Shuyun Wang

Network function virtualization (NFV) is an emerging technology that uses virtualization technology to provide various services in enterprise networks and reduce costs. However, in cloud edge networks, effective virtual network function (VNF) configuration is particularly difficult, and the system design needs to consider the reliability and energy-saving while meeting the requirements of Quality of Service (QoS). This paper uses the binary integer programming (BIP) model to study the service function chain (SFC) orchestration problem, and designs a federated deep reinforcement learning SFC orchestration algorithm (FDOA). With this method, energy consumption can be reduced and the QoS of users can be improved. In addition, considering the limitations of local deep reinforcement learning (DRL) model training, this paper proposes a federated DRL algorithm to help obtain a more robust model, and simultaneously improve the convergence speed of the model. Among them, we introduce reputation theory during model training to evaluate the reliability of the nodes carrying the DRL model, avoiding the influence of unreliable models on the training effect. Finally, the simulation results show that FDOA has better performance in training time and end-to-end delay compared with other existing algorithms.

Aiming at the limitations of the existing saliency detection algorithms in defining saliency features artificially and the poor robustness of the algorithm, a saliency detection algorithm based on deep convolutional neural network was proposed. Firstly, the VGG-16 model used for image classification is modified to make it applicable to significance detection. Then, the network is trained with super-pixel segmentation samples and the initial saliency graph is predicted. Finally, on the basis of preliminary significant image to join the regional contrast, increases significantly the difference of target and background region, further improve the quality of significant image. Compared with the existing algorithms, the proposed algorithm avoids the uncertainty of manually defining significant features, and has stronger robustness and generalization. The effectiveness of the proposed algorithm is demonstrated from two aspects of subjective qualitative observation and objective quantitative detection.