Moving average and neural network-based virtual machine load prediction method and system
A moving average method and neural network technology, applied in the field of virtual machine load prediction, can solve the problems of cloud platform turbulence, prediction lag, prediction accuracy, low flexibility, etc., and achieve the effect of strong adaptability and reduced lag
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0066] refer to figure 1 , a virtual machine load prediction method based on moving average and neural network, including steps:
[0067] S1. Collect the historical load data of the time period to be predicted and the continuous load data before the time period to be predicted;
[0068] S2. Obtain the period-by-period historical load data of the period to be predicted, and use the quadratic moving average method to predict and calculate the load inertia of the virtual machine, and obtain the first load inertia prediction value P1 for the next period;
[0069] S3. Obtain the continuous load data before the period to be predicted, combine the first load inertia prediction value P1, and use the RBF neural network prediction to obtain the second load inertia prediction value P2;
[0070] S4. Taking the second load inertia prediction value P2 as the final virtual machine load inertia prediction value P and outputting it.
[0071] Further, the step S1 specifically includes:
[00...
Embodiment 2
[0097] refer to figure 2 , the present invention also provides a virtual machine load forecasting system based on moving average and neural network, comprising:
[0098] The collection module is used to collect the time-segmented historical load data of the time period to be predicted and the continuous load data before the time period to be predicted;
[0099] The load level inertia prediction module is used to obtain the period-by-period historical load data of the period to be predicted, and use the quadratic moving average method to predict and calculate the load inertia of the virtual machine, and then obtain the first load inertia forecast value P1 for the next period ;
[0100] The continuous load prediction module is used to obtain the continuous load data before the period to be predicted, combined with the first load inertia prediction value P1, and obtain the second load inertia prediction value P2 by using RBF neural network prediction;
[0101] The result outpu...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com