As SDN is increasingly widely used in various scenarios, a new challenge for SDN to support dynamic requirements of various applications begin to emerge. DT can enhance the capabilities of SDN in aspects of real-time analysis, deduction, and network control, and consequently satisfy the dynamic requirements of various applications. Whereas, current DT constructing schemes for SDN usually suffer from the challenges of strict delay constraint, heavy computing overhead, and low cooperating efficiency. To address the above issue, this paper proposed a novel variable granularity-digital twin(VGDT) according to the application requirement and available computing resource. Based on the distribution characteristic of the computing resource in the network, VGDT built a cooperatively optimizing model to ensure the delay and effectiveness of the DT for SDN. Then, this paper proposed a hybrid coding genetic algorithm to solve this model, which could achieve the best granularity and the DT placement policy. The simulation results show the performance of VGDT. Compared with current DT, VGDT has higher integrity and validity of digital twin model under limited computing resource.

[2022-05-16] Accepted Paper /doc/2022.02.0106/v1

[2022-10-05] Printed Article /doc/2022.02.0106/v2