Data center task scheduling method based on dynamic temperature prediction model
A prediction model and task scheduling technology, applied in the direction of resource allocation, multi-programming device, energy-saving calculation, etc., can solve the problem of reducing the prediction accuracy of the temperature model, and achieve the effect of improving the cooling efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0017] The key concepts, definitions and symbols of the present invention:
[0018] 1. Stable state: In computationally intensive cluster applications, the calculation takes a long time. After a sufficient period of time, the ambient temperature and airflow of the cluster will tend to stabilize, and this state will become a stable state.
[0019] , Temperature prediction model: A two-dimensional matrix , It can be distributed according to the current CPU usage of all computing nodes , Predict the inlet temperature distribution of all computing nodes in a steady state by calculating Ac+b, where b is a constant parameter.
[0020] Take as figure 1 Take the system environment shown as an example: use 4 cabinets, each cabinet has 5 layers of racks, and each cabinet uses a power strip for power supply; the cooling fan horizontal blowing represents the cold aisle blowing mechanism; the ventilation entrance of each cabinet A temperature sensor is installed at the place to detect the e...
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.
© 2023 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap