Titulo Estágio
Forecasting Load of Telecom Resources
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
Departamento de Engenharia Informática da Universidade de Coimbra
Enquadramento
AlticeLabs, over the past two decades, has developed and evolved a solution for real-time control and charging of telecommunications services, which started to be called NGIN – Next Generation Intelligent Network. It is a highly flexible Monetization, and Policy Control solution with a concurrent approach applied to any communication service type and any service provider from the smallest to the largest. The NGIN brand continues to stand out with a new perspective on Convergent Charging and Policy (NGIN-CCP) to allow the solution to be applied to or to solve operator's problems related with: Promoting Data Monetization, Delivering Quality of Experience (QoE) Improvement, Supporting Next Generation Networking (NGN) and Internet of Things (IoT), Enabling Over-The-Top (OTT) Partnerships. NGIN-CCP is aimed at telecom operators that monetise and improve QoE to their wireless (mobile xG, WiFi, WiMax) and/or wireline (FTTH, xDSL, cable) data networks. It is also suited for monetising voice and messaging services, thus enabling a full fix-mobile convergence. NGIN-CCP is an ever-evolving product that is now adapting and updating to the new 5G network technologies.
One of the areas of interest for the NGIN-CCP is the resource management and optimisation of its resources based on current data plans and future monetized services alterations or acquisitions. For instance, predicting the impact of a new client and plans acquisitions or changes on NGIN-CPP resources, i.e. existing network plan that is serving the clients, estimating the limit of specific NGIN-CPP components that could eventually be reaching its limits. Since these predictions can help to be pre-emptive to adjust resources and not compromise the experience of all clients, Altice Labs, with the collaboration of the University of Coimbra, is interested in progressing the module for resource usage forecast for the NGIN-CCP framework. The dataset to execute the proposal will be a sample of past data gathered from NGIN-CCP modules available from Altice Labs that is categorized as time-series tabular data with information on NGIN-CCP resources and status of operations, with categorical and numerical attributes (discrete and continuous variables).
Objetivo
-Application of data science techniques to create models for forecasting the usage of resources at a given time, using multiple data sources.
-Design and implementation of a Grafana dashboard to enable the deployment and visualization of the developed models.
Plano de Trabalhos - Semestre 1
T1 – State of the art on data forecast and regression models
T2 - Study of solutions already implemented
T3 - Data preparation, selection and analysis
T4 - Design of the solution and requirements specification
T5 - Writing of the Intermediary report
Plano de Trabalhos - Semestre 2
T1 – Implementation
T2 – Experimentation and validation
T3 - Refinement of the implementation
T4 - Dissemination of the developed work through the writing and submission of a scientific paper
T5 – Writing of the final report
Condições
The work will be conducted in the Cognitive and Media Systems (CMS) and 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 / Tiago Martins
jncor@dei.uc.pt 📩