CN113672383A - Cloud computing resource scheduling method, system, terminal and storage medium - Google Patents

Cloud computing resource scheduling method, system, terminal and storage medium Download PDF

Info

Publication number
CN113672383A
CN113672383A CN202110834069.4A CN202110834069A CN113672383A CN 113672383 A CN113672383 A CN 113672383A CN 202110834069 A CN202110834069 A CN 202110834069A CN 113672383 A CN113672383 A CN 113672383A
Authority
CN
China
Prior art keywords
data center
algorithm
time
task
server
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110834069.4A
Other languages
Chinese (zh)
Inventor
徐敏贤
周启恒
赵娟娟
叶可江
须成忠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Priority to CN202110834069.4A priority Critical patent/CN113672383A/en
Publication of CN113672383A publication Critical patent/CN113672383A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083—Techniques for rebalancing the load in a distributed system
    • G06F9/5088—Techniques for rebalancing the load in a distributed system involving task migration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5094—Allocation of resources, e.g. of the central processing unit [CPU] where the allocation takes into account power or heat criteria
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G06F2209/508—Monitor
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Power Sources (AREA)

Abstract

The application relates to a cloud computing resource scheduling method, a cloud computing resource scheduling system, a terminal and a storage medium. The method comprises the following steps: acquiring a user request, and dividing the user request into an interactive task and a batch processing task; acquiring load state data of the data center, and calculating the total server energy consumption of the data center according to the load state data; based on the total energy consumption of the server of the data center, calculating interactive tasks and batch processing tasks by adopting a green perception algorithm, and generating a scheduling strategy of the interactive tasks and the batch processing tasks; and based on the generated scheduling strategy, executing virtual machine migration and machine expansion operation on the data center by adopting a virtual machine scheduling algorithm and a Host scaling machine expansion algorithm. According to the method and the device, multi-layer resource scheduling based on micro-service management, virtual machine scheduling and physical machine expansion is realized, the utilization of green energy by a data center is considered in a scheduling strategy, and the pollution of cloud computing to the environment is reduced.

Description

Cloud computing resource scheduling method, system, terminal and storage medium
Technical Field
The application belongs to the technical field of cloud computing, and particularly relates to a cloud computing resource scheduling method, a cloud computing resource scheduling system, a terminal and a storage medium.
Background
Cloud computing delivers various IT (Internet Technology, information Technology) service resources on demand through the Internet using a pay-per-utilization pricing scheme. Meanwhile, the cloud computing has the excellent characteristics of strong expandability, low cost, flexible deployment and the like. By means of cloud computing, enterprises do not need to consume a large amount of cost in construction, operation and maintenance of a data center, and can remotely deploy and access services anytime and anywhere. Today, cloud computing has been adopted by organizations of different types and scales, and the productivity of enterprises is improved. However, the continuous work of large-scale data centers consumes a large amount of electric energy and brings a large amount of carbon emission, which causes serious environmental pollution, and this has attracted extensive attention of researchers and proposed many energy-saving technologies for cloud computing.
In recent years, an energy saving method for a cloud computing data center mainly includes:
(1) virtual machine migration (VM consistency): the virtual machine migration method can be used for migrating the virtual machines hosted by the servers with lower loads to other servers, and then adjusting the servers to be in a low-energy consumption mode or directly shutting down the servers so as to reduce the energy consumption of the system. For a server with a high load, the virtual machine needs to be migrated to reduce the probability of server overload and ensure the service quality of users.
(2) Dynamic Voltage Frequency Scaling (DVFS): according to the method, the balance between the computing performance and the energy consumption of the server is balanced according to the current load condition of the system. In the case of a low load, the DVFS technique may reduce the frequency and voltage to reduce the power consumption of the server. When the task load is high, the frequency and voltage are increased to efficiently process the user request.
In summary, the existing energy-saving method for the cloud computing data center generally performs resource scheduling by using a virtual machine as granularity, but cannot effectively schedule tasks, and the existing method for utilizing green energy is not comprehensive enough, and different scheduling schemes are not designed for different types of tasks.
Disclosure of Invention
The application provides a cloud computing resource scheduling method, a cloud computing resource scheduling system, a cloud computing resource scheduling terminal and a storage medium, and aims to solve the technical problems that in the prior art, an energy-saving method for a cloud computing data center cannot effectively schedule tasks and a green energy utilization method is not comprehensive enough.
In order to solve the above problems, the present application provides the following technical solutions:
a cloud computing resource scheduling method comprises the following steps:
acquiring a user request, and dividing the user request into an interactive task and a batch processing task;
acquiring load state data of a data center, and calculating the total server energy consumption of the data center according to the load state data;
calculating the interactive tasks and the batch processing tasks by adopting a green perception algorithm based on the total energy consumption of the server of the data center, and generating a scheduling strategy of the interactive tasks and the batch processing tasks; the method comprises the steps that a green perception algorithm comprises a Brown out control algorithm and a Deferring delay execution algorithm, wherein the Brown out control algorithm is used for detecting whether micro-services which can be stopped or not exist in a current server or not, judging whether green energy can be utilized at the current moment or not and generating a scheduling strategy of the interactive tasks; the Deferring delay execution algorithm is used for judging whether to delay the execution time of the batch processing task according to the available time of green energy in a data center and generating a scheduling strategy of the batch processing task;
and based on the generated scheduling strategy, executing virtual machine migration and machine expansion operation on the data center by adopting a virtual machine scheduling algorithm and a Host scaling machine expansion algorithm.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the calculating of the total server energy consumption of the data center according to the load state data comprises the following steps:
calculating the server energy consumption of each physical machine:
Figure BDA0003176537600000031
wherein the content of the first and second substances,
Figure BDA0003176537600000032
representing server energy consumption, w, of physical machine iiRepresenting the number of virtual machines deployed on physical machine i,
Figure BDA0003176537600000033
representing the power consumption of the physical machine i in the idle state,
Figure BDA0003176537600000034
represents the dynamic energy consumption of the physical machine i in a load state, thetatA regulator value representing time t, which represents a resource utilization percentage of the microservice,
Figure BDA0003176537600000035
representing the sum of the resource utilization of all the microservices run by the jth virtual machine on the physical machine i,
Figure BDA0003176537600000036
the calculation formula of (2) is as follows:
Figure BDA0003176537600000037
wherein A isjRepresenting the number of microservices on virtual machine j,
Figure BDA0003176537600000038
representing the resource utilization rate of the kth micro-service on the virtual machine j;
calculating the energy consumption of the cooling equipment of each physical machine according to the energy consumption of the server:
Figure BDA0003176537600000039
Figure BDA00031765376000000310
wherein, CoP (T)sup) For cooling efficiency, TsupIs the temperature of refrigeration of the cooling equipment;
the total energy consumption of the servers of the data center at the moment t is as follows:
Pt＝d(t)′+c(d(t)′)
wherein the content of the first and second substances,
Figure BDA0003176537600000041
represents the sum of the energy consumptions of all the servers in the data center at the moment t, wherein n represents the number of the servers in the data center,
Figure BDA0003176537600000042
representing the sum of the energy consumptions of all cooling devices in the data center at time t.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the calculating the total server energy consumption of the data center according to the load state data further comprises:
calculating the workload of the data center; the workload calculation mode is as follows:
suppose there are M interactive tasks and N batch tasks in a data center, am(t) represents the workload of the interactive task m at time t, umRepresenting resources required by an interactive task m, am(t)×umResource representing interactive task m request at time t, bn(t) represents the workload of the interactive task n at time t, unRepresenting resources required by an interactive task n, bn(t)×unRepresenting the resource requested by the interactive task n at time t, the scheduler may choose to defer it to the next time for the batch task, so that the resource b actually requested by the interactive task n at time tn(t) is:
Figure BDA0003176537600000043
in the above formula, the first and second carbon atoms are,
Figure BDA0003176537600000044
representing the proportion of interactive tasks that are delayed from execution at time t-1, bn(t)' represents the original workload of the interactive task n at time t;
the workload of the data center at the moment t is as follows:
Figure BDA0003176537600000045
the technical scheme adopted by the embodiment of the application further comprises the following steps: the method for calculating the interactive tasks and the batch processing tasks by adopting the green perception algorithm and generating the scheduling strategies of the interactive tasks and the batch processing tasks specifically comprises the following steps:
for each time t, the resource utilization of server i is known
Figure BDA0003176537600000051
Maximum threshold TU of resource utilizationupAnd a minimum threshold TUlow，
Calculating number of overloaded servers in a data center
Figure BDA0003176537600000052
If it is not
Figure BDA0003176537600000053
For interactive tasks, executing a Brown out policing algorithm; for the batch processing task, executing a Deferring delayed execution algorithm;
calculating average resource utilization rate of server cluster at time t
Figure BDA0003176537600000054
If it is not
Figure BDA0003176537600000055
Executing a virtual machine scheduling algorithm and a host scaling machine expansion algorithm;
and if the two conditions are not met, directly executing the task.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the execution process of the Brown out control algorithm specifically comprises the following steps:
for each server in the server list, the current resource utilization of server i is known
Figure BDA0003176537600000056
Judging whether the green energy R can be utilized at the current moment ttIf the green energy can not be utilized, triggering a brown control algorithm, and calculating according to the overload degree of the data center
Figure BDA0003176537600000057
Using a vernier thetatCalculating an expected utilization reduction value for Server i
Figure BDA0003176537600000058
And according to the value of dimmer thetatSelecting and deactivating a set of microservices on server i;
if the green energy can be utilized, the available green energy R at the current moment t is judgedtWhether or not less than the total energy consumption PtIf yes, triggering crownout control algorithm to calculate
Figure BDA0003176537600000059
The epsilon represents the proportion of the resource utilization rate of the batch processing task to the total resource utilization rate of the physical machine; according to thetatSearching and deactivating a set of microservices; if not, the interactive task is performed using the green energy source.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the execution process of the Deferring delay execution algorithm specifically comprises the following steps:
for all the batch processing tasks, the following three cases of judgment are respectively carried out:
determining whether the deadline for the batch job is at a start time when green energy is available
Figure BDA0003176537600000061
If the batch processing task cannot be executed by utilizing green energy, the batch processing task is directly executed at the time t; whether or notThen, delaying the execution time of the batch processing task by using the Deferring delayed execution algorithm
Figure BDA0003176537600000062
Then at time
Figure BDA0003176537600000063
Updating the task in time;
judging whether the starting time of the batch processing task is in the available time interval of the green energy, if so, executing the batch processing task by using the green energy; otherwise, delaying the execution time of the batch processing task by utilizing the Deferring delayed execution algorithm
Figure BDA0003176537600000064
And at the time of
Figure BDA0003176537600000065
Updating the task in time;
determining whether the start time of the batch processing task is at the time of availability of green energy
Figure BDA0003176537600000066
Thereafter, if yes, indicating that there is no more green energy available, the batch task is executed directly at time t.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the method for executing the virtual machine migration and the machine extension operations on the data center by adopting the virtual machine scheduling algorithm and the Hostscaling machine extension algorithm specifically comprises the following steps:
if the average utilization rate of the server cluster at the time t
Figure BDA0003176537600000067
Less than a resource utilization threshold TUlowThen, migrating the virtual machines by adopting a virtual machine scheduling algorithm, and executing a host scaling machine expansion algorithm to adjust the number of the physical machines, wherein the execution process of the host scaling machine expansion algorithm specifically comprises the following steps:
calculating a difference value n ' between the number of the physical machines required for prediction and the number of the physical machines actually utilized, and if n ' is greater than 0, indicating that green energy at the current time t is abundant, adding n ' servers in the system;
if n '< 0, the total resource of the physical machine at the current time t exceeds the resource requested by the user, closing n' physical machines in the system;
if n' is 0, the resource of the data center just meets the request of the user, and the number of the physical machines is not adjusted.
Another technical scheme adopted by the embodiment of the application is as follows: a cloud computing resource scheduling system, comprising:
a task acquisition module: the system comprises a data processing system, a data processing system and a data processing system, wherein the data processing system is used for acquiring a user request and dividing the user request into an interactive task and a batch processing task;
an energy consumption calculation module: the system comprises a data center, a data center and a server, wherein the data center is used for acquiring load state data of the data center and calculating the total server energy consumption of the data center according to the load state data;
a scheduling policy generation module: the scheduling strategy is used for calculating the interactive tasks and the batch processing tasks by adopting a green perception algorithm based on the total energy consumption of the server of the data center and generating the scheduling strategies of the interactive tasks and the batch processing tasks; the method comprises the steps that a green perception algorithm comprises a Brown out control algorithm and a Deferring delay execution algorithm, wherein the Brown out control algorithm is used for detecting whether micro-services which can be stopped or not exist in a current server or not, judging whether green energy can be utilized at the current moment or not and generating a scheduling strategy of the interactive tasks; the Deferring delay execution algorithm is used for judging whether to delay the execution time of the batch processing task according to the available time of green energy in a data center and generating a scheduling strategy of the batch processing task;
a scheduling policy enforcement module: and the method is used for executing virtual machine migration and machine expansion operation on the data center by adopting a virtual machine scheduling algorithm and a Host scaling machine expansion algorithm based on the generated scheduling strategy.
The embodiment of the application adopts another technical scheme that: a terminal comprising a processor, a memory coupled to the processor, wherein,
the memory stores program instructions for implementing the cloud computing resource scheduling method;
the processor is to execute the program instructions stored by the memory to control cloud computing resource scheduling.
The embodiment of the application adopts another technical scheme that: a storage medium storing program instructions executable by a processor to perform the cloud computing resource scheduling method.
Compared with the prior art, the embodiment of the application has the advantages that: according to the cloud computing resource scheduling method, the cloud computing resource scheduling system, the cloud computing resource scheduling terminal and the storage medium, the user request is divided into the interactive task and the batch processing task, for different types of tasks, the states of the micro-services are adjusted in a self-adaptive mode respectively through a brownnout control algorithm and a deferring delay execution algorithm according to the load condition of the data center, different scheduling strategies are generated, virtual machine migration and machine expansion operation are executed according to the scheduling strategies, and multi-layer resource scheduling based on micro-service management, virtual machine scheduling and physical machine expansion is achieved. According to the embodiment of the application, the utilization of green energy by the data center is considered in the scheduling strategy, the carbon emission of the data center is reduced, the efficient execution of tasks is ensured, and the pollution of cloud computing to the environment is reduced. In the micro-service management algorithm, the utilization rate of green energy is further improved.
Drawings
Fig. 1 is a flowchart of a cloud computing resource scheduling method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a cloud computing resource scheduling system according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a terminal according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Please refer to fig. 1, which is a flowchart illustrating a cloud computing resource scheduling method according to an embodiment of the present application. The cloud computing resource scheduling method in the embodiment of the application comprises the following steps:
s10, acquiring a user request of the data center, and dividing the user request into an interactive task and a batch processing task;
in this step, the obtained user request includes a timestamp of the user request and data of the page to which each user request accesses. The interactive task is a task which needs to provide real-time service so as to ensure the service quality. For example, a web application that requires a quick response from the server. The batch processing task has low requirement on real-time performance and can delay the provision of service.
S20: collecting load state data of each level (physical machine, virtual machine and microservice) in a data center;
in this step, the collected load state data includes data such as resource utilization rate of the virtual machine, physical machine energy consumption, and the like.
S30: calculating the total energy consumption of the server of the data center according to the load state data;
in this step, since the energy consumption of the server mainly comes from the CPU work, the CPU utilization rate is mainly considered when calculating the energy consumption of the server. Since the workload needs to be distributed to the virtual machines for execution, which may affect cpu utilization of the virtual machines and further affect server energy consumption, the workload of the data center (i.e. the sum of resources requested by users in the data center) needs to be calculated first when the server energy consumption is calculated.
In the embodiment of the present application, the workload calculation method is as follows: suppose there are M interactive tasks in a data center, am(t) represents the workload of the interactive task m at time t, umRepresenting resources required by the interactive task m, then am(t)×umIndicating the resources requested by the interactive task m at time t. Suppose there are N batch tasks in a data center, bn(t) represents the workload of the interactive task n at time t, unRepresenting the resources required by the interactive task n, thenbn(t)×unIndicating the resources requested by the interactive task n at time t. For batch processing tasks, the scheduler may choose to postpone execution until the next time, at which point the interactive task n actually requests the resource bnThe formula for calculation of (t) is:
Figure BDA0003176537600000101
in the formula (1), the reaction mixture is,
Figure BDA0003176537600000102
representing the proportion of interactive tasks that are delayed from execution at time t-1, bn(t)' represents the original workload of the interactive task n at time t.
Based on the above, the workload calculation formula of the system at the time t is as follows:
d(t)＝∑mam(t)×um+∑mbn(t)×un (2)
in the embodiment of the application, the resource utilization rates of different levels such as a physical machine, a virtual machine, a micro-service and the like are required to be considered for the calculation of the energy consumption of the server. The total energy consumption of the servers in the data center consists of idle energy consumption and dynamic energy consumption, and the utilization rate of the virtual machine resources on the physical machine determines the dynamic energy consumption of the physical machine. The server energy consumption calculation formula of each physical machine is as follows:
Figure BDA0003176537600000103
wherein the content of the first and second substances,
Figure BDA0003176537600000104
representing server energy consumption, w, of physical machine iiRepresenting the number of virtual machines deployed on physical machine i,
Figure BDA0003176537600000105
representing the power consumption of the physical machine i in the idle state,
Figure BDA0003176537600000106
representing the dynamic energy consumption of the physical machine i under different load conditions. ThetatA dimmer value representing time t, which represents the percentage of resource utilization by the microservice.
Figure BDA0003176537600000107
Representing the sum of the resource utilization of all the microservices run by the jth virtual machine on the physical machine i,
Figure BDA0003176537600000108
the calculation formula of (2) is as follows:
Figure BDA0003176537600000109
wherein A isjRepresenting the number of microservices on virtual machine j,
Figure BDA0003176537600000111
representing the resource utilization of the kth microservice on virtual machine j.
Further, in order to prevent the physical machine from overheating, cooling equipment needs to be deployed in the data center to cool the physical machine, and the work of the cooling equipment consumes a large amount of electric energy, so that the energy consumption of the cooling equipment is further calculated when the server is calculated to always consume time. The energy consumption of the cooling equipment is related to the total energy consumption of the servers in the data center and the cooling efficiency, and the energy consumption of the cooling equipment
Figure BDA0003176537600000112
The calculation formula is as follows:
Figure BDA0003176537600000113
Figure BDA0003176537600000114
in the above formula, CoP (T)sup) For cooling efficiency, TsupIs the temperature at which the cooling device is refrigerating.
Defining total energy consumption of all servers in the data center at the moment t as Ptα ═ d (t) '+ c (d (t)'), where
Figure BDA0003176537600000115
Represents the sum of the energy consumptions of all the servers in the data center at the moment t, wherein n represents the number of the servers in the data center,
Figure BDA0003176537600000116
representing the sum of the energy consumptions of all cooling devices in the data center at time t.
Definition of RtFor the amount of green energy in the data center at time t, where the green energy refers to renewable energy such as wind energy, solar energy, etc., the optimization objective of the present application can be expressed as minimizing the entire operation period (P)t-Rt) The sum of (a):
Figure BDA0003176537600000117
Figure BDA0003176537600000118
Figure BDA0003176537600000119
Figure BDA00031765376000001110
Figure BDA00031765376000001111
meanwhile, the formula (7) should satisfy the following condition: d (t) should be less than the maximum system capacity D, dimmer value thetatIs a [0,1 ]]The total workload of a batch task cannot exceed the total resource requirements of the task.
S40: based on the total energy consumption of the server of the data center, a Green-aware algorithm (Green-ware algorithm) is adopted to respectively calculate the interactive tasks and the batch processing tasks, and scheduling strategies of the interactive tasks and the batch processing tasks are respectively generated;
in this step, the green sensing algorithm includes a brown out policing algorithm and a Deferring delay execution algorithm. The Brown out control algorithm is used for processing interactive tasks, and the Deferring delay execution algorithm is used for processing batch processing tasks. The green perception algorithm is specifically as follows:
for each time t, the resource utilization of server i is known
Figure BDA0003176537600000121
Maximum threshold TU of resource utilizationupAnd a minimum threshold TUlow；
First, the number of overloaded servers in the data center is calculated
Figure BDA0003176537600000122
If it is not
Figure BDA0003176537600000123
For interactive tasks, executing a Brown out policing algorithm; for the batch processing task, executing a Deferring delayed execution algorithm;
calculating average resource utilization rate of server cluster at time t
Figure BDA0003176537600000124
If the average resource utilization rate
Figure BDA0003176537600000125
Less than a predetermined threshold TU for resource utilizationlowIf the data center can close part of the physical machines to reduce the total energy consumption, executing a virtual machine scheduling algorithm and a host scaling machine expansion algorithm;
and if the two conditions are not met, directly executing the task.
Further, the Brownout policing algorithm is used to detect whether there is a micro-service that can be disabled in the server, so as to reduce the overall energy consumption of the system. The algorithm generates different scheduling strategies depending on whether green energy can be utilized at the current time t. The execution process of the Brownout regulation algorithm specifically comprises the following steps:
first, for each server in the server list, the current resource utilization of server i is known
Figure BDA0003176537600000131
Judging whether the green energy R can be utilized at the current moment ttIf the green energy can not be utilized, executing a second step; if the green energy can be utilized, executing the third step;
secondly, triggering a brown out algorithm, and calculating a dimmer value according to the overload degree of the data center
Figure BDA0003176537600000132
Using the value of dimmer thetatCalculating an expected utilization reduction value for Server i
Figure BDA0003176537600000133
Then, according to the value of the dimmer θtA set of microservices on server i is selected and deactivated, thereby reducing the utilization of the server.
Thirdly, judging available green energy R at the current moment ttWhether or not less than the total energy consumption PtIf yes, executing the fourth step; if not, executing the fifth step;
fourthly, triggering a crownout control algorithm to calculate a dimmer value
Figure BDA0003176537600000134
Wherein the epsilon represents the resource utilization rate of the batch processing task to the total resource utilization rate of the physical machine
Figure BDA0003176537600000135
The ratio of (A) to (B); according to the value of dimmer thetatA set of microservices is searched and deactivated.
And fifthly, executing the interactive task by utilizing the green energy.
The Deferring delay execution algorithm is used for determining whether to delay the execution time of the batch processing task according to the available time of the green energy, so that the utilization rate of the green energy is maximized, and the carbon emission of the data center is reduced. The execution process of the Deferring delay execution algorithm specifically comprises the following steps:
for all the batch processing tasks, the following three cases of judgment are respectively carried out:
first, determining if the deadline for a batch job is at a start time when green energy is available
Figure BDA0003176537600000136
Before, if the deadline of the batch task is at
Figure BDA0003176537600000137
Previously, this means that the task cannot be performed using green energy, and therefore cannot be delayed and performed directly at time t; otherwise, delaying the execution time of the task by the Deferring delayed execution algorithm
Figure BDA0003176537600000138
Then at time
Figure BDA0003176537600000139
The task is updated on time.
Secondly, judging whether the starting time of the batch processing task is in the time interval of the availability of the green energy, if so, executing the task by using the green energy; otherwise, delaying the execution time of the task by the Deferring delayed execution algorithm
Figure BDA0003176537600000141
Then at time
Figure BDA0003176537600000142
The task is updated on time.
Thirdly, judging whether the starting time of the batch processing task is greenTime of availability of color energy source
Figure BDA0003176537600000143
Thereafter, if the start time of the batch job is at the time of availability of the green energy source
Figure BDA0003176537600000144
Then, meaning that there is no more green energy available, the batch task is performed directly at time t to guarantee QoS.
S50: based on a scheduling strategy, adopting a virtual machine scheduling algorithm and a Host scaling machine expansion algorithm to execute virtual machine migration and machine expansion operation;
in this step, if the average utilization rate of the server cluster at the time t
Figure BDA0003176537600000145
Less than a predetermined threshold TU for resource utilizationlowAnd migrating the virtual machines by adopting a virtual machine scheduling algorithm, and executing a Hostscaling machine expansion algorithm to adjust the number of the physical machines.
Specifically, the hostesscaling machine extension algorithm execution process specifically includes:
step one, calculating the difference value n ' between the number of physical machines required for prediction and the number of physical machines actually used, judging the value of n ', and if n ' is greater than 0, executing the step two; if n' <0, performing the third step; if n' is 0, executing the fourth step;
step two, representing that the green energy at the current moment t is abundant, adding n' servers in the system to improve the utilization rate of available cpu to improve QoS;
thirdly, if the total resources of the physical machines at the current moment t exceed the resources requested by the user, closing n' physical machines in the system to reduce the energy consumption of the system;
and fourthly, showing that the resources of the data center just meet the user request without adjusting the number of the physical machines.
Based on the above, in the cloud computing resource scheduling method of the embodiment of the application, the user request is divided into the interactive task and the batch processing task, for different types of tasks, the states of the micro-services are respectively adaptively adjusted by using a brown control algorithm and a deferring delay execution algorithm according to the load condition of the data center, different scheduling strategies are generated, and the virtual machine migration and the machine extension operation are executed according to the scheduling strategies, so that the multi-layer resource scheduling based on micro-service management, virtual machine scheduling and physical machine extension is realized. According to the embodiment of the application, the utilization of green energy by the data center is considered in the scheduling strategy, the carbon emission of the data center is reduced, the efficient execution of tasks is ensured, and the pollution of cloud computing to the environment is reduced. In the micro-service management algorithm, the utilization rate of green energy is further improved.
Fig. 2 is a schematic structural diagram of a cloud computing resource scheduling system according to an embodiment of the present application. The cloud computing resource scheduling system 40 according to the embodiment of the present application includes:
the task obtaining module 41: the system comprises a data processing system, a data processing system and a data processing system, wherein the data processing system is used for acquiring a user request and dividing the user request into an interactive task and a batch processing task;
energy consumption calculation module 42: the system comprises a data center, a data center and a server, wherein the data center is used for acquiring load state data of the data center and calculating the total server energy consumption of the data center according to the load state data;
the scheduling policy generation module 43: the method comprises the steps that a green perception algorithm is adopted to calculate interactive tasks and batch processing tasks based on the total energy consumption of a server of a data center, and a scheduling strategy of the interactive tasks and the batch processing tasks is generated; the method comprises the steps that a green perception algorithm comprises a Brown out control algorithm and a Deferring delay execution algorithm, wherein the Brown out control algorithm is used for detecting whether micro-services which can be stopped or not exist in a current server or not, judging whether green energy can be utilized at the current moment or not and generating a scheduling strategy of an interactive task; the Deferring delayed execution algorithm is used for judging whether to postpone the execution time of the batch processing task according to the available time of the green energy in the data center and generating a scheduling strategy of the batch processing task;
the scheduling policy enforcement module 44: and the method is used for executing virtual machine migration and machine expansion operation on the data center by adopting a virtual machine scheduling algorithm and a Host scaling machine expansion algorithm based on the generated scheduling strategy.
Please refer to fig. 3, which is a schematic diagram of a terminal structure according to an embodiment of the present application. The terminal 50 comprises a processor 51, a memory 52 coupled to the processor 51.
The memory 52 stores program instructions for implementing the cloud computing resource scheduling method described above.
The processor 51 is operative to execute program instructions stored by the memory 52 to control cloud computing resource scheduling.
The processor 51 may also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip having signal processing capabilities. The processor 51 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Please refer to fig. 4, which is a schematic structural diagram of a storage medium according to an embodiment of the present application. The storage medium of the embodiment of the present application stores a program file 61 capable of implementing all the methods described above, where the program file 61 may be stored in the storage medium in the form of a software product, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or terminal devices, such as a computer, a server, a mobile phone, and a tablet.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A cloud computing resource scheduling method is characterized by comprising the following steps:
acquiring a user request, and dividing the user request into an interactive task and a batch processing task;
acquiring load state data of a data center, and calculating the total server energy consumption of the data center according to the load state data;
calculating the interactive tasks and the batch processing tasks by adopting a green perception algorithm based on the total energy consumption of the server of the data center, and generating a scheduling strategy of the interactive tasks and the batch processing tasks; the method comprises the steps that a green perception algorithm comprises a Brown out control algorithm and a Deferring delay execution algorithm, wherein the Brown out control algorithm is used for detecting whether micro-services which can be stopped or not exist in a current server or not, judging whether green energy can be utilized at the current moment or not and generating a scheduling strategy of the interactive tasks; the Deferring delay execution algorithm is used for judging whether to delay the execution time of the batch processing task according to the available time of green energy in a data center and generating a scheduling strategy of the batch processing task;
and based on the generated scheduling strategy, executing virtual machine migration and machine expansion operation on the data center by adopting a virtual machine scheduling algorithm and a Host scaling machine expansion algorithm.
2. The cloud computing resource scheduling method according to claim 1, wherein the calculating of the total server energy consumption of the data center according to the load status data specifically comprises:
calculating the server energy consumption of each physical machine:
Figure FDA0003176537590000011
wherein the content of the first and second substances,
Figure FDA0003176537590000012
representing server energy consumption, w, of physical machine iiRepresenting the number of virtual machines deployed on physical machine i,
Figure FDA0003176537590000013
representing the power consumption of the physical machine i in the idle state,
Figure FDA0003176537590000014
represents the dynamic energy consumption of the physical machine i in a load state, thetatA regulator value representing time t, which represents a resource utilization percentage of the microservice,
Figure FDA0003176537590000021
representing the sum of the resource utilization of all the microservices run by the jth virtual machine on the physical machine i,
Figure FDA0003176537590000022
the calculation formula of (2) is as follows:
Figure FDA0003176537590000023
wherein A isjRepresenting the number of microservices on virtual machine j,
Figure FDA0003176537590000024
representing the resource utilization rate of the kth micro-service on the virtual machine j;
calculating the energy consumption of the cooling equipment of each physical machine according to the energy consumption of the server:
Figure FDA0003176537590000025
Figure FDA0003176537590000026
wherein, CoP (T)sup) For cooling efficiency, TsupIs the temperature of refrigeration of the cooling equipment;
the total energy consumption of the servers of the data center at the moment t is as follows:
Pt＝d(t)′+c(d(t)′)
wherein the content of the first and second substances,
Figure FDA0003176537590000027
represents the sum of the energy consumptions of all the servers in the data center at the moment t, wherein n represents the number of the servers in the data center,
Figure FDA0003176537590000028
representing the sum of the energy consumptions of all cooling devices in the data center at time t.
3. The cloud computing resource scheduling method of claim 2, wherein the computing total server energy consumption of the data center according to the load status data further comprises:
calculating the workload of the data center; the workload calculation mode is as follows:
suppose there are M interactive tasks and N batch tasks in a data center, am(t) represents the workload of the interactive task m at time t, umRepresenting resources required by an interactive task m, am(t)×umResource representing interactive task m request at time t, bn(t) represents the workload of the interactive task n at time t, unRepresenting resources required by an interactive task n, bn(t)×unRepresenting the resource requested by the interactive task n at time t, the scheduler may choose to defer it to the next time for the batch task, so that the resource b actually requested by the interactive task n at time tn(t) is:
Figure FDA0003176537590000031
in the above formula, the first and second carbon atoms are,
Figure FDA0003176537590000032
representing the proportion of interactive tasks that are delayed from execution at time t-1, bn(t)' represents the original workload of the interactive task n at time t;
the workload of the data center at the moment t is as follows:
d(t)＝∑mam(t)×um+∑mbn(t)×un。
4. the cloud computing resource scheduling method according to any one of claims 1 to 3, wherein the interactive tasks and the batch tasks are calculated by using a green perception algorithm, and the scheduling policy for generating the interactive tasks and the batch tasks specifically comprises:
for each time t, the resource utilization of server i is known
Figure FDA0003176537590000033
Maximum threshold TU of resource utilizationupAnd a minimum threshold TUlow，
Calculating number of overloaded servers in a data center
Figure FDA0003176537590000034
If it is not
Figure FDA0003176537590000035
For interactive tasks, executing a Brown out policing algorithm; for the batch processing task, executing a Deferring delayed execution algorithm;
calculating average resource utilization rate of server cluster at time t
Figure FDA0003176537590000036
If it is not
Figure FDA0003176537590000037
Executing a virtual machine scheduling algorithm and a host scaling machine expansion algorithm;
and if the two conditions are not met, directly executing the task.
5. The cloud computing resource scheduling method according to claim 4, wherein the execution process of the Brownout policing algorithm is specifically as follows:
for each server in the server list, the current resource utilization of server i is known
Figure FDA0003176537590000038
Judging whether the green energy R can be utilized at the current moment ttIf the green energy can not be utilized, triggering a brown control algorithm, and calculating according to the overload degree of the data center
Figure FDA0003176537590000039
Using a vernier thetatCalculating an expected utilization reduction value for Server i
Figure FDA0003176537590000041
And according to the value of dimmer thetatSelecting and deactivating a set of microservices on server i;
if the green energy can be utilized, the available green energy R at the current moment t is judgedtWhether or not less than the total energy consumption PtIf yes, triggering crownout control algorithm to calculate
Figure FDA0003176537590000042
The epsilon represents the proportion of the resource utilization rate of the batch processing task to the total resource utilization rate of the physical machine; according to thetatSearching and deactivating a set of microservices; if not, the interactive task is performed using the green energy source.
6. The cloud computing resource scheduling method according to claim 5, wherein the execution process of the Deferring delay execution algorithm specifically includes:
for all the batch processing tasks, the following three cases of judgment are respectively carried out:
determining whether the deadline for the batch job is at a start time when green energy is available
Figure FDA0003176537590000043
If the batch processing task cannot be executed by utilizing green energy, the batch processing task is directly executed at the time t; otherwise, delaying the execution time of the batch processing task by utilizing the Deferring delayed execution algorithm
Figure FDA0003176537590000044
Then at time
Figure FDA0003176537590000045
Updating the task in time;
judging whether the starting time of the batch processing task is in the available time interval of the green energy, if so, executing the batch processing task by using the green energy; otherwise, delaying the execution time of the batch processing task by utilizing the Deferring delayed execution algorithm
Figure FDA0003176537590000046
And at the time of
Figure FDA0003176537590000047
Updating the task in time;
determining whether the start time of the batch processing task is at the time of availability of green energy
Figure FDA0003176537590000048
Thereafter, if yes, indicating that there is no more green energy available, the batch task is executed directly at time t.
7. The cloud computing resource scheduling method of claim 6, wherein the executing of the virtual machine migration and the machine expansion operation on the data center by using the virtual machine scheduling algorithm and the Host scaling machine expansion algorithm specifically comprises:
if the average utilization rate of the server cluster at the time t
Figure FDA0003176537590000051
Less than a resource utilization threshold TUlowThen, migrating the virtual machines by adopting a virtual machine scheduling algorithm, and executing a Host scaling machine expansion algorithm to adjust the number of the physical machines, wherein the execution process of the Host scaling machine expansion algorithm specifically comprises the following steps:
calculating a difference value n ' between the number of the physical machines required for prediction and the number of the physical machines actually utilized, and if n ' is greater than 0, indicating that green energy at the current time t is abundant, adding n ' servers in the system;
if n '< 0, it means that the total resource of the physical machine at the current time t exceeds the resource requested by the user, then n' physical machines are closed in the system;
if n' is 0, the resource of the data center just meets the request of the user, and the number of the physical machines is not adjusted.
8. A cloud computing resource scheduling system, comprising:
a task acquisition module: the system comprises a data processing system, a data processing system and a data processing system, wherein the data processing system is used for acquiring a user request and dividing the user request into an interactive task and a batch processing task;
an energy consumption calculation module: the system comprises a data center, a data center and a server, wherein the data center is used for acquiring load state data of the data center and calculating the total server energy consumption of the data center according to the load state data;
a scheduling policy generation module: the scheduling strategy is used for calculating the interactive tasks and the batch processing tasks by adopting a green perception algorithm based on the total energy consumption of the server of the data center and generating the scheduling strategies of the interactive tasks and the batch processing tasks; the method comprises the steps that a green perception algorithm comprises a Brown out control algorithm and a Deferring delay execution algorithm, wherein the Brown out control algorithm is used for detecting whether micro-services which can be stopped or not exist in a current server or not, judging whether green energy can be utilized at the current moment or not and generating a scheduling strategy of the interactive tasks; the Deferring delay execution algorithm is used for judging whether to delay the execution time of the batch processing task according to the available time of green energy in a data center and generating a scheduling strategy of the batch processing task;
a scheduling policy enforcement module: and the method is used for executing virtual machine migration and machine expansion operation on the data center by adopting a virtual machine scheduling algorithm and a Host scaling machine expansion algorithm based on the generated scheduling strategy.
9. A terminal, comprising a processor, a memory coupled to the processor, wherein,
the memory stores program instructions for implementing the cloud computing resource scheduling method of any of claims 1-7;
the processor is to execute the program instructions stored by the memory to control cloud computing resource scheduling.
10. A storage medium storing program instructions executable by a processor to perform the cloud computing resource scheduling method according to any one of claims 1 to 7.
CN202110834069.4A 2021-07-23 2021-07-23 Cloud computing resource scheduling method, system, terminal and storage medium Pending CN113672383A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110834069.4A CN113672383A (en) 2021-07-23 2021-07-23 Cloud computing resource scheduling method, system, terminal and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110834069.4A CN113672383A (en) 2021-07-23 2021-07-23 Cloud computing resource scheduling method, system, terminal and storage medium

Publications (1)

Publication Number Publication Date
CN113672383A true CN113672383A (en) 2021-11-19

Family

ID=78539907

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110834069.4A Pending CN113672383A (en) 2021-07-23 2021-07-23 Cloud computing resource scheduling method, system, terminal and storage medium

Country Status (1)

Country Link
CN (1) CN113672383A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114819508A (en) * 2022-03-28 2022-07-29 上海交通大学 Method and system for calculating distributed photovoltaic maximum access capacity of comprehensive energy system
CN114928633A (en) * 2022-05-16 2022-08-19 江苏赞奇科技股份有限公司 Efficient control method and system based on complex cloud application environment
CN115190121A (en) * 2022-05-25 2022-10-14 上海交通大学 Cross-region-based micro-service overload scheduling system, method and equipment
CN115904258A (en) * 2023-02-27 2023-04-04 南昌大学 Data copying method, system, storage medium and equipment based on carbon emission
CN116302451A (en) * 2023-05-18 2023-06-23 广州豪特节能环保科技股份有限公司 Offline energy-saving scheduling method and system for cloud computing data center
CN116414660A (en) * 2023-04-14 2023-07-11 云储新能源科技有限公司 Data center energy consumption and environment monitoring system based on energy Internet
CN117407248A (en) * 2023-12-08 2024-01-16 南京云玑信息科技有限公司 Method and system for realizing accurate green energy conservation of cloud computer
US11960342B2 (en) 2022-02-09 2024-04-16 Microsoft Technology Licensing, Llc Sustainability-aware computing device behavior management

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11960342B2 (en) 2022-02-09 2024-04-16 Microsoft Technology Licensing, Llc Sustainability-aware computing device behavior management
CN114819508B (en) * 2022-03-28 2024-03-29 上海交通大学 Comprehensive energy system distributed photovoltaic maximum admittance capacity calculation method and system
CN114819508A (en) * 2022-03-28 2022-07-29 上海交通大学 Method and system for calculating distributed photovoltaic maximum access capacity of comprehensive energy system
CN114928633A (en) * 2022-05-16 2022-08-19 江苏赞奇科技股份有限公司 Efficient control method and system based on complex cloud application environment
CN114928633B (en) * 2022-05-16 2024-04-16 江苏赞奇科技股份有限公司 Efficient control method and system based on complex cloud application environment
CN115190121A (en) * 2022-05-25 2022-10-14 上海交通大学 Cross-region-based micro-service overload scheduling system, method and equipment
CN115190121B (en) * 2022-05-25 2023-11-17 上海交通大学 Cross-region-based micro-service overload scheduling system, method and equipment
CN115904258A (en) * 2023-02-27 2023-04-04 南昌大学 Data copying method, system, storage medium and equipment based on carbon emission
CN116414660A (en) * 2023-04-14 2023-07-11 云储新能源科技有限公司 Data center energy consumption and environment monitoring system based on energy Internet
CN116302451B (en) * 2023-05-18 2023-08-08 广州豪特节能环保科技股份有限公司 Offline energy-saving scheduling method and system for cloud computing data center
CN116302451A (en) * 2023-05-18 2023-06-23 广州豪特节能环保科技股份有限公司 Offline energy-saving scheduling method and system for cloud computing data center
CN117407248B (en) * 2023-12-08 2024-03-12 南京云玑信息科技有限公司 Method and system for realizing accurate green energy conservation of cloud computer
CN117407248A (en) * 2023-12-08 2024-01-16 南京云玑信息科技有限公司 Method and system for realizing accurate green energy conservation of cloud computer

Similar Documents

Publication Publication Date Title
CN113672383A (en) Cloud computing resource scheduling method, system, terminal and storage medium
Arshad et al. Utilizing power consumption and SLA violations using dynamic VM consolidation in cloud data centers
CN102868763B (en) The dynamic adjusting method that under a kind of cloud computing environment, virtual web application cluster is energy-conservation
Zhou et al. A novel virtual machine deployment algorithm with energy efficiency in cloud computing
CN113535409B (en) Server-free computing resource distribution system oriented to energy consumption optimization
EP2524277A2 (en) Methods and apparatus for coordinated energy management in virtualized data centers
WO2022246759A1 (en) Power consumption adjustment method and apparatus
US20130080809A1 (en) Server system and power managing method thereof
Li et al. Enhanced parallel application scheduling algorithm with energy consumption constraint in heterogeneous distributed systems
CN101819459B (en) Heterogeneous object memory system-based power consumption control method
JP2005063066A (en) Distributed computing system
CN110008515B (en) Renewable energy data center management method and device
Hu et al. A schedule method for parallel applications on heterogeneous distributed systems with energy consumption constraint
Kant et al. Enhancing data center sustainability through energy-adaptive computing
Thiam et al. Energy efficient cloud data center using dynamic virtual machine consolidation algorithm
Fan et al. GreenSleep: a multi-sleep modes based scheduling of servers for cloud data center
Shah et al. Phase level energy aware map reduce scheduling for big data applications
Dong et al. Energy-efficient scheme based on user task characteristic in virtual cloud platform
Liu et al. Research on Energy Saving Algorithm of Datacenter in Cloud Computing System
WO2022110443A1 (en) Cloud data center energy saving method and system based on container control
Guo et al. Research on a Virtual Machine Mode Transfer Method Supporting Energy Consumption Optimization
CN111897410B (en) System component power consumption optimization method and device, electronic equipment and storage medium
WO2022104500A1 (en) Load control method and apparatus, computer device, and storage medium
CN115543450B (en) Method for dynamically dormancy of server-free calculation of resource optimization in edge scene and application
WO2022141735A1 (en) Processing apparatus, processing method, and related device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination