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 slicing-based communication systems can dynamically and efficientlyallocate resources for diversified services. However, due to the limitation ofthe network interface on channel access and the complexity of the resourceallocation, it is challenging to achieve an acceptable solution in thepractical system without precise prior knowledge of the dynamics probabilitymodel of the service requests. Existing work attempts to solve this problemusing deep reinforcement learning (DRL), however, such methods usually requirea lot of interaction with the real environment in order to achieve goodresults. In this paper, a framework consisting of a digital twin andreinforcement learning agents is present to handle the issue. Specifically, wepropose to use the historical data and the neural networks to build a digitaltwin model to simulate the state variation law of the real environment. Then,we use the data generated by the network slicing environment to calibrate thedigital twin so that it is in sync with the real environment. Finally, DRL forslice optimization optimizes its own performance in this virtualpre-verification environment. We conducted an exhaustive verification of theproposed digital twin framework to confirm its scalability. Specifically, wepropose to use loss landscapes to visualize the generalization of DRLsolutions. We explore a distillation-based optimization scheme for lightweightslicing strategies. In addition, we also extend the framework to offlinereinforcement learning, where solutions can be used to obtain intelligentdecisions based solely on historical data. Numerical simulation experimentsshow that the proposed digital twin can significantly improve the performanceof the slice optimization strategy.

Digital Twin-Enhanced Deep Reinforcement Learning for Resource Management in Networks Slicing