Educational Network Bandwidth Analysis and Prediction

Network monitoring and analytic thinking are important to understand network per-formance, reliability and security, as easily as to identify potential problems. This research work focuses on looking into the educational network data traffic, to under-stand current trends in order to design for the time to come. The aim of the research is to monitor the London South Bank University’s (LSBU) network traffic, and to evolve a software analytic tool that can study the network traffics. The results of this study can assist organisations to enhance their network performance, and offer rec-ommendations for scalability and future upgrades. This paper presents, LSBU network traffic raw data were first captured using the Paessler Router Traffic Grapher (PRTG) network-monitoring tool, and then many numerical analysis algorithms was developed to analyse the captured raw data. A fast Fourier transform (FFT) algorithm developed to study the traffic’s frequency domain data, performing large-scale analytics for user conduct. The initial effects of the FFT show that it holds potential as a tool for evaluating and/or predicting LSBU be-haviour. A wavelet-based algorithm also used in development in order to decompose, demos, and compress the data, as well as analyse the time frequency characteristics of the data. In addition, helps develop methods to control the technique for working network analysis; this technique can analyse and predict data usage in its current and future states, and used as a mechanism to support decision-making in terms of the organization’s future investments.