In this paper, we address a user scheduling (selection) problem in the uplink multiuser multiple input multiple output (MIMO) wireless communication system. For this problem, the computational complexity of exhaustive search grows exponentially with the number of users. We present an iterative, low-complexity, sub-optimal algorithm for this problem. We apply an Estimation of Distribution Algorithm (EDA) for the user scheduling problem. An EDA is an evolutionary algorithm and updates its chosen population at each iteration on the basis of the probability distribution learned from the population of superior candidate solutions chosen at the previous iterations. The proposed EDA has a low computational complexity and can find a nearly optimal solution in real time for the user scheduling problem. Beyond applying the general EDA to user scheduling, we also present specific improvements that reduce computation for obtaining an acceptable solution. These improvements include the idea of generating an initial population by cyclically shifting a candidate solution. The simulation results show that our proposed algorithm performs better than other scheduling algorithms with comparable complexity.
