CN109613971A - A kind of minimum utilization rate free time distribution low energy consumption method - Google Patents
A kind of minimum utilization rate free time distribution low energy consumption method Download PDFInfo
- Publication number
- CN109613971A CN109613971A CN201811474573.2A CN201811474573A CN109613971A CN 109613971 A CN109613971 A CN 109613971A CN 201811474573 A CN201811474573 A CN 201811474573A CN 109613971 A CN109613971 A CN 109613971A
- Authority
- CN
- China
- Prior art keywords
- periodic duty
- utilization rate
- minimum
- time
- free 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.)
- Granted
Links
Classifications
-
- 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
- G06F1/3293—Power saving characterised by the action undertaken by switching to a less power-consuming processor, e.g. sub-CPU
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mobile Radio Communication Systems (AREA)
- Power Sources (AREA)
Abstract
The invention discloses a kind of minimum utilization rate free times to distribute low energy consumption method, comprising: the utilization rate for calculating each periodic duty finds out the minimum periodic duty of utilization rate；Using opposite deadline, the offline speed S of periodic duty collection is calculatedO；According to the absolute cutoff time limit of periodic duty, the priority of periodic duty is determined；Task return period does sth. in advance the free time for completing to generate, and free time is distributed to the minimum periodic duty of utilization rate；The speed of service S of the minimum periodic duty of rate is determined the use of, other periodic duties are with the offline speed S of periodic duty collectionOIt executes；Using dynamic power management technology, low power consumpting state is switched the processor into reduce energy consumption；The method of the present invention can be effectively reduced system energy consumption.
Description
Technical field
The present invention relates to embedded real time system power management technique field, specifically a kind of minimum utilization rate free time
Distribute low energy consumption method.
Background technique
Real-time system is divided into hard real-time system and soft real-time system according to the time-bounded of task.Hard real-time system requires to appoint
Business cannot miss its deadline, otherwise can bring unpredictable consequence, or even can cause serious disaster, for example aircraft is certainly
Dynamic control loop.Soft real-time system allows task missed deadlines once in a while, will not bring serious consequence, may reduce use
The experience at family, such as multimedia play system.Current most of portable devices are such as: mobile phone, laptop, unmanned plane are all
Real-time system is carried, due to the limitation of weight and volume, these portable devices often use battery to power, so leading to these
The cruise duration of equipment is limited.So energy consumption is even more important for these portable devices, making for battery is can be improved in low energy consumption
With the service life, extend its cruise duration, additionally aiding reduces cost.
Task can be divided into periodic duty, aperiodic task according to the release time of task by hard real-time system.Period
The release time of task instances is fixed constant, and aperiodic task is accidental.It is existing to be directed to periodic duty low-power consumption tune
Degree algorithm all takes greedy strategy to distribute free time, causes the computing cost of algorithm big, and processor speed switching is frequently, section
Energy effect is undesirable.
Summary of the invention
It is a primary object of the present invention to overcome drawbacks described above in the prior art, when proposing a kind of minimum utilization rate free time
Between distribute low energy consumption method, free time distributed to the minimum periodic duty of utilization rate, is effectively reduced system energy by this method
Consumption.
The present invention adopts the following technical scheme:
A kind of minimum utilization rate free time distribution low energy consumption method, which is characterized in that include the following:
1) utilization rate for calculating each periodic duty, finds out the minimum periodic duty of utilization rate；
2) using opposite deadline, the offline speed S of periodic duty collection is calculatedO, periodic duty collection is by several weeks
Phase task composition；
3) according to the absolute cutoff time limit of periodic duty, the priority of periodic duty is determined；
4) task return period does sth. in advance the free time for completing to generate, and free time is distributed to the utilization rate minimum period
Task；
5) speed of service S of the minimum periodic duty of rate is determined the use of, other periodic duties are with the offline speed of periodic duty collection
Spend SOIt executes；
6) dynamic power management technology is utilized, switches the processor into low power consumpting state to reduce energy consumption.
The utilization rate for calculating each periodic duty, finds out the minimum periodic duty of utilization rate；Include:
Periodic duty TiBy triple (ei,pi,di) indicate, wherein 1≤i≤n, i are integer, eiIt is periodic duty TiMost
Time, p are executed in bad situationiIt is periodic duty TiPeriod, diIt is periodic duty TiOpposite deadline；Periodic duty Ti's
Utilization rate isPeriodic duty is sorted from small to large according to its utilization rate, finds out the minimum periodic duty of utilization rate.
It is described to utilize opposite deadline, calculate the offline speed S of periodic duty collectionO, specifically include: each cycle Ti
Still there is d within its periodi-eiThe processor surplus of a chronomere, so the offline speed S of periodic duty collectionOBy following formula meter
It calculates:
Wherein, n is positive integer, represents the number of periodic duty.
The absolute cutoff time limit according to periodic duty, determine the priority of periodic duty；Include:
Periodic duty TiThe absolute cutoff time limit be equal to its release time riDeadline d corresponding theretoiThe sum of；Period appoints
The absolute cutoff time limit of business is smaller, and priority is higher；The absolute cutoff time limit of periodic duty is bigger, and priority is lower；It is excellent
The high task of first grade, by priority scheduling.
Task return period does sth. in advance the free time for completing to generate, and free time is distributed to utilization rate minimum week
Phase task；Include:
Free time management queue is established, the periodic duty for having completed to execute is moved on into free time management queue；?
The high periodic duty of the currently performed periodic duty priority of priority ratio is found in free time queue, calculates the sky generated at this time
I between idle；Its value is calculated by following formula:
Wherein, remiIt is periodic duty TiRemaining execute time, h (Ti, t) and it is priority ratio periodic duty TiPriority
Periodic duty that is high and having completed execution, t is current time；Free time I is distributed into priority utilization rate minimum week
Phase task.
The speed of service S for determining the use of the minimum periodic duty of rate, other periodic duties are offline with periodic duty collection
Speed SOIt executes, comprising:
The speed of service of the minimum periodic duty of utilization rate is calculated by following formula
Wherein, ScritIt is the minimum speed of service of processor energy consumption；Other periodic duties are with the offline speed of periodic duty collection
Spend SOIt executes.
It is described to utilize dynamic power management technology, low power consumpting state is switched the processor into reduce energy consumption, comprising:
Processor is in idle condition, and calculates free time N=max { I, A-t at this timec, wherein A is next week
The release time of phase task instances, tcFor current time；Low power consumpting state is switched the processor into as N > O, wherein O is place
Manage device speed handover overhead；Otherwise, processor enters idle state.
By the above-mentioned description of this invention it is found that compared with prior art, the invention has the following beneficial effects:
(1) reduction of system energy consumption can reduce the production cost of product, and extend equipment uses the time, reduce battery
Replacement cycle；
(2) method of the invention averagely saves about 17.83% energy consumption than existing method；
(3) method of the invention can reduce processor speed handover overhead.
Detailed description of the invention
Fig. 1 is the flow chart schematic diagram of the method for the present invention；
Fig. 2 is the simulation experiment result figure that the embodiment of the present invention normalizes energy consumption and utilization rate.
Specific embodiment
Below by way of specific embodiment, the invention will be further described.
Referring to Fig. 1, a kind of minimum utilization rate free time distribution low energy consumption method provided by the invention, including walk as follows
It is rapid:
1) utilization rate for calculating each periodic duty, finds out the minimum periodic duty of utilization rate.
Periodic duty collection is made of n periodic duty, periodic duty Ti(1≤i≤n, i are integer) is by triple (ei,pi,
di) indicate, wherein eiIt is periodic duty TiWorst case under execute time, piIt is periodic duty TiPeriod, diIt is to appoint in the period
Be engaged in TiOpposite deadline；Periodic duty TiUtilization rate beUsing quicksort method by periodic duty according to its benefit
It is sorted from small to large with rate, finds out the minimum periodic duty of utilization rate；When minimum utilization rate is identical, the small periodic duty of subscript is made
For the periodic duty of minimum utilization rate.
2) using opposite deadline, the offline speed S of periodic duty collection is calculatedO。
Each periodic duty TiStill there is d within its periodi-eiThe processor surplus of a chronomere, so periodic duty
The offline speed S of collectionOIt is calculated by following formula:
Wherein, n is positive integer, represents the number of periodic duty.
3) according to the absolute cutoff time limit of periodic duty, the priority of periodic duty is determined.
Periodic duty TiThe absolute cutoff time limit be equal to its release time riDeadline d corresponding theretoiThe sum of；Period appoints
The absolute cutoff time limit of business is smaller, and priority is higher；The absolute cutoff time limit of periodic duty is bigger, and priority is lower；Week
When the deadline of phase task is identical, release time smaller periodic duty, priority is higher；The deadline of periodic duty
When identical as release time, the small periodic duty priority of subscript is higher；It is moved into ready queue after periodic duty release,
Ready queue is according to the priority scheduling of periodic duty, and the high task of priority is by priority scheduling.
4) task return period does sth. in advance the free time for completing to generate, and free time is distributed to the utilization rate minimum period
Task.
Free time management queue is established, the periodic duty for having completed to execute is moved on into free time management queue；?
The high periodic duty of the currently performed periodic duty priority of priority ratio is found in free time queue, calculates the sky generated at this time
I between idle；Its value is calculated by following formula:
Wherein, remiIt is periodic duty TiRemaining execute time, periodic duty TiWhen release, rem is seti=ei；Period
Task TiWhen execution, residue executes time remiIt correspondingly reduces, it is identical that the amount of reduction with it executes the time；h(Ti, t) and it is excellent
First grade is than periodic duty TiPriority is high and has completed the periodic duty executed, and t is current time；Free time I is distributed
To the periodic duty that priority utilization rate is minimum.
5) speed of service S of the minimum periodic duty of rate is determined the use of, other periodic duties are with the offline speed of periodic duty collection
Spend SOIt executes.
The speed of service S of the minimum periodic duty of utilization rate is calculated by following formula
Wherein, ScritIt is the minimum speed of service of processor energy consumption, eiIt is periodic duty TiWorst case under when executing
Between；Other periodic duties are with the offline speed S of periodic duty collectionOIt executes；After free time I is utilized, periodic duty T is seti
Residue executes time remiIt is 0, and removes it free time management queue；
6) dynamic power management technology is utilized, switches the processor into low power consumpting state to reduce energy consumption.
Processor is in idle condition, and calculates free time N=max { I, A-t at this timec, wherein A is next week
The release time of phase task instances, tcFor current time；Low power consumpting state is switched the processor into as N > O, wherein O is place
Manage device speed handover overhead；Otherwise, processor enters idle state；The value of O is calculated by following formula:
Wherein, H is the time overhead of processor state conversion, EOFor the energy consumption expense of processor state conversion, PaFor processing
Power consumption of the device in active state, PsPower consumption for processor in dormant state, max expression maximizing.
As shown in Fig. 2, in the present embodiment, periodic duty TiPeriod random selection from section [2.4,9.6], the period appoints
Be engaged in TiWorst case under execute the time randomly choosed from 0.035 to its period；Compare three kinds of methods in Fig. 2: first,
Power-saving technology method is not used, task is always with the execution of maximum processor speed；Second, greedy strategy distributes free time side
Free time is distributed to the ready task of highest priority by method always；Third, the method for the present invention will be distributed to free time
The minimum ready task of utilization rate, and utilize dynamic power management technical energy saving；Power-saving technology method not to be used to utilize
Rate is normalized on the basis of the energy consumption equal to 0.4.
From figure 2 it can be seen that methodical normalization energy consumption all influenced by utilization rate.When utilization rate increases
When, the methodical normalization energy consumption of institute rises.This is because utilization rate increases, the execution time of task increases, required energy consumption
Increase；When utilization rate is less than 0.3, the energy consumption of the method for the present invention saving is more；In short, by calculating it is found that the method for the present invention
Than the energy consumption that greedy strategy distribution free time method averagely saves 17.82%, than power-saving technology method not being used averagely to save
About 77.83% energy consumption.
The above is only a specific embodiment of the present invention, but the design concept of the present invention is not limited to this, all to utilize this
Design makes a non-material change to the present invention, and should all belong to behavior that violates the scope of protection of the present invention.
Claims (7)
1. a kind of minimum utilization rate free time distributes low energy consumption method, which is characterized in that include the following:
1) utilization rate for calculating each periodic duty, finds out the minimum periodic duty of utilization rate；
2) using opposite deadline, the offline speed S of periodic duty collection is calculatedO, periodic duty collection is by several periodic duties
Composition；
3) according to the absolute cutoff time limit of periodic duty, the priority of periodic duty is determined；
4) task return period does sth. in advance the free time for completing to generate, and free time is distributed to the utilization rate minimum period and is appointed
Business；
5) speed of service S of the minimum periodic duty of rate is determined the use of, other periodic duties are with the offline speed S of periodic duty collectionOIt holds
Row；
6) dynamic power management technology is utilized, switches the processor into low power consumpting state to reduce energy consumption.
2. a kind of minimum utilization rate free time as described in claim 1 distributes low energy consumption method, which is characterized in that the meter
The utilization rate for calculating each periodic duty finds out the minimum periodic duty of utilization rate；Include:
Periodic duty TiBy triple (ei,pi,di) indicate, wherein 1≤i≤n, i are integer, eiIt is periodic duty TiThe worst feelings
Time, p are executed under conditioniIt is periodic duty TiPeriod, diIt is periodic duty TiOpposite deadline；Periodic duty TiUtilization
Rate isPeriodic duty is sorted from small to large according to its utilization rate, finds out the minimum periodic duty of utilization rate.
3. a kind of minimum utilization rate free time as claimed in claim 2 distributes low energy consumption method, which is characterized in that the benefit
With opposite deadline, the offline speed S of periodic duty collection is calculatedO, specifically include: each cycle TiWithin its period still
There is di-eiThe processor surplus of a chronomere, so the offline speed S of periodic duty collectionOIt is calculated by following formula:
Wherein, n is positive integer, represents the number of periodic duty.
4. a kind of minimum utilization rate free time as claimed in claim 2 distributes low energy consumption method, which is characterized in that described
According to the absolute cutoff time limit of periodic duty, the priority of periodic duty is determined；Include:
Periodic duty TiThe absolute cutoff time limit be equal to its release time riDeadline d corresponding theretoiThe sum of；Periodic duty
The absolute cutoff time limit is smaller, and priority is higher；The absolute cutoff time limit of periodic duty is bigger, and priority is lower；Priority
High task, by priority scheduling.
5. a kind of minimum utilization rate free time as claimed in claim 2 distributes low energy consumption method, which is characterized in that described time
It receives periodic duty and does sth. in advance the free time for completing to generate, free time is distributed into the minimum periodic duty of utilization rate；Include:
Free time management queue is established, the periodic duty for having completed to execute is moved on into free time management queue；In the free time
The high periodic duty of the currently performed periodic duty priority of priority ratio is found in time queue, when calculating the free time generated at this time
Between I；Its value is calculated by following formula:
Wherein, remiIt is periodic duty TiRemaining execute time, h (Ti, t) and it is priority ratio periodic duty TiPriority is high and
Periodic duty through completing to execute, t is current time；Free time I is distributed into the minimum periodic duty of priority utilization rate.
6. a kind of minimum utilization rate free time as claimed in claim 5 distributes low energy consumption method, which is characterized in that described true
Determine the speed of service S of the minimum periodic duty of utilization rate, other periodic duties are with the offline speed S of periodic duty collectionOIt executes, packet
It includes:
The speed of service of the minimum periodic duty of utilization rate is calculated by following formula
Wherein, ScritIt is the minimum speed of service of processor energy consumption；Other periodic duties are with the offline speed S of periodic duty collectionOIt holds
Row.
7. a kind of minimum utilization rate free time as claimed in claim 5 distributes low energy consumption method, which is characterized in that the benefit
With dynamic power management technology, low power consumpting state is switched the processor into reduce energy consumption, comprising:
Processor is in idle condition, and calculates free time N=max { I, A-t at this timec, wherein A appoints for next cycle
The release time of pragmatic example, tcFor current time；Low power consumpting state is switched the processor into as N > O, wherein O is processor
Speed handover overhead；Otherwise, processor enters idle state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811474573.2A CN109613971B (en) | 2018-12-04 | 2018-12-04 | Low-energy-consumption method for allocating idle time with lowest utilization rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811474573.2A CN109613971B (en) | 2018-12-04 | 2018-12-04 | Low-energy-consumption method for allocating idle time with lowest utilization rate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109613971A true CN109613971A (en) | 2019-04-12 |
| CN109613971B CN109613971B (en) | 2022-03-04 |
Family
ID=66005924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811474573.2A Active CN109613971B (en) | 2018-12-04 | 2018-12-04 | Low-energy-consumption method for allocating idle time with lowest utilization rate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109613971B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070240163A1 (en) * | 2006-04-05 | 2007-10-11 | Maxwell Technologies, Inc. | Processor power and thermal management |
| CN103810026A (en) * | 2012-11-09 | 2014-05-21 | 中国科学院沈阳计算技术研究所有限公司 | Mixing scheduling method suitable for real-time system periodic tasks |
| CN103810043A (en) * | 2012-11-09 | 2014-05-21 | 中国科学院沈阳计算技术研究所有限公司 | Energy-saving scheduling method suitable for numerical control system periodic tasks |
| CN105630126A (en) * | 2014-11-05 | 2016-06-01 | 中国科学院沈阳计算技术研究所有限公司 | Low-power scheduling method for mixed task based on constant bandwidth server |
| CN107728466A (en) * | 2017-09-28 | 2018-02-23 | 华侨大学 | One kind is applied to digital control system fixed priority reliability and perceives energy consumption optimization method |
| 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 |
-
2018
- 2018-12-04 CN CN201811474573.2A patent/CN109613971B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070240163A1 (en) * | 2006-04-05 | 2007-10-11 | Maxwell Technologies, Inc. | Processor power and thermal management |
| CN103810026A (en) * | 2012-11-09 | 2014-05-21 | 中国科学院沈阳计算技术研究所有限公司 | Mixing scheduling method suitable for real-time system periodic tasks |
| CN103810043A (en) * | 2012-11-09 | 2014-05-21 | 中国科学院沈阳计算技术研究所有限公司 | Energy-saving scheduling method suitable for numerical control system periodic tasks |
| CN105630126A (en) * | 2014-11-05 | 2016-06-01 | 中国科学院沈阳计算技术研究所有限公司 | Low-power scheduling method for mixed task based on constant bandwidth server |
| CN107728466A (en) * | 2017-09-28 | 2018-02-23 | 华侨大学 | One kind is applied to digital control system fixed priority reliability and perceives energy consumption optimization method |
| 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 |
Non-Patent Citations (5)
| Title |
|---|
| DONGKUN SHIN等: ""Dynamic Voltage Scaling of Mixed Task Sets in Priority-Driven Systems"", 《IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS》 * |
| 张忆文: ""常带宽服务器混合任务低功耗调度算法"", 《计算机研究与发展》 * |
| 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》 * |
| 张忆文: "基于平均空闲时间分配的低功耗调度算法", 《小型微型计算机系统》 * |
| 张忆文: "面向数控系统低功耗调度算法研究", 《中国优秀博硕士学位论文全文数据库(博士)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109613971B (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11579934B2 (en) | Scheduler for amp architecture with closed loop performance and thermal controller | |
| CN105893148B (en) | A kind of accidental task low energy consumption dispatching method based on RM strategy | |
| ul Islam et al. | Hybrid DVFS scheduling for real-time systems based on reinforcement learning | |
| CN108984292B (en) | Fixed priority periodic task energy consumption optimization method for hybrid key system | |
| CN101339521B (en) | Tasks priority dynamic dispatching algorithm | |
| CN109117255A (en) | Heterogeneous polynuclear embedded system energy optimization dispatching method based on intensified learning | |
| CN109324891A (en) | A kind of periodic duty low-power consumption scheduling method of ratio free time distribution | |
| CN106445070B (en) | Energy consumption optimization scheduling method for hard real-time system resource-limited sporadic tasks | |
| Li et al. | Energy-efficient scheduling in nonpreemptive systems with real-time constraints | |
| CN109597378B (en) | Resource-limited hybrid task energy consumption sensing method | |
| El Ghor et al. | Energy efficient scheduler of aperiodic jobs for real-time embedded systems | |
| CN105630126B (en) | One kind is based on normal bandwidth server hybrid task low-power consumption scheduling method | |
| CN109613971A (en) | A kind of minimum utilization rate free time distribution low energy consumption method | |
| CN108874517A (en) | The stand-by system availability of fixed priority divides energy consumption optimization method | |
| Yang et al. | Multi-core fixed priority DVS scheduling | |
| Huang et al. | A energy efficient scheduling base on dynamic voltage and frequency scaling for multi-core embedded real-time system | |
| CN105677449B (en) | A kind of low-power consumption scheduling method suitable for digital control system | |
| CN107368176B (en) | Hard real-time task energy consumption optimal speed calculation method based on probability distribution function | |
| CN106933325B (en) | A kind of fixed priority I/O device energy consumption management method | |
| El Osta et al. | An efficient aperiodic task server for energy harvesting embedded systems | |
| HajiKhodaverdian et al. | Reinforcement Learning-Based Task Scheduling Using DVFS Techniques in Mobile Devices | |
| Deng et al. | A dynamic power management algorithm for sporadic tasks in real-time embedded systems | |
| CN106815073B (en) | Balance factor-based dynamic accidental task low-power-consumption scheduling method | |
| CN110837291B (en) | Energy consumption optimization method based on actual execution time mixed key cycle task | |
| Yu et al. | A Framework for Deep Q-Learning Based Hybrid DVFS Algorithms for Real-Time Systems |
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 |