A Study on Federated Learning for Efficient Communication Resource Allocation in 6G Heterogeneous Networks
| Project/Area Number |
22K17877
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 60060:Information network-related
|
|---|
| Research Institution | Tohoku University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2022-04-01 – 2026-03-31
|
| Project Status |
Granted (Fiscal Year 2023)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2025: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2024: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2023: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | Distributed Learning / Machine Learning / Computation Offloading / Satellite Networks / UAV Networks / Quantum Learning / 6G Networks / Network Management / Cloud Systems / Digital Twin / Federated Learning / Computer Networks |
|---|
| Outline of Research at the Start |
With more overlap between different cells in 6G, we need to carefully and smartly configure networks (deciding which frequency and access point to use). In this project, the applicant will use Federated Learning to minimize service delay and energy consumption, optimizing the performance.
|
| Outline of Annual Research Achievements |
This year, 5 papers were published, including two international conference papers. Progress was made in multiple directions. First, an important paper was published that explains how Digital Twins can be used for multiple applications, including the distributed training of learning models. Two papers were published explaining how deployed servers in satellites and aerial vehicles can help with distributed processing and distributed learning. One paper was published explaining how changes in the environment can impact the learning models. Finally, the use of quantum learning in distributed drone systems was also evaluated.
|
| Current Status of Research Progress |
Current Status of Research Progress
1: Research has progressed more than it was originally planned.
Reason
Work has progressed well in training Machine Learning and in using Distributed Learning. I also recruited two international exchange students that have been phenomenal in helping out with the results of this project.
|
| Strategy for Future Research Activity |
For the future, the implementation and use of Federated Learning models, especially in satellite environments, is scheduled.
|
Report
(2 results)
Research Products
(11 results)
