Enabling intent to configure scientific networks for high performance demands

Abstract

Globally distributed scientific experiments usually involve massive data volumes and distributed data analysis being done by many collaborators. With complex workloads and heterogeneous resources, each user may require certain characteristics for their network paths. In this paper, we present the iNDIRA tool, which interacts with SDN northbound interfaces to enable intent-based networking. It provides reliable, simple, and technology-agnostic communication between users and networks. Focusing particularly on science applications, iNDIRA uses natural language processing to construct semantic RDF graphs to understand, interact, and create the required network services. The technical challenges addressed by iNDIRA are: (1) development of a high-level descriptive language to query for network-application requirements, (2) keyword identification and condition checking based on user profiles and topology details, (3) allow user negotiation based on the current network state, (4) provide network provisioning guidance, and finally, (5) automatically provision and monitor a layer-2 network path for use by the application. iNDIRA is implemented on the ESnet network, where it interacts with OpenNSA (aka the NSI client) and Globus data transfer tools, to build complex cross-domain network paths for heterogeneous science applications and perform secure data transfer. We describe our implementation of iNDIRA running on ESnet's production network. We present results of iNDIRA's query processing mechanism, evaluate iNDIRA's intent language evaluation with other approaches, and describe future enhancements for iNDIRA.

A Survey on Intent-Driven Networks

“…The current research focuses on the northbound interface based on intent, enabling the service-oriented network architecture [17], [18], the operator core network [19], and the service function chain [20]. In particular, the authors in [21], [22] proposed the service description framework: iNDIRA, which constructs semantic graphs through natural language processing to understand, interact, and create the required network services.…”

“…INDIRA can translate the intent language into RDF graphs through intent parsing and rendering components, and finally into network commands. The input of the rendering component is the user configuration and topology details [21], [22]. ACINO focuses on network orchestration.…”

Policy-Driven Network Traffic Rerouting Through Intent-Based Control Loops

“…An Intent specifies the "need" rather than the "how". Intent statements can be descriptive or prescriptive [Kiran et al 2018]. A descriptive (or declarative) Intent uses high-level statements to specify the problem context, for example, "allow traffic between X and Y".…”

“…ONOS Intent Framework [Linux Foundation b], ODL Network Intent Composition (NIC) [Linux Foundation 2015], ODL Group Based Policy (GBP) [Linux Foundation a], NEMO [c15 ] are solution examples using a prescriptive approach where users need some knowledge of the network and Intents are controller-specific which means that they depend on the network controller, constraints need to be converted into technology-specific constraints. In case of descriptive frameworks, architectural designs such as DISMI [Sköldström et al 2017] and iNDIRA [Kiran et al 2018] consider a simple, high-level, and technology-agnostic interface, which in turn uses a prescriptive module in order to translate advanced primitives into low-level primitives.…”

“…The DISMI Intent model defines three different classes of primitives: (i) actions (determine the connectivity type), (ii) nouns (determine what to connect), and (iii) modifiers (determine how the connectivity should behave). Another framework, iNDIRA (Intelligent Network Deployment Intent Renderer Application) [Kiran et al 2018] interfaces between the SDN north-bound interface and applications, understanding network QoS requirements, and automating the translation for scientific applications. It uses an ontology-based approach to define queries and translates them to network commands.…”