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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Digital twins (DTs) constitute a critical link between the real-world and themetaverse. To guarantee a robust connection between these two worlds, DTsshould maintain accurate representations of the physical applications, whilepreserving synchronization between real and digital entities. In this paper, anovel edge continual learning framework is proposed to accurately model theevolving affinity between a physical twin (PT) and its corresponding cyber twin(CT) while maintaining their utmost synchronization. In particular, a CT issimulated as a deep neural network (DNN) at the wireless network edge to modelan autonomous vehicle traversing an episodically dynamic environment. As thevehicular PT updates its driving policy in each episode, the CT is required toconcurrently adapt its DNN model to the PT, which gives rise to ade-synchronization gap. Considering the history-aware nature of DTs, the modelupdate process is posed a dual objective optimization problem whose goal is tojointly minimize the loss function over all encountered episodes and thecorresponding de-synchronization time. As the de-synchronization time continuesto increase over sequential episodes, an elastic weight consolidation (EWC)technique that regularizes the DT history is proposed to limitde-synchronization time. Furthermore, to address the plasticity-stabilitytradeoff accompanying the progressive growth of the EWC regularization terms, amodified EWC method that considers fair execution between the historicalepisodes of the DTs is adopted. Ultimately, the proposed framework achieves asimultaneously accurate and synchronous CT model that is robust to catastrophicforgetting. Simulation results show that the proposed solution can achieve anaccuracy of 90 % while guaranteeing a minimal desynchronization time.

Edge Continual Learning for Dynamic Digital Twins over Wireless Networks