Age of Information-based Scheduling for Wireless Device-to-Device Communications using Deep Learning

Device-to-device (D2D) links scheduling for avoiding excessive interference is critical to the success of wireless D2D communications. Most of the traditional scheduling schemes only consider the maximum throughput or fairness of the system and do not consider the freshness of information. In this paper, we propose a novel D2D links scheduling scheme to minimize the average age of information (AoI) of wireless D2D communications. It is motivated by the fact that the more links are activated, the greater the interference with each other, which reduces the probability of successful transmission and in turn increases the AoI. We thus derive the accurate expression of the overall average AoI of the network based on the transmission success probability under the interfering channels. Moreover, a neural network structure is proposed to learn the mapping from the geographic location to the minimum AoI scheduling under a stationary randomized policy, where the scheduling decision can be made without estimating the channel state information. Finally, numerical results reveal that the performance of the deep learning approach is close to that of a local optimal algorithm which has a higher computational complexity.