Abstract
Today, the 5G Internet era has arrived, and network virtualization technology has captured the attention of people. However, traditional single-domain virtual embedding technology generated huge overhead in embedding and caused a certain waste of resources. Therefore, for cutting virtual embedding overhead and improving the embedding efficiency, this paper proposes a new multi-domain embedding programme. For this scheme, firstly, to rationalize the use of physical resources to a higher degree, we set up a model for the embedding problem. Secondly, in order to obtain the optimal global solution, we introduce simulated annealing into the PSO algorithm, and distribute the particles through the particle initialization distribution strategy. In addition, for the parameter of inertia weight in the algorithm, we use the linear differential decline strategy to calculate. The experimental results show that compared with VNE-PSO algorithm, this scheme reduces the cost of virtual network mapping by 32.82%, increases the acceptance rate of virtual requests by 7%, and reduces the running time by 18.7%. This scheme maximizes the benefits.
Highlights
Today, the Internet of Things (IoT) technology is increasingly powerful, and network virtualization technology is advancing with the times
For the sake of solving the virtual network embedding (VNE) problem more effectively, this paper proposes an embedding programme based on hybrid particle swarm
The VNE-HPSO algorithm, particle initialization distribution strategy and linear differential reduction strategy of inertia weight proposed in this paper strikingly optimize the property about VNE, and play an important role in reducing the embedding overhead and improving the VR acceptance rate
Summary
The Internet of Things (IoT) technology is increasingly powerful, and network virtualization technology is advancing with the times. In the traditional network, forwarding and control functions are implemented by switches or routers at the bottom, while SDN realizes the separation of the forwarding plane and the control plane This network architecture makes it possible to clearly recognize the underlying network resources and greatly improve the embedding efficiency of virtual network requests. Due to many reasons such as confidentiality, the local controller does not provide complete domain information, so the VNE done by the global controller is vulnerable With regard to this problem, we propose a new VNE scheme for the multi-domain problem. P.Zhang et al et al.: VNE-HPSO: Virtual Network Embedding Algorithm Based On Hybrid Particle Swarm Optimization global solution. In response to this problem, this paper introduces a new embedding algorithm.
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
