Titulo Estágio
AI-Powered Design of Communication Networks
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
Departamento de Engenharia Informática da Universidade de Coimbra
Enquadramento
Many organizations, such as Altice, consider fibre-based access networks as a major solution to make the most out of the higher speed available for service usage. Fibre-based networks can be delivered to customer premises through point-to-point (P2P) and point-to-multipoint (P2MP) technologies, which increase the difficulty of planning and design the network, due to the large number of variables to consider. So, to create a cost-effective gigabyte passive optical network/fibre-to-the-home (GPON/FTTH) requires considering as many factors as headend position; optical splitter position; maximum splitter ratio; optical distribution point position; maximum distance; routes; number of surveys to attend and; accomplish the optical budget.
The main advantage of automating and optimising network design is minimising the time and cost of the original process of manually projecting calculating and optimize done by network engineers. Moreover, it can reduce the time-to-create from days to hours, and as so, using an AI-based approach allows the operator to automate the process of planning and design the network. By automating the process we can have a solution that allows pre-conditional inputs such as the headend position or optical splitter position and combine it with business rules that may be the optical budget, or cost of construction, among others. Providing the startup information and using an AI approach the operator has access to hardcopy outputs to analyse the results and explore the solutions.
Altice and the University of Coimbra are interested in further developing an AI approach that is able to design communication networks in an automatic way using different AI approaches. The data available include geographic information of the physical infrastructure to construct the network, information about equipment and infrastructure to deploy, and constraints and requirements for the deployment of the solution. Moreover, information on currently deployed solutions is available for validation and comparison.
Objetivo
Study the existing approach for automatic design and optimization of communication networks (GPON/FTTH)
Study and implement different AI-based approaches to improve the model, with a particular interest in collective intelligence approaches, quality diversity algorithms
Plano de Trabalhos - Semestre 1
T1 – State of the art on AI for automatic design of communication networks.
T2 - Data preparation and analysis of existing data and solutions.
T3 - Study and explore the existing approach.
T3 - Proposal of approach(es) to enhance the current approach.
T4 – Writing of the Intermediary report
Plano de Trabalhos - Semestre 2
T1 – Implementation of the proposed approach(es)
T2 – Experimentation and validation
T3 - Adjustments to the implementation
T4 – Writing the final report
Condições
The work will be conducted in the Evolutionary and Complex Systems (ECOS) group from CISUC.
There is a possibility of the student being awarded a scholarship (Bolsa de Investigação para Licenciado) for at least 6 months, renewable for an equal period by agreement between the advisor and the intern. The scholarship will follow the Fundação para a Ciência e Tecnologia (FCT) monthly stipend guidelines.
Orientador
João Correia / Nuno Lourenço
jncor@dei.uc.pt 📩