Integrated approach towards bandwidth aggregation (BAG) in multi-homed devices

The proliferation of (mobile/portable) devices with the ability to connect to multiple interfaces in parallel (e.g., LTE, Wi Fi, small cells, and even wired LAN in case of a laptop) has led to the emergence of a number of usecases involving bandwidth aggregation - i.e., scenarios where more than one available interface is used to support one application requiring higher bandwidth than each of those individual interfaces can provide. A number of bandwidth aggregation (BAG) approaches have been proposed on different layers of the OSI protocol stack, involving different protocols. The BAG approach in any given protocol layer is best suited only for certain specific scenarios. Further, the use of BAG for a particular application when several other applications are also active on the UE, and the real benefits of employing BAG in such a situation have not yet been studied. This paper proposes an integrated approach towards determining the optimum BAG approach taking into account different parameters such as capabilities of the user, network and the remote peer involved in the communication, network conditions, the nature and QoS requirements of applications that are currently active on the UE, transport and application protocols used, operator's policy and charging requirements, etc. A test bed to evaluate the performance of the approach is also proposed. The objective of this paper is to enable the deployment of BAG in a wide variety of real-world scenarios.

[1]  Xiaofei Zhang,et al.  Cross-layer FPS: A SCTP-based cross-layer data scheduling approach , 2011, 2011 IEEE Consumer Communications and Networking Conference (CCNC).

[2]  Mark Handley,et al.  TCP Extensions for Multipath Operation with Multiple Addresses , 2020, RFC.

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

[4]  Samar Shailendra,et al.  MPSCTP: A Simple and Efficient Multipath Algorithm for SCTP , 2011, IEEE Communications Letters.

[5]  Olivier Bonaventure,et al.  Exploring mobile/WiFi handover with multipath TCP , 2012, CellNet '12.

[6]  Khaled A. Harras,et al.  An optimal deployable bandwidth aggregation system , 2013, Comput. Networks.

[7]  Jong-Ok Kim,et al.  MAC-level measurement based traffic distribution over IEEE 802.11 multi-radio networks , 2008, IEEE Transactions on Consumer Electronics.

[8]  Kameswari Chebrolu,et al.  Bandwidth aggregation for real-time applications in heterogeneous wireless networks , 2006 .

[9]  Moustafa Youssef,et al.  DNIS: a middleware for dynamic multiple network interfaces scheduling , 2010, MOCO.

[10]  Kameswari Chebrolu,et al.  A Network Layer Approach to Enable TCP over Multiple Interfaces , 2005, Wirel. Networks.

[11]  Choong Seon Hong,et al.  A Multipath Cubic TCP Congestion Control with Multipath Fast Recovery over High Bandwidth-Delay Product Networks , 2012, IEICE Trans. Commun..

[12]  H. Anthony Chan,et al.  Bandwidth aggregation in heterogeneous wireless networks: A survey of current approaches and issues , 2012, J. Netw. Comput. Appl..

[13]  Hesham Soliman,et al.  Status of this Memo , 1985 .

[14]  Kyriakos Manousakis,et al.  INTELiCON: Intelligent Connectivity Framework for the Simultaneous Use of Multiple Interfaces , 2007, 2007 IEEE International Conference on Communications.

[15]  Paal E. Engelstad,et al.  Using HTTP Pipelining to Improve Progressive Download over Multiple Heterogeneous Interfaces , 2010, 2010 IEEE International Conference on Communications.

[16]  Raghupathy Sivakumar,et al.  A Transport Layer Approach for Achieving Aggregate Bandwidths on Multi-Homed Mobile Hosts , 2002, MobiCom '02.

[17]  Khaled A. Harras,et al.  OSCAR: A Collaborative Bandwidth Aggregation System , 2014, ArXiv.