Spatial Resource Allocation in Massive MIMO Communications : From Cellular to Cell-Free

Abstract

Printed in Sweden by LiU-Tryck, Linköping 2020 investigates the use of deep learning for power control optimization in Massive MIMO. We formulate the joint data and pilot power optimization for maximum sum SE in multi-cell Massive MIMO systems, which is a non-convex problem. We propose a new optimization algorithm, inspired by the weighted MMSE approach, to obtain a stationary point in polynomial time. We then use this algorithm together with deep learning to train a convolutional neural network to perform the joint data and pilot power control in sub-millisecond runtime. The solution is suitable for online optimization.iv Finally, the fifth part of this thesis considers a large-scale distributed antenna system that serves the users by coherent joint transmission called Cell-free Massive MIMO. For a given user set, only a subset of the access points (APs) is likely needed to satisfy the users' performance demands. To find a flexible and energy-efficient implementation, we minimize the total power consumption at the APs in the DL, considering both the hardwareconsumed and transmit powers, where APs can be turned off to reduce the former part. Even though this is a non-convex optimization problem, a globally optimal solution is obtained by solving a mixed-integer second-order cone program (SOCP). We also propose low-complexity algorithms that exploit group-sparsity or received power strength in the problem formulation.

IRS, LIS, and Radio Stripes-Aided Wireless Communications: A Tutorial

“…The number of wireless devices in use along with the amount of data utilized on each device is rapidly increasing, resulting in an exponential increase in data traffic demand. Unfortunately, present MIMO systems are incapable of meeting such needs due to the restrictions of only a few antennas at base stations (BS) [10]. Due to interference, the capacity to serve multiple consumers at a given time-frequency resource is limited, restricting the multiplexing gain.…”

Application of Reinforcement Learning and Deep Learning in Multiple-Input and Multiple-Output (MIMO) Systems

“…In particular, a DQN is modeled to group the users in accordance with the reward that has been calculated after beamforming and power allocation. Moreover, as a part of the study, the use of DL for the optimization of power control in Ma-MIMO systems has been investigated in [ 265 ]. The article [ 266 ] considers deep spatial learning methods for scheduling that have the possibility to bypass the channel estimation step.…”

Joint Pilot Allocation and Pilot Sequence Optimization in Massive MIMO Systems

“…Each cell is composed of a BS and K single-antenna users, BS is deployed with M antennas to suppress interference and communicates with K users simultaneously [4]. In this model, we adopt TDD to achieve communication between users and BS, and exploit the block fading model, thus the channels is smooth in one coherent time block, and change independently in the next coherent time block [11]. For convenience, we use the symbol j, k to represent the kth user in the jth cell, and BS i is represent the BS of the ith cell.…”

“…To detect the transmission signal for the user i, k , supposing that BS i is equipped with a matching filter receiver [11]. After data detection, the user's signal-tointerference plus-noise ratio (SINR) can be obtained based on the detection results.…”

“…In other words, PC is the main factor leading to system performance degradation. Therefore, PC is recognized as a bottleneck for the achievable system capacity of multi-cell massive MIMO systems [9]- [11].…”