Network Function Virtualization (NFV) is set to disrupt the current networking ecosystem by turning vertically-integrated middleboxes into software modules running on general purpose virtualized platforms. NFV will play a key role in future wireless and mobile networks where significant cost reductions can be obtained by virtualizing different layers and functions of the radio access and core network. Such goal raises several challenges in terms of both functional decomposition of the radio nodes and for the management and orchestration of the resulting network. In this work we present Scylla a high-level declarative language for programming network functions that allows programmers to implement per-flow custom packet processing. We also introduce a set of programming abstractions modeling the fundamental aspects of VNF orchestration. Finally, we present a proof-of-concept Controller and an SDK implementing the proposed abstractions.
Scylla: A Language for Virtual Network Functions Orchestration in Enterprise WLANs
Riggio, Roberto;Mohamed Rasheed, Tinku
2016-01-01
Abstract
Network Function Virtualization (NFV) is set to disrupt the current networking ecosystem by turning vertically-integrated middleboxes into software modules running on general purpose virtualized platforms. NFV will play a key role in future wireless and mobile networks where significant cost reductions can be obtained by virtualizing different layers and functions of the radio access and core network. Such goal raises several challenges in terms of both functional decomposition of the radio nodes and for the management and orchestration of the resulting network. In this work we present Scylla a high-level declarative language for programming network functions that allows programmers to implement per-flow custom packet processing. We also introduce a set of programming abstractions modeling the fundamental aspects of VNF orchestration. Finally, we present a proof-of-concept Controller and an SDK implementing the proposed abstractions.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.