Cross-Layer Codebook Allocation for Uplink SCMA and PDNOMA-SCMA Video Transmission Systems and a Deep Learning-Based Approach

Tseng, Shu-Ming; Chen, Walter

doi:10.1109/jsyst.2022.3168851

Cited by 8 publications

(9 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new optimal power allocation is derived to minimize video distortion in the application layer. In [24], a cross-layer codebook allocation for uplink video communication is proposed. Chen et al propose a deep neural network method to reduce the computational complexity.…”

Section: Related Workmentioning

confidence: 99%

“…Then we can get (26). αs,n = ln (µ s,n + 1) T s,n B + ϑ s,n ln 2 λ s ln 2 (26) Solve problem (24), and a subgradient descent method is adopted, i.e.,…”

Section: Power Allocation Algorithmmentioning

confidence: 99%

“…where λ s , µ s,n , and ϑ s,n are Lagrange multipliers and are greater than or equal to zero. Based on the Lagrangian function, the dual function is in (24).…”

Section: Power Allocation Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

Wireless Network Resource Allocation for Video Transmission Based on Non-Orthogonal Multiple Access

Li,

Xu,

Song

et al. 2024

Preprint

View full text Add to dashboard Cite

In wireless networks, we study the downlink scenario of a non-orthogonal multiple access (NOMA) network based on scalable video coding techniques. The resource allocation problem based on wireless NOMA network is modeled as a mixed-integer nonlinear programming problem, which is subject to video coding characteristics, sub-channel capacity, system available power, and real-time requirements of wireless network. In order to solve the resource allocation problem of wireless NOMA network, three sub-problems are proposed, e.g., user grouping sub-problem, power allocation sub-problem, and video layer allocation sub-problem. Firstly, we propose an auction-based solution for the user grouping sub-problem. Then, for the power allocation sub-problem, we choose successive convex approximation and Lagrangian dual decomposition method. Finally, for the video layer allocation sub-problem, we propose a greedy strategy. Simulation experiments show that our proposed algorithms ensure the real-time and reliability requirements of the wireless network and also improve the quality of the video experience.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Then we can get (26). αs,n = ln (µ s,n + 1) T s,n B + ϑ s,n ln 2 λ s ln 2 (26) Solve problem (24), and a subgradient descent method is adopted, i.e.,…”

Section: Power Allocation Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Wireless Network Resource Allocation for Video Transmission Based on Non-Orthogonal Multiple Access

Li,

Xu,

Song

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…However, these studies have focused on the physical layer only and have not considered both physical layer channel state information (CSI) and application layer rate distortion (RD) function. In this regard, the cross-layer solutions proposed in [4,5,24] have addressed this issue, providing better simulations of real-world usage scenarios.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems

Lin,

Chang,

Tseng

2023

Symmetry

Self Cite

View full text Add to dashboard Cite

We propose a deep learning-based cross-layer power allocation method for asymmetric cell-free massive MIMO video communication systems. The proposed cross-layer approach considers physical layer channel state information (CSI) and the application layer rate distortion (RD) function, and it aims to enhance video quality in terms of peak signal-to-noise ratio (PSNR). Our study develops a decentralized deep neural network (DNN) model to capture intricate system patterns, enabling accurate and efficient power allocation decisions. The proposed cross-layer approach includes unsupervised and hybrid (supervised/unsupervised) learning models. The numerical results show that the hybrid method achieves convergence with just 50% of the iterations required by the unsupervised learning model and that it achieves a 1 dB gain in PSNR over the baseline physical layer scheme.

show abstract

“…Generally, DL techniques are applied in PD-NOMA due to their faster computational time, easily configurable, more consistent and reliable performance indices [13]. Furthermore, DL can significantly reduce the computational complexity at the training and testing stages of encoding, resource management and decoding [14]. Additionally, DL can potentially provide significant systemlevel improvements as compared to the conventional modelbased approach for solving highly dimensional, non-convex optimization problems [15].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Multi-User Detection for PD-SCMA

Chege,

Walingo

2024

IEEE Access

View full text Add to dashboard Cite

The performance of hybrid multi-radio access technologies depends on the sufficiency of the multi-user detection (MUD) at the receiver. For optimal performance of the hybrid power-domain sparse code multiple access (PD-SCMA), robust detection strategies are necessary to alleviate MUD complexity and reduce computational time. Deep learning (DL) based MUD techniques are the most promising as they can detect all symbols of an overloaded PD-SCMA without requiring additional operations of channel estimation and interference cancellation. This work proposes a deep neural network (DNN) aided MUD scheme (DNN-MUD) for an uplink PD-SCMA system supporting near users (NUs) and far users (FUs) multiplexed in power-, and code-domain, respectively. The proposed DNN-MUD features a unified framework that jointly performs successive interference cancellation (SIC) and message passing algorithm (MPA)/expectation propagation algorithm (EPA) operations to overcome interference propagation of SIC and computational complexity of MPA/EPA. The DNN training is enhanced by batch normalization to reduce the internal covariant shifts, thus enhancing the efficiency of detection. Performance results show that the average symbol error rate (SER), complexity and computational time of the proposed DNN-MUD significantly outperforms the conventional joint SIC-MPA/EPA schemes.

show abstract

Cross-Layer Codebook Allocation for Uplink SCMA and PDNOMA-SCMA Video Transmission Systems and a Deep Learning-Based Approach

Cited by 8 publications

References 57 publications

Wireless Network Resource Allocation for Video Transmission Based on Non-Orthogonal Multiple Access

Wireless Network Resource Allocation for Video Transmission Based on Non-Orthogonal Multiple Access

Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems

Deep Learning Multi-User Detection for PD-SCMA

Contact Info

Product

Resources

About