Cloud computing system load predicting method capable of automatically adjusting parameters

Abstract

The invention discloses a cloud computing system load predicting method capable of automatically adjusting parameters, which comprises the following steps: at the moment t, computing the actual load O(t) of a system at the moment t through system call; executing short-term prediction; computing alpha (t) and E(t) by utilizing the O(t) value and historical data; executing long-term prediction; computing alpha T(t) and ET(t) by utilizing the O(t) and the historical data; combining the short-term prediction and the long-term prediction; when t is less than T, outputting the O(t) and switching to the next step; otherwise, taking the maximum value or average value of E(t-1) and ET(t-T) as the output at the moment t; and updating the historical data, waiting the moment t+1 and switching to the first step. In the invention, the alpha (t) and the alpha T(t) are computed in real time through error functions, thereby enhancing the prediction accuracy of classic EWMA (Exponentially Weighted Moving Average); the requirement that a prediction value is slightly larger than an actual value can be met by expanding the alpha (t) and the alpha T(t) to an interval (-1, 1); and the responsiveness of the prediction to the load periodicity of a cloud computing platform is enhanced by introducing a long-term prediction module.

Description

technical field [0001] The invention provides a system load prediction method, in particular to a load prediction of a physical machine or a virtual machine in a cloud computing platform, and belongs to the field of computer systems and networks. Background technique [0002] In order to improve the system resource utilization rate of the entire cloud computing platform, it is necessary to schedule the virtual machines running on each physical machine. However, by viewing the information of physical machines and virtual machines, only the load status at the current moment can be obtained. Therefore, an appropriate model should be established to predict the load demand of the system in the future, so as to achieve effective and reasonable scheduling. [0003] In practical applications, load forecasting has two goals: i. The error between the predicted value and the actual value is as small as possible; ii. The predicted value is greater than the actual value. The latter is ...

AI Technical Summary

Problems solved by technology

[0007] The problems of the EWMA method include: when the load sequence shows an upward trend, the predicted value will always be between the historical data and the actual value, which cannot meet the goal ii; the value of

Images