NTAM-LSTM models of network traffic prediction

Accurate prediction of network traffic is very important in allocating resources. With the rapid development technology, becomes more complex and diverse. The traditional model cannot accurately predict current within effective time. This paper proposes a Network Traffic Prediction Model----NTAM-LSTM, which based on Attention Mechanism with Long Short Time Memory. Firstly, preprocesses historical dataset multiple characteristics. Then LSTM used to make initial for processed dataset. Finally, attention mechanism introduced get accurate results. Compared other models, NTAM-LSTM can achieve higher accuracy take shorter running