RAN Architecture
Open Radio Access Network (O-RAN) architecture aims to create more flexible, interoperable, and intelligent mobile networks by disaggregating traditional radio access network functions. Current research heavily focuses on optimizing resource allocation and management within O-RAN, particularly using probabilistic forecasting techniques like DeepAR and reinforcement learning algorithms to improve efficiency and predict resource demands (e.g., Physical Resource Block utilization). This work is significant because it addresses key challenges in deploying and managing the increasingly complex and data-intensive nature of modern mobile networks, leading to improved energy efficiency, network performance, and potentially lower operational costs.
Papers
On the Impact of PRB Load Uncertainty Forecasting for Sustainable Open RAN
Vaishnavi Kasuluru, Luis Blanco, Cristian J. Vaca-Rubio, Engin Zeydan
Enhancing Cloud-Native Resource Allocation with Probabilistic Forecasting Techniques in O-RAN
Vaishnavi Kasuluru, Luis Blanco, Engin Zeydan, Albert Bel, Angelos Antonopoulos
On the use of Probabilistic Forecasting for Network Analysis in Open RAN
Vaishnavi Kasuluru, Luis Blanco, Engin Zeydan