Container-Based Microservices SDN Control Plane for Open Disaggregated Optical Networks

Van, Quan Pham; Verchere, Dominique; Tran-Quang, Huy; Zeghlache, Djamal

doi:10.1109/icton.2019.8840430

Cited by 6 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is no flexible isolated allocation of resources to components in such a system. Unfortunately, most of the SDN controllers are monolithic by design [17] [18] [19] with tight coupling between applications and controller core. An organic organisation of such a system with diverse roles and functions is to separate the functions into communicating modules with dedicated resources.…”

Section: ) Flexible Resource Allocation and Application Isolationmentioning

confidence: 99%

“…[16] defines monolithic application as a single, self-contained unit where components are interconnected and interdependent, resulting in a tightly coupled code. Popular controllers such as ONOS and ODL are monolithic [17] [18] [19]. Due to such tight coupling, monolithic software is heavily technology stack dependent and does not isolate resources leading to inefficient resource allocation.…”

Section: B Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

An agent-based approach to disintegrate and modularise Software Defined Networks controller

Chemalamarri

Braun

2022

2022 IEEE 47th Conference on Local Computer Networks (LCN)

View full text Add to dashboard Cite

The Software Defined Network paradigm deviates from traditional networks by logically centralising and physically separating the control plane from the data plane. In this work, we present the idea of a modular, agent-based SDN controller. We first highlight issues with current SDN controller designs, followed by a description of the proposed framework. We present a prototype for our design to demonstrate the controller in action using a few common use-cases. We continue the discussion by highlighting areas that require further research.

show abstract

Section: ) Flexible Resource Allocation and Application Isolationmentioning

confidence: 99%

Section: B Contributionsmentioning

confidence: 99%

An agent-based approach to disintegrate and modularise Software Defined Networks controller

Chemalamarri

Braun

2022

2022 IEEE 47th Conference on Local Computer Networks (LCN)

View full text Add to dashboard Cite

show abstract

“…In [20,23], the authors experimentally showed a basic cloudnative SDN controller and studied the latency overhead that the communication between microservices introduced, and they performed basic demonstrations of two of the most fundamental benefits of the cloud-native approach, self-healing and auto-scaling. In [24,25] the authors demonstrated the ability of a microservices-based SDN controller to swap modules on the fly, using Open Network Operating System [26] (ONOS) or OpenDaylight [27] (ODL) SDN controllers (monolithic) as the core module. Other projects hosted by the Linux Foundation [28] that started as monolithic controllers have changed their path and have begun the transition to a microservices-based architecture.…”

Section: Related Workmentioning

confidence: 99%

Scalability analysis of machine learning QoT estimators for a cloud-native SDN controller on a WDM over SDM network

Manso

Vilalta

Muñoz

et al. 2022

J. Opt. Commun. Netw.

View full text Add to dashboard Cite

Maintaining a good quality of transmission (QoT) in optical transport networks is key to maintaining the service level agreement between the user and the service provider. QoT prediction techniques have been used to assure the quality of new lightpaths as well as that of the previously provisioned ones. Traditionally, two different approaches have been used: analytical methods, which take into account most physical impairments that are accurate but complex, and high margin formulas, which require much less computational resources at the cost of high margins. With the recent progress of machine learning (ML) together with software defined networking (SDN), ML has been considered as another option that could be both accurate and that does not consume as many resources as analytical methods. SDN architectures are difficult to scale because they are usually centralized; this is even worse with QoT predictors using ML. In this paper, a solution to this issue is presented using a cloud-native architecture, and its scalability is evaluated using three different ML QoT predictors and experimentally validated in a real wavelength-division multiplexing (WDM) over spatial-division multiplexing (SDM) testbed.

show abstract

“…Other frameworks like KANDOO [9] and ORION [10] are logically distributed, but require full (KANDOO) or hybrid (ORION) hierarchy to work. Container-based (or micro-services-based) SDN architectures [11], distribute the services of a monolithic SDN controller across the network. This allows the system to achieve greater scalability and modularity at the cost of higher latency [12] and of heavier difficult management, due to micro-service orchestration and load balancing.…”

Section: A Related Work On Multi-controller Sdn Frameworkmentioning

confidence: 99%

Realizing Flat Multi-Zone Multi-Controller Software-Defined Networks using Zenoh

Federico

Cominardi²,

Casari

2022

2022 IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN)

View full text Add to dashboard Cite

Software Defined Networks (SDNs) are becoming an increasingly important paradigm in modern networking. By making it possible to detach the control plane from network devices and to instruct those devices via a high-level programming language, SDNs yield a number of administration-level improvements, such as better policy-driven network management and easier support for multi-tenancy. However, moving the complexity of network administration to the controllers entails additional challenges, such as scalability, support for different controller network topologies, and efficient maintenance of network state information. In this paper, we consider a distributed and decentralized approach to the SDN paradigm, targeting zero-configuration scalability and transparency through the Zenoh framework. We explore the application of Zenoh as an east/westbound protocol for SDNs and compare its performance against that of a strongly coupled HTTP-based alternative. Our results show that Zenoh's support for distributed queries enables our SDN architecture to effectively scale to hundreds of SDN controllers with zero configuration overhead, while supporting high east/westbound query throughput.

show abstract

Container-Based Microservices SDN Control Plane for Open Disaggregated Optical Networks

Cited by 6 publications

References 2 publications

An agent-based approach to disintegrate and modularise Software Defined Networks controller

An agent-based approach to disintegrate and modularise Software Defined Networks controller

Scalability analysis of machine learning QoT estimators for a cloud-native SDN controller on a WDM over SDM network

Realizing Flat Multi-Zone Multi-Controller Software-Defined Networks using Zenoh

Contact Info

Product

Resources

About