Pawel Kryszkiewicz

Marcin Hoffmann, Pawel Kryszkiewicz

The Massive Multiple-Input Multiple-Output (M-MIMO) is considered as one of the key technologies in 5G, and future 6G networks. From the perspective of, e.g., channel estimation, especially for high-speed users it is easier to implement an M-MIMO network exploiting a static set of beams, i.e., Grid of Beams (GoB). While considering GoB it is important to properly assign users to the beams, i.e., to perform Beam Management (BM). BM can be enhanced by taking into account historical knowledge about the radio environment, e.g., to avoid radio link failures. The aim of this paper is to propose such a BM algorithm, that utilizes location-dependent data stored in a Radio Environment Map (REM). It utilizes received power maps, and user mobility patterns to optimize the BM process in terms of Reinforcement Learning (RL) by using the Policy Iteration method under different goal functions, e.g., maximization of received power or minimization of beam reselections while avoiding radio link failures. The proposed solution is compliant with the Open Radio Access Network (O-RAN) architecture, enabling its practical implementation. Simulation studies have shown that the proposed BM algorithm can significantly reduce the number of beam reselections or radio link failures compared to the baseline algorithm.

Marcin Hoffmann, Pawel Kryszkiewicz, Adrian Kliks

Energy Efficiency (EE) is of high importance while considering Massive Multiple-Input Multiple-Output (M-MIMO) networks where base stations (BSs) are equipped with an antenna array composed of up to hundreds of elements. M-MIMO transmission, although highly spectrally efficient, results in high energy consumption growing with the number of antennas. This paper investigates EE improvement through switching on/off underutilized BSs. It is proposed to use the location-aware approach, where data about an optimal active BSs set is stored in a Radio Environment Map (REM). For efficient acquisition, processing and utilization of the REM data, reinforcement learning (RL) algorithms are used. State-of-the-art exploration/exploitation methods including e-greedy, Upper Confidence Bound (UCB), and Gradient Bandit are evaluated. Then analytical action filtering, and an REM-based Exploration Algorithm (REM-EA) are proposed to improve the RL convergence time. Algorithms are evaluated using an advanced, system-level simulator of an M-MIMO Heterogeneous Network (HetNet) utilizing an accurate 3D-ray-tracing radio channel model. The proposed RL-based BSs switching algorithm is proven to provide 70% gains in EE over a state-of-the-art algorithm using an analytical heuristic. Moreover, the proposed action filtering and REM-EA can reduce RL convergence time in relation to the best-performing state-of-the-art exploration method by 60% and 83%, respectively.