1. The article discusses the design and implementation of a novel DCN system, which utilizes a knowledge-defined NO-M to operate a HOEDCN cost-effectively and energy-efficiently.
2. To realize the knowledge-defined NO-M, three artificial intelligence modules based on deep learning are designed and made to operate collaboratively.
3. Experiments conducted in a network testbed demonstrate that the HOE-DCN simultaneously achieves high performance service provisioning and improved energy efficiency.
The article is generally reliable and trustworthy, as it provides detailed information about the design and implementation of a novel DCN system, which utilizes a knowledge-defined NO-M to operate a HOEDCN cost-effectively and energy-efficiently. The authors provide evidence for their claims by conducting experiments in a network testbed that demonstrate the advantages of the proposed HOE-DCN system. Furthermore, they analyze the pros and cons of the HOE-DCN system, pointing out several directions to work on in the future.
However, there are some potential biases in the article that should be noted. For example, while discussing possible solutions for scalability, energy efficiency, and manageability issues in existing DCNs, only one solution (i.e., HOE-DCN) is presented without exploring other alternatives or counterarguments. Additionally, there is no discussion about possible risks associated with using AI modules for network orchestration or any potential drawbacks of using deep learning algorithms for this purpose. Moreover, while discussing advantages of HOE-DCN system over existing DCNs, only positive aspects are highlighted without presenting both sides equally or exploring any unexplored counterarguments.