Abstract
The optimum utilization of infrastructural resources is a highly desired yet cumbersome task for service providers to achieve. This is because the optimal amount of such resources is a function of various parameters, such as the desired/agreed quality of service (QoS), the service characteristics/profile, workload and service life-cycle. The advent of frameworks that foresee the dynamic establishment and placement of service and network functions further contributes to a decrease in the effectiveness of traditional resource allocation methods. In this work, we address this problem by developing a mechanism which first performs service profiling and then a prediction of the resources that would lead to the desired QoS for each newly deployed service. The main elements of our approach are as follows: (a) the collection of data from all three layers of the deployed infrastructure (hardware, virtual and service), instead of a single layer of the deployed infrastructure, to provide a clearer picture on the potential system break points, (b) the study of well-known container based implementations following that microservice paradigm and (c) the use of a data analysis routine that employs a set of machine learning algorithms and performs accurate predictions of the required resources for any future service requests. We investigate the performance of the proposed framework using our open-source implementation to examine the case of a Hadoop cluster. The results show that running a small number of tests is adequate to assess the main system break points and at the same time to attain accurate resource predictions for any future request.
Highlights
In the context of Network Function Virtualization (NFV), a Network Service (NS), consists of a chain of interconnected Virtual Network Functions (VNF)
The service profiling and accurate performance prediction is a problem which extends to various service categories, such as networking, security, big data, storage, emulation, etc., and the solution we propose here can be adapted to any service category as it is based on open-source technology and it is modular, while it shows a great deployment flexibility
We first examine the data collected from all three layers during the service profiling phase (Section 4.3.1) and we import these data into the six Machine Learning (ML) algorithms in order to perform predictions about the selected metrics (Section 4.3.2)
Summary
In the context of Network Function Virtualization (NFV), a Network Service (NS), (e.g., router, firewall, cache server etc.), consists of a chain of interconnected Virtual Network Functions (VNF). This prediction will define the precise point at which the number of resources allocated ensures both a compliance with the agreed Service Level Agreement (SLA) and zero underutilization, which, on one hand, will avoid resource over-allocation and on the other hand will avoid the under-allocation of resources which may lead to a violation of the SLA The definition of this “critical point” is a complex problem as it requires (a) an extensive NS profiling for a large number of configurations, (b) the monitoring of a vast amount of system metrics from different sources, such as bare metal, virtual machines, containers, services, networking, etc., and (c) an integrated platform which can perform data analysis for all the monitored metrics and can extract the most significant metrics that can potentially lead to a QoS degradation.
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
