SDN network flow prediction method based on graph convolutional network
A network traffic, convolutional network technology, applied in neural learning methods, biological neural network models, electrical components, etc., can solve problems such as inability to process network topology data, and achieve the effect of dynamic changes and accurate network traffic prediction.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0038] S1. Obtain a sample data set
[0039] In this embodiment, ONOS is used as the network controller, and Mininet is used as the network simulation platform to simulate the SDN network environment. The adopted topology diagram includes a total of 12 switches, 15 hosts, 15 unidirectional links, and a total of 30 bidirectional links, such as figure 1 shown. Among them, s1 and s2 are the main switches, which are used as the source address and the destination address respectively. a3s1 to a3s10 are intra-area switches. s1 is connected to 4 hosts, and the rest of the switches are connected to one host. The host h1 sends a total of four services to h11, and the data packets are 1.25Mbps, 0.2Mbps, 0.5Mbps and 1.15Mbps respectively. The link bandwidth is uniformly set to 2Mbps. After the current three packets are sent, the link load reaches 1.95Mbps, which is close to the bandwidth threshold. When the fourth packet is sent, the threshold is clearly exceeded. The service flow...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


