Cost-Aware and AI-based Resource Prediction in Softwarized Networks

Resource prediction algorithms have been recently proposed in Network Function Virtualization Architectures. An prediction-based resource allocation is characterized by higher operation costs due to: i) resource underestimate that leads to Quality of Service degradation; ii) used cloud resource over allocation when a resource overestimate occurs. To reduce such a cost, we propose cost-aware prediction algorithm able to minimize the sum of the two cost components previously mentioned. We compare in a real network and traffic scenario the proposed technique to the traditional one in which the Root Mean Squared Error. We show home the proposed solution allows for cost advantages in the order of 20%.