Co-hosted at The 4th IEEE International Conference on Network Softwarization (NetSoft 2018) will be held on June 25-29, 2018 at Concordia University in Montreal, Canada. IEEE NetSoft has been created as a flagship conference aiming at addressing “Softwarization" of networks and systemic trends concerning the convergence of Cloud Computing, Software-Defined Networking (SDN), and Network Function Virtualization (NFV).
S4SI aims at providing an international forum for researchers and practitioners from academia, industry, network operators, and service providers to discuss and address the advances and the challenges in the field of Slicing plus its emerging scenarios whereby systems, services, and workflows used in both computing and communications domains are converging and can benefit from the new techniques and strategies of infrastructure softwarization.
The current trend of convergence between computing and networking eco-systems puts software into an unprecedented and dominant role in communication environments. Computing, storage, connectivity services along with application instances are foreseen to be deployed in the form of slices of virtualized assets within a so-called Software-Defined Infrastructure (SDI) leveraging general-purpose processing and communication hardware, as well as cutting-edge advances in programmable devices, altogether being managed and made available under “As-a-Service” paradigms in spirit of Cloud Computing. One of the current trends in this space is the concept of a Slice. This has drawn much attention from many people interested in this important and developing area.
The S4SI workshop addresses both the advances and challenges related to Slicing in Softwarized Infrastructures for faster and improved deployment of services in current and future 5G environments.
The advances and challenges are expected to be multiple, and there are clearly many open questions that need to be addressed, including:
- What are the abstractions and models needed to endure slicing is deployable in networks;
- What are the end-to-end issues that need to be addressed to allow slicing everywhere;
- How do the existing technologies of computing, networking, and storage, become elements of a slice, and how are they managed in this context
- Is it better to adapt existing components to support slicing, or is it better to design new ones
The workshop S4SI aims at addressing the multiple open questions around the realization of end-to-end sliced softwarized infrastructures and the fundamental challenges that will facilitate the envisioned intelligent orchestration and programmability of SDI, enabling faster deployment and efficient operation of integrated services across different resource domains. Such advances in future ecosystems, like 5G, are expected to enable dynamic establishment of generalized virtual function chains, according to service requirements.
The challenges are many-fold, with diverse open questions in the areas of:
- End-to-end Infrastructure Slicing, from concepts to realization;
- Softwarization of Multi Domain SDI (MD-SDI), which requires unified management of computing, storage, and network resources for the effective deployment, lifecycle management, and run-time configuration of services;
- Algorithms for self-management and orchestration of service requests mapping onto Sliced virtualized resources and network functions;
- Adaptation and optimization mechanisms, which must be enforced at global and/or local level for coping with user demand, application requirements, resource unavailability, etc in the context of Slicing;
- Platforms for analyzing and storing logs and operational data from Sliced and multi domain sources.
Big Data Analytics are being applied to harness the immense stream of operational data from the Sliced infrastructure in order to perform analytics processing to improve reliability, configuration, orchestration, performance, and security management of slices. To this end, further research is needed to effectively realize the integration of Slicing with intelligent mechanisms based on data collected from the SDI itself.