Feasibility Detection for Time-Sensitive Network Configurations Based on MIC-SSA-SVM
Time-Sensitive Networking(TSN)supports precise clock synchronization,high-accuracy flow scheduling,and intelligent network control mechanism to realize mixed transmission of multiple service flows.Effi-cient detection schemes for network configuration are the crucial guarantees to maintain a safe and steady network system.Here,the feasibility should be achieved in a short time,reduce the maintenance costs of network opera-tion,and improve the efficiency of network use.In order to improve the efficiency of TSN network configuration detection,this paper proposes an algorithmic model based on feature optimization and sparrow search algorithm optimized support vector machine(MIC-SSA-SVM).In the paper,firstly,the maximum information coefficient(MIC)is used to evaluate the relevance of features for feature optimization.Secondly,SSA is chosen to optimize the penalty factor C and kernel parameter g of SVM,and the optimized SVM algorithm model is used to implement TSN network configuration feasibility detection.The experimental results show that compared with the existing al-gorithms,the proposed model is more efficient in detecting the feasibility of TSN network configuration,and the classification accuracy can reach 97.6％.Moreover,the model has fast convergence speed and strong optimization ability.
Time-Sensitive Networkingfeature optimizationmaximal information coefficientsparrow search al-gorithmsupport vector machine
NETL
NSTL
万方数据
维普
