Optimized feedforward convolutional graph attention-based frequency domain predictive channel model for 6G wireless MIMO communications

Ranjitham Govindasamy (), Debarati Sen (), Jamuna Rani Muthu () and Sathish Kumar Nagarajan ()
Additional contact information
Ranjitham Govindasamy: Sri Ramakrishna Engineering College, Department of Robotics and Automation Engineering
Debarati Sen: Indian Institute of Technology, Department of Telecommunication Engineering, G.S Sanyal School of Telecommunication
Jamuna Rani Muthu: Sona College of Technology, Department of Electronics and Communication Engineering
Sathish Kumar Nagarajan: Sri Ramakrishna Engineering College, Department of Biomedical Engineering

Telecommunication Systems: Modelling, Analysis, Design and Management, 2026, vol. 89, issue 1, No 4, 24 pages

Abstract: Abstract The development of 6G communication systems presents major obstacles for an effective network model, primarily due to the elevated costs and complexities associated with measurements across various scenarios and frequency ranges. Predictive channel modeling has surfaced as a viable and practical approach to tackle these issues. This research introduces an innovative framework, the Feedforward convolutional graph attention network with Groupers and Moray Eels (FCAGME), which is integrated with a gated recurrent unit. This framework is specifically designed to capture both spatial and temporal dependencies within the frequency domain. As a result, it facilitates accurate predictions of unknown frequency band characteristics by utilizing insights derived from existing channel measurements. Furthermore, this approach incorporates a Groupers and Moray Eels optimization algorithm to refine the parameters of FCAGME, thereby enhancing training stability and efficiently optimizing loss and error parameters. The proposed methodology demonstrates exceptional performance, achieving a channel prediction rate of 97.8%, an accuracy of 98.6%, a frequency prediction rate of 65 MHz, a mean squared error of 0.015, a mean absolute error of 0.009, and a root mean squared error of 0.132, surpassing the performance of current methods. In summary, the FCAGME framework provides a precise, stable, and efficient solution for predictive channel modeling in 6G systems.

Keywords: Frequency bands; Multiple input multiple output; Wireless communication networks; Channel prediction; Signal processing (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11235-025-01375-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:telsys:v:89:y:2026:i:1:d:10.1007_s11235-025-01375-y

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/11235

DOI: 10.1007/s11235-025-01375-y

Access Statistics for this article

Telecommunication Systems: Modelling, Analysis, Design and Management is currently edited by Muhammad Khan

More articles in Telecommunication Systems: Modelling, Analysis, Design and Management from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().