Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network

Nishu Gupta; Jukka Mäkelä; Mikko Uitto; Arun Prakash

doi:10.1007/978-981-95-0203-5_9

Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network

Nishu Gupta^*
, Jukka Mäkelä
, Mikko Uitto
, Arun Prakash

^*Corresponding author for this work

BA6402 Future communication networks

Motilal Nehru National Institute of Technology (MNNIT)

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

In 5G networks, reliable data transmission for massive machine-type communication (mMTC) devices hinges on accurate channel prediction. This paper introduces a novel approach based on channel prediction for resource allocation in 5G mMTC using graph neural network (AMC-mMTC-GCIGNN). The method leverages granger causality-inspired graph neural networks to enhance channel prediction accuracy by analyzing feature relationships within channel data. Comparative analysis against existing techniques using performance metrics like bit error rate, mean squared error, and signal-to-noise ratio highlights the superiority of the proposed approach. The results underscore its potential to significantly enhance communication performance within 5G mMTC systems, thereby addressing a crucial aspect of next-generation wireless networks.

Original language	English
Title of host publication	Advances in VLSI, Communication, and Signal Processing
Subtitle of host publication	Select Proceedings of the 7th International Conference, VCAS 2024
Editors	Ram Awadh Mishra, Santosh Kumar Gupta, Vaibhav Kumar Srivastava, Jukka Mäkelä
Publisher	Springer
Pages	101-113
Number of pages	13
ISBN (Electronic)	978-981-95-0203-5
ISBN (Print)	978-981-95-0202-8
DOIs	https://doi.org/10.1007/978-981-95-0203-5_9
Publication status	Published - 2025
MoE publication type	A4 Article in a conference publication
Event	7th International Conference on VLSI, Communication, and Signal processing, VCAS 2024 - Prayagraj, India Duration: 25 Oct 2024 → 27 Oct 2024

Publication series

Series	Lecture Notes in Electrical Engineering
Volume	1457 LNEE
ISSN	1876-1100

Conference

Conference	7th International Conference on VLSI, Communication, and Signal processing, VCAS 2024
Country/Territory	India
City	Prayagraj
Period	25/10/24 → 27/10/24

Keywords

5G communication technology
Adaptive modulation and coding
Channel prediction
Graph neural network
Massive machine-type communication

Access to Document

10.1007/978-981-95-0203-5_9

Cite this

Gupta, N., Mäkelä, J., Uitto, M., & Prakash, A. (2025). Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network. In R. A. Mishra, S. K. Gupta, V. K. Srivastava, & J. Mäkelä (Eds.), Advances in VLSI, Communication, and Signal Processing: Select Proceedings of the 7th International Conference, VCAS 2024 (pp. 101-113). Springer. https://doi.org/10.1007/978-981-95-0203-5_9

Gupta, Nishu ; Mäkelä, Jukka ; Uitto, Mikko et al. / Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network. Advances in VLSI, Communication, and Signal Processing: Select Proceedings of the 7th International Conference, VCAS 2024. editor / Ram Awadh Mishra ; Santosh Kumar Gupta ; Vaibhav Kumar Srivastava ; Jukka Mäkelä. Springer, 2025. pp. 101-113 (Lecture Notes in Electrical Engineering, Vol. 1457 LNEE).

@inproceedings{0ff8202388fc4e8ea69605132e1e18b1,

title = "Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network",

abstract = "In 5G networks, reliable data transmission for massive machine-type communication (mMTC) devices hinges on accurate channel prediction. This paper introduces a novel approach based on channel prediction for resource allocation in 5G mMTC using graph neural network (AMC-mMTC-GCIGNN). The method leverages granger causality-inspired graph neural networks to enhance channel prediction accuracy by analyzing feature relationships within channel data. Comparative analysis against existing techniques using performance metrics like bit error rate, mean squared error, and signal-to-noise ratio highlights the superiority of the proposed approach. The results underscore its potential to significantly enhance communication performance within 5G mMTC systems, thereby addressing a crucial aspect of next-generation wireless networks.",

keywords = "5G communication technology, Adaptive modulation and coding, Channel prediction, Graph neural network, Massive machine-type communication",

author = "Nishu Gupta and Jukka M{\"a}kel{\"a} and Mikko Uitto and Arun Prakash",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 7th International Conference on VLSI, Communication, and Signal processing, VCAS 2024 ; Conference date: 25-10-2024 Through 27-10-2024",

year = "2025",

doi = "10.1007/978-981-95-0203-5\_9",

language = "English",

isbn = "978-981-95-0202-8",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer",

pages = "101--113",

editor = "Mishra, \{Ram Awadh\} and Gupta, \{Santosh Kumar\} and Srivastava, \{Vaibhav Kumar\} and Jukka M{\"a}kel{\"a}",

booktitle = "Advances in VLSI, Communication, and Signal Processing",

address = "Germany",

}

Gupta, N, Mäkelä, J , Uitto, M & Prakash, A 2025, Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network. in RA Mishra, SK Gupta, VK Srivastava & J Mäkelä (eds), Advances in VLSI, Communication, and Signal Processing: Select Proceedings of the 7th International Conference, VCAS 2024. Springer, Lecture Notes in Electrical Engineering, vol. 1457 LNEE, pp. 101-113, 7th International Conference on VLSI, Communication, and Signal processing, VCAS 2024, Prayagraj, India, 25/10/24. https://doi.org/10.1007/978-981-95-0203-5_9

Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network. / Gupta, Nishu; Mäkelä, Jukka ; Uitto, Mikko et al.
Advances in VLSI, Communication, and Signal Processing: Select Proceedings of the 7th International Conference, VCAS 2024. ed. / Ram Awadh Mishra; Santosh Kumar Gupta; Vaibhav Kumar Srivastava; Jukka Mäkelä. Springer, 2025. p. 101-113 (Lecture Notes in Electrical Engineering, Vol. 1457 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network

AU - Gupta, Nishu

AU - Mäkelä, Jukka

AU - Uitto, Mikko

AU - Prakash, Arun

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - In 5G networks, reliable data transmission for massive machine-type communication (mMTC) devices hinges on accurate channel prediction. This paper introduces a novel approach based on channel prediction for resource allocation in 5G mMTC using graph neural network (AMC-mMTC-GCIGNN). The method leverages granger causality-inspired graph neural networks to enhance channel prediction accuracy by analyzing feature relationships within channel data. Comparative analysis against existing techniques using performance metrics like bit error rate, mean squared error, and signal-to-noise ratio highlights the superiority of the proposed approach. The results underscore its potential to significantly enhance communication performance within 5G mMTC systems, thereby addressing a crucial aspect of next-generation wireless networks.

AB - In 5G networks, reliable data transmission for massive machine-type communication (mMTC) devices hinges on accurate channel prediction. This paper introduces a novel approach based on channel prediction for resource allocation in 5G mMTC using graph neural network (AMC-mMTC-GCIGNN). The method leverages granger causality-inspired graph neural networks to enhance channel prediction accuracy by analyzing feature relationships within channel data. Comparative analysis against existing techniques using performance metrics like bit error rate, mean squared error, and signal-to-noise ratio highlights the superiority of the proposed approach. The results underscore its potential to significantly enhance communication performance within 5G mMTC systems, thereby addressing a crucial aspect of next-generation wireless networks.

KW - 5G communication technology

KW - Adaptive modulation and coding

KW - Channel prediction

KW - Graph neural network

KW - Massive machine-type communication

UR - https://www.scopus.com/pages/publications/105021833314

U2 - 10.1007/978-981-95-0203-5_9

DO - 10.1007/978-981-95-0203-5_9

M3 - Conference article in proceedings

AN - SCOPUS:105021833314

SN - 978-981-95-0202-8

T3 - Lecture Notes in Electrical Engineering

SP - 101

EP - 113

BT - Advances in VLSI, Communication, and Signal Processing

A2 - Mishra, Ram Awadh

A2 - Gupta, Santosh Kumar

A2 - Srivastava, Vaibhav Kumar

A2 - Mäkelä, Jukka

PB - Springer

T2 - 7th International Conference on VLSI, Communication, and Signal processing, VCAS 2024

Y2 - 25 October 2024 through 27 October 2024

ER -

Gupta N, Mäkelä J , Uitto M, Prakash A. Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network. In Mishra RA, Gupta SK, Srivastava VK, Mäkelä J, editors, Advances in VLSI, Communication, and Signal Processing: Select Proceedings of the 7th International Conference, VCAS 2024. Springer. 2025. p. 101-113. (Lecture Notes in Electrical Engineering, Vol. 1457 LNEE). doi: 10.1007/978-981-95-0203-5_9

Channel Prediction for Resource Allocation in 5G Massive Machine-Type Communications Using Graph Neural Network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this