Submit to Special Issue Submit Abstract to Special Issue Review for Network Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

AI-Driven Evolution in Next-Generation Wireless Networks

Print Special Issue Flyer
Editor
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Network (ISSN 2673-8732).

Deadline for manuscript submissions: 31 March 2027 | Viewed by 919

Share This Special Issue

Editor

Dr. Iacovos I. Ioannou

E-Mail Website
Guest Editor

Department of Computer Science, Philips University, Nicosia, Cyprus
Interests: mobile and wireless communications; next-generation networks (5G); device-to-device (D2D) communications using artificial intelligence techniques
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence is reshaping wireless systems, transforming them from discrete optimizers into autonomous, learning-enabled infrastructures. As 5G evolves toward 5G-Advanced and 6G, this shift is essential for networks that must operate under tighter reliability, latency, and sustainability constraints while spanning heterogeneous domains, including edge/cloud computing, joint communication and sensing, and non-terrestrial segments. In response, the community has made significant progress on point solutions and components, such as schedulers, channel estimators, and beam managers. However, a comprehensive and consolidated systems view remains an open challenge. The field still lacks a framework that effectively couples learning with overarching control, governance, and lifecycle operations.

We are pleased to invite you to contribute your latest findings to this Special Issue. This Special Issue aims to respond to that gap by positioning AI not as an add-on, but as the organizing principle for design, orchestration, and assurance across the full stack. We welcome contributions that advance learning-assisted physical and MAC layers; integrate cross-layer control with O-RAN and service management/orchestration; demonstrate digital-twin methods for safe exploration and sim-to-real transfer; and extend terrestrial systems with reconfigurable intelligent surfaces, non-terrestrial and LEO constellations, and joint communication-and-sensing. Submissions should move beyond accuracy-only narratives to report latency distributions, reliability under shift, interpretability and operator trust, data and model governance, privacy preservation, and the compute/energy/carbon costs of intelligence. By emphasizing open artifacts—datasets, code, pipelines—and validation on realistic channels, testbeds, and field deployments, the collection aims to provide evidence that travels from simulation to operations.

The Aim of the Special Issue is to treat Artificial Intelligence (AI) as the organizing principle for the design, orchestration, and assurance across the full technology stack. This focus is fully aligned with the journal’s Aims and Scope. The way the subject relates to the journal's mission is by fundamentally advancing fundamental methods and practical architectures for next-generation communications, computing, and sensing. This Special Issue, by its very nature, treats AI as the core enabling technology, which aligns directly with the journal's Aims and Scope for next-generation communications, computing, and sensing. In terms of publication goals, the Special Issue is calibrated to attract at least ten high-quality contributions. This target is at least ten high-quality articles. If that crucial threshold is reached by securing this number of excellent submissions, the collection may be issued in book form in accordance with the journal’s policies. To reiterate, if this number is reached, the collection may be considered for publication in book form, per journal policy.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

Learning-assisted beamforming and channel estimation
Sample-efficient and energy-efficient control of reconfigurable intelligent surfaces
AI for non-terrestrial networks, including routing, handover, and Doppler mitigation
Joint communication and sensing with learning-based fusion
Semantic and goal-oriented communications
Intent-based networking
Intelligent spectrum sharing and coexistence
Lifecycle MLOps for wireless, data governance, drift detection, online learning guardrails, rollback strategies
Privacy-preserving and federated or split learning at the edge
Robustness to non-stationarity, adversarial conditions, and hardware impairments
Carbon and energy-aware scheduling and inference placement
Digital twin methodologies for safe experimentation and sim-to-real deployment
Optimization for Enhanced Mobile Broadband (eMBB) (e.g., VR/AR, high-speed video)
Optimization for Ultra-Reliable Low-Latency Communications (URLLC) (e.g., Tactile Internet, industrial automation)
Scalability and management for Massive Machine-Type Communications (mMTC) (e.g., massive IoT, smart cities)
AI-driven Network Slicing and end-to-end service orchestration
AI-driven security, anomaly detection, and threat mitigation
Edge AI and inference optimization for edge computing

We look forward to receiving your contributions.

Dr. Iacovos I. Ioannou
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Network is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

AI native wireless
5G advanced
6G
O-RAN
massive MIMO
reconfigurable intelligent surfaces
non-terrestrial networks
joint communication and sensing
semantic communications
network automation

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

36 pages, 6407 KB

Open AccessArticle

A Coupled Multi-Stage Hybrid Framework for BER Prediction and Beam Angle Optimization in Massive MIMO Systems: Combining Classical Regression with Coupled Deep Learning Approaches

by Iacovos Ioannou, Michael Georgiades, Prabagarane Nagaradjane, Ala Khalifeh, Christophoros Christophorou, Marios Raspopoulos and Vasos Vassiliou

Network 2026, 6(2), 35; https://doi.org/10.3390/network6020035 - 27 May 2026

Viewed by 268

Abstract

A coupled multi-stage learning framework is presented for joint bit error rate (BER) prediction and beam angle optimization in massive multiple-input multiple-output (MIMO) systems under a controlled simulation protocol. Unlike purely sequential benchmarking pipelines, the proposed method jointly coordinates BER prediction and beam-angle selection through a shared latent representation, an uncertainty-guided refinement mechanism, a cross-stage consistency loss and alternating optimization. Ten diverse approaches are systematically evaluated across two task-specific stages: Stage 1 examines six classical and adapted methods for BER prediction, including polynomial regression and deep unfolding networks; Stage 2 investigates four machine-learning and generative adversarial network (GAN)-based approaches for angle optimization, including conditional GANs and the proposed Direct-Angle neural network. Stage 3 couples the best-performing methods into a unified hybrid architecture through a shared encoder, explicit consistency regularization and alternating cross-stage updates, thereby producing an integrated beamforming decision strategy rather than an independent cascade. It is shown through the evaluation that the coupled hybrid framework achieves 96.0% overall angle-selection accuracy, a mean BER of

8.0 \times 10^{- 5}

and 100% BER tolerance compliance within

\pm 3

dB. In this framework, a differentiable BER surrogate initialized from a second-degree polynomial-regression teacher is coupled with the proposed Direct-Angle-NN for angle optimization. Relative to the strongest reimplemented literature baseline under the same controlled simulation assumptions, a 33.3% reduction in mean BER is achieved. Ablation experiments show that the coupling mechanism provides a modest but consistent improvement over the decoupled sequential baseline, increasing angle-selection accuracy from 93.5% to 96.0% and reducing mean BER from

1.05 \times 10^{- 4}

8.0 \times 10^{- 5}

; the shared encoder accounts for the largest part of this gain while the consistency loss adds 0.6 percentage points. These results indicate that the shared encoder, consistency regularization and uncertainty-guided refinement improve the final beamforming decision, although the gain should be interpreted as incremental rather than as a large architectural breakthrough. A spectral efficiency of 38.0 bps/Hz and an energy efficiency of 0.466 Gbps/W are achieved with a power consumption of only 32.6 W. The theoretical discussion is presented as an analytical characterization of BER sensitivity, complemented by a computational-complexity assessment and empirical convergence diagnostics for the alternating optimization, rather than as a formal optimality proof. The effectiveness of the framework across multiple performance metrics is supported by Monte Carlo simulations, while the limitations of the current setup, including perfect CSI, uncoded QPSK, ideal hardware assumptions and a fixed beam codebook, are explicitly discussed. The complete simulation framework, including code and trained models, can be made available by the corresponding author upon reasonable request to facilitate reproducible research in massive MIMO optimization. Full article

(This article belongs to the Special Issue AI-Driven Evolution in Next-Generation Wireless Networks)

► Show Figures