Air-To-Air Collaborative Learning: A Multi-Task Orchestration in Federated Aerial Computing
Authors: Awada, U., Zhang, J., Chen, S. and Li, S.
Journal: IEEE International Conference on Cloud Computing, CLOUD
Volume: 2021-September
Pages: 671-680
eISSN: 2159-6190
ISBN: 9781665400602
ISSN: 2159-6182
DOI: 10.1109/CLOUD53861.2021.00086
Abstract:Recent research on edge computing (EC) has proposed federated or collaborative learning technique, where machine learning models are shared among participating edge deployments, thereby benefiting from all available datasets without exchanging them. In addition, EC systems are currently exploiting attaching portable edge devices on drones for data processing close to the sources, to achieve high performance, fast response times and real-Time insights. Existing researches lack the potential to federate edge resources and manage corresponding service entities running across multiple drones, thus resulting to sub-optimal performance. Therefore, we introduce Aerial Edge, a federated learning-based orchestration framework for a federated aerial EC system. We propose a federated multi-output linear regression model to estimate multi-Task resource requirements and execution time, to select the closest drone deployment having congruent resource availability and flight time to execute ready tasks at any given time. For better utilization of resources, we propose a variant bin-packing optimization approach through gang-scheduling of multi-dependent containerized tasks that co-schedules and co-locates tasks tightly on nodes to fully utilize available resources. Extensive experiments on real-world data-Trace from Alibaba cluster trace with information on task dependencies show the effectiveness, fast executions, and resource efficiency of our approach.
https://eprints.bournemouth.ac.uk/35747/
Source: Scopus
Air-to-Air Collaborative Learning: A Multi-Task Orchestration in Federated Aerial Computing
Authors: Awada, U., Zhang, J., Chen, S. and Li, S.
Journal: 2021 IEEE 14TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (CLOUD 2021)
Pages: 671-680
ISSN: 2159-6182
DOI: 10.1109/CLOUD53861.2021.00086
https://eprints.bournemouth.ac.uk/35747/
Source: Web of Science (Lite)
Air-to-Air Collaborative Learning: A Multi-Task Orchestration in Federated Aerial Computing
Authors: Awada, U., Zhang, J., Chen, S. and Li, S.
Conference: The 2021 IEEE International Conference on Cloud Computing
Dates: 5-10 September 2021
https://eprints.bournemouth.ac.uk/35747/
Source: Manual
Air-to-Air Collaborative Learning: A Multi-Task Orchestration in Federated Aerial Computing
Authors: Awada, U., Zhang, J., Chen, S. and Li, S.
Conference: The 2021 IEEE International Conference on Cloud Computing
Abstract:—Recent research on edge computing (EC) has proposed federated or collaborative learning technique, where machine learning models are shared among participating edge deployments, thereby benefiting from all available datasets without exchanging them. In addition, EC systems are currently exploiting attaching portable edge devices on drones for data processing close to the sources, to achieve high performance, fast response times and real-time insights. Existing research lack the potential to federate edge resources and manage corresponding service entities running across multiple drones, thus resulting to suboptimal performance. Therefore, we introduce AerialEdge, a federated learning-based orchestration framework for a federated aerial EC system. We propose a federated multi-output linear regression models to estimate multi-task resource requirements and execution time, to select the closest drone deployment having congruent resource availability and flight time to execute ready tasks at any given time. For better utilization of resources, we propose a variant bin-packing optimization approach through gang-scheduling of multi-dependent containerized tasks that coschedules and co-locates tasks tightly on nodes to fully utilize available resources. Extensive experiments on real-world datatrace from Alibaba cluster trace with information on task dependencies show the effectiveness, fast executions, and resource efficiency of our approach.
https://eprints.bournemouth.ac.uk/35747/
Source: BURO EPrints