Pedro Enrique Iturria Rivera

Pedro Enrique Iturria Rivera, Medhat Elsayed, Majid Bavand et al.

5G New Radio proposes the usage of frequencies above 10 GHz to speed up LTE's existent maximum data rates. However, the effective size of 5G antennas and consequently its repercussions in the signal degradation in urban scenarios makes it a challenge to maintain stable coverage and connectivity. In order to obtain the best from both technologies, recent dual connectivity solutions have proved their capabilities to improve performance when compared with coexistent standalone 5G and 4G technologies. Reinforcement learning (RL) has shown its huge potential in wireless scenarios where parameter learning is required given the dynamic nature of such context. In this paper, we propose two reinforcement learning algorithms: a single agent RL algorithm named Clipped Double Q-Learning (CDQL) and a hierarchical Deep Q-Learning (HiDQL) to improve Multiple Radio Access Technology (multi-RAT) dual-connectivity handover. We compare our proposal with two baselines: a fixed parameter and a dynamic parameter solution. Simulation results reveal significant improvements in terms of latency with a gain of 47.6% and 26.1% for Digital-Analog beamforming (BF), 17.1% and 21.6% for Hybrid-Analog BF, and 24.7% and 39% for Analog-Analog BF when comparing the RL-schemes HiDQL and CDQL with the with the existent solutions, HiDQL presented a slower convergence time, however obtained a more optimal solution than CDQL. Additionally, we foresee the advantages of utilizing context-information as geo-location of the UEs to reduce the beam exploration sector, and thus improving further multi-RAT handover latency results.

Marco Skocaj, Pedro Enrique Iturria Rivera, Roberto Verdone et al.

Federated Learning (FL) has emerged as a promising framework for distributed training of AI-based services, applications, and network procedures in 6G. One of the major challenges affecting the performance and efficiency of 6G wireless FL systems is the massive scheduling of user devices over resource-constrained channels. In this work, we argue that the uplink scheduling of FL client devices is a problem with a rich relational structure. To address this challenge, we propose a novel, energy-efficient, and importance-aware metric for client scheduling in FL applications by leveraging Unsupervised Graph Representation Learning (UGRL). Our proposed approach introduces a relational inductive bias in the scheduling process and does not require the collection of training feedback information from client devices, unlike state-of-the-art importance-aware mechanisms. We evaluate our proposed solution against baseline scheduling algorithms based on recently proposed metrics in the literature. Results show that, when considering scenarios of nodes exhibiting spatial relations, our approach can achieve an average gain of up to 10% in model accuracy and up to 17 times in energy efficiency compared to state-of-the-art importance-aware policies.

Md Arafat Habib, Medhat Elsayed, Majid Bavand et al.

In this paper, we propose an Agentic Artificial Intelligence (AI) framework for wireless networks. The framework coordinates a pool of AI agents guided by Natural Language (NL) inputs from a human operator. At its core, the super agent is powered by a Hierarchical Online Decision Transformer (H-ODT). It orchestrates three categories of agents: (i) inter-slice, intra-slice resource allocation agents, (ii) network application orchestration agents, and (iii) self-healing agents. The orchestration takes place with the help of an Agentic Retrieval-Augmented Generation (RAG) module that integrates knowledge from heterogeneous sources. In this proposed methodology, the super agent directly interfaces with operators and generates sequential policies to activate relevant agents. The proposed framework is evaluated against three state-of-the-art baselines, showing improved throughput, reduced network delay, and higher energy efficiency at both slice-level and system-wide performance metrics. Also, the proposed Agentic framework introduces a bi-level human operator intent validation methodology, both at the slice-level and Key Performance Indicator (KPI)-level using generative AI-based time series predictors. We could rule out performance-degrading operator intents with an accuracy of 88.5%. Lastly, while being interrupted by any performance-degrading events, the self-healing capability of Agentic AI in our framework automatically recovers 90% of its previous performance, avoiding quality-of-service drifts when there is no human involvement.