An Adaptive Hybrid Optimization Strategy for Resource Allocation in Network Function Virtualization.

With the rapid development of Network Function Virtualization (NFV), the problem of low resource utilization in traditional data centers is gradually being addressed. However, existing research does not optimize both local and global allocation of resources in data centers. Hence, we propose an adaptive hybrid optimization strategy that combines dynamic programming and neural networks to improve resource utilization and service quality in data centers. Our approach encompasses a service function chain simulation generator, a parallel architecture service system, a dynamic programming strategy for maximizing the utilization of local server resources, a neural network for predicting the global utilization rate of resources and a global resource optimization strategy for bottleneck and redundant resources. With the implementation of our local and global resource allocation strategies, the system performance is significantly optimized through simulation. [ABSTRACT FROM AUTHOR]