Abstract
Ultra-Reliable Low-Latency Communication services are intrinsically challenging to deliver, with many 5G and future services, including mobile game streaming, adding further complexity by demanding zero service downtime in high-mobility
scenarios. Solving these challenges is essential and must be addressed beyond mobile gaming to realise a multitude of current and future services like Virtual Reality or holoportation in mobile scenarios. Multi-access Edge Computing brings services “closer” to user consumption with evident advantages yet at the cost of
maintaining a zero downtime guarantee when user handovers (HOs) are prevalent due to the decentralisation of services towards the network edge. In this work, we design and evaluate intelligent HO prediction models between radio 5G Base Stations. The motivation for timely user HO prediction lies in being a vital presupposition for path steering and other Management and Network Orchestration control actions in contemporary programmable 5G networks to deliver a zero downtime perception during HO events. Our meticulous simulation and actual testbed evaluation results show that effective HO prediction can
be achieved using a combination of Long Short-Term Memory (LSTM) or gradient boost regression with classification models, with the latter filtering out any Reference Signal Received Power (RSRP) prediction input outliers for predicting the serving cell.
scenarios. Solving these challenges is essential and must be addressed beyond mobile gaming to realise a multitude of current and future services like Virtual Reality or holoportation in mobile scenarios. Multi-access Edge Computing brings services “closer” to user consumption with evident advantages yet at the cost of
maintaining a zero downtime guarantee when user handovers (HOs) are prevalent due to the decentralisation of services towards the network edge. In this work, we design and evaluate intelligent HO prediction models between radio 5G Base Stations. The motivation for timely user HO prediction lies in being a vital presupposition for path steering and other Management and Network Orchestration control actions in contemporary programmable 5G networks to deliver a zero downtime perception during HO events. Our meticulous simulation and actual testbed evaluation results show that effective HO prediction can
be achieved using a combination of Long Short-Term Memory (LSTM) or gradient boost regression with classification models, with the latter filtering out any Reference Signal Received Power (RSRP) prediction input outliers for predicting the serving cell.
| Original language | English |
|---|---|
| Title of host publication | 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| ISBN (Electronic) | 9781728181042 |
| ISBN (Print) | 978-1-7281-8105-9 |
| DOIs | |
| Publication status | Published - 2 Feb 2022 |
| Event | 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Madrid, Spain Duration: 7 Dec 2021 → 11 Dec 2021 |
Publication series
| Name | 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings |
|---|
Conference
| Conference | 2021 IEEE Global Communications Conference, GLOBECOM 2021 |
|---|---|
| Country/Territory | Spain |
| City | Madrid |
| Period | 7/12/21 → 11/12/21 |
Bibliographical note
Funding Information:This work was funded by Samsung Electronics (UK) Limited, as part of the “Zero Downtime Edge Application Mobility” research project ran by the University of Bristol’s Smart Internet Lab in partnership with Samsung Electronics (UK) Limited.
Publisher Copyright:
© 2021 IEEE.
Keywords
- 5G network
- handover
- machine learning
- mobility prediction
- multi-access edge computing