Digital signature to help network management using flow analysis

摘要: Because of constant growth in proportion and complexity networks, flow analysis has become an indispensable tool for network management mechanisms. Through this resource, a traffic characterization, called digital signature segment using DSNSF, is accomplished. The models used purpose are the ant colony optimization metaheuristic, Holt-Winters forecasting method statistical procedure, principal component analysis. obtained DSNSF by each model compared with actual packets bits then subjected to specific evaluations order measure its accuracy. experimental results show that three methods could achieve good correlation indices low normalized mean square error values between curve real movement, indicating adaptability efficiency characterizing segment. Copyright © 2015 John Wiley & Sons, Ltd.