Efficient use of the available licensed radio spectrum is becoming increasingly difficult as the demand and usage of the radio spectrum increases. This usage of the spectrum is not uniform within the licensed band but concentrated in certain frequencies of the spectrum while other parts of the spectrum are inefficiently utilized. In cognitive radio environments, the primary users are allocated licensed frequency bands while secondary cognitive users dynamically allocate the empty frequencies within the licensed frequency band according to their requested QoS (Quality of Service) specifications. This dynamic decision-making is a multi-criteria optimization problem, which the authors propose to solve using a genetic algorithm. Genetic algorithms traverse the optimization search space using a multitude of parallel solutions and choosing the solution that has the best overall fit to the criteria. Due to this parallelism, the genetic algorithm is less likely than traditional algorithms to get caught at a local optimal point.
[1]
Charles W. Bostian,et al.
COGNITIVE RADIOS WITH GENETIC ALGORITHMS: INTELLIGENT CONTROL OF SOFTWARE DEFINED RADIOS
,
2004
.
[2]
Joseph Mitola,et al.
Cognitive radio: making software radios more personal
,
1999,
IEEE Wirel. Commun..
[3]
Jarek Gryz,et al.
Algorithms and analyses for maximal vector computation
,
2007,
The VLDB Journal.
[4]
John R. Koza,et al.
Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems
,
1990
.
[5]
R. M. Buehrer,et al.
Game theoretic analysis of a network of cognitive radios
,
2002,
The 2002 45th Midwest Symposium on Circuits and Systems, 2002. MWSCAS-2002..