practitioners to network and discusses the latestprogress in theoretical, technological, and educational aspects of signal andinformation processing.