arXiv subjects

Nelson L. S. da Fonseca

Publications and source records attributed to Nelson L. S. da Fonseca.

12 recordsLinked to original sources

arXiv2026

SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems

Large-scale multi-agent ecosystems require mechanisms for discovering suitable agents without exposing entire registries to a large language model (LLM) orchestrator. The challenge is not only to retrieve relevant Agent Cards from a growing registry, but also to maintain a compact candidate context, since each additional candidate increases prompt size, inference cost, latency, and the risk of exceeding the model context window. We formulate this problem as candidate-context scalability and propose the Structural Signal Retriever (SSR), our deterministic and training-free retrieval method designed for Agent Card discovery. SSR derives structural lexical signals from capability-bearing Agent Card fields, weights them using inverse document frequency (IDF), and uses an Inverted Signal Index (ISI) for selective candidate scoring. We evaluate SSR using a synthetic agent benchmark, a public MS MARCO adaptation, and end-to-end LLM orchestration. At 1,000 agents, SSR reduces LLM input by 98.8% and orchestration latency by 70.9% relative to full-catalog orchestration. On MS MARCO, IDF improves retrieval effectiveness within the structural representation, while the ISI preserves retrieval effectiveness and reduces explicitly scored passages by 96.8%. End-to-end experiments show that candidate pre-selection maintains a compact candidate context as registry size grows and avoids the operational failures observed with full-catalog orchestration. These results support SSR as an Agent-Card-native, traceable retrieval mechanism for candidate-context scalability.

cs.MA↗

arXiv2026

Wireless Foundation Models: State-of-the-Art and Open Challenges

Wireless foundation models (WFMs) have emerged as a promising approach for learning reusable representations from large-scale wireless data and adapting them to downstream tasks. However, the rapidly growing literature remains fragmented across modalities, pretraining objectives, architectures, adaptation strategies, and evaluation protocols, making it difficult to assess progress toward broadly transferable models. This survey provides a systematic analysis of WFMs for physical-layer applications. We first introduce the main WFM design components, including pretraining, backbone architectures, and downstream adaptation. We then organize the literature into five physical-layer task families: signal recognition and demodulation, channel representation learning, RF sensing and localization, beam management, and spectrum sensing and monitoring, while separately examining multi-task PHY models. Across these categories, we analyze how existing models are pretrained, adapted, and evaluated, with particular attention to downstream task diversity and the distinction between in-distribution, partial-shift, and out-of-distribution transfer. Our analysis shows that current WFMs provide increasing evidence of reusable wireless representations, but this evidence varies considerably across task families and evaluation settings. Differences in datasets, modalities, architectures, pretraining objectives, adaptation protocols, and distribution shifts make it difficult to determine which design choices drive transfer and generalization. We conclude by identifying open directions for improving data availability, evaluation rigor, generalization, efficient adaptation, and real-world deployment, providing a unified framework for understanding the current WFM landscape and the requirements for developing more reusable foundation models for future physical-layer wireless systems.

eess.SP↗

arXiv2026

LLM-Driven Automated Reward Design for Reinforcement Learning-Based Routing in LEO Satellite Networks

Routing in Low Earth Orbit (LEO) satellite networks is challenging due to highly dynamic topologies and spatio-temporal network conditions. Reinforcement Learning (RL) has emerged as a promising approach for adaptive routing; however, its performance critically depends on reward function design, which must balance objectives such as goodput and end-to-end delay. In practice, reward design remains a complex manual process requiring significant domain expertise and extensive trial-and-error. Recent works have explored Large Language Models (LLMs) for automated reward design, but their application to highly dynamic systems such as LEO satellite networks remains largely unexplored. We propose LARGE, a framework that automates reward design for RL-based routing by combining LLM- driven generation with iterative simulator-in-the-loop evaluation. LARGE generates an initial reward from LLM prior knowledge and iteratively refines it using simulation feedback. This loop enables exploration of diverse reward formulations while aligning them with network objectives. Results show that LARGE improves reward quality within a few iterations through feedback-driven refinement. Across different backbones, the framework achieves performance comparable to an expert-designed baseline, with the best-performing configuration reaching goodput within approximately 3% of the baseline and slightly lower end-to-end delay, without manual reward engineering. These results indicate that effectiveness emerges from the iterative feedback-driven process enabled by LARGE, highlighting the potential of framework-driven LLM-in-the-loop optimization for RL-based routing in dynamic satellite networks.

cs.NI↗

arXiv2026

Energy-Latency Optimization for Dynamic Disaggregated Radio Access Networks

In 5G networks, base station disaggregation and new services pose challenges for radio access network (RAN) configuration, particularly in meeting bandwidth and latency constraints. The BS disaggregation is enabled by functional splitting (FS), which distributes the RAN functions in processing nodes and alleviates latency and bandwidth requirements in the fronthaul (FH). In addition to network performance, energy consumption is a critical concern for mobile network operators (MNO), since RAN operations constitute a significant portion of their operational expenditure. RAN configuration optimization is essential for balancing service performance and cost-effective energy consumption. In this paper, we propose a mixed-integer linear programming (MILP) model incorporating three objective functions: (i) minimizing fronthaul latency, (ii) minimizing energy consumption, and (iii) a bi-objective optimization that jointly balances both latency and energy consumption. The model determines the optimal FS Option, RAN function placement, and routing for eMBB, URLLC, and mMTC slices. While prior studies have addressed RAN configuration from either an energy minimization or a latency reduction perspective, few have considered both aspects simultaneously in realistic scenarios. Our evaluation accounts for different topologies, accounts for variations in aggregated gNB demand, explores diverse FS combinations, and incorporates Time Sensitive Networking modeling for latency analysis, which is critical for RAN performance. Given that MILP execution can be computationally intensive, we propose a heuristic algorithm that adheres to RAN constraints while providing near-optimal solutions. The results reveal an inherent trade-off between latency and energy consumption, highlighting the need for dynamic RAN reconfiguration. These insights provide a foundation for optimizing existing and future RAN deployments.

cs.NI↗

arXiv2025

ML-Based Preamble Collision Detection in the Random Access Procedure of Cellular IoT Networks

Preamble collision in the random access channel (RACH) is a major bottleneck in massive machine-type communication (mMTC) scenarios, typical of cellular IoT (CIoT) deployments. This work proposes a machine learning-based mechanism for early collision detection during the random access (RA) procedure. A labeled dataset was generated using the RA procedure messages exchanged between the users and the base station under realistic channel conditions, simulated in MATLAB. We evaluate nine classic classifiers -- including tree ensembles, support vector machines, and neural networks -- across four communication scenarios, varying both channel characteristics (e.g., Doppler spread, multipath) and the cell coverage radius, to emulate realistic propagation, mobility, and spatial conditions. The neural network outperformed all other models, achieving over 98\% balanced accuracy in the in-distribution evaluation (train and test drawn from the same dataset) and sustaining 95\% under out-of-distribution evaluation (train/test from different datasets). To enable deployment on typical base station hardware, we apply post-training quantization. Full integer quantization reduced inference time from 2500 ms to as low as 0.3 ms with negligible accuracy loss. The proposed solution combines high detection accuracy with low-latency inference, making it suitable for scalable, real-time CIoT applications found in real networks.

cs.NI↗

arXiv2024

Large Language Models for Zero Touch Network Configuration Management

The Zero-touch Network & Service Management (ZSM) paradigm, a direct response to the increasing complexity of communication networks, is a problem-solving approach. In this paper, taking advantage of recent advances in generative Artificial Intelligence, we introduce the Network ConFiguration Generator (LLM-NetCFG) that employs Large Language Model and architects ZSM configuration agents by Large Language Models. LLM-NetCFG can automatically generate configurations, verify them, and configure network devices based on intents expressed in natural language. We also show the automation and verification of network configurations with minimum human intervention. Moreover, we explore the opportunities and challenges of integrating LLM in functional areas of network management to fully achieve ZSM.

cs.NI↗

arXiv2022

Management of Resource at the Network Edge for Federated Learning

Federated learning has been explored as a promising solution for training at the edge, where end devices collaborate to train models without sharing data with other entities. Since the execution of these learning models occurs at the edge, where resources are limited, new solutions must be developed. In this paper, we describe the recent work on resource management at the edge, and explore the challenges and future directions to allow the execution of federated learning at the edge. Some of the problems of this management, such as discovery of resources, deployment, load balancing, migration, and energy efficiency will be discussed in the paper.

cs.NI↗

arXiv2021

Passive Optical Networking for 5G and Beyond 5G Low-Latency Mobile Fronthauling Services

Passive optical network (PON) technology offers an attractive cost-efficient alternative to support 5G and Beyond 5G mobile network fronthauling (MFH). However, MFH for such networks is challenging given its high bandwidth and strict latency requirements. To reduce these requirements, radio access network (RAN) functional splitting has been introduced in 5G networks; this provides more flexibility in resource allocation since the protocol stack is distributed between the centralized and the distributed units. In contrast to the conventional MFH requirement of the RF-PHY splitting, the MFH traffic produced by higher-layer splittings becomes more dependent on the actual user traffic load. By capitalizing on the new characteristics of the MFH traffic with RAN functional splitting, this article introduces a resource allocation mechanism to improve the performance of PONs serving MFH.

cs.NI↗

arXiv2021

Federated Learning over Next-Generation Ethernet Passive Optical Networks

Federated Learning (FL) is a distributed machine learning (ML) type of processing that preserves the privacy of user data, sharing only the parameters of ML models with a common server. The processing of FL requires specific latency and bandwidth demands that need to be fulfilled by the operation of the communication network. This paper introduces a Dynamic Wavelength and Bandwidth Allocation algorithm for Quality of Service (QoS) provisioning for FL traffic over 50 Gb/s Ethernet Passive Optical Networks. The proposed algorithm prioritizes FL traffic and reduces the delay of FL and delay-critical applications supported on the same infrastructure.

cs.NI↗

arXiv2021

Random Access Based on Maximum Average Distance Code for Massive MTC in Cellular IoT Networks

Code-expanded Random Access (CeRA) is a promising technique for supporting mMTC in cellular IoT networks. However, its potentiality is limited by code ambiguity, which results from the inference of a larger number of codewords than those actually transmitted. In this letter, we propose a random access scheme to alleviate this problem by allowing devices to select the preambles to be transmitted considering a q-ary code with maximum average distance. Moreover, a CeRA decoding approach based on hypergraphs is proposed and an analytical model is derived. Numerical results show that the proposed scheme significantly increases the probability of successful channel access as well as resource utilization.

cs.IT↗

arXiv2019

Scheduling in distributed systems: A cloud computing perspective

Scheduling is essentially a decision-making process that enables resource sharing among a number of activities by determining their execution order on the set of available resources. The emergence of distributed systems brought new challenges on scheduling in computer systems, including clusters, grids, and more recently clouds. On the other hand, the plethora of research makes it hard for both newcomers researchers to understand the relationship among different scheduling problems and strategies proposed in the literature, which hampers the identification of new and relevant research avenues. In this paper we introduce a classification of the scheduling problem in distributed systems by presenting a taxonomy that incorporates recent developments, especially those in cloud computing. We review the scheduling literature to corroborate the taxonomy and analyze the interest in different branches of the proposed taxonomy. Finally, we identify relevant future directions in scheduling for distributed systems.

cs.DC↗

arXiv2018

The Internet of Things, Fog and Cloud Continuum: Integration and Challenges

The Internet of Things needs for computing power and storage are expected to remain on the rise in the next decade. Consequently, the amount of data generated by devices at the edge of the network will also grow. While cloud computing has been an established and effective way of acquiring computation and storage as a service to many applications, it may not be suitable to handle the myriad of data from IoT devices and fulfill largely heterogeneous application requirements. Fog computing has been developed to lie between IoT and the cloud, providing a hierarchy of computing power that can collect, aggregate, and process data from/to IoT devices. Combining fog and cloud may reduce data transfers and communication bottlenecks to the cloud and also contribute to reduced latencies, as fog computing resources exist closer to the edge. This paper examines this IoT-Fog-Cloud ecosystem and provides a literature review from different facets of it: how it can be organized, how management is being addressed, and how applications can benefit from it. Lastly, we present challenging issues yet to be addressed in IoT-Fog-Cloud infrastructures.

cs.DC↗