Joint Channel Estimation and Active-User Detection for Massive Access in Internet of Things—A Deep Learning Approach

Mao, Zhendong; Liu, Xiqing; Peng, Mugen; Chen, Zijie; Wei, Guiming

doi:10.1109/jiot.2021.3097133

Cited by 21 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where ς is a constant that depends on n 2 . Since the coefficient vector β is unknown, the existing l 1 -norm minimization methods cannot be employed to solve (12) directly.…”

Section: A An Off-grid Basis For Massive Mimo Channelsmentioning

confidence: 99%

“…In general, the black-box DNNs have poor interpretability and generalization ability, and require a sufficient number of training samples. To address these issues, deep-unfolding neural networks (NNs) are proposed in [9]- [12], where the iterative algorithms are unfolded into a layer-wise architecture similar to DNNs [9]. Specifically, the classical weighted minimum mean-square error algorithm Q. Hu, S. Shi, Y. Cai, and G. Yu are with the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China (e-mail: qiyhu@zju.edu.cn; ssh16@zju.edu.cn; ylcai@zju.edu.cn; yuguanding@zju.edu.cn).…”

Section: Introduction a Prior Workmentioning

confidence: 99%

“…An approximate message passing based deep-unfolding NN has been proposed in [11]. In [12], an alternative direction method of multipliers algorithm has been unfolded for channel estimation. Moreover, to solve the mixed integer non-linear problems, deep Q-network (DQN) [13] has been widely employed in communications, such as beam selection [14], dynamic channel access [15], and resource allocation [16], where the problems are modeled as Markov decision process (MDP).…”

Section: Introduction a Prior Workmentioning

confidence: 99%

See 2 more Smart Citations

DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning

Hu,

Shi,

Cai

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep-unfolding neural networks (NNs) have received great attention since they achieve satisfactory performance with relatively low complexity. Typically, these deepunfolding NNs are restricted to a fixed-depth for all inputs. However, the optimal number of layers required for convergence changes with different inputs. In this paper, we first develop a framework of deep deterministic policy gradient (DDPG)-driven deep-unfolding with adaptive depth for different inputs, where the trainable parameters of deep-unfolding NN are learned by DDPG, rather than updated by the stochastic gradient descent algorithm directly. Specifically, the optimization variables, trainable parameters, and architecture of deep-unfolding NN are designed as the state, action, and state transition of DDPG, respectively. Then, this framework is employed to deal with the channel estimation problem in massive multiple-input multipleoutput systems. Specifically, first of all we formulate the channel estimation problem with an off-grid basis and develop a sparse Bayesian learning (SBL)-based algorithm to solve it. Secondly, the SBL-based algorithm is unfolded into a layer-wise structure with a set of introduced trainable parameters. Thirdly, the proposed DDPG-driven deep-unfolding framework is employed to solve this channel estimation problem based on the unfolded structure of the SBL-based algorithm. To realize adaptive depth, we design the halting score to indicate when to stop, which is a function of the channel reconstruction error. Furthermore, the proposed framework is extended to realize the adaptive depth of the general deep neural networks (DNNs). Simulation results show that the proposed algorithm outperforms the conventional optimization algorithms and DNNs with fixed depth with much reduced number of layers.

show abstract

“…where ς is a constant that depends on n 2 . Since the coefficient vector β is unknown, the existing l 1 -norm minimization methods cannot be employed to solve (12) directly.…”

Section: A An Off-grid Basis For Massive Mimo Channelsmentioning

confidence: 99%

Section: Introduction a Prior Workmentioning

confidence: 99%

Section: Introduction a Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning

Hu,

Shi,

Cai

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For a BS equipped with a single antenna, the massive access problem is detecting active users and estimating their channel with one measurement [9], [11]. For a BS equipped with multiple antennas, we have multiple measurements and activity detection and data recovery is constructed as a row-sparse matrix recovery problem [7], [12], [14]. Furthermore, with some appropriate transform, the users' channel becomes sparse in the virtual angular domain in massive MIMO, especially in the mmWave domain.…”

Section: A Problem Formulation and Data-driven Cs Solutionsmentioning

confidence: 99%

“…However, most existing networks are not designed for communication systems. There exist various features of mMTC that can be utilized to enhance the NN design, i.e., the low-rank property in massive MIMO [7], the asynchronous information [10], various structure sparsity described in subsection A [12], etc. These communication-specific designs can be combined with various parts of NNs.…”

Section: B Utilizing Domain Knowledge In Communication Systemsmentioning

confidence: 99%

Data-Driven Compressed Sensing for Massive Wireless Access

Bai¹,

Chen²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

The central challenge in massive machine-type communications (mMTC) is to connect a large number of uncoordinated devices through a limited spectrum. The typical mMTC communication pattern is sporadic, with short packets. This could be exploited in grant-free random access in which the activity detection, channel estimation, and data recovery are formulated as a sparse recovery problem and solved via compressed sensing algorithms. This approach results in new challenges in terms of high computational complexity and latency. We present how data-driven methods can be applied in grant-free random access and demonstrate the performance gains. Variations of neural networks for the problem are discussed, as well as future challenges and potential directions.

show abstract

A comparative study of deep learning and iterative algorithms for joint channel estimation and signal detection in OFDM systems

Ju,

Zhang,

et al. 2024

Signal Processing

View full text Add to dashboard Cite

Joint Channel Estimation and Active-User Detection for Massive Access in Internet of Things—A Deep Learning Approach

Cited by 21 publications

References 36 publications

DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning

DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning

Data-Driven Compressed Sensing for Massive Wireless Access

A comparative study of deep learning and iterative algorithms for joint channel estimation and signal detection in OFDM systems

Contact Info

Product

Resources

About