A process level network traffic prediction algorithm based on ARIMA model in smart substation

The introduction of the concept of process level into smart substation makes protection and control of input and output values depend on the network communication. In order to ensure the stability and reliability of the smart substation process layer network, it must forecast the process level network traffic effectively and make early analysis warning. This paper proposed a smart substation process level network traffic prediction algorithm based on ARIMA model from the demand of smart substation process layer network traffic monitoring system. Our proposed algorithm introduces a dynamic error correction factor on the basis of Astrom algorithm based on the linear minimum variance prediction principle. It can solve the problem of stochastic effects in prediction, and the prediction precision is improved. The experimental results show that the algorithm can effectively predict the process level network traffic, reproduce the statistical properties of the real flow measurement, and guarantee the safe operation of power grid.