S3: Characterizing Sociality for User-Friendly Steady Load Balancing in Enterprise WLANs
Authors:
- Chaoqun YueCYChaoqun Yue
- Guangtao XueGXGuangtao Xue
- Hongzi ZhuHZHongzi Zhu
- Jiadi YuJYJiadi Yu
- Minglu LiMLMinglu Li
- 1 July 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 8 (10636927) , 491-499
Abstract
Traffic load is often unevenly distributed among the access points (APs) in enterprise WLANs. Such load imbalance results in sub-optimal network throughput and unfair bandwidth allocation among users. In this paper, we collect real traces from over twelve thousand WiFi users in Shanghai Jiao Tong University. Through intensive data analysis, we find that user behavior like leaving together may cause significant AP load imbalance problem. We also observe from the trace that users with similar application usage have the potential to leave together. Inspired by those observations, we propose an innovative scheme, Social-aware AP Selection Scheme(S3), which can actively learn the sociality information among users trained with their history application profiles and elegantly assign users based on the obtained knowledge. Both real prototype implementation and simulation results show that S3 is feasible and can achieve 41.2% balancing performance gain on average.Keywords
This publication has 22 references indexed in Scilit:
- SAP: Smart Access Point with seamless load balancing multiple interfaces2012
- HJam: Attachment transmission in WLANs2012
- A New AP-Selection Strategy for High Density IEEE802.11 WLANs2010
- Designing a Practical Access Point Association Protocol2010
- Cell Breathing Techniques for Load Balancing in Wireless LANsIEEE Transactions on Mobile Computing, 2009
- Cooperative load balancing in IEEE 802.11 networks with cell breathing2008
- IEEE 802.11 Load Balancing: An Approach for QoS EnhancementInternational Journal of Wireless Information Networks, 2008
- Improved access point selection2006
- Load balancing in overlapping wireless LAN cells2004
- Fairness in routing and load balancing2003