Detection of Spectral Resources in Cognitive Radios Using Reinforcement Learning

On-Off-Keying with energy detection is a promising candidate when aiming at simple receiver concepts, due to the fact that simple energy detection reduces receiver complexity. On the other hand, data rates are low and interference mitigation by correlation is no longer possible. This paper proposes and analyzes a method for mitigating asynchronous interferers in energy detection receivers by adapting the maximum likelihood decision rule. It is shown that detection in the presence of interferers is improved and detection in absence of interferers is not declined.