Abstract
Network function virtualization (NFV) enables flexible deployment of virtual network function (VNF) in 5G mobile communication network. Due to the inherent dynamics of network flows, fluctuated resources are required to embedding VNFs. VNF migration has become a critical issue because of the time-varying resource requirements. In this paper, we propose a real-time VNF migration algorithm based on the deep belief network (DBN) to predict future resource requirements, which resolves the problem of lacking effective prediction in the existing methods. Firstly, we propose optimizing bandwidth utilization and migration overhead simultaneously in VNF migration. Then, to model the resource utilization that evolves over time, we adopt online learning with the assistant of offline training in the prediction mechanism, and further introduce multi-task learning (MTL) in our deep architecture in order to improve the prediction accuracy. Moreover, we utilize adaptive learning rate to speed up the convergence speed of DBN. For the migration, we design a topology-aware greedy algorithm with the goal to optimize system cost by taking full advantage of the prediction result. In addition, based on tabu search, the proposed migration mechanism is further optimized. Simulation results show that the proposed scheme can achieve a good performance in reducing system cost and improving the service level agreements (SLA) of service.
Highlights
With the widespread access of mobile terminals and rapid development of internet technologies, there will be a tremendous growth in the amount of mobile transmission data
This paper firstly proposes a topology-aware algorithm for global dynamic migration to migrate virtual network function (VNF) to physical node that satisfies the constraint of resource threshold through greedy selection, and optimize the migration strategy by using the obtained solution as the initial solution based on tabu search algorithm [35]
In order to verify the performance of deep belief network (DBN) prediction model and the migration algorithm proposed in this paper, we use the superposition of sinusoidal and cosine signals to simulate the sample data of service function chain (SFC) resource requirements and discretize it
Summary
With the widespread access of mobile terminals and rapid development of internet technologies, there will be a tremendous growth in the amount of mobile transmission data. Since RBM can make full use of non-labeled data in pre-training as a generation model, DBN has the capability of processing big data and mining hidden information depended on the multiple layer structure which are inherent in deep learning, and can extract nonlinear features of samples more effectively It solves the problems exist in other neural network models those require a large amount of labels and fall into local optimal solution quickly as the number of layers increase. Adaptive learning rate is adopted to speed up convergence rate of RBM; 3) According to the prediction results, we propose a topology-aware migration algorithm in which VNFs are migrated to physical nodes meeting resource threshold constraints through greedy selection with the goal to optimize system cost, and using the strategy obtained above as the initial solution, an optimization algorithm of migration based on tabu search is designed to further improve the efficiency.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
