Smart Routing: Towards Proactive Fault-Handling in Software-Defined Networks
April 01, 2019 Β· Declared Dead Β· π Comput. Networks
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Ali Malik, Benjamin Aziz, Mo Adda, Chih-Heng Ke
arXiv ID
1904.00717
Category
cs.NI: Networking & Internet
Citations
32
Venue
Comput. Networks
Last Checked
6 months ago
Abstract
Software-defined networking offers numerous benefits against the legacy networking systems through simplifying the process of network management and reducing the cost of network configuration. Currently, the management of failures in the data plane is limited to two mechanisms: proactive and reactive. Such failure recovery techniques are activated after occurrences of failures. Therefore, packet loss is highly likely to occur as a result of service disruption and unavailability. This issue is not only related to the slow speed of recovery mechanisms, but also the delay caused by the failure detection process. In this paper, we define a new approach to the management of fault tolerance in software-defined networks where the goal is to eliminate the convergence process altogether, rather than speed up failure detection and recovery. We propose a new framework, called Smart Routing, which works based on the forewarning signs on failures in order to compute alternative paths and isolate the risky links from the routing tables of the data plane devices. We validate our framework through a set of experiments that demonstrate how the underlying model runs.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Networking & Internet
R.I.P.
π»
Ghosted
π
π
The Cartographer
Federated Learning in Mobile Edge Networks: A Comprehensive Survey
π
π
The Cartographer
A Survey of Indoor Localization Systems and Technologies
R.I.P.
π»
Ghosted
Survey of Important Issues in UAV Communication Networks
π
π
The Cartographer
Network Function Virtualization: State-of-the-art and Research Challenges
π
π
The Cartographer
Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted