CN109120416B - Self-adaptive delay shutdown method of server based on cloud network - Google Patents

Self-adaptive delay shutdown method of server based on cloud network Download PDF

Info

Publication number
CN109120416B
CN109120416B CN201810946902.2A CN201810946902A CN109120416B CN 109120416 B CN109120416 B CN 109120416B CN 201810946902 A CN201810946902 A CN 201810946902A CN 109120416 B CN109120416 B CN 109120416B
Authority
CN
China
Prior art keywords
node
energy consumption
delay
shutdown
time
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.)
Expired - Fee Related
Application number
CN201810946902.2A
Other languages
Chinese (zh)
Other versions
CN109120416A (en
Inventor
孙健
周润
孙罡
廖丹
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.)
University of Electronic Science and Technology of China
Original Assignee
University of Electronic Science and Technology of China
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 University of Electronic Science and Technology of China filed Critical University of Electronic Science and Technology of China
Priority to CN201810946902.2A priority Critical patent/CN109120416B/en
Publication of CN109120416A publication Critical patent/CN109120416A/en
Application granted granted Critical
Publication of CN109120416B publication Critical patent/CN109120416B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/02—Details
    • H04L12/12—Arrangements for remote connection or disconnection of substations or of equipment thereof
    • 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
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer And Data Communications (AREA)
  • Power Sources (AREA)

Abstract

The invention discloses a self-adaptive delayed shutdown method of a server based on a cloud network, which comprises the following steps: s1, starting a server of the node and updating the attribute; s2, initializing no-load delay time; s3, traversing all SRs in the working state; s4, traversing the SR node, and judging whether the SR node is in an unloaded state; s5, judging whether the no-load delay time is reached; s6, closing the current node server and updating the node attribute; s7, updating the idle delay time, the idle waiting time and the idle energy consumption; s8, restoring the delay time to an initial value, and updating the working time of the node and the working energy consumption during operation; s9, returning the energy consumption and the time delay cost; s10, judging whether a next node exists or not; s11, judging whether the next SR exists or not, if not, returning the total consumed energy and the total delay cost to realize delayed shutdown; the invention solves the problems of large energy consumption and large machine abrasion in the prior art.

Description

Self-adaptive delay shutdown method of server based on cloud network
Technical Field
The invention belongs to the technical field of cloud networks, and particularly relates to a self-adaptive delay shutdown method of a server based on a cloud network.
Background
With the rapid development and popularization of information technology, the construction of central machine rooms such as cloud networks and the like and the quantity of communication equipment are rapidly increased, and the machine rooms become core platforms for business management of various enterprises and public institutions. The computer room with network equipment, computer server and other communication equipment becomes an important place for data exchange and storage, and needs special measures for protection. But the machine room consumes energy seriously, which also becomes a very troublesome thing for performance manufacturers. The IT equipment power consumption comprises all loads of the IT equipment, such as servers, storage and network equipment, and the total data center power consumption comprises power consumption supporting the load condition of the IT equipment. With the rapid increase and shortage of energy demand, "green energy conservation" has attracted great attention all over the world. Therefore, following the great era background of NFV, energy saving research in networks such as cloud networks and data centers is imperative.
The computer is a high-tech top product, is durable, is normally used after being started for a long time (such as a machine room server), is not used or is closed well, and is always left open. However, frequent powering on and off impairs the life of the computer, and what is deeply harmed is the hard disk and the display. When the hard disk is out of work, the read-write magnetic head is close to the disk surface, the magnetic head floats above the disk to work by buoyancy generated by high-speed operation after the hard disk is started, and the read-write magnetic head returns to the original position after the hard disk is shut down, so that the abrasion to the disk is naturally increased after the hard disk is opened and closed. When the display works normally, the current of the display is relatively stable, and when the display is turned on or turned off, the display is impacted to a certain extent due to sudden increase and reduction of the current, and the display is naturally unfavorable due to frequent turning on or off.
At present, most energy-saving strategies are based on the combination of VNFs, the number of started servers is reduced as much as possible, and the waste of non-working performance sources of the servers, caused by untimely online arrival and revocation of dynamic service function chains, is ignored (the non-working performance source consumption caused by the time interval from the last VNF to the next VNF is in two conditions, namely, the server is kept in a startup state and runs in a no-load mode for waiting, or the server is firstly closed (shutdown energy consumption) and then opened (startup energy consumption) when the next VNF arrives). In the existing literature, there is almost no research on the system of non-working energy overhead of the server caused by the continuous update and the alternate and dynamic deployment of the online SFC, and certainly, there is no effective method to solve the problem at present. Some studies have mentioned that a lot of energy consumption is caused by idle servers and frequent switching opportunities in data centers, but no effective solution to this problem has been proposed.
In summary, the prior art has the following problems:
(1) between continuous update and alternation of the online SFC, a large amount of energy consumption is caused by dynamically deployed idle servers and frequent switching opportunities;
(2) frequent switching of the server may cause machine wear and energy consumption.
Disclosure of Invention
Aiming at the defects in the prior art, the self-adaptive delay shutdown method of the cloud network-based server, which is provided by the invention, has the advantages of low energy consumption and long service life of a machine, improves the utilization rate and the deployment efficiency of network resources, and solves the problems of high energy consumption and high machine abrasion in the prior art.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
a self-adaptive delay shutdown method of a server based on a cloud network comprises the following steps:
s1: traversing nodes in the SFC deployment scheme, starting servers of all the nodes, and updating the startup times, the startup energy consumption, the startup time delay and the deployment resources of the nodes;
s2: initializing the no-load delay time of all starting nodes;
s3: traversing all user service requests SR in a working state of the successfully deployed SFC, judging whether the working time of the current SR is reached, if so, canceling the current SR of the SFC, recovering the deployed resources occupied by the SFC, entering the step S4, and otherwise, repeating the step S3;
s4: traversing physical nodes used by the current expired SR, judging whether the current nodes are in an idle state, if so, entering a step S5, otherwise, entering a step S8;
s5: judging whether the no-load delay time of the current node is reached, if so, entering a step S6, otherwise, entering a step S7;
s6: closing the current node server, updating the shutdown times, shutdown energy consumption and shutdown time delay of the node, and entering step S9;
s7: updating the no-load delay time, the no-load waiting time and the no-load energy consumption of the current node, and entering the step S9;
s8: restoring the delay time to an initial value, updating the current node working time and the working energy consumption during operation, and entering the step S9;
s9: returning the consumed energy and the time delay cost of the current node, and entering the step S10;
s10: judging whether the current node in the current expired SR has a next node or not, if so, taking the next node as the current node, and entering a step S4, otherwise, entering a step S11;
s11: and judging whether the next SR in the working state exists, if so, taking the next SR as the current SR, and entering the step S3, otherwise, returning all the nodes in all the SRs to the total energy consumption and the total time delay cost, and realizing delayed shutdown.
Further, in step S1, the update formulas of the boot frequency, boot energy consumption, boot latency, and deployment resource of the current node are:
Figure BDA0001770466160000031
in the formula (I), the compound is shown in the specification,
Figure BDA0001770466160000032
the number of times of starting the node is;
Figure BDA0001770466160000033
starting up energy consumption for the nodes;
Figure BDA0001770466160000034
energy consumption for starting the server;
Figure BDA0001770466160000035
starting up time delay for the node;
Figure BDA0001770466160000036
a time delay for starting the server;
Figure BDA0001770466160000037
is the remaining resource of the current physical network;
Figure BDA0001770466160000038
is the physical network total resource;
Figure BDA0001770466160000039
deploying required resources of the scheme for the SR; v. ofiIs the current node.
Further, in step S2, the initialization formula of the dead time of the node is:
Figure BDA0001770466160000041
in the formula (I), the compound is shown in the specification,
Figure BDA0001770466160000042
ξ dead timeemptyIs the initial value of the dead time delay.
Further, in step S3, the recovery formula of the deployment resource occupied by the SFC is:
Figure BDA0001770466160000043
in the formula (I), the compound is shown in the specification,
Figure BDA0001770466160000044
is the remaining resource of the current physical network;
Figure BDA0001770466160000045
the required resources of the scheme are deployed for the SR.
Further, in step S4, the formula is determined as:
Figure BDA0001770466160000046
in the formula (I), the compound is shown in the specification,
Figure BDA0001770466160000047
requesting a set of VNFs for different SFCs deployed in the node;
Figure BDA0001770466160000048
a set used as a forwarding function in a node;
the above formula is satisfied, and the current node is in an idle state; the above formula is not satisfied, and the current node is not in an idle state.
Further, in step S6, the update formula of the shutdown frequency, the shutdown energy consumption, and the shutdown delay of the current node is as follows:
Figure BDA0001770466160000049
in the formula (I), the compound is shown in the specification,
Figure BDA00017704661600000410
is the shutdown frequency of the node;
Figure BDA00017704661600000411
energy consumption for node shutdown;
Figure BDA00017704661600000412
power consumption for server shutdown;
Figure BDA00017704661600000413
a node shutdown delay;
Figure BDA00017704661600000414
the server power-off delay is provided.
Further, in step S7, the current node dead time delay time, dead time waiting time, and dead energy consumption are updated by the following formula:
Figure BDA00017704661600000415
in the formula (I), the compound is shown in the specification,
Figure BDA00017704661600000416
is the node dead time delay;
Figure BDA00017704661600000417
is the node no-load waiting time;
Figure BDA00017704661600000418
no-load energy consumption of the nodes is realized;
Figure BDA0001770466160000051
the server is in no-load energy consumption.
Further, in step S8, the delay time is restored to the initial value, and the update formula of the node operating time and the operating energy consumption during the operation is as follows:
Figure BDA0001770466160000052
in the formula,
Figure BDA0001770466160000053
ξ for node dead timeemptyIs the initial value of the dead time delay;
Figure BDA0001770466160000054
the working time of the node is;
Figure BDA0001770466160000055
operating energy consumption for the node;
Figure BDA0001770466160000056
operating energy consumption for the server.
Further, in step S9, the calculation formula of the consumed energy and the delay cost of the current node is:
Figure BDA0001770466160000057
in the formula (I), the compound is shown in the specification,
Figure BDA00017704661600000518
energy consumption of the current node;
Figure BDA00017704661600000519
time delay cost of the current node;
Figure BDA0001770466160000058
starting up energy consumption for the nodes;
Figure BDA0001770466160000059
energy consumption for starting the server;
Figure BDA00017704661600000510
no-load energy consumption of the nodes is realized;
Figure BDA00017704661600000511
operating energy consumption for the node;
Figure BDA00017704661600000512
starting up time delay for the node;
Figure BDA00017704661600000513
a node shutdown delay;
Figure BDA00017704661600000514
is the node no-load waiting time;
Figure BDA00017704661600000515
is the node operating time.
Further, in step S11, the calculation formula of the total consumed energy and the total delay cost of all nodes is:
Figure BDA00017704661600000516
in the formula, ESFCTotal consumed energy for all nodes; t isSFCThe total latency cost for all nodes;
Figure BDA00017704661600000517
is a collection of nodes for all SRs in working state.
The beneficial effect of this scheme does:
(1) green and energy-saving: the invention considers the working energy consumption of the server in each state, eliminates a large amount of energy waste caused by long-time no-load waiting of the server, can also avoid machine abrasion and energy consumption caused by frequent startup and shutdown of the server, reduces the energy expenditure and the operation cost of SFC deployment to the maximum extent, greatly reduces the service abrasion of the server, prolongs the service life of the server, and reduces the replacement rate and the purchase cost of equipment to a certain extent;
(2) the network resource utilization rate is high: the dynamic deployment of the online SFC considers the online survival time for the service request of the SFCs which arrive at an irregular time, and when the survival time arrives, the service request can be cancelled and the occupied resources are released, so that the service request can be continuously used by the subsequent SFCs, and the utilization rate of network resources is improved;
(3) the deployment efficiency is high: the energy-saving system is more flexible, the delayed shutdown time of each server of the bottom node is adaptively and intelligently adjusted according to different service requirements, the flexibility is improved, and the deployment time of the VNF is not prolonged by waiting for the shutdown or restart of the node after the shutdown when a large number of requests arrive, so that the deployment efficiency is improved.
Drawings
Fig. 1 is a flowchart of an adaptive delayed shutdown method for a server based on a cloud network.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
A method for adaptive delayed shutdown of a server based on a cloud network, as shown in fig. 1, includes the following steps:
s1: traversing nodes in the SFC deployment scheme, starting servers of all the nodes, and updating the startup times, the startup energy consumption, the startup time delay and the deployment resources of the nodes, wherein the updating formula is as follows:
Figure BDA0001770466160000071
in the formula (I), the compound is shown in the specification,
Figure BDA0001770466160000072
the number of times of starting the node is;
Figure BDA0001770466160000073
starting up energy consumption for the nodes;
Figure BDA0001770466160000074
energy consumption for starting the server;
Figure BDA0001770466160000075
starting up time delay for the node;
Figure BDA0001770466160000076
a time delay for starting the server;
Figure BDA0001770466160000077
is the remaining resource of the current physical network;
Figure BDA0001770466160000078
is the physical network total resource;
Figure BDA0001770466160000079
deploying required resources of the scheme for the SR; v. ofiIs the current node;
s2: initializing the no-load delay time of all the open nodes, wherein the initialization formula is as follows:
Figure BDA00017704661600000710
in the formula (I), the compound is shown in the specification,
Figure BDA00017704661600000711
ξ dead timeemptyIs the initial value of the dead time delay;
s3: traversing all user service requests SR in a working state of the successfully deployed SFC, judging whether the working time of the current SR is reached, if so, canceling the current SR of the SFC, recovering the deployed resources occupied by the SFC, including bottom node resources and bandwidth resources, entering step S4, otherwise, repeating step S3;
the recovery formula of the deployment resources occupied by the SFC is as follows:
Figure BDA00017704661600000712
in the formula (I), the compound is shown in the specification,
Figure BDA00017704661600000713
is the remaining resource of the current physical network;
Figure BDA00017704661600000714
deploying required resources of the scheme for the SR;
s4: traversing physical nodes used by the current expired SR, and judging whether the current node is in an idle state, if so, entering a step S5, otherwise, entering a step S8, wherein the judgment formula is as follows:
Figure BDA00017704661600000715
in the formula (I), the compound is shown in the specification,
Figure BDA00017704661600000716
requesting a set of VNFs for different SFCs deployed in the node;
Figure BDA00017704661600000717
a set used as a forwarding function in a node;
the above formula is satisfied, and the current node is in an idle state; the above formula is not satisfied, and the current node is not in an idle state;
s5: judging whether the no-load delay time of the current node is reached, if so, entering a step S6, otherwise, entering a step S7;
s6: closing the current node server, updating the shutdown times, shutdown energy consumption and shutdown time delay of the node, and entering step S9, where the update formula is:
Figure BDA0001770466160000081
in the formula (I), the compound is shown in the specification,
Figure BDA0001770466160000082
is the shutdown frequency of the node;
Figure BDA0001770466160000083
energy consumption for node shutdown;
Figure BDA0001770466160000084
power consumption for server shutdown;
Figure BDA0001770466160000085
a node shutdown delay;
Figure BDA0001770466160000086
a server power-off time delay;
s7: and (4) updating the idle delay time, the idle waiting time and the idle energy consumption of the current node, and entering the step S9, wherein the updating formula is as follows:
Figure BDA0001770466160000087
in the formula (I), the compound is shown in the specification,
Figure BDA0001770466160000088
is the node dead time delay;
Figure BDA0001770466160000089
is the node no-load waiting time;
Figure BDA00017704661600000810
no-load energy consumption of the nodes is realized;
Figure BDA00017704661600000811
no-load energy consumption of the server is achieved;
s8: restoring the delay time to the initial value, updating the current node working time and the working energy consumption during the operation, and entering the step S9, wherein the updating formula is as follows:
Figure BDA00017704661600000812
in the formula,
Figure BDA00017704661600000813
ξ for node dead timeemptyIs the initial value of the dead time delay;
Figure BDA00017704661600000814
the working time of the node is;
Figure BDA00017704661600000815
operating energy consumption for the node;
Figure BDA00017704661600000816
operating energy consumption for the server;
s9: returning the consumed energy and the delay cost of the current node, and proceeding to step S10, where the calculation formula of the consumed energy and the delay cost of the current node is:
Figure BDA0001770466160000091
in the formula (I), the compound is shown in the specification,
Figure BDA0001770466160000092
energy consumption of the current node;
Figure BDA0001770466160000093
time delay cost of the current node;
Figure BDA0001770466160000094
starting up energy consumption for the nodes;
Figure BDA0001770466160000095
energy consumption for starting the server;
Figure BDA0001770466160000096
is node nullConsumption of energy-carrying source;
Figure BDA0001770466160000097
operating energy consumption for the node;
Figure BDA0001770466160000098
starting up time delay for the node;
Figure BDA0001770466160000099
a node shutdown delay;
Figure BDA00017704661600000910
is the node no-load waiting time;
Figure BDA00017704661600000911
the working time of the node is;
s10: judging whether the current node in the current expired SR has a next node or not, if so, taking the next node as the current node, and entering a step S4, otherwise, entering a step S11;
s11: judging whether the next SR in the working state exists, if so, taking the next SR as the current SR, and entering step S3, otherwise, returning all the node total energy consumption and total delay cost in all the SRs to realize delayed shutdown, wherein the calculation formulas of all the node total energy consumption and total delay cost are as follows:
Figure BDA00017704661600000912
in the formula, ESFCTotal consumed energy for all nodes; t isSFCThe total latency cost for all nodes;
Figure BDA00017704661600000913
is a collection of nodes for all SRs in working state.
The self-adaptive delay shutdown method of the cloud network-based server, which is provided by the invention, has the advantages of low energy consumption and long service life of a machine, improves the utilization rate of network resources and the deployment efficiency, and solves the problems of high energy consumption and high machine abrasion in the prior art.

Claims (10)

1. A self-adaptive delay shutdown method of a server based on a cloud network is characterized by comprising the following steps:
s1: traversing nodes in the SFC deployment scheme, starting servers of all the nodes, and updating the startup times, the startup energy consumption, the startup time delay and the deployment resources of the nodes;
s2: initializing the no-load delay time of all starting nodes;
s3: traversing all user service requests SR in a working state of the successfully deployed SFC, judging whether the working time of the current SR is reached, if so, canceling the current SR of the SFC, recovering the deployed resources occupied by the SFC, entering the step S4, and otherwise, repeating the step S3;
s4: traversing physical nodes used by the current expired SR, judging whether the current nodes are in an idle state, if so, entering a step S5, otherwise, entering a step S8;
s5: judging whether the no-load delay time of the current node is reached, if so, entering a step S6, otherwise, entering a step S7;
s6: closing the current node server, updating the shutdown times, shutdown energy consumption and shutdown time delay of the node, and entering step S9;
s7: updating the no-load delay time, the no-load waiting time and the no-load energy consumption of the current node, and entering the step S9;
s8: restoring the delay time to an initial value, updating the current node working time and the working energy consumption during operation, and entering the step S9;
s9: returning the consumed energy and the time delay cost of the current node, and entering the step S10;
s10: judging whether the current node in the current expired SR has a next node or not, if so, taking the next node as the current node, and entering a step S4, otherwise, entering a step S11;
s11: and judging whether the next SR in the working state exists, if so, taking the next SR as the current SR, and entering the step S3, otherwise, returning all the nodes in all the SRs to the total energy consumption and the total time delay cost, and realizing delayed shutdown.
2. The adaptive delayed shutdown method for the cloud network-based server according to claim 1, wherein in step S1, the update formulas of the startup times, the startup energy consumption, the startup delay and the deployment resources of the current node are:
Figure FDA0002295424840000021
in the formula (I), the compound is shown in the specification,
Figure FDA0002295424840000022
the number of times of starting the node is;
Figure FDA0002295424840000023
starting up energy consumption for the nodes;
Figure FDA0002295424840000024
energy consumption for starting the server;
Figure FDA0002295424840000025
starting up time delay for the node;
Figure FDA0002295424840000026
a time delay for starting the server;
Figure FDA0002295424840000027
is the remaining resource of the current physical network;
Figure FDA0002295424840000028
is the physical network total resource;
Figure FDA0002295424840000029
deploying required resources of the scheme for the SR; v. ofiIs the current node.
3. The method of claim 1, wherein in step S2, the initialization formula of the dead time of the node is:
Figure FDA00022954248400000210
in the formula (I), the compound is shown in the specification,
Figure FDA00022954248400000211
ξ dead timeemptyIs the initial value of the dead time delay.
4. The adaptive delayed shutdown method for the cloud network-based server according to claim 1, wherein in the step S3, a recovery formula of the deployment resource occupied by the SFC is:
Figure FDA00022954248400000212
in the formula (I), the compound is shown in the specification,
Figure FDA00022954248400000213
is the remaining resource of the current physical network;
Figure FDA00022954248400000214
the required resources of the scheme are deployed for the SR.
5. The method for adaptive delayed shutdown of a cloud network-based server according to claim 1, wherein in step S4, the determination formula is:
Figure FDA00022954248400000215
in the formula (I), the compound is shown in the specification,
Figure FDA00022954248400000216
requesting a set of VNFs for different SFCs deployed in the node;
Figure FDA00022954248400000217
a set used as a forwarding function in a node;
the above formula is satisfied, and the current node is in an idle state; the above formula is not satisfied, and the current node is not in an idle state.
6. The adaptive delayed shutdown method for the cloud network-based server according to claim 1, wherein in step S6, the update formulas of the shutdown times, the shutdown energy consumption, and the shutdown delay of the current node are:
Figure FDA0002295424840000031
in the formula (I), the compound is shown in the specification,
Figure FDA0002295424840000032
is the shutdown frequency of the node;
Figure FDA0002295424840000033
energy consumption for node shutdown;
Figure FDA0002295424840000034
power consumption for server shutdown;
Figure FDA0002295424840000035
a node shutdown delay;
Figure FDA0002295424840000036
the server power-off delay is provided.
7. The adaptive delay shutdown method for the cloud network-based server according to claim 1, wherein in the step S7, the update formulas of the current node no-load delay time, no-load waiting time and no-load energy consumption are as follows:
Figure FDA0002295424840000037
in the formula (I), the compound is shown in the specification,
Figure FDA0002295424840000038
is the node dead time delay;
Figure FDA0002295424840000039
is the node no-load waiting time;
Figure FDA00022954248400000310
no-load energy consumption of the nodes is realized;
Figure FDA00022954248400000311
the server is in no-load energy consumption.
8. The adaptive delayed shutdown method for the cloud network-based server according to claim 1, wherein in the step S8, the update formula of the delay time recovery initial value, the node working time and the runtime working energy consumption is:
Figure FDA00022954248400000312
in the formula (I), the compound is shown in the specification,
Figure FDA00022954248400000313
ξ for node dead timeemptyIs the initial value of the dead time delay;
Figure FDA00022954248400000314
the working time of the node is;
Figure FDA0002295424840000041
operating energy consumption for the node;
Figure FDA0002295424840000042
operating energy consumption for the server.
9. The method of claim 1, wherein in step S9, the calculation formula of the consumed energy and the delay cost of the current node is:
Figure FDA0002295424840000043
in the formula (I), the compound is shown in the specification,
Figure FDA0002295424840000044
energy consumption of the current node;
Figure FDA0002295424840000045
time delay cost of the current node;
Figure FDA0002295424840000046
starting up energy consumption for the nodes;
Figure FDA0002295424840000047
no-load energy consumption of the nodes is realized;
Figure FDA0002295424840000048
operating energy consumption for the node;
Figure FDA0002295424840000049
starting up time delay for the node;
Figure FDA00022954248400000410
a node shutdown delay;
Figure FDA00022954248400000411
is the node no-load waiting time;
Figure FDA00022954248400000412
the working time of the node is;
Figure FDA00022954248400000413
the number of times of starting the node is;
Figure FDA00022954248400000414
energy consumption for node shutdown;
Figure FDA00022954248400000415
is the number of times the node is powered off.
10. The method for adaptive delayed shutdown of a cloud network-based server according to claim 9, wherein in step S11, the calculation formula of the total consumed energy and the total delay cost of all nodes is:
Figure FDA00022954248400000416
in the formula, ESFCTotal consumed energy for all nodes; t isSFCThe total latency cost for all nodes;
Figure FDA00022954248400000417
is a collection of nodes for all SRs in working state.
CN201810946902.2A 2018-08-20 2018-08-20 Self-adaptive delay shutdown method of server based on cloud network Expired - Fee Related CN109120416B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810946902.2A CN109120416B (en) 2018-08-20 2018-08-20 Self-adaptive delay shutdown method of server based on cloud network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810946902.2A CN109120416B (en) 2018-08-20 2018-08-20 Self-adaptive delay shutdown method of server based on cloud network

Publications (2)

Publication Number Publication Date
CN109120416A CN109120416A (en) 2019-01-01
CN109120416B true CN109120416B (en) 2020-03-10

Family

ID=64853354

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810946902.2A Expired - Fee Related CN109120416B (en) 2018-08-20 2018-08-20 Self-adaptive delay shutdown method of server based on cloud network

Country Status (1)

Country Link
CN (1) CN109120416B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112559057B (en) * 2020-11-17 2022-05-27 新华三技术有限公司成都分公司 Shutdown processing method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103823545A (en) * 2014-03-05 2014-05-28 南京邮电大学 Server awaking method of cloud computing system
CN106059835A (en) * 2016-07-28 2016-10-26 北京神狐时代通信技术有限公司 High-reliability control method for low-energy-consumption computer cluster nodes
CN108200202A (en) * 2018-02-06 2018-06-22 电子科技大学 A kind of service function chain security deployment method that network is calculated applied to cloud and mist
EP3506593A1 (en) * 2017-12-28 2019-07-03 Wirepas Oy Wireless mesh network

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103823545A (en) * 2014-03-05 2014-05-28 南京邮电大学 Server awaking method of cloud computing system
CN106059835A (en) * 2016-07-28 2016-10-26 北京神狐时代通信技术有限公司 High-reliability control method for low-energy-consumption computer cluster nodes
EP3506593A1 (en) * 2017-12-28 2019-07-03 Wirepas Oy Wireless mesh network
CN108200202A (en) * 2018-02-06 2018-06-22 电子科技大学 A kind of service function chain security deployment method that network is calculated applied to cloud and mist

Also Published As

Publication number Publication date
CN109120416A (en) 2019-01-01

Similar Documents

Publication Publication Date Title
CA2741088C (en) Methods of achieving cognizant power management
CN108023958B (en) Resource scheduling system based on cloud platform resource monitoring
CN102868763B (en) The dynamic adjusting method that under a kind of cloud computing environment, virtual web application cluster is energy-conservation
US8250382B2 (en) Power control of servers using advanced configuration and power interface (ACPI) states
Ricciardi et al. Saving energy in data center infrastructures
US9274585B2 (en) Combined dynamic and static power and performance optimization on data centers
US20100287390A1 (en) Device, system and method for computer network traffic monitoring, distribution and power management
CN106059835B (en) A kind of High-reliability Control method of low energy consumption computer set group node
Li et al. An energy-efficient scheduling approach based on private clouds
CN101637053A (en) Sleep optimization for mobile devices in a broadband network
CN102025509A (en) Power-off control method and device
WO2010077923A2 (en) Computer energy conservation with a scalable psu configuration
CN105721170B (en) The power-economizing method and device of multi-controller based on SDN network framework
CN101286854A (en) Ethernet power supply method and system
Ranjana et al. A survey on power aware virtual machine placement strategies in a cloud data center
CN105515791A (en) Ethernet method and use method in ethernet device
Dalvandi et al. Time-aware vm-placement and routing with bandwidth guarantees in green cloud data centers
CN109120416B (en) Self-adaptive delay shutdown method of server based on cloud network
Kulseitova et al. A survey of energy-efficient techniques in cloud data centers
Kliazovich et al. Accounting for load variation in energy-efficient data centers
Van Heddeghem et al. Energy in ICT-Trends and research directions
CN107015622B (en) Spark cluster power-off self-protection and incoming call self-starting method
Lu et al. Popcorns: Power optimization using a cooperative network-server approach for data centers
Naidu et al. Efficient strategies for green cloud computing
US20030088797A1 (en) Adapting link speed of a network controller to available power supply

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
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20200310

Termination date: 20210820

CF01 Termination of patent right due to non-payment of annual fee