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

The optimal multicast tree problem in the Software-Defined Networking (SDN)multicast routing is an NP-hard combinatorial optimization problem. Althoughexisting SDN intelligent solution methods, which are based on deepreinforcement learning, can dynamically adapt to complex network link statechanges, these methods are plagued by problems such as redundant branches,large action space, and slow agent convergence. In this paper, an SDNintelligent multicast routing algorithm based on deep hierarchicalreinforcement learning is proposed to circumvent the aforementioned problems.First, the multicast tree construction problem is decomposed into twosub-problems: the fork node selection problem and the construction of theoptimal path from the fork node to the destination node. Second, based on theinformation characteristics of SDN global network perception, the multicasttree state matrix, link bandwidth matrix, link delay matrix, link packet lossrate matrix, and sub-goal matrix are designed as the state space of intrinsicand meta controllers. Then, in order to mitigate the excessive action space,our approach constructs different action spaces at the upper and lower levels.The meta-controller generates an action space using network nodes to select thefork node, and the intrinsic controller uses the adjacent edges of the currentnode as its action space, thus implementing four different action selectionstrategies in the construction of the multicast tree. To facilitate theintelligent agent in constructing the optimal multicast tree with greaterspeed, we developed alternative reward strategies that distinguish betweensingle-step node actions and multi-step actions towards multiple destinationnodes.

DHRL-FNMR: An Intelligent Multicast Routing Approach Based on Deep Hierarchical Reinforcement Learning in SDN