The upcoming 5th generation of networks (5G) is expected to be the backbone and enabler of many innovative services, ranging from those that require ultra-low latency to those with ultra-high bandwidth demands. This performance evolution comes primarily from new enhancements in the radio layer, but its innovation potential emerges from new paradigms deployed in the upper layers of the 5G networks where concepts and technologies comparable to those deployed in the cloud infrastructure are being used. 5G networks completely embrace the virtualisation of services building upon virtual machines and more recently containerised services. In 5G jargon, this is called Network functions Virtualisation (NFV) or Network Functions containerisation (NFC). Sets of NFV/NFC are composed to deploy and propose new Network Services (NS) targeting specific needs on top of a 5G network.

The latest years, lot of work has been realised for the design and implementation of profiling approaches for cloud computing applications, focusing mainly on resource efficiency aspects and optimal infrastructure setup to serve the applications workload. Similar approaches are being adopted in the 5G world and especially in the NFV community, where specifications evolve with regards to standard mechanisms for realising analysis. Following this trend, within 5GTANGO, we have designed and implemented an Analytics Engine, supporting the execution of various analysis processes. The objective is to get analysis insights that lead to the design of efficient policies and introduce automation within orchestration mechanisms.

 

These insights cover many different aspects, including identification of resources consumption trends and capacity limits through Resource Efficiency Analysis, evaluation of the performance gain achieved upon scaling actions through Elasticity Efficiency Analysis, identification of thresholds for proactive decision making based on formulation, training and evaluation of Machine Learning Models, design of forecasting models upon Time Series Decomposition as well as identification of unforeseen correlations among VNF-specific and resources usage metrics based on Correlation Analysis. Automation can be introduced in orchestration mechanisms and DevOps processes based on the exploitation of the provided outcomes (e.g. elasticity actions triggered based on machine learning models). Autonomic functionalities based on the design and implementation of control loops that are considering the current state and the potential actions that can be realised per decision making entity for satisfying performance objectives can be designed, exploiting feedback provided by Reinforcement Learning mechanisms.

The necessity to monitor Network Services in the 5G ecosystem


In the next years, 5G infrastructure will become a ubiquitous, flexible and programmable network that will be in the core of every social, business and cultural process, enabling both economic growth and social prosperity. However, the 5G vision poses significant technical challenges that must be fulfilled, including the concept of agile programmability and supporting the introduction of management mechanisms for the efficient instantiation of innovative services across heterogeneous network components, virtualized infrastructures and geographically dispersed cloud environments.

Modern applications, from critical Internet of Things (IoT) systems to real time multimedia communications, require low and stable latencies in order to be useful. 5G will bring more bandwidth at very low latencies which will enable new use cases and enhance the performance of applications which are currently used over 4G.

Apart from the air segment where 5G brings a significative improvement, the Network Functions Virtualization (NFV) architectures associated to running the services must be able to warrant that latency values are contained within a range of tolerable values. 5GTANGO puts special focus on innovative strategies to deal with the different network requirements of a wide range of applications from the Sonata NFV Service Platform. This means that the operator will not only be able to use different quality of service (QoS) defined by 5QI values from the device to the 5G Core, but also in the NFV platform.

A key objective of 5G and Software Defined Networking (SDN) technologies is the provision of Quality of Service (QoS) guarantees. These guarantees are reflected to the requirements emerging from the agreements between the customers and service providers, the corresponding Service Level Agreements (SLAs). While traditional SLAs included aspects for example regarding data center availability of "five 9s", or five minutes of downtime per year [1], a 5G-driven SLA includes additional aspects related both to the infrastructure and to the provisioned services, as for example: “five 9s availability” while also “2 seconds to deploy a new Service Instance”.
But what is an SLA? An SLA is a contract between the Network Service (NS) provider and the customer, which underlines each party’s responsibilities while at the same time defining the performance standards that are to be met by the provider [2]. SLAs establish customer expectations regarding the service provider's performance and overall quality. Over the past few years, SLAs set the expectations for a service provider performance, establish penalties for missing the targets and, in some cases, bonuses for exceeding them. In that concept, SDN explosion could not leave unaffected the evolution of SLA models, and their flexibility in adapting more demanded parameters. 5GTANGO is a frontrunner in defining SLAs for 5G environments, by introducing a complete SLA Management Framework, in order to fulfill the gap between NS providers and their customers [3].

We use cookies to facilitate navigation and improve your experience across our website. By clicking "Accept", you will be storing these cookies.
More information Accept Decline