Neural network deployment method in network based on SDN (Software Defined Network) mode

By adopting a neural network deployment method based on SDN mode in network devices, the deep neural network model is mapped into flow table items, and combined with model compression and binarization technology, the problem of high complexity of neural network inference calculation in network devices is solved, and efficient deep neural network deployment and intelligent network functions are realized.

CN119728434AActive Publication Date: 2025-03-28FUZHOU UNIV
4 Cites 0 Cited by

Patent Information

Application Number
CN202510015873.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-06
Publication Date
2025-03-28
Estimated Expiration
2045-01-06

AI Technical Summary

Technical Problem

The calculation complexity of neural network inference process in existing network devices is high and resource consumption, making it difficult to efficiently deploy deep neural networks on traditional network devices, especially on edge devices and small and medium-sized network devices.

Method used

The in-network neural network deployment method based on SDN mode is adopted to map the input features of the deep neural network model and the output results into flow table entries of network equipment, and deep neural network inference is realized through table entries matching, and combined with neural network model compression technology and binary neural network technology, the computing and storage resource requirements are optimized.

Benefits of technology

It significantly reduces the computing complexity and storage consumption of network devices, improves inference speed and real-time performance, and can efficiently deploy deep neural networks on programmable network devices, realizes intelligent functions such as traffic classification and abnormal detection, and reduces network latency.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to an in-network neural network deployment method based on an SDN modal, and the method comprises the steps: mapping an input feature and an output result of a deep neural network model into a flow table item of network equipment, achieving the deep neural network reasoning through a table item matching mode, and achieving the network functions of flow classification, anomaly detection and the like. According to the method, the deep neural network model is compressed and converted into the table item matching task suitable for the programmable network equipment, so that efficient network data plane reasoning is realized. According to the method, the utilization of storage and computing resources is optimized, the computing complexity of network equipment is remarkably reduced, and the throughput and the real-time performance are improved. Through an innovative table item compression and adaptive matching mechanism, the method supports high-precision applications such as traffic classification and anomaly detection, and the network intelligent management and optimization capability is remarkably improved. According to the method, efficient deployment of the deep neural network in the in-network equipment can be realized, and an effective solution is provided for development of an intelligent network technology.
Need to check novelty before this filing date? Find Prior Art