Deep Q-Learning Based Resource Allocation in 6G Interference Systems With Outage Constraints

This paper considers the resource allocation problem in the sixth generation (6G) wireless interference channel (IC) under link outage constraints. Since the optimization problem is non-convex in nature, existing approaches to find the optimal power allocation are computationally intensive. When it comes to internet of things (IoT) and massive machine-type communications (mMTC) in the emerging 6G, the computational complexity becomes practically infeasible. Recently, deep reinforcement learning has shown promising outcome in solving non-convex optimization problems with reduced complexity. In this paper, we utilize a deep Q-learning (DQL) approach which interacts with the wireless environment and learns the optimal power allocation of a wireless IC while maximizing overall sum-rate of the system and maintaining reliability requirement of each link. We have used two separate deep Q-networks to remove the inherent instability in learning process. Simulation results demonstrate that the proposed DQL approach outperforms existing geometric programming based solutions.