User Clustering Techniques for Massive MIMO-NOMA Enabled mmWave/THz Communications in 6G

Shahjalal, Md.; Rahman, Md. Habibur; Ali, Md. Osman; Chung, ByungDeok; Jang, Yeong Min

doi:10.1109/icufn49451.2021.9528659

Cited by 6 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work in [21] classified user clustering problems in mmWave-NOMA systems into joint resource aware user clustering techniques such as the ones applying the cosine similarity metric as described above and a second class of algorithms called learning assisted user clustering techniques to bring down the complexity. In [21], the complexity of several user clustering schemes in the mmWave-NOMA literature is analyzed and it is shown that a significant run-time complexity is inherited by all schemes to make clustering decisions on a millisecond granularity, especially as the network size grows. However, the machine learning techniques applying K-means like clustering algorithms bring down the complexity compared to traditional optimization schemes.…”

Section: A Related Workmentioning

confidence: 99%

“…In (21), W (t) y ∈ R N ×H represents a weight matrix containing all the weights associated with the output layer. Specifically, each row in W (t) y is associated with each output neuron o = 1, 2, • • • , N .…”

mentioning

confidence: 99%

“…Specifically, each row in W (t) y is associated with each output neuron o = 1, 2, • • • , N . Since each of these neurons is fed with the vector h (t) the matrix multiplication defined in (21) results in the vector v (t) y ∈ R N ×1 in which each element is related to a neuron o. Similar to (20), in (22)…”

mentioning

confidence: 99%

See 2 more Smart Citations

Neural Network Aided User Clustering in mmWave-NOMA Systems With User Decoding Capability Constraints

Rajasekaran

Yanıkömeroğlu

2023

IEEE Access

View full text Add to dashboard Cite

This paper proposes a computationally efficient two-stage machine learning based approach using neural networks to solve the cluster assignment problem in a millimeter wave-non orthogonal multiple access (mmWave-NOMA) system where each user's individual successive interference cancellation (SIC) decoding capabilities are taken into consideration. The artificial neural network (ANN) is applied in real time to assign users to clusters taking each user's instantaneous channel state information (CSI) and SIC decoding capabilities as inputs. The algorithm is trained offline on cloud resources, i.e., not using the base station (BS) compute resources. This training is done using a dataset obtained by offline computation of input parameters using the optimization algorithms called NOMA-minimum exact cover (NOMA-MEC) and NOMA-best beam (NOMA-BB) from our earlier work in this area. As a result, we term the proposed algorithms in this paper as ANN-NOMA-MEC and ANN-NOMA-BB, respectively. The problem with applying optimization techniques, even low-complexity heuristics, in live networks for user clustering is that they require a very large number of computation steps to make a clustering decision. If these clustering decisions are based on the instantaneous channel of hundreds of users, it becomes prohibitively complex to implement in practical systems on a millisecond granularity as required by beyond 5G (B5G) systems. Instead, our proposed approach takes all this complexity offline and even off the BS compute resources and instead only applies a trained neural network to make such clustering decisions at a microsecond granularity on hundreds of users. Simulation results show the effectiveness of the ANN-NOMA-MEC and ANN-NOMA-BB schemes as the neural network trained on offline simulation data performs comparably with the NOMA-MEC and NOMA-BB heuristics that is applying computationally intensive algorithms to make every clustering decision in a live network.INDEX TERMS Non-orthogonal multiple access (NOMA), successive interference cancellation (SIC), neural networks (NN), millimeter-wave (mmWave), user clustering (UC).

show abstract

Section: A Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Neural Network Aided User Clustering in mmWave-NOMA Systems With User Decoding Capability Constraints

Rajasekaran

Yanıkömeroğlu

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To address the real-time complexity issue with user clustering schemes that need to be run on a millisecond granularity, machine learning has often been proposed an enabler. The work in [138] classified user clustering problems in mmWave-NOMA systems into joint resource aware user clustering techniques such as the ones applying the cosine similarity metric as described in Chapter 3 and a second class of algorithms called learning assisted user clustering techniques to bring down the complexity. In [138], the complexity of several user clustering schemes in the mmWave-NOMA literature is analyzed and it is shown that a significant run-time complexity is inherited by all schemes to make clustering decisions on a millisecond granularity, especially as the network size grows.…”

Section: Related Workmentioning

confidence: 99%

“…The work in [138] classified user clustering problems in mmWave-NOMA systems into joint resource aware user clustering techniques such as the ones applying the cosine similarity metric as described in Chapter 3 and a second class of algorithms called learning assisted user clustering techniques to bring down the complexity. In [138], the complexity of several user clustering schemes in the mmWave-NOMA literature is analyzed and it is shown that a significant run-time complexity is inherited by all schemes to make clustering decisions on a millisecond granularity, especially as the network size grows. However, the machine learning techniques applying K-means like clustering algorithms bring down the complexity compared to traditional optimization schemes.…”

Section: Related Workmentioning

confidence: 99%

NOMA Integrated with Enabling Technologies and Practical Challenges

Rajasekaran

View full text Add to dashboard Cite

Non-orthogonal multiple access (NOMA) schemes allow multiple users to share the same resource and separate the users in either the power-domain (PD -NOMA) or in the code domain (CD-NOMA). To make NOMA a reality in networks, several important practical challenges need to be considered. This thesis addresses some of these challenges in both the PD-NOMA and CD-NOMA space. In PD-NOMA systems integrated with mmWave technology, the thesis considers the practical constraint of the end user processing capabilities, modelled through an successive interference cancellation (SIC) decoding capability constraint that captures the number of other user's signals any given user can decode in the SIC decoding procedure. 6G networks are expected to include a mix of users of varying processing capabilities, all needing to access the same spectrum. To solve the rate maximization problem when each user has different processing capabilities, the thesis proposes low-complexity heuristics to maximize the sum-rate after factoring in each individual users SIC decoding capability constraint. However, these algorithms are based on the instantaneous channel conditions of users and need to be run on a millisecond granularity. To address this, a machine learning based neural network approach is proposed that takes this complexity offline where the neural network is trained on simulated and past network data, and the trained network is directly applied to solve the clustering problem in live networks. The thesis also addresses the practical constraint around the availability of CSI by exploiting the growing field of integrated communication and sensing solutions using a camera equipped base station to aid the user clustering process in NOMA. In CD-NOMA systems using the widely promoted sparse code multiple access (SCMA) scheme for uplink (UL) NOMA, the thesis studies the PAPR problem in UL SCMA-OFDM systems. A novel link between the obtained PAPR statistics and the SCMA modulation scheme and the placement of the sub-carriers (SC's) that carry the SCMA codewords is presented. The thesis highlights unique opportunities that SCMA-OFDM systems present to the widely studied PAPR problem due to the I would like to express sincere gratitude to my supervisor, Prof. Halim Yanikomeroglu, for (a) believing in me and giving me the opportunity to pursue this Ph.D. degree while studying part-time, and (b) motivating me and providing continuous support throughout my Ph.D. study and research. I would like to acknowledge the people I got to collaborate with at different points in this journey. Particularly, I want to thank Monirosharieh Vameghestahbanati who provided me guidance during my early days and also Omar Maraqa, with whom I got to collaborate extensively on a number of different papers during my Ph.D. I would also like to acknowledge Ericsson Canada, to whom I was employed throughout this degree, for providing tuition assistance and encouragement throughout the years.I am deeply grateful to my parents for all their support and encouragement over many y...

show abstract

Terahertz Communications and Sensing for 6G and Beyond: A Comprehensive Review

Jiang,

Zhou,

et al. 2024

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

User Clustering Techniques for Massive MIMO-NOMA Enabled mmWave/THz Communications in 6G

Cited by 6 publications

References 17 publications

Neural Network Aided User Clustering in mmWave-NOMA Systems With User Decoding Capability Constraints

Neural Network Aided User Clustering in mmWave-NOMA Systems With User Decoding Capability Constraints

NOMA Integrated with Enabling Technologies and Practical Challenges

Terahertz Communications and Sensing for 6G and Beyond: A Comprehensive Review

Contact Info

Product

Resources

About