Adaptive network traffic prediction system based on user feature and method thereof

Abstract

An adaptive network traffic prediction system based on user features and method thereof, the method includes storing and managing a basic configuration information of each line in a telecommunication network; collecting network traffic data of each line in real time, and generating each line feature label corresponding to each line, using a prediction algorithm group corresponding to each line feature label and conducting a model training according to historical network traffic data of each line to obtain prediction results corresponding to at least two prediction algorithms, and obtaining scores corresponding to the at least two prediction algorithms according to the network traffic data and the prediction results of each line, select a best prediction algorithm according to the score, using the best prediction algorithm and predicting according to the network traffic data of each line to obtain a best prediction result.

Images