Data center network energy consumption and service quality optimization method based on reinforcement learning
A data center network and reinforcement learning technology, applied in the field of computer networks, can solve the problems of not fully considering the diversity of DCN traffic types, not being able to promote well, and reducing QoS, so as to save power, improve effectiveness, and improve energy efficiency. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Examples
Embodiment Construction
[0020] Examples are given below to describe the present invention in detail.
[0021] The method for optimizing energy consumption and quality of service of a data center network based on reinforcement learning provided by the present invention has the basic idea of: using a deep reinforcement learning framework (DRL framework) to establish an optimization model for energy consumption and quality of service of a data center network; The historical data of the traffic and network performance of each link in the network constructs a training sample set for the data center network energy consumption and service quality optimization model, and uses this sample set to complete the training of the data center network energy consumption and service quality optimization model. During the deployment process, input the current traffic and network performance characteristics of the data center network to be optimized into the optimization model obtained through training to obtain the link...
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