FGn and Poisson process-based power Internet of Things flow prediction method

The invention relates to an FGn and Poisson process-based power Internet of Things traffic prediction method, which comprises the following steps of: carrying out data classification on power Internet of Things access nodes, and establishing a plurality of traffic characteristic data storage libraries according to the classification; collecting data according to the classification of each flow characteristic database; effective data in a specific time node being selected, data preprocessing and feature extraction being carried out, and data features being obtained; establishing a preliminary flow prediction model according to the data features, and constructing a fractional order Gaussian noise model and a Poisson distribution data model; the fractional order Gaussian noise model and the Poisson distribution data model being merged into the initial flow prediction model for denoising, and a single-time-node prediction model being formed; and repeating the steps to generate prediction models of single time nod