Deep learning-based SDN network traffic advantageous monitoring node dynamic selection system and dynamic selection method thereof
A technology for monitoring nodes and deep learning, applied in the field of network security, can solve problems such as demanding switch hardware and software requirements, reducing SDN traffic monitoring information redundancy rate and monitoring overhead, and incomplete network global view acquisition.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0120] In this embodiment, a dynamic selection system for SDN network traffic advantage monitoring nodes based on deep learning is implemented, and it is applied to SDN traffic monitoring. The system uses the Mininet emulator to simulate the underlying physical forwarding device of SDN, the software switch selects Open VSwitch, supports OpenFlow1.3, uses Ryu as the SDN controller, and uses the network topology randomly generated by the Waxman graph widely used in network research, such as image 3 As shown, the network topology includes 35 nodes, and connections are established with a probability of p=0.05, that is, the probability of connections between nodes in the randomly switched network graph is 0.05.
[0121] Implement the routing and forwarding rules in the Ryu controller according to the bandwidth-based optimal path algorithm process, and send them to the switch in the form of a flow table. Run Iperf on the host to create and release traffic, generate a set of paths be...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com