AI-Driven Mobility Management in 5G-Advanced Networks
Garigipati, Purna Sai (2024)
2024
Master's Programme in Information Technology
Informaatioteknologian ja viestinnän tiedekunta - Faculty of Information Technology and Communication Sciences
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2024-11-11
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202410319750
https://urn.fi/URN:NBN:fi:tuni-202410319750
Tiivistelmä
The rapid evolution of 5G networks and the impending advent of 6G have intensified challenges in mobility management, particularly within ultra-dense networks (UDNs) environments characterized by increased small-cell deployments and overlapping coverage areas. Traditional handover mechanisms have become increasingly inadequate in selecting the optimal cell for handover, leading to potential declines in network performance.
This thesis focuses on implementing Mobility Robustness Optimization (MRO) using Deep Reinforcement Learning (DRL) in micro-network deployments to reduce unnecessary handovers while maintaining adequate network performance. Leveraging the Ericsson Radio System Simulator and advanced Artificial Intelligence (AI) techniques, this research develops a model designed to optimize the selection of target cells during the handover process. The model processes measurement reports (MRs) from User Equipment (UE) to Base Stations (BSs) to enhance the handover decision-making process by considering various network conditions. The DRL model is crafted to favor successful handovers while penalizing undesirable outcomes such as handover failures, radio link failures, and instances of ping-pong or fast handovers.
This thesis focuses on implementing Mobility Robustness Optimization (MRO) using Deep Reinforcement Learning (DRL) in micro-network deployments to reduce unnecessary handovers while maintaining adequate network performance. Leveraging the Ericsson Radio System Simulator and advanced Artificial Intelligence (AI) techniques, this research develops a model designed to optimize the selection of target cells during the handover process. The model processes measurement reports (MRs) from User Equipment (UE) to Base Stations (BSs) to enhance the handover decision-making process by considering various network conditions. The DRL model is crafted to favor successful handovers while penalizing undesirable outcomes such as handover failures, radio link failures, and instances of ping-pong or fast handovers.