From: Cognitive Networks: Adaptation and Learning to Achieve End-to-End Performance Objectives

Cognitive Networks: Adaptation and
Learning to Achieve End-to-End
Performance Objectives

ABSTRACT
In this article we advance the idea of a cognitive
network, capable of perceiving current network
conditions and then planning, learning, and
acting according to end-to-end goals. Cognitive
networks are motivated by the complexity, heterogeneity,
and reliability requirements of
tomorrow’s networks, which are increasingly
expected to self-organize to meet user and application
objectives. We compare and contrast cognitive
networks with related research on
cognitive radios and cross-layer design. By defining
cognitive networks, examining their relationship
to other technologies, discussing critical
design issues, and providing a framework for
implementation, we aim to establish a foundationsize of the system state space, wireless networks
are a natural focus of research in complex
networks. Previous wireless research into
cognitive radio and crosslayer design have
addressed some of these issues, but have shortcomings
from the network perspective. Cognitive
networks represent a new scope and
approach to dealing with this complexity. This
article is written to provide the reader with a
primer on the cognitive network concept, as
envisioned by the authors. As such, it begins by
first explaining the need for cognitive networks,
how they are defined, and possible
applications for the technology. Then the article
examines how cognitive networks are related
to, but distinct from, previous work in
cognitive radios and cross-layer design. A practical
discussion of the implementation of a cognitive
network and important areas of future
work closes the article.

DEFINITION
We suggest the following definition for a cognitive
network, first described by us in [1]: A cognitive
network is a network with a cognitive
process that can perceive current network conditions,
and then plan, decide, and act on those
conditions. The network can learn from these
adaptations and use them to make future decisions,
all while taking into account end-to-end
goals.

The cognitive aspect of this definition is similar
to that used to describe cognitive radio and
broadly encompasses many simple models of
cognition and learning. More critical to the definition
are the network and end-to-end aspects.
Without the network and end-to-end scope, the
system is perhaps a cognitive radio or layer, but
not a cognitive network. Here, end-to-end
denotes all the network elements involved in the
transmission of a data flow. For a unicast transmission,
this might include the subnets, routers,
switches, virtual connections, encryption
schemes, mediums, interfaces, or waveforms, to
mention just a few. The end-to-end goals are
what gives a cognitive network its network-wide
scope, separating it from other adaptation
approaches, which have only a local, single element
scope.

Ryan W. Thomas, Daniel H. Friend, Luiz A. DaSilva, and Allen B. MacKenzie, Virginia Tech

REFERENCES
[1] R. W. Thomas, L. A. DaSilva, and A. B. Mackenzie,
“Cognitive Networks,” Proc. IEEE DySPAN 2005, Nov.
2005, pp. 352–60.
[2] J. Mitola, Cognitive Radio: An Integrated Agent Architecture
for Software Defined Radio, Ph.D. thesis, Royal
Inst. Technology, 2000.
[3] V. Srivastava and M. Motani, “Cross-Layer Design: A
Survey and the Road Ahead,” IEEE Commun. Mag., vol.
43, no. 12, 2005, pp. 112–19.
[4] V. Kawadia and P. R. Kumar, “A Cautionary Perspective[5] D. D. Clark et al., “A Knowledge Plane for the Internet,”
Proc. SIGCOMM ’03, New York, NY, 2003, pp. 3–10.
[6] D. Bourse et al., “End-to-End Reconfigurability (E2R II):
Management and Control of Adaptive Communication
Systems,” IST Mobile Summit 2006, June 2006.
[7] P. Demestichas et al., “m@ANGEL: Autonomic Management
Platform for Seamless Cognitive Connectivity to
the Mobile Internet,” IEEE Commun. Mag., vol. 44, no.
6, June 2006, pp. 118–27.
[8] P. Sutton, L. E. Doyle, and K. E. Nolan, “A Reconfigurable
Platform for Cognitive Networks,” Proc. CROWNCOM
2006, 2006.
[9] P. Mähönen et al., “Cognitive Wireless Networks: Your
Network Just Became a Teenager,” Proc. IEEE INFOCOM
2006, 2006.
[10] P. N. Johnson-Laird, The Computer and the Mind,
Cambridge, MA: Harvard Univ. Press, 1988.
[11] J. Jin and K. Nahrstedt, “QoS Specification Languages for
Distributed Multimedia Applications: A Survey and Taxonomy,”
IEEE Multimedia, vol. 11, no. 3, 2004, pp. 74–87.
[12] C. H. Papadimitriou, “Algorithms, Games, and the
Internet,” Proc. STOC 2001, 2001.
[13] M. A. L. Thathachar and P. S. Sastry, Networks of
Learning Automata, Kluwer, 2004.