Novel network prediction algorithm based on SDN
A technology of network forecasting and forecasting algorithms, applied in data exchange networks, digital transmission systems, electrical components, etc., can solve the problems of system updates that cannot add new functions, high cost of use, and low computing efficiency, so as to improve computing efficiency and convergence The effects of speed, O&M cost savings, scalability and flexibility
Pending Publication Date: 2020-12-15
JIANGSU FUTURE NETWORKS INNOVATION
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the current common neural network prediction algorithm has a simple structure and decentralized control, resulting in low computational efficiency. At the same time, the completed network architecture cannot be added with new functions without system updates, and the cost of use is high.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0048] Such as Figure 1-7 As shown, this embodiment provides a novel network prediction algorithm based on SDN, including an application unit 100, a control unit 200, and a basic unit 300; the control unit 200 is connected to the application unit 100 through an open interface, and the control unit 200 is connected to the The basic network communicates with the basic unit 300; the application unit 100 is used to program the underlying device through the programming interface provided by the control layer and open the network control right to the user; the control unit 200 is used to centrally manage all devices in the network and control resources to allocate.
[0049] Among them, the signal transmission channel between the physical device and the controller is the southbound interface, and the open interface between the controller and the service application is the northbound interface.
[0050]In this embodiment, the application unit 100 includes a software operation module...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to the technical field of artificial intelligence, in particular to a novel network prediction algorithm based on an SDN. The algorithm comprises an application unit, a control unit and a basic unit; the application unit is used for programming underlying equipment through a programming interface provided by a control layer and opening the network control right to a user; andthe control unit is used for centrally managing all equipment in the network and distributing resources. According to the design of the invention, the operation efficiency and convergence speed can be improved, the resource utilization rate can be improved, the operation and maintenance cost can be saved, the degree and flexibility of traditional differentiated services can be expanded, the testand rapid deployment of new services are facilitated, and the intellectualization and automation of a network and the standardization of hardware are facilitated.
Description
technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a novel network prediction algorithm based on SDN. Background technique [0002] Artificial neural network is a part of machine intelligence, it simulates the nervous system of the brain, more simply, it is a mathematical model of the nervous system of the human brain. Machine intelligence is the application of artificial neural networks to machines, so that they can imitate the human brain to engage in reasoning, design, thinking, learning and other thinking activities to solve and deal with more complex problems. However, the current common neural network prediction algorithm has a simple structure and decentralized control, resulting in low computational efficiency. At the same time, the completed network architecture cannot be added with new functions without system updates, and the cost of use is high. Contents of the invention [0003] The purpose of the ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): H04L12/24
CPCH04L41/14H04L41/142H04L41/147
Inventor 马玥谭航鲍全松范亮凯
Owner JIANGSU FUTURE NETWORKS INNOVATION