SYNC: Synergistic Network Policy Management for Cloud Data Centres

All computer networks, including cloud data centre networks, are governed by high-level policies derived from network-wide requirements, such as "file servers should only be accessible by internal IP (Internet Protocol) addresses". Upon deployment, an individual policy is realised as a composition (or chain) of network packets processing rules that will be placed in a specified sequence of network function boxes within the network.

Traditionally, implementing network policy is an error-prone manual configuration process. Emerging technologies such as Software-Defined Networking (SDN) and Network Function Virtualisation (NFV) have largely eliminated the need of manual configuration through software automation. Nevertheless, the use of SDN and NFV have resulted in greater number of independent network nodes that dynamically generate and implement policy rules respectively, making correct policy implementation a hard problem to solve. Worse still, this problem is amplified by the dynamic virtual machine (VM) consolidation in cloud data centre since migrating VMs means that the "specified sequence" must also be updated across the network. Imperfect policy implementation will lead to policy violation that attributes to 78% of data centre downtime, which costs $5,600(£3,758) per minute.

This demonstrates the necessity of synergistic placement of network policy rules and application VMs, as captured in the SYNC project hypothesis: Infrastructural configuration and utilisation as well as application performance of cloud data centres is largely dictated by the placement of network policy rules and application virtual machines. This is in contrast to the existing approaches which either only consider static rules placement, or perform dynamic placement without taking into account the application VMs.

In this project, we propose the development of SYNC, a synergistic network policy management framework that will lever synergy amongst a) policy rules, b) applications and c) underlying temporal network state for achieving network-wide performance optimisation. In order to realise SYNC, the following research and development tasks will take place:
i). The high-level network policy expressions will be decomposed into minimum set of network-wide consistent chains of rules, which are in turn implemented in network function boxes at different network locations, e.g. middleboxes, network switches, and end hosts.
ii). The underlying network state will be exploited to (re)arrange application virtual machines and rules so that the network-wide impact of pairwise traffic patterns is minimised.

The key challenge in this innovation will be the scale of the underlying infrastructure, which can have up to a million VMs and millions of rules. We will construct appropriate models and efficient algorithms, combined with SDN and NFV overcome this challenge.

We intend to publish research outcome in prestigious journals and conferences, provide open-access to the research data, and commercialise our intellectual property.

EPSRC's Towards an Intelligent Information Infrastructure (TI3) emphasises on smarter computing architectures, sustainable networks and secure storage solutions in order to resolve telecommunications bottlenecks in the presence of the future digital society. The research described here will contribute to the development of intelligent communications infrastructures.

Short term benefit within the next 3-10 years include direct interest from:
1). UK data centres: Data centres are now a critical part of the ICT infrastructure, vital to economic growth and productivity. The UK is a major user and operator of data centres and is home to 239 data centre (http://www.datacentermap.com/united-kingdom/). The largest data centre in Europe is based in Newport, Wales. Also, Microsoft and Amazon are reportedly to build data centres in the UK (http://goo.gl/H6iUvO). Our SYNC framework will have an immediate impact on improving the reliability and performance of these cloud infrastructures that users will increasingly access in a fully transparent manner. Improving service delivery of data centre networks will have a significant impact on a) the accessibility of the global infrastructure since it will underpin the development of novel applications and, b) charging/pricing models for Cloud Computing.

2). Private sector IT companies: The research described in this proposal contributes directly to the Digital economy theme (ICT Network and Distributed Systems; Cloud Computing) of the EPSRC portfolio. The work is primarily aligned with the IT as a Utility challenge area. We will enable technology that gives UK private sector companies a competitive advantage in the area of ever growing cloud computing. Small and medium enterprises, such as our project partner BrightOffice, can benefit directly via embedding our research in their products, or advancing on our research methodologies during their research and development cycles.

3). Our researchers and project students: Postdoctoral researcher and project student directly involved in this project will learn transferable skills, gain experiences, forge collaborations, in preparation for the job market. To further generate a pipeline of researchers and professional engineers with a strong background in data centre networking technologies, we will engage undergraduate and masters level students with the project.

Long term benefit within the next 10-50 years include direct interest from:
1). Government and public sectors: Many of which use private clouds and will rely on highly available information networks. Our techniques will give greater confidence on the network resiliency and audibility of established networking requirements in shared public cloud infrastructure. This will enable companies and government to move more of their critical infrastructure onto the cloud to exploit the economy of scale. For example NHS could speedup modernisation via hosting computation and huge volume of data to one or more of the UK's data centres.

2). The UK economy: Our research will have direct impact on new economic models for sustainable IT. Alongside mega data centres, another branch of cloud development is moving towards more distributed but federated manner. Being able to provide flexibility in network policies/functions management in multi-sovereignty federated cloud settings will be equally, if not more, important. Advance building upon our research will improve both of performance and lifetime of mission-critical data centre network and compute infrastructures. Hence the UK economy will benefit from lowered cloud computing costs and increased adoption.

3). UK citizens: The resilient cloud infrastructures will underpins future development of Internet of things, smart cities, e-governance, etc., which promotes digital living.