A cross-layer approach for improving WiFi performance

This paper introduces a cross-layer implementation, named WiPoMu, that aims to improve efficiency and resilience of the traditional WiFi model. WiPoMu is developed based on three key technologies: Wireless virtualization, Policy routing, and Multipath TCP (MPTCP). Specifically, WiPoMu adopts the wireless virtualization to create multiple virtual WiFi interfaces on a single physical one, hence WiPoMu enables concurrent connections with different access points (APs). In addition, WiPoMu leverages the policy routing and MPTCP in order to efficiently direct and schedule traffic flows over multiple virtual interfaces. On the other hand, WiPoMu is transparent to users since it requires no modification in the physical and application layers. We have conducted evaluations to validate the efficiency of WiPoMu on an indoor testbed and a real home network. The evaluation results show that a WiFi client equipped WiPoMu is able to establish multiple active paths to Internet across different APs. Besides that, WiPoMus is resilient to path failure by achieving seamless handover between the active paths. Furthermore, WiPoMu improves up to 300% aggregated throughput comparing to the traditional WiFi model using TCP in the testbed.

[1]  Srikanth Kandula,et al.  FatVAP: Aggregating AP Backhaul Capacity to Maximize Throughput , 2008, NSDI.

[2]  Sanjay Kumar,et al.  Virtual WiFi: bring virtualization from wired to wireless , 2011, VEE '11.

[3]  Martin Heusse,et al.  Performance anomaly of 802.11b , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[4]  Brian Neil Levine,et al.  Spider: improving mobile networking with concurrent wi-fi connections , 2011, SIGCOMM.

[5]  Injong Rhee,et al.  WiFox: scaling WiFi performance for large audience environments , 2012, CoNEXT '12.

[6]  Nick McKeown,et al.  OpenFlow: enabling innovation in campus networks , 2008, CCRV.

[7]  LiLi,et al.  Fairness and load balancing in wireless LANs using association control , 2007 .

[8]  Paramvir Bahl,et al.  MultiNet: connecting to multiple IEEE 802.11 networks using a single wireless card , 2004, IEEE INFOCOM 2004.

[9]  Thierry Turletti,et al.  Efficient caching in content-centric networks using OpenFlow , 2013, 2013 Proceedings IEEE INFOCOM.

[10]  Mark Handley,et al.  Design, Implementation and Evaluation of Congestion Control for Multipath TCP , 2011, NSDI.

[11]  Yusheng Ji,et al.  Improving WiFi networking with concurrent connections and multipath TCP , 2013, 2013 IEEE 14th International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM).

[12]  Brian Neil Levine,et al.  Concurrent Wi-Fi for mobile users: analysis and measurements , 2011, CoNEXT '11.

[13]  Mark Handley,et al.  How Hard Can It Be? Designing and Implementing a Deployable Multipath TCP , 2012, NSDI.

[14]  Seung-Jae Han,et al.  Fairness and Load Balancing in Wireless LANs Using Association Control , 2004, IEEE/ACM Transactions on Networking.

[15]  Brian D. Noble,et al.  Juggler: Virtual Networks for Fun and Profit , 2010, IEEE Transactions on Mobile Computing.

[16]  Mark Handley,et al.  Architectural Guidelines for Multipath TCP Development , 2011, RFC.

[17]  Yahya Al-Hazmi,et al.  Virtualization of 802.11 interfaces for Wireless Mesh Networks , 2011, 2011 Eighth International Conference on Wireless On-Demand Network Systems and Services.