Horário: 14h
Palestrante:Cássio Giorgio Couto Coelho (doutorando)
Orientadora: Profa Célia Ghedini Ralha
Título: MASE-EGTI: An Agent-based Simulator for Environmental Land Change
Resumo: Interacting entities in human society and their roles considering land exploration and occupation are crucial for studying land use/cover change (LUCC) in landscape ecology. For investigation of games in LUCC models, this work presents an agent-based decision model based on evolutionary game theory with three layers of interactive deliberation (individual, peer-to-peer, and social) implemented in MASE-EGTI - Multi-Agent System for Environmental simulation with Evolutionary Game Theory Interactions. The conceptual model details STAIP, an acronym for cellular Space, Time, Agents, Interactions, and Public policy. The theoretical model baseline focus on evolutionary game theory. The experiments use real data from the MapBiomas Brazilian public geographic database. The results show that agents' peer-to-peer interactions may influence the final land usage and conversion of natural systems. We believe the conducted simulations present insights for LUCC studies that consider space transformation and population interactions.
Horário: 14h20
Palestrante:Leonardo Henrique Moreira (doutorando)
Orientadora: Profa Célia Ghedini Ralha
Título: Plan Recovery Process in Multi-agent Dynamic Environments
Evento:Proceedings of the 18th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2021)
Disponível em:https://www.scitepress.org/PublicationsDetail.aspx?ID=21KlPagGVIk=&t=1
Resumo: Planning is the process that focuses on the choice and organization of actions through their expected effects. Plans can be affected by unexpected, uncontrolled, non-deterministic events leading to failures. Such challenging problem boosted works focusing agent distribution, communication mechanisms, privacy, among other issues. Nevertheless, the plan recovery process does not have a defined standard solution. Thus, in this work, we present a three-phase plan recovery process to provide resilience to agent plans by supporting a staggered solution. Whenever an action execution fails, agents try to solve individually through their own capabilities. But when not possible, agents start an interaction protocol to ask for help. Finally, when previous two phases were unsuccessful, a centralized planning process is trigged. Regardless the phase in which the solution is found, agents’ plans are coordinated to guarantee cooperation maintaining information privacy. An empirical analysis applyin g metrics such as planning time, final plan length and message exchange was conducted. Results give statistical significant evidence that agents’ autonomy is better explored in agents’ loosely coupled environments. The contributions of this work include: a three-phase plan recovery process, a simulation tool for benchmarks, and a statistical robust evaluation method to multi-agent planning.
Horário: 14h40
Palestrante:Aurélio Ribeiro Costa (doutorando)
Orientadora: Profa Célia Ghedini Ralha
Título: A Community Detection Framework for Dynamic Complex Networks
Resumo: The identification of community structure in social network is an important problem tackled in literature of network analysis. There are many solutions to this problem using a static scenario, when facing a dynamic scenarios some solutions may be adapted but others simply do not fit, moreover when considering the demand to analyze constantly growing networks. In this context, we propose an approach to the problem of community detection in dynamic networks based on reinforcement learning strategy to deal with changes on big networks using a local optimization on modularity of the changed entities. An experiment using synthetic and real-world dynamic network data shows results comparable to static scenarios.
Horário: 15h
Palestrante:Aldo Henrique Dias Mendees (doutorando)
Orientadora: Profa Célia Ghedini Ralha
Título: Modelo Baseado em Agentes para Gerenciamento Dinâmico de Recursos em Nuvem Computacional
Resumo: O crescimento das ferramentas envolvidas na internet favoreceu o surgimento de novos paradigmas e novas áreas de pesquisas. Uma das grandes áreas de pesquisa que surgiu é a computação em nuvem. Juntamente com a computação em nuvem outras áreas da computação vêm demonstrando grande importância como é o caso das aplicações baseadas em Sistemas Multiagentes que também traz consigo muitas áreas a serem investigadas. Neste projeto pretende-se trabalhar a junção dessas duas grandes áreas para que seja extraído o melhor de ambas. É uma arquiteturas de gerenciamento e balanceamento dos recursos através do monitoramento, predição, provisionamento e elasticidade de recursos das instâncias nas maquinas virtuais da nuvem e garanta a execução de aplicações.
Horário: 15h20
Palestrante:Gustavo Catalbiano Eichler (mestrando)
Orientadores: Prof. Marcelo Marotta e Profa Célia Ghedini Ralha
Título: An Agent-Based Communication Architecture to Hybrid NOMA-OMA Decisions
Resumo: The emerging of Internet of Things (IoT), massive Machine Type Communication (mMTC) and Industry 4.0, will massively increase the demand for connectivity and raise Quality of Service (QoS) requirements, regarding data rates, latency, reliability, among others that exceed the limits of current mobile communication systems. To excel these limits, both Non Orthogonal Multiple Access (NOMA) and Orthogonal Multiple Access (OMA) technologies present individual benefits and drawbacks that can be compensated by interchanging them creating communication opportunities with enhanced Spectral Efficiency (SE). To turn feasible such an interchanging, we modeled a spectrum sharing problem and propose an Agent-Based Communication Architecture to make decisions in order to study the detected trade-off. Through our simulations, our results highlight opportunities to interchange NOMA and OMA meeting QoS requirements with enhanced SE. This work is a submission for the Master Degree Qualification Exam in Informatics.
Horário: 15h40
Palestrante:Charles Antonio Nascimento Costa (mestrando)
Orientadora: Profa Célia Ghedini Ralha
Título: Trust and Reputation Multiagent-driven Model for Distributed Transcoding on Fog-Edge
Evento:Proceedings of the 21st International Workshop on Trust in Agent Societies, co-located with the$20th Int. Conference on Autonomous Agents and Multiagent Systems (AAMAS)
Resumo: Adaptive Bitrate Streaming is a popular technique for providing video media over the Internet. Nevertheless, the computational cost of transcoding a video in many formats can limit its application on live video streaming. Besides, the network overhead of transmitting simultaneously many versions of the same content is a problem. Offloading the transcoding job to the network edge can deal with the problem. Users and providers of live video could benefit from a joint scheme that allowed edge devices to do the transcoding with tolerable latency and delay. This work presents a multiagent-driven model to deal with the problem of distributed transcoding on fog-edge computing. Agents have well-defined roles relating to Broker, Transcoder, and Viewer Proxy. Trust and Reputation metrics derived from utility functions that take into account users’ quality of experience (QoE) are defined and applied. The \textbf{Re}putation-based \textbf{No}de \textbf{S}election (ReNoS) algorithm is presented for selecting the best nodes to perform the transcoding tasks. The conducted experiments indicate that the proposed approach can afford utility gain keeping viewers’ QoE having the potential to be applied in real edge computing environments.
Local: Teams MS - Equipe PPGI-316415 Seminário, Canal Seminários 1-2021
Profa Célia Ghedini Ralha (Este endereço de email está sendo protegido de spambots. Você precisa do JavaScript ativado para vê-lo.)
Coordenadora Seminários de Pós-Graduação em Informática 1-2021