CN107329817A - A kind of stand-by system mixing divides reliability and perceives energy consumption optimization method - Google Patents
A kind of stand-by system mixing divides reliability and perceives energy consumption optimization method Download PDFInfo
- Publication number
- CN107329817A CN107329817A CN201710507525.8A CN201710507525A CN107329817A CN 107329817 A CN107329817 A CN 107329817A CN 201710507525 A CN201710507525 A CN 201710507525A CN 107329817 A CN107329817 A CN 107329817A
- Authority
- CN
- China
- Prior art keywords
- task
- processor
- backup
- primary processor
- execution
- 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.)
- Granted
Links
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
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
- G06F9/4893—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues taking into account power or heat criteria
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/329—Power saving characterised by the action undertaken by task scheduling
-
- 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
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/48—Indexing scheme relating to G06F9/48
- G06F2209/484—Precedence
-
- 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)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Hardware Redundancy (AREA)
Abstract
Reliability is divided the invention discloses a kind of stand-by system mixing and perceives energy consumption optimization method, is comprised the following steps:Periodic task model and dynamic priority strategy are limited using stand-by system resource, the minimum speed S for meeting system requirements is calculatedT, calculate the minimum speed S for meeting system reliability demand;Determine primary processor and the execution speed S of backup processorU;Whether there is resource requirement to map that in primary processor or backup processor according to task;Main task and backup tasks are assigned to primary processor and backup processor by the method divided using mixing simultaneously;Task to primary processor and backup processor is scheduled.The method combination DVS technologies and DPM technologies of the present invention, on the basis of the original reliability of system is ensured, is effectively reduced system energy consumption.
Description
Technical field
The low energy consumption for being limited periodic duty the present invention relates to the stand-by system resource in embedded real time system field is real-time
Scheduling, more particularly to a kind of stand-by system mixing divides reliability and perceives energy consumption optimization method.
Background technology
Embedded real time system is generally all special real-time system, its task type have periodic duty, accidental task with
And hybrid task.Embedded real time system is powered using battery, and the finite capacity of battery, causes the endurance of system and has
Limit.In addition, the working environment of embedded real time system is more severe.With the fast development of processor technology, and system work(
Continuous, the energy consumption more and more higher of system of energy.High energy consumption can be adversely affected to system reliability, and then have influence on system just
Really perform.Therefore, reliability and energy consumption are to design two key factors that embedded real time system must take into consideration.
Stand-by system is made up of primary processor and backup processor, during one computing device task of any of which,
Another processor can perform the backup tasks of corresponding task, during the tasks carrying failure of so one of processor, separately
The backup tasks of an outer processor are continued executing with, and this improves system reliability.Energy consumption for stand-by system is excellent
The research work of change method is fewer, and main task is assigned to primary processor by only several research work, and backup is appointed
Business is assigned to backup processor, and the task of backup processor is performed with maximum processor speed all the time, does not utilize dynamic
Power management is saved, so the energy consumption of system is too high.
The content of the invention
It is an object of the invention to overcome the deficiencies in the prior art, propose that a kind of stand-by system mixing divides reliability
Energy consumption optimization method is perceived, this method is limited periodic task model according to stand-by system resource and system reliability is limited
Whether system, determine the execution speed of primary processor and backup processor, have resource requirement to map that to main process task according to task
On device and backup processor, the method divided using mixing distributes backup tasks, to primary processor and the task of backup processor
It is scheduled.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of stand-by system mixing divides reliability and perceives energy consumption optimization method, comprises the following steps:
Periodic task model and dynamic priority strategy are limited using stand-by system resource, the system of satisfaction is calculated
The minimum speed S of demandT;
The minimum speed S for meeting system reliability demand is calculated, determine primary processor and backup processor performs speed
Spend SU;
Whether there is resource requirement to map that in primary processor or backup processor according to task;
Main task and backup tasks are assigned to primary processor and backup processor by the method divided using mixing simultaneously;
Task to primary processor and backup processor is scheduled.
Specifically, described be limited periodic task model and dynamic priority strategy, meter using stand-by system resource
Calculate the minimum speed S for meeting system requirementsT, including:
Stand-by system resource is limited periodic task model by two processor groups into respectively primary processor and standby
Processor;Periodic duty collection is made up of n periodic duty;Each periodic duty TiBy triple (ei,ri,pi) composition, eiIt is to appoint
Be engaged in TiExecution time under worst case, riIt is task TiResource requirement, piIt is task TiCycle;And each periodic duty Ti
(main task) has a backup tasks Bi, backup tasks BiParameter and TiIt is identical;Periodic duty collection shared resource set
R={ R1,R2,…,RmBe made up of m resource;According to dynamic priority scheduling strategy, the minimum speed S of system requirements is metT,
Computational methods are as follows:
ST=SRS+SNRS
Wherein, SRSIt is the minimum speed for having resource requirement task-set, SNRSIt is the lowest speed without resource requirement task-set
Degree;SRSComputational methods it is as follows:
Wherein, SRS(i) it is to meet task TiDeadline and the minimum speed of resource requirement, riIt is task TiResource need
Ask.
Specifically, described calculate the minimum speed S for meeting system reliability demand, primary processor and standby processing are determined
The execution speed S of deviceU, its process step is as follows:
Wherein, PoF (1) is probability of failure of the task under maximum processor speed, and PoF (S) is task under speed S
Probability of failure, PoF (S) computational methods are as follows:
PoF (S)=1-R (S)
Wherein R (S) is reliability of the task under speed S;R (S) computational methods are as follows:
Wherein, λ (S) is wrong arrival rate of the task under speed S, and W is the execution time under task worst case;Main place
Manage device and the execution speed S of backup processorUComputational methods it is as follows:
SU=max { S, ST,Scrit}
Wherein, ScritIt is processor energy consumption optimal velocity.
Specifically, whether described have resource requirement to map that in primary processor or backup processor according to task,
Including:
Task TiWhen having resource requirement, that is, riWhen ≠ 0, by task TiIt is assigned to primary processor;Task TiThere is no resource
During demand, that is, riWhen=0;By task TiIt is assigned to backup processor.
Specifically, main task and backup tasks are assigned to primary processor and standby by the method divided using mixing simultaneously
With processor, including:
As task TiWhen being assigned on primary processor, its corresponding backup tasks BiThen it is assigned in backup processor;When
Task TiWhen being assigned to backup processor, it backs up B accordinglyiThen it is assigned on primary processor.
Specifically, the task to primary processor and backup processor is scheduled, including:
The scheduling of primary processor task:Two queues of ready queue and delay queue, main task T are setiAs long as it is ready just
It can be immediately performed, and backup tasks BiNeed first to calculate its delay execution time Yi, it is examined when task is completed and performed
Survey, if the main task T of primary processoriExecution is smoothly completed, cancels its backup tasks B in backup processoriExecution, such as
The backup tasks B of fruit primary processorkExecution is smoothly completed, cancels the main task T of backup processorkExecution;At primary processor
When idle condition, free time ST now is calculated, and it is compared with processor state handover overhead;All appoints
Business is scheduled according to the earliest deadline strategy of modification;
The scheduling of backup processor task:Two queues of ready queue and delay queue, main task T are setiAs long as ready
It can just be immediately performed, and backup tasks BiNeed first to calculate its delay execution time Yi, it is carried out when task is completed and performed
Detection, if the main task T of backup processoriExecution is smoothly completed, cancels its backup tasks B in primary processoriExecution,
If the backup tasks B of backup processorkExecution is smoothly completed, cancels the main task T of primary processorkExecution;When standby processing
When device is in idle condition, free time ST now is calculated, and it is compared with processor state handover overhead;It is all
Task be scheduled according to the earliest deadline strategy of modification;
Backup tasks BiDelay perform time YiComputational methods it is as follows:
Yi=Di-γi-t
Wherein, DiIt is task TiThe absolute cutoff time limit, t is current time, γiIt is task TiResponse under worst case
Time, γiComputational methods it is as follows:
Wherein, βiIt is task TiThe maximum obstruction time, Φ (Ti) it is the function that a value is 0 or 1, remkIt is task Tk
The remaining execution time, hp (Ti) it is priority ratio task TiThe high task of priority set, eiIt is task TiThe worst feelings
Execution time under condition, SiIt is task TiExecution speed.
The present invention has the advantages that:
(1) method of the invention saves about 52.95% energy than existing standby system period task scheduling method
Consumption;
(2) it is able to ensure that periodic duty completes execution in its deadline, and is able to ensure that resource by the use of mutual exclusion;
(3) reduction of system energy consumption, can reduce the production cost of product, and the use time of delay apparatus reduces battery
Replacement cycle.
The present invention is described in further detail below in conjunction with drawings and Examples, but the stand-by system of the present invention is mixed
Close division reliability perception energy consumption optimization method and be not limited to embodiment.
Brief description of the drawings
Fig. 1 is the flow chart schematic diagram of the inventive method;
Fig. 2 is the normalization energy consumption of the embodiment of the present invention and the simulation experiment result figure of system availability.
Embodiment
Referring to Fig. 1, a kind of stand-by system mixing that the present invention is provided divides reliability and perceives energy consumption optimization method, bag
Include following steps:
Step 101:Periodic task model and dynamic priority strategy are limited using stand-by system resource, is calculated
Meet the minimum speed S of system requirementsT。
Stand-by system resource is limited periodic task model by two processor groups into respectively primary processor and standby
Processor;Periodic duty collection is made up of n periodic duty;Each periodic duty TiBy triple (ei,ri,pi) composition, eiIt is to appoint
Be engaged in TiExecution time under worst case, riIt is task TiResource requirement, piIt is task TiCycle;And each periodic duty Ti
(main task) has a backup tasks Bi, backup tasks BiParameter and TiIt is identical;Periodic duty collection shared resource set
R={ R1,R2,…,RmBe made up of m resource;According to dynamic priority scheduling strategy, the minimum speed S of system requirements is metT,
Computational methods are as follows:
ST=SRS+SNRS
Wherein, SRSIt is the minimum speed for having resource requirement task-set, SNRSIt is the lowest speed without resource requirement task-set
Degree;SRSComputational methods it is as follows:
Wherein, SRS(i) it is to meet task TiDeadline and the minimum speed of resource requirement, riIt is task TiResource need
Ask;SRS(i) computational methods are as follows:
Wherein, eiIt is task TiExecution time under worst case, ejIt is task TjExecution time under worst case, piIt is
Task TiCycle,It is all use resourcesThe minimum period of task, L is real number;SNRSComputational methods it is as follows:
Wherein, NRS is the set without resource requirement task, uiIt is task TiUtilization rate, uiComputational methods it is as follows:
Wherein, eiIt is task TiExecution time under worst case, piIt is task TiCycle.
Step 102:The minimum speed S for meeting system reliability demand is calculated, primary processor and backup processor is determined
Execution speed SU。
The minimum speed S of system reliability demand is met, computational methods are as follows:
Wherein, PoF (1) is probability of failure of the task under maximum processor speed, and PoF (S) is task under speed S
Probability of failure, PoF (S) computational methods are as follows:
PoF (S)=1-R (S)
Wherein, R (S) is reliability of the task under speed S;R (S) computational methods are as follows:
Wherein, λ (S) is wrong arrival rate of the task under speed S, and W is the execution time under task worst case;λ(S)
Computational methods it is as follows:
Wherein, λ0It is the wrong arrival rate under maximum processor speed, d is constant, SminIt is the minimum that processor is provided
Speed;The execution speed S of primary processor and backup processorUComputational methods it is as follows:
SU=max { S, ST,Scrit}
Wherein, ScritIt is processor energy consumption optimal velocity.
Step 103:Whether there is resource requirement to map that in primary processor or backup processor according to task.
Task TiWhen having resource requirement, that is, riWhen ≠ 0, by task TiIt is assigned to primary processor;Task TiThere is no resource
During demand, that is, riWhen=0, by task TiIt is assigned to backup processor.
Step 104:Main task and backup tasks are assigned to primary processor and standby by the method divided using mixing simultaneously
Processor.
As task TiWhen being assigned on primary processor, its corresponding backup tasks BiThen it is assigned in backup processor;When
Task TiWhen being assigned to backup processor, its corresponding backup tasks BiThen it is assigned on primary processor.
Step 105:Task to primary processor and backup processor is scheduled.
The scheduling of primary processor task:Two queues of ready queue and delay queue, main task T are setiAs long as it is ready just
It can be immediately performed, and backup tasks BiNeed first to calculate its delay execution time γi, it is carried out when task is completed and performed
Detection, if the main task T of primary processoriExecution is smoothly completed, cancels its backup tasks B in backup processoriExecution,
If the backup tasks B of primary processorkExecution is smoothly completed, cancels the main task T of backup processorkExecution;Work as primary processor
During in idle condition, free time ST now is calculated, and it is compared with processor state handover overhead;All
Task is scheduled according to the earliest deadline strategy of modification;
The scheduling of backup processor task:Two queues of ready queue and delay queue, main task T are setiAs long as ready
It can just be immediately performed, and backup tasks BiNeed first to calculate its delay execution time γi, it is entered when task is completed and performed
Row detection, if the main task T of backup processoriExecution is smoothly completed, cancels its backup tasks B in primary processoriHold
OK, if the backup tasks B of backup processorkExecution is smoothly completed, cancels the main task T of primary processorkExecution;When standby
When processor is in idle condition, free time ST now is calculated, and it is compared with processor state handover overhead;
All tasks are scheduled according to the earliest deadline strategy of modification;
Backup tasks BiDelay perform time YiComputational methods it is as follows:
Yi=Di-γi-t
Wherein, DiIt is task TiThe absolute cutoff time limit, t is current time, γiIt is task TiResponse under worst case
Time, γiComputational methods it is as follows:
Wherein, βiIt is task TiThe maximum obstruction time;βiComputational methods it is as follows:
Wherein, riIt is task TiResource requirement, rjIt is task TjResource requirement, ejIt is task TjHolding under worst case
The row time;Φ(Ti) it is the function that a value is 0 or 1, Φ (Ti) computational methods it is as follows:
Wherein, riIt is task TiResource requirement, rjIt is task TjResource requirement, tjIt is task TjStart perform when
Between, rtiIt is task TiRelease time;That is Φ (Ti) it is equal to 1 and if only if task TiBy task TjObstruction, remkIt is to appoint
Be engaged in TkThe remaining execution time, hp (Ti) it is priority ratio task TiThe high task of priority set, eiIt is task TiMost
Execution time in the case of bad, SiIt is task TiExecution speed.
As shown in Fig. 2 in the present embodiment, each cycle collection includes 8 periodic duties.Periodic duty collection shares two resources
R1And R2, whether task have resource requirement random selection.Each periodic duty TiCycle select in [2.4,9.6], its is the worst
In the case of randomly choosed 0.035 between its cycle.Performed under setting task worst case under time and best-case
The ratio of execution time is 5.λ is set0=10-6, d=2;After the generation of periodic duty collection, by adjusting task worst case
Under the execution time, make system availability be no more than specified value.Investigate influence of the system availability to algorithm energy consumption, system profit
It is 0.10 to 0.8 with the scope of rate, step-length is 0.05.Two methods, first, SSPT (stand-by system weeks are compared in Fig. 2
Phase task) method, primary processor is using dynamic voltage regulation technical energy saving, and backup processor task is with maximum processor speed
Perform, and do not utilize dynamic power management technical energy saving.Second, method of the invention, according to stand-by system resource by
Periodic task model and system reliability limitation are limited, the execution speed of primary processor and backup processor is determined, according to task
Whether there is resource requirement to map that on primary processor and backup processor, the method divided using mixing distributes standby
Business, the task to primary processor and backup processor is scheduled.From figure 2 it can be seen that the methodical normalization energy consumption of institute
All influenceed by system availability.As system availability rises, the methodical normalization energy consumption of institute all rises.Because
Higher system availability causes the execution time of task elongated, so system energy consumption rises.The normalization energy of the inventive method
Energy consumption of the consumption less than SSPT methods.Because backup processor is performed with maximum processor speed in SSPT methods, and
Dynamic power management technical energy saving can not be utilized.The primary processor and backup processor of the inventive method are all held with unified speed
OK, and dynamic power management technical energy saving can be utilized.The inventive method saves about 52.95% energy consumption than SSPT method.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (6)
1. a kind of stand-by system mixing divides reliability and perceives energy consumption optimization method, it is characterised in that including:
Periodic task model and dynamic priority strategy are limited using stand-by system resource, calculates and meets system requirements
Minimum speed ST;
The minimum speed S for meeting system reliability demand is calculated, primary processor and the execution speed S of backup processor is determinedU;
Whether there is resource requirement to map that in primary processor or backup processor according to task;
Main task and backup tasks are assigned to primary processor and backup processor by the method divided using mixing simultaneously;
Task to primary processor and backup processor is scheduled.
2. stand-by system mixing according to claim 1 divides reliability and perceives energy consumption optimization method, its feature exists
In being limited periodic task model and dynamic priority strategy using stand-by system resource, calculate and meet system requirements
Minimum speed ST;Including:
Stand-by system resource is limited periodic task model by two processor groups into respectively primary processor and standby processing
Device;Periodic duty collection is made up of n periodic duty;Each periodic duty TiBy triple (ei,ri,pi) composition, eiIt is task Ti
Execution time under worst case, riIt is task TiResource requirement, piIt is task TiCycle;And each periodic duty TiHave
One backup tasks Bi, backup tasks BiParameter and TiIt is identical;Periodic duty collection shared resource set R={ R1,R2,…,
RmBe made up of m resource;According to dynamic priority scheduling strategy, the minimum speed S of system requirements is metT, computational methods are as follows:
ST=SRS+SNRS
Wherein, SRSIt is the minimum speed for having resource requirement task-set, SNRSIt is the minimum speed without resource requirement task-set.
3. stand-by system mixing according to claim 2 divides reliability and perceives energy consumption optimization method, its feature exists
In calculating the minimum speed S for meeting system reliability demand, determine primary processor and the execution speed S of backup processorU,
Its process step is as follows:
<mrow>
<mi>P</mi>
<mi>o</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mi>S</mi>
<mo>)</mo>
</mrow>
<mo>&le;</mo>
<msqrt>
<mrow>
<mi>P</mi>
<mi>o</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</msqrt>
</mrow>
Wherein, PoF (1) is probability of failure of the task under maximum processor speed, and PoF (S) is mistake of the task under speed S
Probability is lost, PoF (S) computational methods are as follows:
PoF (S)=1-R (S)
Wherein, R (S) is reliability of the task under speed S;The execution speed S of primary processor and backup processorUCalculating side
Method is as follows:
SU=max { S, ST,Scrit}
Wherein, ScritIt is processor energy consumption optimal velocity.
4. stand-by system mixing according to claim 3 divides reliability and perceives energy consumption optimization method, its feature exists
In:Whether there is resource requirement to map that in primary processor or backup processor according to task, including:
Task TiWhen having resource requirement, that is, riWhen ≠ 0, by task TiIt is assigned to primary processor;Task TiThere is no resource requirement
When, that is, riWhen=0;By task TiIt is assigned to backup processor.
5. stand-by system mixing according to claim 4 divides reliability and perceives energy consumption optimization method, its feature exists
In main task and backup tasks are assigned to primary processor and backup processor by the method divided using mixing simultaneously, are specifically:
As task TiWhen being assigned on primary processor, its corresponding backup tasks BiThen it is assigned in backup processor;Work as task
TiWhen being assigned to backup processor, its corresponding backup tasks BiThen it is assigned on primary processor.
6. stand-by system mixing according to claim 5 divides reliability and perceives energy consumption optimization method, its feature exists
In the task to primary processor and backup processor is scheduled, and is specifically included:
The scheduling of primary processor task:Two queues of ready queue and delay queue, main task T are setiAs long as ready can just stand
Perform, and backup tasks BiNeed first to calculate its delay execution time Yi, it is detected when task is completed and performed, such as
The main task T of fruit primary processoriExecution is smoothly completed, cancels its backup tasks B in backup processoriExecution, if main place
Manage the backup tasks B of devicekExecution is smoothly completed, cancels the main task T of backup processorkExecution;When primary processor is in the free time
During state, free time ST now is calculated, and it is compared with processor state handover overhead;All tasks according to
The earliest deadline strategy of modification is scheduled;
The scheduling of backup processor task:Two queues of ready queue and delay queue, main task T are setiAs long as ready just can be with
It is immediately performed, and backup tasks BiNeed first to calculate its delay execution time Yi, it is detected when task is completed and performed,
If the main task T of backup processoriExecution is smoothly completed, cancels its backup tasks B in primary processoriExecution, if standby
With the backup tasks B of processorkExecution is smoothly completed, cancels the main task T of primary processorkExecution;When backup processor is in
During idle condition, free time ST now is calculated, and it is compared with processor state handover overhead;All tasks
It is scheduled according to the earliest deadline strategy of modification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710507525.8A CN107329817B (en) | 2017-06-28 | 2017-06-28 | Standby standby system mixed partitioning reliability perception energy consumption optimization method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710507525.8A CN107329817B (en) | 2017-06-28 | 2017-06-28 | Standby standby system mixed partitioning reliability perception energy consumption optimization method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107329817A true CN107329817A (en) | 2017-11-07 |
CN107329817B CN107329817B (en) | 2021-06-29 |
Family
ID=60198026
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710507525.8A Active CN107329817B (en) | 2017-06-28 | 2017-06-28 | Standby standby system mixed partitioning reliability perception energy consumption optimization method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107329817B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108874517A (en) * | 2018-04-19 | 2018-11-23 | 华侨大学 | The stand-by system availability of fixed priority divides energy consumption optimization method |
CN109799805A (en) * | 2019-01-17 | 2019-05-24 | 湖南大学 | A kind of high-performing car electronic schedule algorithm of reliability perception |
CN109857084A (en) * | 2019-01-18 | 2019-06-07 | 湖南大学 | A kind of high-performing car electronic Dynamic dispatching algorithm of energy consumption perception |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080148273A1 (en) * | 2006-12-15 | 2008-06-19 | Institute For Information Industry | Dynamic voltage scaling scheduling mechanism for sporadic, hard real-time tasks with resource sharing |
CN102129646A (en) * | 2011-03-09 | 2011-07-20 | 华东电网有限公司 | Method for uniformly monitoring multi-dimensional electric power market transaction data interaction |
-
2017
- 2017-06-28 CN CN201710507525.8A patent/CN107329817B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080148273A1 (en) * | 2006-12-15 | 2008-06-19 | Institute For Information Industry | Dynamic voltage scaling scheduling mechanism for sporadic, hard real-time tasks with resource sharing |
CN102129646A (en) * | 2011-03-09 | 2011-07-20 | 华东电网有限公司 | Method for uniformly monitoring multi-dimensional electric power market transaction data interaction |
Non-Patent Citations (2)
Title |
---|
张忆文: "可靠性感知周期任务能耗管理调度算法", 《计算机科学与探索》 * |
张忆文: "资源受限周期任务低能耗调度算法", 《小型微型计算机系统》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108874517A (en) * | 2018-04-19 | 2018-11-23 | 华侨大学 | The stand-by system availability of fixed priority divides energy consumption optimization method |
CN108874517B (en) * | 2018-04-19 | 2021-11-02 | 华侨大学 | Method for optimizing utilization rate division energy consumption of standby system with fixed priority |
CN109799805A (en) * | 2019-01-17 | 2019-05-24 | 湖南大学 | A kind of high-performing car electronic schedule algorithm of reliability perception |
CN109857084A (en) * | 2019-01-18 | 2019-06-07 | 湖南大学 | A kind of high-performing car electronic Dynamic dispatching algorithm of energy consumption perception |
Also Published As
Publication number | Publication date |
---|---|
CN107329817B (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105893148B (en) | A kind of accidental task low energy consumption dispatching method based on RM strategy | |
CN102904955B (en) | The self-adapting stretching control system of Web application in cloud computing platform and method thereof | |
CN105320570B (en) | Method for managing resource and system | |
CN102655685B (en) | Task fault-tolerance allocation method for wireless sensor networks | |
JP2017510899A (en) | Method and apparatus for increasing the capacity of computing resources in a real-time stream computing system and method and apparatus for releasing the capacity | |
CN103399626B (en) | Towards Parallel application dispatching system and the method for the power-aware of hybrid compute environment | |
CN105389206A (en) | Method for rapidly configuring virtual machine resources in cloud computing data center | |
CN107329817A (en) | A kind of stand-by system mixing divides reliability and perceives energy consumption optimization method | |
CN104808770A (en) | Data center energy consumption management method and system based on dynamic frequency modulation | |
WO2015100995A1 (en) | Intelligent service scheduling method | |
CN103699433A (en) | Method and system for performing dynamic adjustment on number of tasks in Hadoop platform | |
CN106445070B (en) | Energy consumption optimization scheduling method for hard real-time system resource-limited sporadic tasks | |
CN105629873B (en) | A kind of hybrid tasks scheduling method suitable for digital control system | |
CN112306696B (en) | Energy-saving and efficient edge computing task unloading method and system | |
CN102402461A (en) | Balanced scheduling method based on operation scale | |
CN103455375A (en) | Load-monitoring-based hybrid scheduling method under Hadoop cloud platform | |
CN112905330B (en) | Fixed priority hybrid key sporadic task energy consumption sensing method | |
CN104156505A (en) | Hadoop cluster job scheduling method and device on basis of user behavior analysis | |
CN104461722A (en) | Job scheduling method used for cloud computing system | |
CN107797870A (en) | A kind of cloud computing data resource dispatching method | |
CN105094944A (en) | Virtual machine migration method and apparatus | |
CN108874517A (en) | The stand-by system availability of fixed priority divides energy consumption optimization method | |
CN103973811A (en) | High-availability cluster management method capable of conducting dynamic migration | |
Chen et al. | Delay-optimal distributed edge computation offloading with correlated computation and communication workloads | |
Shah et al. | Phase level energy aware map reduce scheduling for big data applications |
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 |