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

Online Network Resource Allocation (ONRA) for service provisioning is afundamental problem in communication networks. As a sequential decision-makingunder uncertainty problem, it is promising to approach ONRA via ReinforcementLearning (RL). But, RL solutions suffer from the sample complexity issue; i.e.,a large number of interactions with the environment needed to find an efficientpolicy. This is a barrier to utilize RL for ONRA as on one hand, it is notpractical to train the RL agent offline due to lack of information about futurerequests, and on the other hand, online training in the real network leads tosignificant performance loss because of the sub-optimal policy during theprolonged learning time. This performance degradation is even higher innon-stationary ONRA where the agent should continually adapt the policy withthe changes in service requests. To deal with this issue, we develop a generalresource allocation framework, named RADAR, using model-based RL for a class ofONRA problems with the known immediate reward of each action. RADAR improvessample efficiency via exploring the state space in the background andexploiting the policy in the decision-time using synthetic samples by the modelof the environment, which is trained by real interactions. Applying RADAR onthe multi-domain service federation problem, to maximize profit via selectingproper domains for service requests deployment, shows its continual learningcapability and up to 44% performance improvement w.r.t. the standard model-freeRL solution.

Model-Based Reinforcement Learning Framework of Online Network Resource Allocation