Distributed intelligence in communications networks and in the internet of things

• Grant number: 23/00673-7
• Support Opportunities: Research Projects - Thematic Grants
• Start date: February 01, 2024
• End date: January 31, 2029
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Agreement: MCTI/MC
• Principal Investigator: Nelson Luis Saldanha da Fonseca
• Grantee: Nelson Luis Saldanha da Fonseca
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Pesquisadores principais: Antonio Alfredo Ferreira Loureiro ; Eduardo Coelho Cerqueira ; Leandro Aparecido Villas ; Luis Henrique Maciel Kosmalski Costa
• Associated researchers: Alberto Egon Schaeffer Filho ; Allan Mariano de Souza ; Antonio Jorge Gomes Abelém ; Carlos Alberto Astudillo Trujillo ; Denis Lima do Rosário ; Eder John Scheid ; Edmundo Roberto Mauro Madeira ; Fabrizio Granelli ; Heitor Soares Ramos Filho ; Jéferson Campos Nobre ; Joahannes Bruno Dias da Costa ; Judy Carolina Guevara Amaya ; Juliano Araujo Wickboldt ; Lisandro Zambenedetti Granville ; Lucas Francisco Wanner ; Luciano Paschoal Gaspary ; Luiz Fernando Bittencourt ; Marcos Cesar da Rocha Seruffo ; Marilia Pascoal Curado ; Miguel Elias Mitre Campista ; Muriel Figueredo Franco ; Oscar Mauricio Caicedo Rendon ; Pedro Henrique Cruz Caminha ; Rodrigo de Souza Couto ; Torsten Braun ; Weverton Luis da Costa Cordeiro
• Associated scholarship(s): 24/17524-7 - Dynamic Network Slicing for 5G mobile users, BP.TT; 24/11309-7 - Development of applications for the Internet of Things using edge computing, BP.IC; 24/07007-5 - Federated Learning over Passive Optical Networks, BP.TT

Abstract

Currently, the execution of machine learning algorithms is typically batch, offline and centralized. Managing networks and their services requires running massively distributed, real-time data. In several situations, the real-time validity of the generated data is limited, demanding the reduction of latency in communication and processing. Furthermore, data transmission in a distributed environment is subject to the quality of communication channels, network congestion, and available energy in mobile devices. Such restrictions demand solutions based on Distributed Artificial Intelligence (DAI), which goes far beyond the traditional execution of machine learning algorithms. An additional strong restriction stems from the adoption of the new General Data Protection Law -LGPD. The data privacy restriction is addressed by the federated learning technique. The large number of devices connected to the Internet of Things requires the manipulation of a high volume of data generated by thousands of sensors, requiring solutions that meet scalability, geographic distribution, mobility, heterogeneity, security, and privacy requirements. Adaptive allocation and resource orchestration are challenges to overcome in large-scale IoT networks with thousands of sensors. The integration of IoT and AI enables the construction of several intelligent systems, such as smart cities, smart health and energy systems. In addition to typical IoT challenges, solutions must consider the dynamic variation of different demands. Demand prediction is crucial for adaptive systems. DAI will play a critical role in the realization of 6G networks and their applications. There are several ways that AI can be used in 6G, including conventional use of AI for prescriptive, predictive, diagnostic and descriptive analytics. Prescriptive analytics can be used to make decisions or predictions related to edge AI, such as cache placement, AI model migration, dynamically and adaptively scaling network slices and their service function chains, as well as automatic resource allocation ( for example, spectrum, cloud, and backhaul). Predictive analytics help predict the future from data acquired in real time for events such as resource availability, user behavior, user location and traffic patterns to proactively change the network. Proactive actions can adjust resource allocation, instantiation of security solutions, pre-migration of edge services. Diagnostic analysis refers to detecting network faults and anomalies. The present research project intends to investigate intelligent solutions for communication networks and IoT based on DAI, solutions for the allocation and orchestration of distributed resources, for infrastructure management and the provision of intelligent services. (AU)

Scientific publications

(8)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

BARROS, ALEX; VEIGA, RAFAEL; MORAIS, RENAN; ROSARIO, DENIS; CERQUEIRA, EDUARDO. MESFLA: Model Efficiency through Selective Federated Learning Algorithm. JOURNAL OF INTERNET SERVICES AND APPLICATIONS, v. 15, n. 1, p. 12-pg., 2024-01-01. (23/00673-7)

CICERI, OSCAR J.; ASTUDILLO, CARLOS A.; FIGUEIREDO, GUSTAVO B.; ZHU, ZUQING; DA FONSECA, NELSON L. S.. Resource Allocation in Passive Optical Networks for Low-Latency Mobile Fronthauling Services. IEEE NETWORK, v. 39, n. 1, p. 11-pg., 2025-01-01. (23/00673-7)

TRINDADE, SILVANA; DA FONSECA, NELSON L. S.. Client Selection in Hierarchical Federated Learning. IEEE INTERNET OF THINGS JOURNAL, v. 11, n. 17, p. 16-pg., 2024-09-01. (23/00673-7)

LAMB, IVAN PETER; PINHEIRO ROSA DUARTE, PEDRO ARTHUR; LUIZELLI, MARCELO CAGGIANI; GASPARY, LUCIANO PASCHOAL; AZAMBUJA, JOSE RODRIGO; DA COSTA CORDEIRO, WEVERTON LUIS. Multi-Tenant Programmable Switch Virtualization Leveraging Explicit Resource Sharing. 2024 20TH INTERNATIONAL CONFERENCE ON NETWORK AND SERVICE MANAGEMENT, CNSM 2024, v. N/A, p. 9-pg., 2024-01-01. (21/00199-8, 20/05183-0, 23/00673-7, 23/00816-2)

SOUSA, JOHN; RIBEIRO, EDUARDO; BUSTINCIO, ROMULO; BASTOS, LUCAS; MORAIS, RENAN; CERQUEIRA, EDUARDO; ROSARIO, DENIS. Enhancing robustness in federated learning using minimal repair and dynamic adaptation in a scenario with client failures. ANNALS OF TELECOMMUNICATIONS, v. N/A, p. 15-pg., 2025-02-27. (23/00673-7)

LIRA, OSCAR G.; CAICEDO, OSCAR M.; DA FONSECA, NELSON L. S.. Large Language Models for Zero Touch Network Configuration Management. IEEE COMMUNICATIONS MAGAZINE, v. N/A, p. 8-pg., 2024-10-22. (23/00673-7)

DADAUTO, CAIO VINICIUS; DA FONSECA, NELSON L. S.; TORRES, RICARDO DA S.. Data-Driven Intra-Autonomous Systems Graph Generator. IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, v. 21, n. 5, p. 14-pg., 2024-10-01. (15/24494-8, 14/12236-1, 16/50250-1, 23/00673-7, 17/20945-0)

GUIMARAES, LUCAS C. B.; COUTO, RODRIGO S.. A Performance Evaluation of Neural Networks for Botnet Detection in the Internet of Things. Journal of Network and Systems Management, v. 32, n. 4, p. 24-pg., 2024-10-01. (23/00811-0, 23/00673-7)