A case for Predictive DiffServ on mobile networks

Differentiated service is intended to achieve scalable service differentiation within the network. A protocol with its QoS semantics left up to off-line service level agreements (SLAs) between the network and application, it is inapplicable to mobile environments: (1) lacks real-time QoS feedback from the network to the application; (2) cannot guarantee SLAs under dynamically changing network conditions; (3) forces the application to actively probe the network for QoS measurements thereby needlessly consuming bandwidth; and (4) can only provide network conditions information in the near past, thereby diminishing its utility. We introduce predictive DiffServ, a novel missing design point in the space of QoS network services, as an adaptable mechanism intended to provide the application with real-time, in-band predictions of network conditions, and enable the application to autonomously reconfigure its requirements in response to these conditions. Contributions include the concept, properties, architecture and API of predictive DiffServ. Additionally, we identify newly enabled application services, and portray quantitative results.

[1]  Gunnar Karlsson,et al.  Quality of Service and the End-to-End Argument , 2007, IEEE Network.

[2]  J. Zinky,et al.  Complementary methods for QoS adaptation in component-based multi-agent systems , 2004, IEEE First Symposium onMulti-Agent Security and Survivability, 2004.

[3]  Juha Heinänen,et al.  Multiprotocol Encapsulation over ATM Adaptation Layer 5 , 1993, RFC.

[4]  W. Richard Stevens,et al.  TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms , 1997, RFC.

[5]  Richard Wolski,et al.  The network weather service: a distributed resource performance forecasting service for metacomputing , 1999, Future Gener. Comput. Syst..

[6]  K. K. Ramakrishnan,et al.  A Proposal to add Explicit Congestion Notification (ECN) to IP , 1999, RFC.

[7]  Wendi B. Heinzelman,et al.  A Survey of Routing Protocols that Support QoS in Mobile Ad Hoc Networks , 2007, IEEE Network.

[8]  David L. Black,et al.  An Architecture for Differentiated Service , 1998 .

[9]  Dan Grossman,et al.  New Terminology and Clarifications for Diffserv , 2002, RFC.

[10]  Yitzchak M. Gottlieb,et al.  Snow on silk: Layering NodeOS functionality on conventional operating systems , 2006, Comput. Networks.

[11]  Zheng Wang,et al.  An Architecture for Differentiated Services , 1998, RFC.

[12]  John A. Zinky,et al.  Towards an architecture for extreme P2P applications , 2007 .

[13]  John Moy,et al.  OSPF for IPv6 , 1999, RFC.

[14]  T. Michel,et al.  Real-Time Network Simulation for the GIG Tactical Edge , 2006, MILCOM 2006 - 2006 IEEE Military Communications conference.

[15]  Dino Farinacci,et al.  Anycast Rendevous Point (RP) mechanism using Protocol Independent Multicast (PIM) and Multicast Source Discovery Protocol (MSDP) , 2003, RFC.

[16]  Bruce S. Davie,et al.  Deploying IP and MPLS QoS for Multiservice Networks: Theory & Practice , 2007 .

[17]  Larry Wong,et al.  Bandwidth broker architecture for VoIP QoS , 2001, SPIE ITCom.

[18]  Lixia Zhang,et al.  Resource ReSerVation Protocol (RSVP) - Version 1 Functional Specification , 1997, RFC.

[19]  David L. Black,et al.  Definition of the Differentiated Services Field (DS Field) in the IPv4 and IPv6 Headers , 1998, RFC.

[20]  Henning Schulzrinne,et al.  RTP: A Transport Protocol for Real-Time Applications , 1996, RFC.

[21]  John A. Zinky,et al.  Case Studies of Node-level QoS Adaptation in Cougaar , 2004 .