Training-Based Antenna Selection for PER Minimization: A POMDP Approach

Padmanabhan, Sinchu; Stephen, Reuben George; Murthy, Chandra R.; Coupechoux, Marceau

doi:10.1109/tcomm.2015.2455504

Cited by 14 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimization-driven methods employ suboptimal search algorithms to find the best subset. Padmanabhan et al [6] considered the problem of receive antenna selection using the known temporal correlation of the channel symbols embedded in the data packets; the model was stated as a problem of minimizing the average packet error rate and converted to a partially observable Markov decision process framework which was solved by heuristic searching schemes. Gulati and Dandekar [7] stated the antenna state selection problem as a multi-armed bandit problem, and used the criterion of optimizing the arbitrary link quality metrics to solve it.…”

Section: Relative Workmentioning

confidence: 99%

See 1 more Smart Citation

Antenna selection for multiple-input multiple-output systems based on deep convolutional neural networks

Cai

Zhong²,

2019

PLoS ONE

View full text Add to dashboard Cite

Antenna selection in Multiple-Input Multiple-Output (MIMO) systems has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity. Recently, deep learning based methods have achieved promising performance in many application fields. This paper proposed a deep learning (DL) based antenna selection technique. First, we generated the label of training antenna systems by maximizing the channel capacity. Then, we adopted the deep convolutional neural network (CNN) on the channel matrices to explicitly exploit the massive latent cues of attenuation coefficients. Finally, we used the adopted CNN to assign the class label and then select the optimal antenna subset. Experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based antenna selection.

show abstract

Section: Relative Workmentioning

confidence: 99%

“…The optimization-driven methods use the communication quality criteria, such as bit-error-rate (BER), channel capacity or bit error ratio, as the objective of antenna subset selection [6–10]. The optimization problems of antenna selection are always non-convex.…”

Section: Introductionmentioning

confidence: 99%

Antenna selection for multiple-input multiple-output systems based on deep convolutional neural networks

Cai

Zhong²,

2019

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Myopic policy is one of the examples of such solutions [14,15]. In [16], considering the positively correlated two-state Gilbert-Elliot channel model, the authors formulate the antenna selection problem at a multi-antenna receiver, with a single RF chain, as a POMDP problem with the goal of minimizing the packet error rate (PER). Defining the reward function as one unit of reward if the packet is correctly received, the authors show that under such a simple reward function model, the myopic policy is optimal for antenna selection problem.…”

Section: Introductionmentioning

confidence: 99%

“…Defining the reward function as one unit of reward if the packet is correctly received, the authors show that under such a simple reward function model, the myopic policy is optimal for antenna selection problem. Considering an extension of the scenario considered in [16], the authors of [17] prove the optimality of the myopic policy for the case where the user is allowed to access more than one channel for data transmission.…”

Section: Introductionmentioning

confidence: 99%

Antenna Selection for Massive MIMO Systems Based on POMDP Framework

Sharifi

Panahi

Dong

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We use a partially observable Markov decision process (POMDP) framework to formulate the problem of antenna selection for a basestation, equipped with a large-scale antenna array and a smaller number of RF chains. Assuming that the fading channel evolves according to a finite-state Markov chain and that only partial channel state information (CSI) from the limited selected antennas is available at each time slot, we rely on a POMDP framework for antenna selection to maximize the long-term expected downlink data rate. To avoid the computational complexity associated with the value iteration algorithm, we herein propose to use the simple myopic antenna selection policy based on the fact that for any arbitrary number of antennas and RF chains, under the assumption of positively correlated two-state Markov channel model, the myopic policy is optimal. To apply the optimal myopic policy-based antenna selection for general fading channels, we propose to quantize the channels into two values only for the purpose of antenna selection. Interestingly, our results show that the performance of the myopic antenna selection policy is close to that of the policy which relies on un-quantized full CSI.

show abstract

“…There has been a considerable amount of work on AS with both conventional and M-MIMO systems, for example, in [4], it was found that not all antennas contribute equally in M-MIMO systems, and AS can reduce the complexity and cost of M-MIMO without large degradation in the performance; while the authors in [9] designed an AS scheme to reject the co-channel interference for a single user uplink scenario. Moreover, the authors in [10] and [11] aimed to enhance the error performance through AS by exploiting the temporal correlation, and the constructive interference, respectively. Although the proposed algorithm in [11] has low complexity, it works efficiently only for low modulation Phase Shift Keying (PSK) signalling, and it is data dependent, which means that extremely fast RF switching is required.…”

mentioning

confidence: 99%

Efficient Low-Complexity Antenna Selection Algorithms in Multi-User Massive MIMO Systems With Matched Filter Precoding

Abdullah

Tsimenidis

Chen

et al. 2020

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

In this work, two efficient low complexity Antenna Selection (AS) algorithms are proposed for downlink Multi-User (MU) Massive Multiple-Input Multiple-Output (M-MIMO) systems with Matched Filter (MF) precoding. Both algorithms avoid vector multiplications during the iterative selection procedure to reduce complexity. Considering a system with N antennas at the Base Station (BS) serving K single-antenna users in the same time-frequency resources, the first algorithm divides the available antennas into K groups, with the kth group containing the N/K antennas that have the maximum channel norms for the kth user. Therefore, the Signal-to-Interference plus Noise Ratio (SINR) for the kth user can be maximized by selecting a subset of the antennas from only the kth group, thereby resulting in a search space reduction by a factor of K. The second algorithm is a semiblind interference rejection method that relies only on the signs of the interference terms, and at each iteration the antenna that rejects the maximum number of interference terms will be selected. The performance of our proposed methods is evaluated under perfect and imperfect Channel State Information (CSI) and compared with other low complexity AS schemes in terms of the achievable sum rate as well as the energy efficiency. In particular, when the Signal-to-Noise Ratio (SNR) is 10 dB, and for a system with 20 MHz of bandwidth, the proposed methods outperform the case where all the antennas are employed by 108.8 and 49.2 Mbps for the first and second proposed algorithms, respectively, given that the BS has perfect CSI knowledge and is equipped with 256 antennas, out of which 64 are selected to serve 8 single-antenna users.

show abstract

Training-Based Antenna Selection for PER Minimization: A POMDP Approach

Cited by 14 publications

References 36 publications

Antenna selection for multiple-input multiple-output systems based on deep convolutional neural networks

Antenna selection for multiple-input multiple-output systems based on deep convolutional neural networks

Antenna Selection for Massive MIMO Systems Based on POMDP Framework

Efficient Low-Complexity Antenna Selection Algorithms in Multi-User Massive MIMO Systems With Matched Filter Precoding

Contact Info

Product

Resources

About