Percorrer por autor "Prieta, Fernando De la"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- A cloud-driven support layer for enhancing distributed IDS in IoT networksPublication . Funchal, Gustavo Silva; Pedrosa, Tiago; Prieta, Fernando De la; Leitão, PauloThe exponential growth of connected devices, including sensors, mobile equipment, and various Internet of Things (IoT) nodes, has significantly increased the volume of data generated at the edge. Traditionally, data analysis tasks are offloaded to centralized cloud servers, resulting in increased latency, bandwidth bottlenecks and privacy concerns. While edge computing addresses these limitations by enabling local processing, it also faces challenges related to limited computational capacity and isolated decision-making. In this context, Multi-Agent Systems provide a promising solution by enabling collaboration among edge nodes for distributed machine learning-based intrusion detection. This work extends previous research by introducing a hierarchical approach within the edge-cloud continuum, where agents deployed in the cloud continuously monitor edge-level behaviour and employ reinforcement learning techniques to suggest dynamic updates to decision parameters of edge agents. This feedback-driven mechanism allows agents to adapt their behaviour over time, improving detection accuracy and collaboration efficiency while keeping communication overhead under control. The proposed architecture balances decentralisation and adaptability, offering a scalable and privacy-preserving solution for intrusion detection in dynamic and resource-constrained IoT environments.
- The role of multi-agent systems in realizing asset administration shell type 3Publication . Sakurada, Lucas; Prieta, Fernando De la; Leitão, PauloIn the context of Industry 4.0 (I4.0), the Asset Administration Shell (AAS) has been gaining significant attention in recent years. The AAS serves as a standardized digital representation of an asset, encapsulating all relevant information about the asset throughout its lifecycle. Since its introduction in 2015, the past decade has seen considerable progress in developing traditional AAS solutions, namely AAS Type 1 and Type 2. As this initial phase reaches maturity, it becomes essential to shift focus toward AAS Type 3 (proactive), a specific category that extends traditional AAS functionalities by incorporating higher levels of autonomy, intelligence, and collaborative capabilities. However, AAS Type 3 is still in its early stages, lacking formal specifications and comprehensive implementation guidelines. In this context, Multi-Agent Systems (MAS) have been investigated as a means to enhance traditional AAS solutions toward the realization of AAS Type 3, particularly by embedding autonomous, intelligent, and collaborative behaviors. Building on this perspective, this paper explores the role of MAS in realizing AAS Type 3 through a comprehensive analysis of existing agent-based AAS approaches in the literature. Furthermore, this paper proposes a reference model based on common patterns found in the literature to support the development of AAS Type 3 solutions, contributing to the discussion on the formalization of specifications and providing greater clarity on this emerging topic. Finally, to better demonstrate key aspects of the model, some illustrative examples are presented to guide its application and facilitate understanding.