Design and Implementation of an Elastic Monitoring Architecture for Cloud Network Slices

A key feature of the cloud network slicing concept is the dynamic (de)provision of end-to-end infrastructures composed by computing, network, and storage resources, in order to meet the service needs of a variety of vertical industries. The resulting resource ensemble needs to be instantiated over a (potentially large) number of administrative and technological domains – a complex challenge for the management and orchestration of the allocated resources. Resource monitoring in this new so-called slice entity is extremely important in order to address the above operations. Therefore, in this work, we discuss the design and implementation of an elastic architecture for the monitoring of physical and virtual resources in cloud network slices that span both multiple administrative and technological domains. Since the concept of cloud network slices is quite recent in the literature, we highlight that our results present the performance evaluation of the proposed monitoring architecture when instantiating, stopping or performing elasticity operations on the slices. Additionally, we also analyze the performance of the architecture by scaling the number of metrics being monitored in overloaded scenarios.