Analysis and Improvements of a Tabu Search Approach for 5G scenarios

Description

In 5G networks, a dense deployment of small cells in hotspot area is envisioned to cope with the always-increasing demand from the users. In a scenario where multiple point of access are available for connection, it becomes very important to develop strategies to turn on and off the small cells according to the users’ needs, so to reduce costs and CO2 emissions. These strategies, however, may require a lot of computational resources in order to come with the optimal solution.

This work focuses on a Tabu Search metaheuristic approach that can provide a quasi-optimal solution to the problem in real time. To this end, the student is requested to have a good knowledge of Java. The metaheuristic will be developed in Optaplanner; the scenario considers a snapshot of the 5G network and provides a jointly optimized solution for the association of mobile users and the routing in the backhaul 5G mesh network.

The first objective is to analyse and improve the proposed metaheuristic (i.e., improve the results with respect to the true optima). The second objective of this work is to study the tuning parameters in Optaplanner and propose an automatic selection of those parameters for each proposed scenario.

Period

Start date: --
End date: --
Status: Open

Funding

No funding is provided for this project.

Participants

Supervisor: Enrica Zola (GRXCA)

Student: To be assigned.

Further information

No additional information is provided.