Title :
Learning algorithm for reconfigurable antenna state selection
Author :
Gulati, Nikhil ; Gonzalez, David ; Dandekar, Kapil R.
Author_Institution :
Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
Abstract :
In this paper, we propose an online learning algorithm for selecting the state of a reconfigurable antenna. We formulate the antenna state selection as a multiarmed bandit problem and present a selection technique, implemented for a 2 × 2 MIMO OFDM system employing highly directional metamaterial Reconfigurable Leaky Wave Antennas. We quantify the performance of our selection technique using a software defined radio testbed and present results for a wireless network in a typical indoor environment.
Keywords :
MIMO communication; OFDM modulation; directive antennas; electrical engineering computing; indoor environment; learning (artificial intelligence); metamaterial antennas; software radio; telecommunication computing; MIMO OFDM system; directional metamaterial reconfigurable leaky wave antenna; indoor environment; multiarmed bandit problem; online learning algorithm; reconfigurable antenna state selection technique; software defined radio testbed; wireless network; MIMO; Receiving antennas; Transmitting antennas; Wireless communication; Learning algorithms; MIMO; OFDM; bandit problem; reconfigurable antennas;
Conference_Titel :
Radio and Wireless Symposium (RWS), 2012 IEEE
Conference_Location :
Santa Clara, CA
Print_ISBN :
978-1-4577-1153-4
DOI :
10.1109/RWS.2012.6175375
