Invited Paper: Intelligent Agent Support for Achieving Low Latency in Cloud-Native NextG Mobile Core Networks

Choudhury, Shalini; Das, Sushovan; Paul, Sanjoy; Seskar, Ivan; Raychaudhuri, Dipankar

doi:10.1145/3571306.3571386

Cited by 1 publication

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, built on top of physical facilities to provide customized services to user equipment (UE), network slices not only depend on physical facilities to adjust the virtual network topology and to decide on the resource allocation strategies, but also are deeply coupled with services and UEs for ensuring service continuity [10], [11]. Under this circumstance, when the slices' serving UEs move across areas, the ongoing sessions between each pair of the moving UEs and slices may suffer a degradation in quality of service (QoS) and thus induce service continuity concern [12], [13]. Additionally, the dynamically changing requests from associated UEs also require the slices to quickly adjust their provisioning resources, which can lead to resource unavailable issues.…”

Section: Introductionmentioning

confidence: 99%

Federated Deep Reinforcement Learning for Prediction-Based Network Slice Mobility in 6G Mobile Networks

Ming,

Yu,

Taleb

2024

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Network slices are generally coupled with services and face service continuity/unavailability concerns due to the high mobility and dynamic requests from users. Network slice mobility (NSM), which considers user mobility, service migration, and resource allocation from a holistic view, is witnessed as a key technology in enabling network slices to respond quickly to service degradation. Existing studies on NSM either ignored the trigger detection before NSM decision-making or didn't consider the prediction of future system information to improve the NSM performance, and the training of deep reinforcement learning (DRL) agents also faces challenges with incomplete observations. To cope with these challenges, we consider that network slices migrate periodically and utilize the prediction of system information to assist NSM decision-making. The periodical NSM problem is further transformed into a Markov decision process, and we creatively propose a prediction-based federated DRL framework to solve it. Particularly, the learning processes of the prediction model and DRL agents are performed in a federated learning paradigm. Based on extensive experiments, simulation results demonstrate that the proposed scheme outperforms the considered baseline schemes in improving long-term profit, reducing communication overhead, and saving transmission time.

show abstract