Improving application support in 6G networks with CAPOM: Confluence-aided process organization method
Systems requiring terahertz transmission and high sampling capabilities can be supported by sixth-generation (6G) technology with minimal latency and excellent service throughput. Regardless of the distributions of data and services, High-Performance Computing (HPC) enhances speed and provides diver...
Saved in:
| Main Authors: | , , , |
|---|---|
| 格式: | Article |
| 語言: | English |
| 出版: |
Institute Of Electrical And Electronics Engineers Inc.
2023
|
| 在線閱讀: | http://eprints.utem.edu.my/id/eprint/27112/2/0270213092023353.PDF http://eprints.utem.edu.my/id/eprint/27112/ https://ieeexplore.ieee.org/document/10235956 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Systems requiring terahertz transmission and high sampling capabilities can be supported by sixth-generation (6G) technology with minimal latency and excellent service throughput. Regardless of the distributions of data and services, High-Performance Computing (HPC) enhances speed and provides diversified applications and functionality. The Confluence-Aided Process Organization Method (CAPOM) is suggested in this article to take advantage of process allocations while using an HPC paradigm. The process allocations and completions are scheduled based on prior and current system conditions to minimize waiting
time based on the 6G qualities. This implies that state requirements for process allocation, distribution, and completion are carried out with the assistance of federated learning. The initial state allocations are based on the user/application request; in other allocations, the application's request for completion time and capacity
for processing are considered. Offloading and shared processing are therefore combined to maximize resource
deliveries. The federated learning states are checked post-completion times to mitigate the waiting duration of dense service demands. Indicators such as distribution ratios, latency, wait time, and processing rate are considered for the effectiveness of the proofs. The suggested CAPOM achieves an 8.67% higher processing rate, 9.09% reduced latency, 8.76% less wait time, and a 6.73% higher distribution ratio for the various capacities. |
|---|