Network flow time sequence prediction method based on distributed clustering

Abstract

The invention discloses a network flow time sequence prediction method based on distributed clustering. The method comprises the steps: carrying out the fusion of a distributed clustering algorithm and an auto-regression model; obtaining time segment groups through the segmenting of time sequence data, and carrying out the distributed clustering of the time segment groups through employing a distributed K-means clustering algorithm; carrying out the normal distribution fitting of each cluster in a clustering result, and obtaining a normal distribution N(mu, sigma2), wherein mu is a preliminary prediction value. At a prediction stage, the to-be-predicted time sequence data is preprocessed, and the to-be-predicted time segment prefix groups. The method achieves the distributed calculation of the preliminary prediction value corresponding to the nearest cluster, and achieves the correction of the preliminary prediction value through combining with an autoregressive model, thereby obtaining a more precise final prediction value.

Description

technical field [0001] The invention relates to the technical field of network flow monitoring, in particular to a method for predicting network flow time series based on distributed clustering. Background technique [0002] In the field of network traffic monitoring, it is very important to analyze and predict network traffic time series data. Currently existing solutions include differential moving average autoregressive model (Autoregressive Integrated MovingAverage model), multilayer perceptron (Multilayer Perceptron), time recurrent neural network (Recurrent Neural Network), long-short term memory artificial neural network (Long-Short Term ), techniques such as clustering-based time series prediction have been extensively studied as possible solutions. From the comparison and measurement of cost, accuracy, energy consumption and scalability, we can analyze that the time series prediction method based on clustering has better advantages in the online environment, and th...

AI Technical Summary

Problems solved by technology

These mainstream technologies work well when the time-series data is flat and the rise and fall are stable. When analyzing and predicting network traffic time-series data with large fluctuations and strong randomness, the prediction effect and prediction accuracy will continue to decline.

At the same time, in actual use, techniques such as temporal recurrent neural networks and long-short-term memory artificial neural networks are computationally intensive and time-consuming, and are not suitable for real-time environments.

Images