Optimal Cooperative Cognitive Relaying and Spectrum Access for an Energy Harvesting Cognitive Radio: Reinforcement Learning Approach

摘要

In this paper, we consider a cognitive setting under the context ofcooperative communications, where the cognitive radio (CR) user is assumed tobe a self-organized relay for the network. The CR user and the PU are assumedto be energy harvesters. The CR user cooperatively relays some of theundelivered packets of the primary user (PU). Specifically, the CR user storesa fraction of the undelivered primary packets in a relaying queue (buffer). Itmanages the flow of the undelivered primary packets to its relaying queue usingthe appropriate actions over time slots. Moreover, it has the decision ofchoosing the used queue for channel accessing at idle time slots (slots wherethe PU's queue is empty). It is assumed that one data packet transmissiondissipates one energy packet. The optimal policy changes according to theprimary and CR users arrival rates to the data and energy queues as well as thechannels connectivity. The CR user saves energy for the PU by taking theresponsibility of relaying the undelivered primary packets. It optimallyorganizes its own energy packets to maximize its payoff as time progresses.