Deep-Learned Approximate Message Passing for Asynchronous Massive Connectivity

Zhu, Weifeng; Tao, Meixia; Yuan, Xiaojun; Guan, Yunfeng

doi:10.1109/twc.2021.3067903

Cited by 39 publications

(16 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following asynchronous schemes of the literature [65], [56], in this case each device is allowed to transmit L symbols, which we denote here as a frame, at the beginning of any symbol interval t. The sparsity of the mMTC scenario is represented by the Boolean variable γ nt = 1 that indicates that the n-th device is active in the t-th symbol interval and γ nt = 0, otherwise. Thus, considering ρ n as the probability of being active of the n-th device, P (γ nt = 1) = 1 − P (γ nt = 0) = ρ n , where all activity indicators γ nt are considered i.i.d.…”

Section: A Asynchronous Grant-free Random Accessmentioning

confidence: 99%

“…With the message-passing approach, there are plenty of solutions that address the activity detection and channel estimation problems as in [47], [48], [49], [50], [51], [52]. There are also works [53], [54], [55], [56], [57] that use machine-learning to estimate the channels. Furthermore, variational inference techniques combined with AMP that use Kullback-Leibler divergence to transform an intractable inference problem into a tractable optimization problem have been reported [50], [58], [59], [60].…”

Section: Introductionmentioning

confidence: 99%

“…In particular, BiMSGAMP updates messages according to the activity user detection (AUD) and the residual belief propagation (RBP), metrics already available in the factor graph. Additionally, we examine the mMTC overhead issues described before by considering in our framework non-orthogonal pilots and investigate the asynchronous mMTC scenario [65], [68], [69], [56], [70]. Therefore, BiMSGAMP departs from the common synchronous transmissions and addresses the problem without requiring frame-level synchronization.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Joint Channel Estimation, Activity Detection and Decoding using Dynamic Message-Scheduling for Machine-Type Communications

Renna¹,

Lamare²

2022

Preprint

View full text Add to dashboard Cite

In this work, we present a joint channel estimation, activity detection and data decoding scheme for massive machinetype communications. By including the channel and the a priori activity factor in the factor graph, we present the bilinear message-scheduling GAMP (BiMSGAMP), a message-passing solution that uses the channel decoder beliefs to refine the activity detection and data decoding. We include two messagescheduling strategies based on the residual belief propagation and the activity user detection in which messages are evaluated and scheduled in every new iteration. An analysis of the convergence of BiMSGAMP along with a study of its computational complexity is carried out. Numerical results show that BiMSGAMP outperforms state-of-the-art algorithms, highlighting the gains achieved by using the dynamic scheduling strategies and the effects of the channel decoding part in the system.

show abstract

Section: A Asynchronous Grant-free Random Accessmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Joint Channel Estimation, Activity Detection and Decoding using Dynamic Message-Scheduling for Machine-Type Communications

Renna¹,

Lamare²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Indeed, active device identification and channel estimation are initial steps to enable message decoding in MTC. Due to the sporadic traffic in MTC, these problems are usually cast as neighbor discover or compressed sensing problems [8]- [17], [35]- [41]. When the channel coefficients are known at the AP, several compressed sensing schemes were proposed for active device identification [39]- [41].…”

Section: Introductionmentioning

confidence: 99%

Asynchronous Massive Access in Multi-cell Wireless Networks Using Reed-Muller Codes

Yang¹,

Guo²,

Yang³

2021

Preprint

View full text Add to dashboard Cite

Providing connectivity to a massive number of devices is a key challenge in 5G wireless systems.In particular, it is crucial to develop efficient methods for active device identification and message decoding in a multi-cell network with fading, path loss, and delay uncertainties. This paper presents such a scheme using second-order Reed-Muller (RM) sequences and orthogonal frequency-division multiplexing (OFDM). For given positive integer m, a codebook is generated with up to 2 m(m+3)/2 codewords of length 2 m , where each codeword is a unique RM sequence determined by a matrixvector pair with binary entries. This allows every device to send m(m + 3)/2 bits of information where an arbitrary number of these bits can be used to represent the identity of a node, and the remaining bits represent a message. There can be up to 2 m(m+3)/2 different identities. Using an iterative algorithm, an access point can estimate the matrix-vector pairs of each nearby device, as long as not too many devices transmit in the same frame. It is shown that both the computational complexity and the error performance of the proposed algorithm exceed another state-of-the-art algorithm. The device identification and message decoding scheme developed in this work can serve as the basis for grant-free massive access for billions of devices with hundreds of simultaneously active devices in each cell.

show abstract

“…There are other works, as in [56][57][58][59][60][61][62][63] that use the factor graph approach. There are also works as in [64][65][66][67][68] that use the machine-learning as a tool to estimate the channels. Recently, there are a few solutions that jointly perform the activity and data detection and channel estimation.…”

mentioning

confidence: 99%

Channel Estimation and Multiuser Detection Techniques for Machine-Type Communications

Renna¹

View full text Add to dashboard Cite

Machine-type communications supports a plenty new applications, as environment sensing, vigilance surveillance, remote manufacturing, among others. Due to unique traffic and medium access characteristics, new estimation, detection and decoding techniques are required. This work, presents an extensive literature review that highlights innovation opportunities and presents novel solutions for the main uplink mMTC problems. Based on the adaptive Recursive Least Squares (RLS) algorithm, the proposed regularized techniques jointly performs activity detection and signal decoding, without the need to perform explicit channel estimation. In order to improve the detection performance, a list detection technique that uses two candidate-list schemes is developed. Rewriting the problem with factor-graphs, novel message-passing algorithms with dynamic scheduling that jointly estimates the channels and detects devices activity are proposed. Lastly, a complete message-passing solution is presented, where LDPC decoding beliefs are introduced in the system, in a way that the algorithm besides the channel estimation and activity detection, also jointly decodes the signals.In order to evaluate the proposed techniques, numerical results are provided as well as a computational complexity, state-evolution, convergence and a diversity analysis. Uplink sum-rate expressions that take into account metadata collisions, interference and a variable activity probability for each user are also derived. Finally, conclusions and future directions are discussed.

show abstract

Deep-Learned Approximate Message Passing for Asynchronous Massive Connectivity

Cited by 39 publications

References 27 publications

Joint Channel Estimation, Activity Detection and Decoding using Dynamic Message-Scheduling for Machine-Type Communications

Joint Channel Estimation, Activity Detection and Decoding using Dynamic Message-Scheduling for Machine-Type Communications

Asynchronous Massive Access in Multi-cell Wireless Networks Using Reed-Muller Codes

Channel Estimation and Multiuser Detection Techniques for Machine-Type Communications

Contact Info

Product

Resources

About