SDN data center congestion control method based on reinforcement learning
A congestion control and data center technology, applied in the field of network communication, can solve problems such as increased packet loss, decreased throughput, data center network congestion, etc., to achieve the effects of ensuring healthy development, improving throughput, and promoting energy saving
Active Publication Date: 2018-04-20
ZHEJIANG GONGSHANG UNIVERSITY
View PDF3 Cites 15 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Under the current technical conditions, the data center network will frequently be congested, resulting in increased packet loss, increased delay, and reduced throughput, seriously affecting business performance and service quality
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0052] In order to make it easier for those skilled in the art to understand and realize the present invention, the technical solution of the present invention will be further described in conjunction with the accompanying drawings, and a specific embodiment of the method described in the present invention will be given.
[0053] The invention introduces the enhanced learning method into the data center based on the software-defined network to solve the problem of congestion control. figure 1 It is a system architecture diagram, and the basic functions of each module are: (1) Sensing module: adopting the current link state information of the data center network; (2) Learning module: learning the received link state information or according to relevant Quantitative information obtained from empirical knowledge provides decision-making basis for the decision-making module; (3) Decision-making module: formulate corresponding control strategies according to the information provided...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an SDN data center congestion control method based on reinforcement learning. According to the method, based on the network background of SDN, the flow-based congestion controlthought is proposed, a Q-learning algorithm in reinforcement learning is introduced, and the flow rate is intelligently and globally distributed, so that the data link utilization rate of the networkis as high as possible; meanwhile, congestion of the whole network is avoided, thereby achieving congestion control of a data center; the method comprises the steps that firstly, a quintuple is modeled to describe a problem; then, the improved Q-learning algorithm is proposed for training a Q matrix; and finally, according to the request of the flow, congestion control is carried out according tothe Q matrix obtained through training. The SDN data center congestion control method provided by the invention has the advantages of good control effect, easy realization of the control algorithm, good stability and efficient self-adaption. The invention provides an intelligent solution method based on reinforcement learning for the congestion control problem of the SDN data center.
Description
technical field [0001] The present invention relates to the technical field of network communication, in particular to a congestion control method of an SDN (Software Defined Network, Software Defined Network) Data Center Network (DCN) based on reinforcement learning. Background technique [0002] In recent years, cloud computing has become a hot spot and future trend in the field of information construction, and the number of users of many new Internet online services (such as search, social networking, instant messaging, etc.) is also growing rapidly. During the rapid development of cloud computing and Internet online business, the data center as an information infrastructure has always been at the core. With the development of business and the use of new technologies, data centers are undergoing and forming major changes and trends, thus bringing new challenges and problems to data center networks. Emerging services require a large number of one-to-many and many-to-many ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/801H04L12/825H04L12/851
CPCH04L47/10H04L47/24H04L47/2425H04L47/25
Inventor 金蓉王伟明李姣姣庹鑫
Owner ZHEJIANG GONGSHANG UNIVERSITY