Combined Relay Selection in Spatially Random Networks

Fu, Tianhao; Dang, Shuping; Wu, Lexiang; Wen, Miaowen

doi:10.1109/jsyst.2020.3014504

Cited by 3 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Equipped with such an upgrading module, either the source or the destination will occasionally send real-time unlabeled samples to a centralized server for producing labels and updating the trained ANN. Also, although we studied the enabling scheme of combined relay selection under the assumption of perfect centralized coordination among relays for simplicity, with the progress of distributed learning architectures and techniques [16], the enabling scheme can also be applied to distributed relay networks with the support of timers mounted on relays [17].…”

Section: B Discussion Of the Experimental Resultsmentioning

confidence: 99%

Combined Relay Selection Enabled by Supervised Machine Learning

Dang

Tang

et al. 2021

IEEE Trans. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

Combined relay selection only requires two relays to forward signals transmitted on multiple subcarriers, but the optimal outage performance is almost surely achievable in the high signal-to-noise ratio (SNR) region. However, because combined relay selection involves the generation of the full set of two-relay combinations, the selection complexity of combined relay selection is much higher than that of per-subcarrier relay selection when the number of relays goes large. This drawback restricts the implementation of combined relay selection in dense networks. To overcome this drawback, we propose to enable combined relay selection by supervised machine learning (ML). Because the training procedure is off-line, the proposed implementation scheme can considerably reduce the selection complexity and the processing latency. We carry out extensive experiments on TensorFlow 2.1 over a graphics processing unit (GPU) aided computing cloud server to validate the effectiveness of the proposed scheme. The experimental results confirm that supervised ML can provide near-optimal performance with lower computing latency that well matches that provided by brute-force search and the optimal relay selection in a per-subcarrier manner.Index Terms-Multi-carrier relay selection, supervised machine learning (ML), cooperative relaying, artificial neural network (ANN), back-propagation algorithm.

show abstract

Section: B Discussion Of the Experimental Resultsmentioning

confidence: 99%

Combined Relay Selection Enabled by Supervised Machine Learning

Dang

Tang

et al. 2021

IEEE Trans. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Admittedly, considering a huge number of relays in SWNs, this assumption is strong when channel estimation is implemented in a centralized manner. In this regard, a decentralized implementation strategy using multiple timers can be introduced to eliminate relays in disadvantageous positions from the channel estimation process and thereby simplify the channel estimation process at the cost of negligible performance degradation [19].…”

Section: System Modelmentioning

confidence: 99%

“…The experimental results have verified the effectiveness of this machine learning enabling strategy under the assumption that the global channel state information (CSI) has been perfectly known. However, the immutable architecture of ANN hinders the scalability of this method to stochastic wireless networks (SWNs) 1 , where the number of nodes is dynamic and could change over time [19]. Fig.…”

Section: Introductionmentioning

confidence: 99%

Enabling Combined Relay Selection in Stochastic Wireless Networks by Recurrent Neural Computing

Tang

Dang

Abdullah

et al. 2022

IEEE Trans. on Mobile Comput.

Self Cite

View full text Add to dashboard Cite

Multi-carrier relay selection is of particular interest and challenge due to the spatio-frequency coupling and the dynamics of available spectral and relay resources. Among a number of promising relay selection schemes, combined relay selection stands out as an equilibrium between system complexity and reliability. Recent research progress has witnessed the capability of neural computing as a powerful tool to efficiently realize combined relay selection for a given network topology where the number of relays and their locations are fixed and known. However, for contemporary wireless networks that are highly dynamic, the classic neural computing methods can hardly help out because of the scale drifts of input and output matrices. To enable multi-carrier combined relay selection in stochastic wireless networks (SWNs) where the number of available relays for selection could vary, we propose a recurrent neural network (RNN) based framework and devise several training methods suited for various application scenarios. In addition, we conduct a set of computer experiments to verify the effectiveness and efficiency of the proposed RNN-based framework compared with several baselines. With the obtained experimental results, we also evaluate and discuss the proposed framework's reliability, generalization ability, and the robustness against imperfect channel state information (CSI).

show abstract