Since the emergence of Cloud Computing and the associated Over-The-Top (OTT) valueadded service providers more than a decade ago, the architecture of the communication infrastructure − namely the Internet and the (mobile) telecommunication infrastructure – keep improving with computing, caching and networking services becoming more coupled. OTTs are moving from being purely cloud-based to being more distributed and residing close to the edge, a concept known to be “Fog Computing”. Network operators and telecom vendors advertise the “Mobile Edge Computing (MEC)” capabilities they may offer within their 5G Radio-Access and Core Networks. Lately, the GAFAM (Google, Apple, Facebook, Amazon and Microsoft) came into the play as well offering what is known as Smart Speakers (Amazon Echo, Apple HomePod and Google Home), which can also serve as IoT hubs with “Mist/Skin Computing” capabilities. While these have an important influence on the underlying network performances, such computing paradigms are still loosely coupled with each other and with the underlying communication and data storage infrastructures, e.g., even for the forthcoming 5G systems. It is expected that a tight coupling of computing platforms with the networking infrastructure will be required in post-5G networks, so that a large number of distributed and heterogeneous devices belonging to different stakeholders communicate and cooperate with each other in order to execute services or store data in exchange for a reward. This is what we call here the smart collaborative computing, caching and networking paradigm. The objective of SCORING project is to develop and analyse this new paradigm by targeting the following research challenges, which are split into five different strata:
- At the computing stratum: Proactive placement of computing services, while taking into account users mobility as well as per-computing-node battery status and computing load;
- At the storage stratum: Proactive placement of stores and optimal caching of contents/functions, while taking into account the joint networking and computing constraints;
- At the software stratum: Efficient management of micro-services in such a multi-tenant distributed realm, by exploiting the Information-Centric Networking principles to support both name and compute function resolution;
- At the networking stratum: Enforcement of dynamic routing policies, using Software Defined Networking (SDN), to satisfy the distributed end-user computation requirements and their Quality of Experience (QoE);
- At the resource management stratum: Design of new network-economic models to support service offering in an optimal way, while considering the multi-stakeholder feature of the collaborative computing, caching and networking paradigm proposed in this project. Smartness will be brought here by using adequate mathematical tools used in combination for the design of each of the five strata: machine learning (proactive placement problems), multi-objective optimization, graph theory and complex networks (information-centric design of content and micro-services caching) and game theory (network-economics model).
Demonstration of the feasibility of the proposed strata on a realistic and integrated testbed as well as on an integrated simulation platform (based on available open-source network-simulation toolkits), will be one of the main goals of the project. The test-bed will be built by exploiting different virtualization (VM/Containers) technologies to deploy compute and storage functions within a genuine networking architecture. Last but not least, all building blocks forming the realistic and integrated test-bed, on the one hand, and the integrated simulation platform, on the other hand, will be made available to the research community at the end of the project as open source software.
Start date: (36 months)
Funding support: 585 280 €
- L3i - La Rochelle Université - France
- Université du Québec à Montréal - Canada
- Concordia University - Canada
- Sabanci Universitesi - Turkey