Learning-Based Reservation of Virtualized Network Resources

Abstract

Network slicing markets have the potential to increase significantly the utilization of virtualized network resources and facilitate the low-cost deployment of over-the-top services. However, their success is conditioned on the service providers (SPs) being able to bid effectively for the virtualized resources. In this paper, we consider a hybrid advancereservation and spot slice market and study how the SPs should reserve resources to maximize their services' performance while not violating a time-average budget threshold. We consider this problem in its general form where the SP demand and slice prices are time-varying and revealed only after the reservations are decided. We develop a learning-based framework, using the theory of online convex optimization, that allows the SP to employ a no-regret reservation policy, i.e., achieve the same performance with an oracle that has full access to all future demand and prices. We extend the framework to the scenario where the SP decides dynamically its slice orchestration and hence needs to learn the performance-maximizing resource composition; and we further develop a mixed-time scale scheme that allows the SP to leverage spot-market information that is revealed between successive reservations. The proposed learning framework is evaluated using representative simulation scenarios that highlight its efficacy as well as the impact of key system and algorithm parameters.

Reservation of Virtualized Resources with Optimistic Online Learning

“…These works presume a stationary environment where user statistics do not change and/or cost of resources are supposed constant. This paper differs from our previous works [19], [20], as we now use prediction to support the reservation model.…”

Construction of an Event Knowledge Graph Based on a Dynamic Resource Scheduling Optimization Algorithm and Semantic Graph Convolutional Neural Networks

“…KVM is loaded into the Libvirt kernel in the form of a driver module, making the Libvirt kernel an efficient virtual machine monitor and QEMU for device virtualization. Loading the hypervisor and Hyper-visor controls virtual resources after constructing the virtualized resource pool [48]. Immediately following this, the Device plugin enables kubernetes to properly schedule pods to GPU and CPU resource nodes based on constraints.…”