Power Control in Cellular Massive MIMO With Varying User Activity: A Deep Learning Solution

Chien, Trinh Van; Canh, Thuong Nguyen; Björnson, Emil; Larsson, Erik G.

doi:10.1109/twc.2020.2996368

Cited by 127 publications

(109 citation statements)

References 45 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…Unfortunately, the SCA method often recalls the CVX tools to calculate the numerical solution which will cost huge runtime. In this article, motivated by the weighted MMSE strategy, 16,17 we propose a low‐complexity iterative algorithm to determine a local optimum to

P_{1}

, where the solution to each iteration can be obtained in closed form. Prior to presenting the detailed algorithm, we give the following theorem which helps us to solve

P_{1}

efficiently.…”

Section: Sum‐rate Maximizationmentioning

confidence: 99%

“…In contrast to References 13‐15, we advocate sum‐rate as the main metric and propose an iterative power optimization algorithm to maximize the sum‐rate, which can compensate for the rate degradation caused by jamming. The weighted minimum mean square error (MMSE) methodology is introduced to obtain a local optimum in polynomial time, 16,17 which is a standard way for decomposing the sum‐rate maximization problem into several subproblems that can be determined sequentially. It should be mentioned that our power control algorithm is different from the sequential convex approximation (SCA) strategy in References 6,18 since our algorithm can determine the closed‐form solution to each iteration.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sum‐rate maximization in uplink cell‐free massive multiinput multioutput system with jamming

Zhang

Zhou

Cao

et al. 2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

This article takes the first look at jamming attacks on both uplink training and data transmission phases in uplink cell‐free massive multi‐input multi‐output systems. Closed‐form rate expressions for that system are derived, which provide us with the opportunities to analyze the achievable rate in the presence of jamming. To compensate for the sum‐rate degradation caused by jamming, we propose an iterative sum‐rate maximization power control algorithm without redesigning the estimator and receiver. Specifically, by virtue of the Lagrange multiplier methodology, the proposed algorithm can determine the closed‐form solution to each iteration and thus, benefiting from less runtime. Simulation results reveal the effectiveness of the proposed algorithm.

show abstract

P_{1}

, where the solution to each iteration can be obtained in closed form. Prior to presenting the detailed algorithm, we give the following theorem which helps us to solve

P_{1}

efficiently.…”

Section: Sum‐rate Maximizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sum‐rate maximization in uplink cell‐free massive multiinput multioutput system with jamming

Zhang

Zhou

Cao

et al. 2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Deep learning is capable of providing efficient solutions, given that the complicated design and training phases have been successful. In Paper D [40], we first formulate a joint data and pilot power control for maximizing the ergodic sum SE. The 1 Introduction non-convexity of this problem is overcome by proposing a new algorithm, inspired by the weighted minimum mean square error (MMSE) approach, which finds a stationary point with polynomial complexity instead of seeking the global optimum with exponential computational complexity.…”

Section: Introductionmentioning

confidence: 99%

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

Chien

2020

Linköping Studies in Science and Technology. Dissertations

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…This is the main difference between the current work and the work in [27]; (ii) The authors in [27] consider a cellular massive MIMO system, while here we consider a cell-free massive MIMO system. Note that unlike [27], having pure LSF components (i.e., the coefficients defined in (1)) as a raw input of the DCNN does not work in cell-free massive MIMO, and the network cannot learn the power elements obtained through the convex optimization approach. Hence, we generate a novel and unique input matrix to feed as the input to the DCNN for each ZF and MRC receiver.…”

mentioning

confidence: 96%

“…There are three important differences between the proposed DCNN-based algorithm in this paper and the scheme presented in [27], which are: (i) In [27], the authors propose to use a deep learning approach to solve an optimization problem which could be solved through the standard convex optimization software. However, the main contribution of our work is finding an unrevealed mapping between the LSF components and the power elements obtained using the quantized version of the estimated channel.…”

mentioning

confidence: 99%

Exploiting Deep Learning in Limited-Fronthaul Cell-Free Massive MIMO Uplink

Bashar

Akbari

Cumanan

et al. 2020

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

A cell-free massive multiple-input multiple-output (MIMO) uplink is considered, where quantize-and-forward (QF) refers to the case where both the channel estimates and the received signals are quantized at the access points (APs) and forwarded to a central processing unit (CPU) whereas in combinequantize-and-forward (CQF), the APs send the quantized version of the combined signal to the CPU. To solve the non-convex sum rate maximization problem, a heuristic sub-optimal scheme is exploited to convert the power allocation problem into a standard geometric programme (GP). We exploit the knowledge of the channel statistics to design the power elements. Employing largescale-fading (LSF) with a deep convolutional neural network (DCNN) enables us to determine a mapping from the LSF coefficients and the optimal power through solving the sum rate maximization problem using the quantized channel. Four possible power control schemes are studied, which we refer to as i) small-scale fading (SSF)-based QF; ii) LSF-based CQF; iii) LSF use-and-then-forget (UatF)-based QF; and iv) LSF deep learning (DL)-based QF, according to where channel estimation is performed and exploited and how the optimization problem is solved. Numerical results show that for the same fronthaul rate, the throughput significantly increases thanks to the mapping obtained using DCNN.

show abstract

Power Control in Cellular Massive MIMO With Varying User Activity: A Deep Learning Solution

Cited by 127 publications

References 45 publications

Sum‐rate maximization in uplink cell‐free massive multiinput multioutput system with jamming

Sum‐rate maximization in uplink cell‐free massive multiinput multioutput system with jamming

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

Exploiting Deep Learning in Limited-Fronthaul Cell-Free Massive MIMO Uplink

Contact Info

Product

Resources

About