Multi-Objective Optimization of Open RAN Data Center Placement for Enhanced 5G Deployments
Daniel Rodrigues de Luna, Fuad M. Abinader, Paulo Ricardo Branco da Silva, Michel Bernardo de Paiva, Vicente A. de Sousa, Augusto Neto · 2024
This paper tackles the optimization of placement and quantity of Open RAN Data Centers (ODCs) for hosting virtualized Open Distributed Units (O-DUs) in 5G NR networks, promoting flexible and scalable SDN architectures. Utilizing a Multi-Objective Facility Location Problem (MO-FLP) framework, we aim to minimize infrastructure costs related to network function virtualization (NFV) while meeting strict fronthaul latency and processing capacity requirements. Our method employs Non-dominated Sorting Genetic Algorithms (NSGA-II) to manage these trade-offs, achieving significant cost-efficiency and network performance gains through extensive city-wide 5G NR deployment simulations. We validated our approach in Natal and Manaus, evaluating ODC locations, capacities, and fiber usage. This study offers new insights and practical strategies for efficient 5G NR deployments, addressing key challenges in modern telecommunications infrastructure.