A Method for Online Monitoring Data Release of Composite Submarine Cable Based on Horizontal Federated Learning
-
Published:2023-09-10
Issue:3
Volume:24
Page:389-397
-
ISSN:1895-1767
-
Container-title:Scalable Computing: Practice and Experience
-
language:
-
Short-container-title:SCPE
Author:
Lao Xinli,Zhang Jiajian,Gao Chuanlian,Deng Huakun,Wei Yanlei,Liu Zhenzhong
Abstract
Conventional online composite submarine cable monitoring data release mostly adopts the method and principle of blockchain dynamic zoning consensus. In the data release process, there are omissions, and it takes a long time to complete the task, which reduces the timeliness of online composite submarine cable monitoring data release. Based on this, a new data publishing method is proposed by introducing horizontal federation learning. First, the online monitoring data of composite submarine cables are collected and preprocessed to eliminate the high-frequency capacitive effect of submarine cables. Secondly, manage composite submarine cable data nodes, transform the status relationship of data nodes, and ensure the quality of subsequent data release. A horizontal federation learning model is established to design the online monitoring data release process. The experimental results show that the new data release method is highly feasible. With the increasing online monitoring data of composite submarine cables, the time required for data release is short, and the timeliness is high.
Publisher
Scalable Computing: Practice and Experience
Subject
General Computer Science