Offering reliable novel service in modern heterogeneous networks is a key challenge and an importa..
Offering reliable novel service in modern heterogeneous networks is a key challenge and an important prospective income source for many network operators and providers. Providing reliable future service in a cost effective scalable manner requires efficient use of networking and computing resources. This can be done by making the network more self enabled, i.e. making it capable of making distributed local decisions regarding the utilization of the available resources. However such decisions must be correlated in order to achieve the global overall goal (maximizing the performance and minimizing the cost) Since network administrators are always worried about making fast decisions to monitor and regulate the Internet traffic, a novel approach for online flow-based network traffic classification is proposed. This proposal is based on Machine learning algorithm C4.5 and a custom built network traffic data set captured from a university campus environment. Furthermore the aim of this effort is to build a complete online flow based traffic classification and control system. Validation on the proposed system is done from accuracy and time points of views. Firstly, an offline training and testing data sets are applied to Weka s C4.5 and our system. And their corresponding accuracy has been compared. Our experimental results show that the accuracy is the exactly the same. Secondly, the received UDP NetFlow packets have been send to our system and to a basic packet sniffing program and the number of NetFlow packets has been counted in each. The comparison result show that no packet overwriting due to race condition.