Cross stratum optimization for software defined multi-domain and multi-layer optical transport networks deploying with data centers

Yang, Hui; Zhang, Jie; Zhao, Yongli; Han, Jianrui; Lin, Yi; Lee, Young

doi:10.1016/j.osn.2015.10.006

Cited by 7 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The value of OSNR can be calculated by analytical formula through the measured power and noise, which is limited by whether the power and noise can be accurately calculated. In reference [4], it is proposed to monitor OSNR indexes through high-order statistical moments. However, as the evolution process of optical network technology, traditional OSNR monitoring acquisition method does not capture the many important OSNR characteristics.…”

Section: Introductionmentioning

confidence: 99%

OSNR Prediction Based on Federal Learning in Multi-Domain Optical Networks

Huang

Zhu

Zhou

et al. 2021

Proceedings of CECNet 2021

Self Cite

View full text Add to dashboard Cite

With the continuous expansion of the scale of optical communication network and the rapid increase of network traffic demand, the management form of multi-domain optical network has widely existed. OSNR is an important indicator to judge the quality of communication. It is very important to predict OSNR more accurately in a low-cost and energy-saving way in multi-domain optical networks. In this paper, a scheme of federal learning in multi-domain optical networks is proposed to improve the accuracy of the OSNR prediction. The main idea is to train hybrid machine learning model in each single domain, then the strategy of federal learning is used for optimization it in multi-domains. The performance of the proposed scheme is verified by simulation experiments. The strategy can alleviate the problems of data silos and model training set caused by multi-domain optical network. According to simulation result, when the amount of data reaches 5×103, adding this strategy will reduce the mean square error of the prediction model by about 18%. It can improve the performance of machine learning model, the ability of OSNR prediction and the reliability of network operation.

show abstract

Section: Introductionmentioning

confidence: 99%