Delay- and Diversity-Aware Buffer-Aided Relay Selection Policies in Cooperative Networks

Buffer-Aided (BA) relaying has shown tremendous performance improvements in terms of throughput and outage probability, although it has been criticized of suffering from long delays that are restrictive for applications, such as video streaming, Web browsing, and file sharing. In this paper, we propose novel relay selection policies aiming at reducing the average delay by incorporating the buffer size of the relays into the decision making of the relay selection process. More specifically, we first propose two new delay-aware policies. One is based on the hybrid relay selection algorithm, where the relay selection takes into account the queue sizes so that the delay is reduced and the diversity is maintained. The other approach is based on the max - link relay selection algorithm. For the max - link algorithm, a delay-aware only approach starves the buffers and increases the outage probability of the system. Thus, for max - link, we propose a delay- and diversity-aware BA relay selection policy targeting the reduction of the average delay, while maintaining the diversity of the transmission. The proposed policies are analyzed by means of Markov Chains and expressions for the outage, throughput, and delay are derived. The asymptotic performance of the policies is also discussed. The improved performance in terms of delays and the use of the proposed algorithms are demonstrated via extensive simulations and comparisons, signifying, at the same time, the need for adaptive mechanisms to handle the interplay between delay and diversity.