Toward native explainable and robust AI in 6G networks: Current state, challenges and road ahead

Fiandrino, Claudio; Attanasio, Giulia; Fiore, Marco; Widmer, Joerg

doi:10.1016/j.comcom.2022.06.036

Cited by 18 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we provide an ML algorithm for the autonomous operation of the system which we use to discuss the explainability of its decisions, as it introduces a completely new paradigm in the operation of mobile networks. By introducing explainable intelligence [11], the usual blackbox behavior of the AI/ML models is opened up, allowing operators to interpret the decisions of the deployed intelligent algorithms [12]. This concept has been recently extended into the Machine Reasoning (MR) [13], which tries to imitate human reasoning in an analytical way, further devising decisions based on the decisions taken by intelligent algorithms.…”

Section: Management and Orchestrationmentioning

confidence: 99%

See 1 more Smart Citation

ATHENA: Machine Learning and Reasoning for Radio Resources Scheduling in vRAN Systems

Apostolakis,

Gramaglia,

Chatzieleftheriou

et al. 2024

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

Next-generation mobile networks will rely on their autonomous operation. Virtual Network Functions empowered by Artificial Intelligence (AI) and Machine Learning (ML) can adapt to varying environments that encompass both network conditions and the cloud platform executing them. In this view, it becomes paramount to understand why AI/ML algorithms made a decision, to be able to reason upon those decisions and, eventually, take further decisions related to e.g., network orchestration. In this paper, we present ATHENA, an ML-based radio resource scheduler for virtualized Radio Access Network (RAN) system. Our real-software implementation shows that the proposed MLbased approach can outperform the baseline solution. We discuss how additional re-orchestration actions can be taken by analyzing our scheduling decisions and learning from the past.

show abstract

Section: Management and Orchestrationmentioning

confidence: 99%

“…3) Reasoning and explainability in ML and AI: AI and ML interpretability is a new topic that emerged recently and is currently very active [28], [11]. The interest in ML and AI explainability is to evaluate a learned model and to also help its users to trust its decisions.…”

Section: B Related Work 1) Deep Reinforcement Learning-based Radio Sc...mentioning

confidence: 99%

ATHENA: Machine Learning and Reasoning for Radio Resources Scheduling in vRAN Systems

Apostolakis,

Gramaglia,

Chatzieleftheriou

et al. 2024

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

show abstract

“…Human operators cannot handle the increased complexity in traditional way of deploying, optimizing, and operating the next generation mobile networks [56]. Thus, AI and ML features can be leveraged to automate the operations of network functions and reduce operational expenditures.…”

Section: Rics Automation and Optimization Of The Ranmentioning

confidence: 99%

“…However, DL based models are considered as black-box and thus it is difficult to understand the underlying operations and reasons that why the model have taken certain complex actions and decisions [56]. This lack of transparency may lead to an issue of vulnerability to attacks and inject malicious data.…”

Section: B Future Research Directionsmentioning

confidence: 99%

Open RAN: Evolution of Architecture, Deployment Aspects, and Future Directions

Thiruvasagam¹,

Chandrasekar²,

Venkataram³

et al. 2023

Preprint

View full text Add to dashboard Cite

The Open Radio Access Network (Open RAN) aims to enable disaggregated, virtualized, programmable, and data-driven intelligent network with open interfaces to support various real-time and non-real-time applications for different classes of users and multiple industry verticals in beyond 5G and 6G networks while providing interoperability among multi-vendor network functions and components. In this article, we first discuss the evolution of RAN and then the O-RAN Alliance standardization activities and objectives to provide a comprehensive overview of O-RAN from a standardization point of view. Then, we discuss the O-RAN security aspects, use cases, deployment aspects, and open source projects and related activities in other forums. Finally, we summarize the open issues, challenges, and future research directions to explore further for in-depth study and analysis.

show abstract

“…Initial access is an essential component of MMW/THZ communication systems. These systems often rely on narrow, directional beams to establish and maintain reliable communication links [10]- [13]. Nevertheless, achieving accurate beam alignment and beam selection can be challenging and time-consuming due to narrow beams, propagation characteristics, multi-path propagation, mobility environments, and antenna variability [14]- [18].…”

mentioning

confidence: 99%

Hydra Radio Access Network (H-RAN): Multi-Functional Communications and Sensing Networks, Initial Access Implementation, Task-1 Approach

Abd,

Findley,

Soon Kim

2024

IEEE Access

View full text Add to dashboard Cite

Next-generation sensor and radio access networks (NG-SRANs) namely, Hydra radio access networks (H-RANs) represent a significant evolution in the telecommunications and sensor ecosystem landscape in anticipation of 6G deployment and beyond. H-RAN's vision derives its strength from integrating various technologies and networks into a single central network with the widespread incorporation of artificial intelligence (AI) technologies throughout the network. As a result, H-RAN's unique features and characteristics can serve as a baseline for innovating new applications and significantly enhance the overall functions of conventional open radio access networks (O-RANs). However, among the many improvements and innovations that the H-RAN architecture promises in its functionality, this paper focuses on the initial access implementation "task 1 " approach. Our solution contains several novelties that enhance both overhead and model accuracy. To this end, we define a novel intelligent perception network inspired by the knowledge distribution idea for collaborative H-RAN networks. We develop sparse multi-task learning (SMTL) as part of the AI/ML D-engine for federated learning to perform multiple tasks simultaneously. The SMTL is designed to select the optimal solution from a list of recommended solutions, namely "tasks". In the simulation, figures of merit include metrics such as top-k validation accuracy, beam selection accuracy, throughput ratios, beam sweep time, latency, and initial access times, which are used to evaluate the performance and efficiency of the proposed technologies. Simulation results demonstrate that by exploiting contextual information from distributed collaborative SRUs, and UE sends its own sensing information via a physical random-access channel in addition to using SMTL, our H-RAN-based initial access scheme can achieve 82.9% throughput of an exhaustive beam search (EBS) based-O-RAN network without any beam search overhead and 96.7% by searching among as few as 5 beams. Compared to the conventional MMW 5G-NR solution, our proposed method significantly minimizes the beam search time needed to reach the desired throughput. INDEX TERMSHydra Radio Access Network (H-RAN), Multi-functional networks, Perceptive networks, heterogeneous data, AI/ML engines, Collaborative-based approach, Sparse multi-task learning (SMTL), Initial access.

show abstract

Toward native explainable and robust AI in 6G networks: Current state, challenges and road ahead

Cited by 18 publications

References 27 publications

ATHENA: Machine Learning and Reasoning for Radio Resources Scheduling in vRAN Systems

ATHENA: Machine Learning and Reasoning for Radio Resources Scheduling in vRAN Systems

Open RAN: Evolution of Architecture, Deployment Aspects, and Future Directions

Hydra Radio Access Network (H-RAN): Multi-Functional Communications and Sensing Networks, Initial Access Implementation, Task-1 Approach

Contact Info

Product

Resources

About