English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Network Virtualization (NV) is an emerging network dynamic planning techniqueto overcome network rigidity. As its necessary challenge, Virtual NetworkEmbedding (VNE) enhances the scalability and flexibility of the network bydecoupling the resources and services of the underlying physical network. Forthe future multi-domain physical network modeling with the characteristics ofdynamics, heterogeneity, privacy, and real-time, the existing related worksperform satisfactorily. Federated learning (FL) jointly optimizes the networkby sharing parameters among multiple parties and is widely employed in disputesover data privacy and data silos. Aiming at the NV challenge of multi-domainphysical networks, this work is the first to propose using FL to model VNE, andpresents a VNE architecture based on Horizontal Federated Learning (HFL)(HFL-VNE). Specifically, combined with the distributed training paradigm of FL,we deploy local servers in each physical domain, which can effectively focus onlocal features and reduce resource fragmentation. A global server is deployedto aggregate and share training parameters, which enhances local data privacyand significantly improves learning efficiency. Furthermore, we deploy the DeepReinforcement Learning (DRL) model in each server to dynamically adjust andoptimize the resource allocation of the multi-domain physical network. InDRL-assisted FL, HFL-VNE jointly optimizes decision-making through specificlocal and federated reward mechanisms and loss functions. Finally, thesuperiority of HFL-VNE is proved by combining simulation experiments andcomparing it with related works.

Multi-Domain Virtual Network Embedding Algorithm based on Horizontal Federated Learning