An efficient transmission mode selection based on reinforcement learning for cooperative cognitive radio networks

Cooperative communication systems use cooperative relays for transmitting their data packets to the destination. Cooperative communication schemes having all relays participating in transmission may cause unnecessary wastes of most valuable spectrum resources. So it is mandatory to effectively select a transmission mode for cooperative cognitive radio networks (CCRNs). In this paper, an efficient transmission mode scheme based on Q-learning algorithm is proposed. State, action, and reward are defined to achieve a good performance on time delay and energy efficiency in data transmission as well as the interference to primary users during secondary users transmission. The proposed scheme selects an optimal action on the networks environment to maximize the total revenue of the multilateral metric. The simulation result shows that the proposed scheme can efficiently support the determination for the transmission mode and outperforms conventional schemes for a single metric in CCRNs.