A cloud server elastic scaling and performance optimization method based on model predictive control
A model predictive control and cloud server technology, applied in the direction of instruments, hardware monitoring, energy-saving computing, etc., can solve the problems of incomplete control and management research on power consumption and service quality, and limited commercial development of hardware manufacturers, so as to reduce system performance. Consumption, improve the effect of system service quality
Active Publication Date: 2022-05-31
HANGZHOU DIANZI UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing research on the control management of power consumption and quality of service is not comprehensive, and some only consider the unilateral influence factors of two levels of power consumption application request performance, and cannot provide clear guarantees for both at the same time
On the other hand, although many current researches have proposed many control management scheduling strategies, such as effectively reducing server power consumption by switching hardware components to low-power states, most of these strategies are difficult to be directly applied to actual On the cluster-level server data center based on virtualization technology, and some strategies are limited by the commercial development of hardware manufacturers
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 Construction
[0037] Power
[0040] The MPC controller optimizes the future defined cost function over a time interval. The controller utilizes a system
[0041] At the end of each control cycle, the controller calculates the control input Δf(k) to minimize the following cost function:
[0042]
[0056]
[0058] According to the aforementioned model, the present invention proposes a virtualized server cluster performance and power consumption coordination control method,
[0070] Step 2. The performance controller of each virtual machine calculates the required amount of CPU resources and sends this value to the CPU resources
[0071] Step 3. The CPU resource allocator calculates the total CPU resources of all virtual machines requested by the performance controller.
[0073] The above implementation steps are described in detail below.
[0076] The power consumption monitor measures the total power consumption of all servers in the last control cycle and sends the measured value to the power c...
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 relates to a cloud server elastic scaling and performance optimization method based on model prediction control. The present invention includes the control of server power consumption and the control of virtual machine application-level performance, wherein the power controller in the cluster-level power control loop adjusts the CPU frequency of each server through dynamic voltage and frequency scaling (DVFS), and dynamically controls The total power consumption of all servers. In the performance control loop, the performance controller dynamically controls the application performance of the virtual machine by adjusting the CPU resources allocated to it. Since the total power consumption of the cluster needs to be kept below the capacity of the shared power supply, and cluster-level power conversion between different servers can lead to better system performance. The method for elastic scaling and performance optimization of a cloud server based on model predictive control provided by the present invention can reduce system power consumption, ensure that application program performance on the virtual machine meets certain requirements, and improve system service quality.
Description
A method for elastic scaling and performance optimization of cloud server based on model predictive control technical field The present invention relates to a kind of optimization method of power consumption of virtualized server and application-level performance, especially large-scale Deploy a virtualized computer system, such as a coordinated control method for the performance and power consumption of server clusters in a data center. Background technique [0002] With the development of technologies such as cloud computing, big data, and machine learning, users are increasingly interested in data storage, processing, and intelligent analysis. As the demand increases, through server virtualization technology, the data center can provide more flexible resources to carry more application services, and improve service manageability. However, with the expansion of the scale of the server system in the data center, the server The energy consumption of the server increas...
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 Patents(China)
IPC IPC(8): G06F11/30G06F11/34
CPCG06F11/301G06F11/3409Y02D10/00
Inventor 蒋从锋陈圣蕾黄杰仇烨亮樊甜甜李尤慧子殷昱煜张纪林
Owner HANGZHOU DIANZI UNIV