Generation of Optimal Coverage and Resource Allocation Policies from a VANET Infrastructure Using Machine Learning Algorithms (Phase 2)

This project addresses persistent technical challenges in Vehicular Ad-hoc Networks (VANETs), specifically network topology instability caused by vehicle movement, leading to frequent disconnections and performance degradation. A critical issue is the need for accurate and reliable vehicular congestion information to efficiently manage essential resources like coverage, capacity, and communication channel allocation from the infrastructure. To resolve this, the development of a policy-based planning algorithmic model for vehicular networks is proposed. This model will consider key variables such as capacity and channel assignment as resources, confronting the dynamic changes inherent to mobility and congestion. Through advanced algorithmic procedures, the ultimate goal is to achieve optimal resource allocation to maximize coverage and meet the demand of vehicular users, ensuring adequate connectivity within planned areas.<br/><br/><b>Goal</b>: <br/>To propose an algorithmic model for coverage and resource allocation based on VANET infrastructure within urban planning scenarios, aiming to cover the majority of users in dynamic, predictive, and scalable environments using Machine Learning algorithms.<br/><br/><b>Research lines</b>: <br/>New generation telecommunications networks