Novel techniques for modeling, programming and provisioning network services

5G should provide dramatic increase in bandwidth and decrease in latency to the end user applications. This poses serious challenges on the underlying networks and clouds that are currently being addressed through the concepts of network slicing and services at the edges. The recent paradigm shift in networking driven by SDN (Software Defined Networking), NFV (Network Function Virtualization), and the evolution of cloud technologies are a step in that direction to support service creation, development and provisioning. However, several essential components are still missing which are addressed by Ericsson Hungary. The EIT Digital Doctoral School announces thus an open position for an industrial doctorate in Budapest. The thesis aims to investigate application models and techniques within the emerging standard frameworks fostering service development and providing portability across cloud platforms, together with the orchestration methods responsible for deploying the service components on-the-fly even in multi-provider environments. A 6-month mobility at a European university or research institution is also part of the program.

Challenge

Future networked systems, encompassing cloud and fog infrastructures, IoT devices and wired/wireless networks connecting them, and envisioned 5G applications, such as remote surgery based on Tactile Internet or Industry 4.0 use-cases, pose serious challenges on the Telecom Operators. A diverse set of cloud and network resources owned by cooperating or competing providers should be orchestrated by the means of technical and business level interactions. Current cloud platforms accelerate the development of new services, however, the outsourcing of application functionalities, such as resiliency or scalability, into cloud platforms, in most cases results in cloud provider lock-in. Technical building blocks are provided by NFV and SDN in collaboration with evolved cloud platforms. However, creating and provisioning services spanning across multiple technology and administrative domains is not a trivial task, and concrete solutions are needed. Today’s Software as a Service solutions do not take networking related requirements (e.g., latency, bandwidth) into consideration which can be crucial in future applications. With the advent of 5G and network slicing this becomes possible. Hence the service description shall take this into account to enable flexible service creation and on-demand deployment together with the resource orchestration mechanisms satisfying strict SLA requirements.

Approach

The goal of the thesis is to provide enhanced and generally applicable solutions for service development, creation and orchestration exploiting emerging networking and cloud technologies and concepts, such as SDN, NFV, IaaS (Infrastructure as a Service), and FaaS (Function as a Service). It shall provide as well solutions for multi-operators environments since these will become the norm in the next decade. More exactly, the inter-operation among different compute- and network virtualization technologies needs technology-agnostic service and resource models which can be the glue between the main components of the new integrated system. In this thesis, the service and orchestration layers of the architecture are addressed. The exact tasks include i) the definition of new service/application models supporting network-related requirements and the composition of 3rd party and own software modules; ii) implementation of software components which can foster/simplify service development and provide a model based development environment; iii) the design and implementation of orchestration algorithms for deploying the software components of the services/applications on-the-fly even in multi-provider environments.

Expected outcome

The results of the PhD include approaches that offer portability across cloud platforms eliminating the problem of cloud platform provider lock-in, and software tools fostering service development. More specifically the expected results are the following: application/service models with advanced capabilities; compiler/translator providing automation for developers; orchestration algorithms usable by Ericsson in service offering; working and verified proof-of-concept prototypes and SW modules embeddable into Ericsson products; formal proofs on the correctness of the operation; published papers at top conferences/journals; and demos with prototypes at industry events.

Location

The doctoral student will reside in the EIT Digital Doctoral Training Centre in Budapest and share his/her time with the premises of Ericsson Hungary and the Budapest University of Technology and Economics. A 6-month mobility to a European university or research institution will be also part of the program.

Facts

  • Industrial partner: Ericsson Hungary Ltd.
  • Academic/research partner: Budapest University of Technology and Economics
  • Number of available PhD positions: 1 
  • Duration: 4 years
  • This PhD will be funded by EIT Digital, Budapest University of Technology and Economics, and Ericsson Hungary Ltd.

Apply

Those interested in applying should send an e-mail to zoltan.istenes@eitdigital.eu, including a CV, a motivation letter, and documents showing their academic track records. Please apply before April 20, 2018.

READ HERE THE FULL POSITION PAPER