Cognitive radio adaptation engines use machine learning techniques such as evolutionary algorithms or expert systems to adapt the transmission parameters of a wireless system in order to optimize the performance of the communication. The cognitive engine models the environment internally and uses relationships between the transmission parameters and environmental measurements to perform the adaptation. Selecting an appropriate set of transmission parameters is key to the design of a cognitive wireless system. Each additional parameter adds another dimension of control over the cognitive radio. However, with the added control comes added complexity in the implementation of the cognitive engine. Whether it be a more complex fitness function used in the evolutionary algorithm, an added dimension of rules in an expert system, or another similarity metric in a case-based reasoning engine, increasing the amount of parameters used by the cognitive engine increases the complexity of the system. In this paper we explore the sensitivity of the cognitive system to individual parameters. We use a genetic algorithm based cognitive engine, and fitness functions derived in previous work to demonstrate how the optimality of the cognitive engine decision is affected when certain parameters are held constant and not allowed to be adapted by the cognitive engine. By comparing the resulting cognitive engine decisions when not adapting specific parameters to those of systems that are fully adaptable, we identify the parameters that do not affect the outcome and can be disregarded in order to lessen the complexity of the system.
[1]
C.W. Bostian,et al.
Cognitive radio testbed: further details and testing of a distributed genetic algorithm based cognitive engine for programmable radios
,
2004,
IEEE MILCOM 2004. Military Communications Conference, 2004..
[2]
Charles W. Bostian,et al.
Biologically Inspired Cognitive Radio Engine Model Utilizing Distributed Genetic Algorithms for Secure and Robust Wireless Communications and Networking
,
2004
.
[3]
Ian F. Akyildiz,et al.
NeXt generation/dynamic spectrum access/cognitive radio wireless networks: A survey
,
2006,
Comput. Networks.
[4]
Dong Chao,et al.
Universal Software Radio Peripheral
,
2010
.
[5]
Thao Nguyen,et al.
XG dynamic spectrum access field test results [Topics in Radio Communications]
,
2007,
IEEE Communications Magazine.
[6]
Charles W. Bostian,et al.
Application of artificial intelligence to wireless communications
,
2007
.
[7]
Thao Nguyen,et al.
XG Dynamic Spectrum Access Field Test Results
,
2007
.
[8]
G. Ganesan,et al.
Cooperative spectrum sensing in cognitive radio networks
,
2005,
First IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, 2005. DySPAN 2005..
[9]
Srinivasan Seshan,et al.
CogNet: an architectural foundation for experimental cognitive radio networks within the future internet
,
2006,
MobiArch '06.
[10]
Joseph Mitola,et al.
Cognitive Radio An Integrated Agent Architecture for Software Defined Radio
,
2000
.