Title :
Power allocation in cognitive radio networks using distributed machine learning
Author :
Van den Biggelaar, Olivier ; Dricot, Jean-Michel ; De Doncker, Philippe ; Horlin, François
Author_Institution :
Univ. Libre de Bruxelles (ULB), Brussels, Belgium
Abstract :
In cognitive radios systems, the sparse assigned frequency bands are opened to secondary users, provided that the aggregated interferences induced by the secondary transmitters on the primary receivers are negligible. In this paper, a decentralized Q-learning power allocation algorithm is proposed to maximize the Signal on Interference-plus-Noise Ratio (SINR) at the secondary receivers while meeting the primary protection constraint. Numerical simulations allow to compare the performance of the proposed algorithm with the performance of the optimal centralized power allocation scheme in the scenario of multiple independent secondary cells located on the border of a primary network protection contour. The impact of the definition of the learning algorithm cost function on the secondary user fairness and the system performance is discussed. The optimal execution frequency of the algorithm is obtained and different strategies for the exploration of new solutions are compared.
Keywords :
cognitive radio; learning (artificial intelligence); radio receivers; radio transmitters; radiofrequency interference; resource allocation; telecommunication computing; SINR; aggregated interferences; cognitive radio networks; decentralized Q-learning power allocation algorithm; distributed machine learning; independent secondary cells; learning algorithm cost function; optimal centralized power allocation; optimal execution frequency; primary protection constraint; primary receivers; secondary receivers; secondary transmitters; secondary user fairness; secondary users; signal on interference-plus-noise ratio; sparse assigned frequency bands; Base stations; Batteries; Cost function; Equations; Interference; Resource management; Signal to noise ratio;
Conference_Titel :
Personal Indoor and Mobile Radio Communications (PIMRC), 2012 IEEE 23rd International Symposium on
Conference_Location :
Sydney, NSW
Print_ISBN :
978-1-4673-2566-0
Electronic_ISBN :
2166-9570
DOI :
10.1109/PIMRC.2012.6362898