A Service Oriented Framework for Efficient Resource Orchestration in Future Optical Networks

Abstract

The future Internet evolution is driven by applications that require simultaneous real-time access to multiple heterogeneous IT (e.g. computing and storage) resources interconnected by high-speed optical networks. Service oriented architectural frameworks have been considered to improve service delivery in this environment by organising distributed heterogeneous resources owned by multiple providers. In this paper, we discuss a service oriented architectural framework tailored to the needs of future Internet applications. The framework introduces the capability to orchestrate the provisioning of distributed heterogeneous resources owned by multiple providers. Central to the framework is a novel resource orchestration model. This model focuses on the optimized selection of heterogeneous IT and network resources owned by different Infrastructure Providers (InPs). The proposed model aims to achieve a global optimum from both the end-users’ and InPs’ point of view across different administrative domains. An integer linear program (ILP) is formulated to obtain optimal results that maximizes the number of accepted requests while minimising resource usage. It is compared against a co-scheduling ILP model, whose objective is to maximise the number of accepted requests only. We then propose a heuristic solution for scalability. Its performance is compared against (i) our proposed ILP (ii) a co-scheduling heuristic that aim to maximise the number of accepted requests only and (iii) an algorithm that does not take into account cross-domain optimisations. Finally, two online algorithms for operational scenarios is proposed which outperforms three benchmark algorithms.