Searcharxiv⌕ Search

arXiv subjects

Rodrigo Moreira

Publications and source records attributed to Rodrigo Moreira.

At least 19 recordsLinked to original sources

Agentic Orchestration for SLA-Constrained Network Slicing in Programmable Mobile Data Planes

The Third Generation Partnership Project (3GPP) Technical Specification 23.501 (Release 17) defines Maximum Bit Rate (MBR) enforcement at the User Plane Function (UPF) in fifth-generation (5G) networks. Supporting differentiated service-level agreements across the radio access and core networks requires the UPF to enforce MBR limits according to configured slice priorities. During overload, the challenge is to adapt these limits while preserving that differentiation and avoiding oscillations. Building on programmable enforcement and intelligent orchestration, we propose an agentic control loop combining UPF telemetry with locally hosted Large Language Model (LLM) selection from a finite set of admissible rate candidates. Deterministic logic validates each selection and derives Packet Forwarding Control Protocol (PFCP) updates. The evaluated runs show no oscillations or fallbacks and unchanged highest-priority rate limits. These observations establish configuration preservation; delivered per-class QoS protection remains unmeasured.

cs.NI↗

Sustainable Federated Fine-Tuning with LoRA: Environmental Impact and Performance Footprint

Federated Learning (FL) with Parameter-Efficient Fine-Tuning (PEFT) enables efficient adaptation of Large Language Models (LLMs), yet its energy and carbon costs across hardware remain poorly understood. We evaluated federated Low-Rank Adaptation (LoRA) fine-tuning on NVIDIA A40, RTX 6000 Ada, and A100 GPUs using a $2^2$ full factorial design with 135M/360M models and 10/100 local steps. CodeCarbon tracked energy and estimated CO$_2$-equivalent emissions. Descriptive allocation of variation assigned 84.8-91.2% of energy and emissions variation to local steps within these ranges. On A40 and RTX 6000 Ada, configurations with fewer steps achieved comparable accuracy with roughly 6-8-fold lower energy consumption and higher accuracy per kWh. These findings support smaller local budgets for energy-efficient federated fine-tuning within the evaluated setting.

cs.LG↗

Energy-Aware Agentic Orchestration for Multi-Site Service Deployment

Energy-aware orchestration across geographically distributed infrastructures is increasingly important as data centers absorb growing Artificial Intelligence (AI) workloads. However, existing approaches often exclude the energy cost of automated decision-making from system-level sustainability assessments. This paper presents an energy-aware agentic orchestration framework that treats Large Language Model (LLM) reasoning as a measurable component of the control loop. We compare single-shot tool calling, ReAct, and plan-and-execute strategies on a multi-site Kubernetes testbed spanning two European data centers and instrumented at layers ranging from power distribution units to per-pod energy attribution. Using ten natural-language orchestration intents with varying decision complexity, we show that reasoning strategy and intent complexity strongly influence graphics processing unit (GPU) energy consumption during orchestration decisions. ReAct and plan-and-execute generated executable tool calls across all evaluated intents but required multiple LLM inferences, whereas the single-shot configuration was less costly but non-actionable. Prefix caching reduced mean ReAct GPU energy consumption by 29.4%. For the evaluated lightweight workload, the infrastructure-energy changes observed within the one-second measurement window were insufficient to offset the measured GPU decision energy. These findings demonstrate the importance of accounting for reasoning overhead when assessing the sustainability of AI-native orchestration and motivate energy-budgeted selection of agent strategies.

cs.NI↗

Conflict-Aware Autonomous Resource Orchestration for 5G Edge Slicing Using Multi-Agent Systems and LLMs

5G edge network slicing must reconcile two coupled requirements: understanding high-level operator intent and reallocating scarce computing and bandwidth resources under dynamic contention. Centralized optimization can face computational and responsiveness challenges under rapidly changing edge contention, and Multi-Agent System (MAS)-based auctions can support resource arbitration but still depend on operator-defined economic parameters and priorities. Embedding a Large Language Model (LLM) directly in a recurring control loop, by contrast, may introduce non-negligible inference latency and non-deterministic behavior. This paper proposes a two-timescale architecture that addresses this gap: an LLM-based Strategist translates natural-language network intents into economic policy parameters (budget, income, and bidding-aggressiveness) at the macro scale, while a deterministic, Vickrey-inspired second-price mechanism run by SPADE-based slice agents resolves recurring resource contention at the operational scale, with the resulting allocations enforced by patching Kubernetes CPU limits and Calico CNI bandwidth annotations directly on User Plane Function pods. We evaluate the architecture end-to-end on a real Kubernetes/Open5GS edge cluster across two complementary scenarios, each repeated 30 times: a Smart-City scenario, in which natural-language public-safety intents propagate into measurable changes in slice bids and bandwidth allocations within a few auction rounds, and a Hierarchical-slicing scenario, in which the mechanism provides priority-dependent resource and QoE differentiation, adapts to abrupt demand changes, and preserves configured minimum guarantees while maintaining near-complete allocation of the shared bandwidth pool.

cs.NI↗

Exposing AI Inference as a Telco Network API over the 5G User Plane

Supporting edge Artificial Intelligence (AI) inference as a network service is challenging because current mobile systems can transport tensors but do not expose or understand the inference context that gives those tensors operational meaning. Prior studies have addressed this gap through dynamic partitioning, collaborative inference, and split pipelines; however, these solutions remain application-bound, network-blind, or context-free. This work proposes Inference on Demand (IoD), an inference-on-demand abstraction that exposes split inference through a CAMARA-like Application Program Interface (API) and carries a split-aware tensor context in-band across the 5G user plane path. We evaluate the IoD on a programmable user plane function (UPF)-based testbed using a partitionable visual AI workload, showing that adaptive split selection can operate as a network-facing service while avoiding the rigid cost profile of static configurations. Including our findings, split inference becomes more than offloading when the service intent, runtime partitioning, and tensor transport are made visible to the mobile data plane. This opens a path toward network-native AI services, in which programmable telco infrastructure coordinates computation, context, and connectivity for user-facing applications.

cs.AI↗

PRISM: Perinuclear Ring-based Image Segmentation Method for Acute Lymphoblastic Leukemia Classification

Automated analysis of peripheral blood smears for Acute Lymphoblastic Leukemia (ALL) is hindered by low contrast and substantial variability in cytoplasmic appearance, which complicate conventional membrane-based segmentation. We found that many recent approaches rely on heavy neural architectures and extensive training, but still struggle to generalize across staining and acquisition variability. To address these limitations, we propose the Perinuclear Ring-based Image Segmentation Method (PRISM), which replaces explicit cytoplasmic delineation with adaptive concentric zones constructed around the nucleus. These perinuclear regions enable the extraction of robust cytoplasmic descriptors by integrating color information with texture statistics derived from grey-level co-occurrence patterns, without requiring accurate cell-boundary detection. A calibrated stacking ensemble of traditional classifiers leverages these descriptors to achieve a high performance, with an accuracy of 98.46% and a precision-recall AUC of 0.9937.

cs.CV↗

An Intelligent eUPF for Time-Sensitive Path Selection in B5G Edge Networks

In Beyond 5G (B5G) networks, intelligent, flexible traffic management is essential to meet the stringent speed and reliability requirements of new applications. This paper presents an improved User Plane Function (eUPF) design that uses a Deep Q-Network (DQN) agent for real-time path selection between Multi-access Edge Computing (MEC) and cloud endpoints. The path selection problem is formulated as a Partially Observable Markov Decision Process (POMDP). We propose a novel passive delay measurement method that uses eBPF programs to link TEID-based timestamps in GTP-U traffic, allowing for low-cost delay estimation without active testing. Experiments show that the DQN agent substantially outperforms a random baseline, with lower average latency, more stable rewards, and more reliable low-delay path choices. These results demonstrate the effectiveness of AI-driven control in B5G core networks and the promise of reinforcement learning for modern network management.

cs.NI↗

Evaluating Temporal and Structural Anomaly Detection Paradigms for DDoS Traffic

Unsupervised anomaly detection is widely used to detect Distributed Denial-of-Service (DDoS) attacks in cloud-native 5G networks, yet most studies assume a fixed traffic representation, either temporal or structural, without validating which feature space best matches the data. We propose a lightweight decision framework that prioritizes temporal or structural features before training, using two diagnostics: lag-1 autocorrelation of an aggregated flow signal and PCA cumulative explained variance. When the probes are inconclusive, the framework reserves a hybrid option as a future fallback rather than an empirically validated branch. Experiments on two statistically distinct datasets with Isolation Forest, One-Class SVM, and KMeans show that structural features consistently match or outperform temporal ones, with the performance gap widening as temporal dependence weakens.

cs.LG↗

Asynchronous Probability Ensembling for Federated Disaster Detection

Quick and accurate emergency handling in Disaster Decision Support Systems (DDSS) is often hampered by network latency and suboptimal application accuracy. While Federated Learning (FL) addresses some of these issues, it is constrained by high communication costs and rigid synchronization requirements across heterogeneous convolutional neural network (CNN) architectures. To overcome these challenges, this paper proposes a decentralized ensembling framework based on asynchronous probability aggregation and feedback distillation. By shifting the exchange unit from model weights to class-probability vectors, our method maintains data privacy, reduces communication requirements by orders of magnitude, and improves overall accuracy. This approach enables diverse CNN designs to collaborate asynchronously, enhancing disaster image identification performance even in resource-constrained settings. Experimental tests demonstrate that the proposed method outperforms traditional individual backbones and standard federated approaches, establishing a scalable and resource-aware solution for real-time disaster response.

cs.LG↗

Empowering Mobile Networks Security Resilience by using Post-Quantum Cryptography

The transition to a cloud-native 5G Service-Based Architecture (SBA) improves scalability but exposes control-plane signaling to emerging quantum threats, including Harvest-Now, Decrypt-Later (HNDL) attacks. While NIST has standardized post-quantum cryptography (PQC), practical, deployable integration in operational 5G cores remains underexplored. This work experimentally integrates NIST-standardized ML-KEM-768 and ML-DSA into an open-source 5G core (free5GC) using a sidecar proxy pattern that preserves unmodified network functions (NFs). Implemented on free5GC, we compare three deployments: (i) native HTTPS/TLS, (ii) TLS sidecar, and (iii) PQC-enabled sidecar. Measurements at the HTTP/2 request-response boundary over repeated independent runs show that PQC increases end-to-end Service-Based Interface (SBI) latency to approximately 54 ms, adding a deterministic 48-49 ms overhead relative to the classical baseline, while maintaining tightly bounded variance (IQR <= 0.2 ms, CV < 0.4%). We also quantify the impact of Certification Authority (CA) security levels, identifying certificate validation as a tunable contributor to overall delay. Overall, the results demonstrate that sidecar-based PQC insertion enables a non-disruptive and operationally predictable migration path for quantum-resilient 5G signaling.

cs.CR↗

TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning

Detecting Internet routing instability is a critical yet challenging task, particularly when relying solely on endpoint active measurements. This study introduces TRACE, a MachineLearning (ML)pipeline designed to identify route changes using only traceroute latency data, thereby ensuring independence from control plane information. We propose a robust feature engineering strategy that captures temporal dynamics using rolling statistics and aggregated context patterns. The architecture leverages a stacked ensemble of Gradient Boosted Decision Trees refined by a hyperparameter-optimized meta-learner. By strictly calibrating decision thresholds to address the inherent class imbalance of rare routing events, TRACE achieves a superior F1-score performance, significantly outperforming traditional baseline models and demonstrating strong effective ness in detecting routing changes on the Internet.

cs.NI↗

Data Augmentation and Convolutional Network Architecture Influence on Distributed Learning

Convolutional Neural Networks (CNNs) have proven to be highly effective in solving a broad spectrum of computer vision tasks, such as classification, identification, and segmentation. These methods can be deployed in both centralized and distributed environments, depending on the computational demands of the task. While much of the literature has focused on the explainability of CNNs, which is essential for building trust and confidence in their predictions, there remains a gap in understanding their impact on computational resources, particularly in distributed training contexts. In this study, we analyze how CNN architectures primarily influence model accuracy and investigate additional factors that affect computational efficiency in distributed systems. Our findings contribute valuable insights for optimizing the deployment of CNNs in resource-intensive scenarios, paving the way for further exploration of variables critical to distributed learning.

cs.DC↗

NeuroScaler: Towards Energy-Optimal Autoscaling for Container-Based Services

Future networks must meet stringent requirements while operating within tight energy and carbon constraints. Current autoscaling mechanisms remain workload-centric and infrastructure-siloed, and are largely unaware of their environmental impact. We present NeuroScaler, an AI-native, energy-efficient, and carbon-aware orchestrator for green cloud and edge networks. NeuroScaler aggregates multi-tier telemetry, from Power Distribution Units (PDUs) through bare-metal servers to virtualized infrastructure with containers managed by Kubernetes, using distinct energy and computing metrics at each tier. It supports several machine learning pipelines that link load, performance, and power. Within this unified observability layer, a model-predictive control policy optimizes energy use while meeting service-level objectives. In a real testbed with production-grade servers supporting real services, NeuroScaler reduces energy consumption by 34.68% compared to the Horizontal Pod Autoscaler (HPA) while maintaining target latency.

cs.NI↗

AGORA: Agentic Green Orchestration Architecture for Beyond 5G Networks

Effective management and operational decision-making for complex mobile network systems present significant challenges, particularly when addressing conflicting requirements such as efficiency, user satisfaction, and energy-efficient traffic steering. The literature presents various approaches aimed at enhancing network management, including the Zero-Touch Network (ZTN) and Self-Organizing Network (SON); however, these approaches often lack a practical and scalable mechanism to consider human sustainability goals as input, translate them into energy-aware operational policies, and enforce them at runtime. In this study, we address this gap by proposing the AGORA: Agentic Green Orchestration Architecture for Beyond 5G Networks. AGORA embeds a local tool-augmented Large Language Model (LLM) agent in the mobile network control loop to translate natural-language sustainability goals into telemetry-grounded actions, actuating the User Plane Function (UPF) to perform energy-aware traffic steering. The findings indicate a strong latency-energy coupling in tool-driven control loops and demonstrate that compact models can achieve a low energy footprint while still facilitating correct policy execution, including non-zero migration behavior under stressed Multi-access Edge Computing (MEC) conditions. Our approach paves the way for sustainability-first, intent-driven network operations that align human objectives with executable orchestration in Beyond-5G infrastructures.

cs.NI↗

Generalizable Hyperparameter Optimization for Federated Learning on Non-IID Cancer Images

Deep learning for cancer histopathology training conflicts with privacy constraints in clinical settings. Federated Learning (FL) mitigates this by keeping data local; however, its performance depends on hyperparameter choices under non-independent and identically distributed (non-IID) client datasets. This paper examined whether hyperparameters optimized on one cancer imaging dataset generalized across non-IID federated scenarios. We considered binary histopathology tasks for ovarian and colorectal cancers. We perform centralized Bayesian hyperparameter optimization and transfer dataset-specific optima to the non-IID FL setup. The main contribution of this study is the introduction of a simple cross-dataset aggregation heuristic by combining configurations by averaging the learning rates and considering the modal optimizers and batch sizes. This combined configuration achieves a competitive classification performance.

cs.CV↗

Exploiting Test-Time Augmentation in Federated Learning for Brain Tumor MRI Classification

Efficient brain tumor diagnosis is crucial for early treatment; however, it is challenging because of lesion variability and image complexity. We evaluated convolutional neural networks (CNNs) in a federated learning (FL) setting, comparing models trained on original versus preprocessed MRI images (resizing, grayscale conversion, normalization, filtering, and histogram equalization). Preprocessing alone yielded negligible gains; combined with test-time augmentation (TTA), it delivered consistent, statistically significant improvements in federated MRI classification (p<0.001). In practice, TTA should be the default inference strategy in FL-based medical imaging; when the computational budget permits, pairing TTA with light preprocessing provides additional reliable gains.

cs.CV↗

Noisy Neighbor Influence in the Data Plane of Beyond 5G Networks

Virtualization and containerization enhance the modularity and scalability of mobile network architectures, facilitating customized user services and improving management and orchestration across the network. In the context of the 5th Generation Mobile Network (5G), these advancements contribute to reduced Operational Expenditures (OPEX) and enable sliced-based networking for novel applications and services. However, as beyond fifth-generation (B5G) networks aim to address the remaining challenges regarding network slice isolation, the shared underlying hardware can lead to data plane contention among slices, resulting in the Noisy Neighbor (NN) effect, which may compromise network slicing and Service-Level Agreements (SLAs). We propose a kernel-level instrumentation of the User Plane Function (UPF) to assess the impact of noisy slices on data plane processing. Our findings reveal that even prioritized slices are susceptible to degradation induced by NN, with observable effects on latency metrics pertinent to user experience.

cs.NI↗

Energy-Aware Ensemble Learning for Coffee Leaf Disease Classification

Coffee yields are contingent on the timely and accurate diagnosis of diseases; however, assessing leaf diseases in the field presents significant challenges. Although Artificial Intelligence (AI) vision models achieve high accuracy, their adoption is hindered by the limitations of constrained devices and intermittent connectivity. This study aims to facilitate sustainable on-device diagnosis through knowledge distillation: high-capacity Convolutional Neural Networks (CNNs) trained in data centers transfer knowledge to compact CNNs through Ensemble Learning (EL). Furthermore, dense tiny pairs were integrated through simple and optimized ensembling to enhance accuracy while adhering to strict computational and energy constraints. On a curated coffee leaf dataset, distilled tiny ensembles achieved competitive with prior work with significantly reduced energy consumption and carbon footprint. This indicates that lightweight models, when properly distilled and ensembled, can provide practical diagnostic solutions for Internet of Things (IoT) applications.

cs.CV↗