Network Traffic Prediction in an Edge–Cloud Continuum Network for Multiple Network Service Providers

Network function virtualization (NFV) allows the dynamic configuration of virtualized network functions to adapt services to complex and real-time network environments to improve network performance. The dynamic nature of physical networks creates significant challenges for virtual network function (VNF) migration and energy consumption, especially in edge–cloud continuum networks. This challenge can be addressed by predicting network traffic and proactively migrating VNFs using the predicted values. However, historical network traffic data are held by network service providers, and different network service providers are reluctant to share historical data due to privacy concerns; in addition, network resource providers that own the underlying networks are unable to effectively predict network traffic. To address this challenge, we apply a federated learning (FL) framework to enable network resource providers to no longer need historical network traffic data to be able to effectively predict network traffic. Further, to enable the predicted network traffic to lead to better migration effects, such as reducing the number of migrations, decreasing energy consumption, and increasing the request acceptance rate, we apply the predicted values of the network traffic to the network environment and feed the migration results of the network environment on the multiple factors described above to the neural network model. To obtain the migration results of the network environment, we analyzed and developed mathematical models for edge–cloud continuum networks with multiple network service providers. The effectiveness of our algorithm is evaluated through extensive simulations, and the results show a significant reduction in the number of migrated nodes and energy consumption, as well as an increase in the acceptance rate of the service function chain (SFC), compared with the commonly used scheme that uses only the difference between the predicted and actual traffic to define the loss function.