CN109597378B - Resource-limited hybrid task energy consumption sensing method - Google Patents

Resource-limited hybrid task energy consumption sensing method Download PDF

Info

Publication number
CN109597378B
CN109597378B CN201811301749.4A CN201811301749A CN109597378B CN 109597378 B CN109597378 B CN 109597378B CN 201811301749 A CN201811301749 A CN 201811301749A CN 109597378 B CN109597378 B CN 109597378B
Authority
CN
China
Prior art keywords
task
periodic
resource
deadline
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.)
Active
Application number
CN201811301749.4A
Other languages
Chinese (zh)
Other versions
CN109597378A (en
Inventor
张忆文
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.)
Huaqiao University
Original Assignee
Huaqiao University
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 Huaqiao University filed Critical Huaqiao University
Priority to CN201811301749.4A priority Critical patent/CN109597378B/en
Publication of CN109597378A publication Critical patent/CN109597378A/en
Application granted granted Critical
Publication of CN109597378B publication Critical patent/CN109597378B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
    • G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32252—Scheduling production, machining, job shop
    • 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
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

The invention relates to a resource-limited hybrid task energy consumption sensing method, which comprises the following steps of establishing a resource-limited hybrid task real-time scheduling model; setting a deadline for distributing the non-periodic tasks, scheduling the deadline and the periodic tasks together, and ensuring resource exclusive access by using a stack resource protocol; computing resource-constrained energy consumption optimum speed So(ii) a Calculating the dynamic idle time I generated by the system; determining the execution speed S of a periodic taskiAnd the non-periodic tasks are executed at maximum processor speed; the processor speed is switched to a low power state using dynamic power management techniques. The method of the invention not only can recover the idle time generated by the early completion of the periodic task and the idle time generated by the server, but also can ensure that the resources can be mutually exclusive accessed; moreover, the speed of the processor can be switched to a low power consumption state by utilizing a dynamic power consumption management technology, so that more energy consumption is saved; the product of the energy consumption and the response time of the method is 7.18 percent lower than that of the existing mixed task low-power-consumption scheduling method.

Description

Resource-limited hybrid task energy consumption sensing method
Technical Field
The invention relates to mixed task energy consumption perception real-time scheduling in the field of real-time systems, in particular to a resource-limited mixed task energy consumption perception method.
Background
A numerical control system is typically a real-time system. The numerical control system comprises hard real-time periodic tasks with deadline limit and non-periodic tasks with response time requirements. It is necessary for a numerical control system to ensure that hard real-time periodic tasks can be completed within their deadlines and then minimize the response time of non-periodic tasks. Due to the increase of the functions of the numerical control system and the rapid development of the CMOS technology, the energy consumption of the numerical control system is higher and higher, so the energy consumption also becomes an important target for designing the numerical control system.
The system resources are required to be shared among the periodic tasks of the numerical control system. This leads to a problem of priority reversal since the resources must be accessed mutually exclusively. The existing low-power-consumption scheduling method for the hybrid tasks does not consider the problem of resource sharing, only utilizes a simple protocol to ensure the exclusive access of resources, and has low utilization efficiency of the idle time of the system, so that the energy consumption of the system is too high, and the method cannot meet the development requirement of a numerical control system.
Disclosure of Invention
The invention aims to overcome the defects of the existing low-power-consumption scheduling method of the hybrid task, provides a resource-limited hybrid task energy consumption sensing method, and takes the resource sharing problem into consideration; ensuring resource exclusive access by using a stack resource protocol, calculating the optimal speed of resource limitation, and fully utilizing the static idle time generated by the system; in addition, the dynamic idle time generated by the system can be recovered, and the energy consumption of the system is effectively reduced by utilizing the DVS technology and the DPM technology.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a resource-constrained hybrid task energy consumption sensing method comprises the following steps:
establishing a resource-limited mixed task real-time scheduling model;
setting a deadline for distributing the non-periodic tasks, scheduling the deadline and the periodic tasks together, and ensuring resource exclusive access by using a stack resource protocol;
computing resource-constrained energy consumption optimum speed So；
Calculating the dynamic idle time I generated by the system;
determining the execution speed S of a periodic taskiAnd the non-periodic tasks are executed at maximum processor speed;
switching the processor speed to a low power consumption state by using a dynamic power consumption management technology;
the establishing of the resource-limited mixed task real-time scheduling model comprises the following steps:
the mixed task comprises a periodic task set and an aperiodic task set; the periodic task set consists of n hard real-time periodic tasks, wherein n is a positive integer; hard real-time periodic task composed of TiIs shown in whichi is an integer, and the value range of i is more than or equal to 1 and less than or equal to n; periodic tasks share m reusable resources RlWherein m and l are positive integers, and the value range of l is more than or equal to 1 and less than or equal to m; aperiodic task composed of JkWherein k is a positive integer greater than 1; periodic task TiFrom a triplet (p)i,ei,ri) Is represented by the formula, wherein piIs a periodic task TiA period of (a); e.g. of the typeiIs a periodic task TiA worst case execution time; r isiIs a periodic task TiThe resource requirements of (1); aperiodic task JkComposed of two tuples (A)k,Ck) Is shown in the specification, wherein AkIs an aperiodic task JkThe release time of (c); ckIs an aperiodic task JkAverage execution time of;
the setting and distributing the deadline of the non-periodic task, scheduling the non-periodic task and the periodic task together, and ensuring resource mutual exclusion access by using a stack resource protocol comprises the following steps:
initializing the deadline of the non-periodic task to d00 and the deadline of the server is also set to 0; updating the deadline of the aperiodic task according to the following rules:
budget q of serversSet q equal to 0s＝QsThe deadline of the non-periodic task is set as dk+TsWherein Q issIs the maximum budget of the server, TsIs the period of the server, dkIs the deadline of the current server;
when the server is in an idle state and the non-periodic task arrives, the budget of the server meets qs≥(dk-Ak)·UsSetting qs＝QsThe deadline of the non-periodic task is set as dk+TsWherein, UsFor server bandwidth, AkIs an aperiodic task JkThe release time of (c); otherwise, the deadline of the non-periodic task is set to dk；
The scheduling the non-periodic task and the periodic task together comprises:
the non-periodic tasks and the periodic tasks are distributed with priorities according to deadline; the closer the deadline is, the higher its priority; the farther the deadline is, the lower its priority; the deadline is the same, and the earlier the release time is, the higher the priority is; the later the release time, the lower its priority; when the deadline is the same as the priority, the lower the task index is, the higher the priority is; tasks with high priority are scheduled preferentially;
the stack resource protocol ensures resource mutual exclusion access, and comprises the following steps:
when the task is executed without accessing the resource, the priority of the task is kept unchanged; when a resource is accessed, its priority becomes the highest priority for the task using that resource; after the task releases the resources, the priority of the task is restored to the original priority;
the computing system generated dynamic idle time, I, is represented by:
I＝Ih+Ic
wherein, IcIdle time generated for the server; i ishIdle time generated for early completion of periodic tasks, IhBy
Represented by the formula:
Figure BDA0001852579830000021
wherein M isiIs task TiIs determined by the remaining execution time, P (T)iT) is task T with priority ratio and having completed execution at time TiA task set with high priority;
the processor speed is switched to a low power consumption state by utilizing a dynamic power consumption management technology, and the processing steps are as follows:
when the processor is in an idle state and the dynamic idle time I is larger than the time overhead of switching the processor state, switching the processor to a low power consumption state by using a dynamic power consumption management technology; otherwise, the processor remains in an idle state.
Preferably, said resource-constrained energy consumption optimum speed SOThe calculation method of (2) is as follows:
So＝max{Scrit,ST}
wherein S iscritThe running speed is the optimal running speed of the energy consumption of the processor; sTFor optimum speed in resource-constrained situations, STThe values of (d) are expressed as:
Figure BDA0001852579830000031
wherein D isminIs a processor requirement under resource constraints.
Preferably, the execution speed S of the periodic taskiThe calculation method of (2) is as follows:
Figure BDA0001852579830000032
wherein, WiFor task TiThe worst-case remaining execution time.
As can be seen from the above description of the present invention, compared with the prior art, the present invention has the following advantages:
(1) the method combines two low-power-consumption technologies of DVS and DPM, can efficiently recycle idle time, and has the product of system energy consumption and response time 7.18 percent lower than that of the conventional low-power-consumption scheduling method for the mixed tasks.
(2) The product of the energy consumption and the non-periodic task response time of the system is reduced, thereby being beneficial to improving the reliability of the system, improving the performance of the system and reducing the error probability of the system.
(3) The product of the system energy consumption and the non-periodic task response time is reduced, the production cost of the product can be reduced, and the competitiveness of an enterprise is improved.
The present invention is further described in detail with reference to the drawings and the embodiments, but the method for sensing energy consumption of a resource-constrained hybrid task is not limited to the embodiments.
Drawings
FIG. 1 is a flow chart of the process steps of the method of the present invention;
FIG. 2 is a graph of the results of a simulation experiment of the product of normalized energy consumption and non-periodic task response time and non-periodic task load.
Detailed Description
The technical solutions in the embodiments of the present invention will be described and discussed in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the method for sensing energy consumption of a resource-limited hybrid task of the present invention includes the following steps:
step 101: and establishing a resource-limited mixed task real-time scheduling model.
Specifically, the hybrid task includes a periodic task set and a non-periodic task set; the periodic task set consists of n hard real-time periodic tasks, wherein n is a positive integer; hard real-time periodic task composed of TiWherein i is an integer and has a value range of 1 to n; periodic tasks share m reusable resources RlWherein m and l are positive integers, and the value range of l is more than or equal to 1 and less than or equal to m; aperiodic task composed of JkWherein k is a positive integer greater than 1; periodic task TiFrom a triplet (p)i,ei,ri) Is represented by the formula, wherein piIs a periodic task TiA period of (a); e.g. of the typeiIs a periodic task TiA worst case execution time; r isiIs a periodic task TiThe resource requirements of (1); when r isi0; periodic task TiThere is no resource requirement, that is it does not need to access resources during execution, and there is no priority reversal problem; when r isiNot equal to 0; periodic task TiThe resource is required to be accessed in the execution process, and when the resource is occupied by other tasks, the periodic task TiBlocked until the resource is released; aperiodic task JkComposed of two tuples (A)k,Ck) Is shown in the specification, wherein AkIs an aperiodic task JkThe release time of (c); ckIs an aperiodic task JkAverage execution time of.
Step 102: and setting a deadline for distributing the non-periodic tasks, scheduling the non-periodic tasks and the periodic tasks together, and ensuring resource exclusive access by using a stack resource protocol.
Specifically, the deadline of the non-periodic task is initialized to d00 and the deadline of the server is also set to 0; updating the deadline of the aperiodic task according to the following rules:
budget q of serversSet q equal to 0s＝QsThe deadline of the non-periodic task is set as dk+TsWherein Q issIs the maximum budget of the server, TsIs the period of the server, dkIs the deadline of the current server;
when the server is in an idle state and the non-periodic task arrives, the budget of the server meets qs≥(dk-Ak)·UsSetting qs＝QsThe deadline of the non-periodic task is set as dk+TsWherein d iskIs the deadline of the current server, UsIs the server bandwidth, which has a value of
Figure BDA0001852579830000041
QsIs the maximum budget of the server, TsIs the period of the server, AkIs an aperiodic task JkThe release time of (c); otherwise, the deadline of the non-periodic task is set to dk；
The scheduling the non-periodic task and the periodic task together comprises:
the non-periodic tasks and the periodic tasks are distributed with priorities according to deadline; the closer the deadline is, the higher its priority; the farther the deadline is, the lower its priority; the deadline is the same, and the earlier the release time is, the higher the priority is; the later the release time, the lower its priority; when the deadline is the same as the priority, the lower the task index is, the higher the priority is; tasks with high priority are scheduled preferentially;
the stack resource protocol ensures resource mutual exclusion access, and comprises the following steps:
when the task is executed without accessing the resource, the priority of the task is kept unchanged; when a resource is accessed, its priority becomes the highest priority for the task using that resource; after the task releases the resources, the priority of the task is restored to the original priority;
step 103: computing resource-constrained energy consumption optimum speed So。
The resource-limited energy consumption optimum speed SOCalculated from the following formula:
So＝max{Scrit,ST}
wherein S iscritFor optimal operating speed of the processor, STThe optimal speed for a resource-constrained case is represented by:
Figure BDA0001852579830000051
wherein, UsIs the server bandwidth, which has a value of
Figure BDA0001852579830000052
QsIs the maximum budget of the server, TsIs the period of the server;
Dminis a processor requirement under resource constraints.
The periodic tasks are firstly arranged according to the periods thereof in a non-descending order, namely T1≤T2≤…≤TnThen, D is calculated from the following formulamin：
Figure BDA0001852579830000053
Wherein p isiIs a periodic task TiA period of (a); e.g. of the typeiIs a periodic task TiA worst case execution time; b iskIs task TkK, i are positive integers.
Step 104: calculating the dynamic idle time I generated by the system;
the system generated dynamic idle time, I, is calculated by:
I＝Ih+Ic
wherein, IcIdle time generated for the server, IhThe resulting idle time for the periodic task to complete earlier.
IhCalculated from the following formula:
Figure BDA0001852579830000054
wherein M isiIs task TiIs determined by the remaining execution time, P (T)iT) is task T with priority ratio and having completed execution at time TiThe task set with high priority.
When the server is in an idle state, that is, the server does not schedule an aperiodic task; or when the server schedules the non-periodic tasks but the load of the non-periodic tasks is lower than the utilization rate of the server, the server generates idle time. At two adjacent scheduling points, i.e. intervals ti-1,ti]Wherein t isi-1And tiRespectively representing the last and current scheduling points of the task. When the server is in idle state, the idle time I generated by the serverc＝Us·(ti-ti-1) Wherein U issIs the bandwidth of the server, which has a value of
Figure BDA0001852579830000061
QsIs the maximum budget of the server, TsIs the period of the server; otherwise, server generated idle time Ic＝Us·(ti-ti-1)-CapIn which C isapIn interval [ t ] for non-periodic tasksi-1,ti]The sum of the time slices that have been executed.
Step 105: determining the execution speed S of a periodic taskiAnd the non-periodic tasks are executed at maximum processor speed.
Execution speed S of periodic taskiThe calculation formula of (a) is as follows:
Figure BDA0001852579830000062
wherein, WiFor periodic tasks TiI is the dynamic idle time generated by the system, MiIs a periodic task TiIs executed for the remaining execution time, ScritFor optimal operating speed of the processor, SoFor the optimal speed of resource-limited energy consumption, the non-periodic task is always executed at the maximum processor speed;
step 106: switching the processor speed to a low power consumption state by using a dynamic power consumption management technology;
when the processor is in an idle state and the dynamic idle time I is larger than the time overhead of switching the processor state, switching the processor to a low power consumption state by using a dynamic power consumption management technology; otherwise, the processor remains in an idle state.
Referring to fig. 2, the periodic task set utilization rate is set to be 0.4, the server bandwidth is set to be 0.4, and the influence of the load of the non-periodic task on the product of the normalized energy consumption and the non-periodic task response time is examined. In fig. 2, three methods are compared, first, the BL method using no energy saving technique is used; secondly, an SMTS method ensures resource exclusive access by using a stack resource protocol, a periodic task is always executed at the optimal speed of resource limited energy consumption, and an aperiodic task is always operated at the maximum processor speed; thirdly, the method of the invention ensures the exclusive access of resources by using stack resource protocol, recycles the dynamic idle time generated by the system, reduces the execution speed of periodic tasks by using DVS, and non-periodic tasks always run at the maximum processor speed, and further reduces the energy consumption of the system by using DPM technology when the processor is in idle state. It can be seen from fig. 2 that the product of the normalized energy consumption and the aperiodic task response time of the SMTS method and the method of the present invention decreases as the load of the aperiodic task increases. This is because the SMTS process and the inventive process increase energy consumption at a slower rate than the BL process. The product of the normalized energy consumption and the non-periodic task response time of the method is always lower than that of other methods no matter how the load of the non-periodic task changes. This is because the method of the present invention not only utilizes the DVS technique to save energy, but also utilizes the DPM technique to reduce energy consumption. According to calculation, the product of the energy consumption and the response time of the method is 7.18% lower than that of the SMTS method.
The above is only one preferred embodiment of the present invention. However, the present invention is not limited to the above embodiments, and any equivalent changes and modifications made according to the present invention, which do not bring out the functional effects beyond the scope of the present invention, belong to the protection scope of the present invention.

Claims (1)

1. A resource-constrained hybrid task energy consumption sensing method is characterized by comprising the following steps:
establishing a resource-limited mixed task real-time scheduling model;
setting a deadline for distributing the non-periodic tasks, scheduling the deadline and the periodic tasks together, and ensuring resource exclusive access by using a stack resource protocol;
computing resource-constrained energy consumption optimum speed So；
Calculating the dynamic idle time I generated by the system;
determining the execution speed S of a periodic taskiAnd the non-periodic tasks are executed at maximum processor speed;
switching the processor speed to a low power consumption state by using a dynamic power consumption management technology;
the establishing of the resource-limited mixed task real-time scheduling model comprises the following steps:
the mixed task comprises a periodic task set and an aperiodic task set; the periodic task set consists of n hard real-time periodic tasks, wherein n is a positive integer; hard real-time periodic task composed of TiWherein i is an integer and has a value range of 1 to n; periodic tasks share m reusable resources RlWherein m and l are positive integers, and the value range of l is more than or equal to 1 and less than or equal to m; aperiodic task composed of JkWherein k is a positive integer greater than 1; periodic task TiFrom a triplet (p)i,ei,ri) Is shown byIn (c) piIs a periodic task TiA period of (a); e.g. of the typeiIs a periodic task TiA worst case execution time; r isiIs a periodic task TiThe resource requirements of (1); aperiodic task JkComposed of two tuples (A)k,Ck) Is shown in the specification, wherein AkIs an aperiodic task JkThe release time of (c); ckIs an aperiodic task JkAverage execution time of;
the setting and distributing the deadline of the non-periodic task, scheduling the non-periodic task and the periodic task together, and ensuring resource mutual exclusion access by using a stack resource protocol comprises the following steps:
initializing the deadline of the non-periodic task to d00 and the deadline of the server is also set to 0; updating the deadline of the aperiodic task according to the following rules:
budget q of serversSet q equal to 0s＝QsThe deadline of the non-periodic task is set as dk+TsWherein Q issIs the maximum budget of the server, TsIs the period of the server, dkIs the deadline of the current server;
when the server is in an idle state and the non-periodic task arrives, the budget of the server meets qs≥(dk-Ak)·UsSetting qs＝QsThe deadline of the non-periodic task is set as dk+TsWherein, UsFor server bandwidth, AkIs an aperiodic task JkThe release time of (c); otherwise, the deadline of the non-periodic task is set to dk；
Scheduling the non-periodic tasks together with the periodic tasks, comprising:
the non-periodic tasks and the periodic tasks are distributed with priorities according to deadline; the closer the deadline is, the higher its priority; the farther the deadline is, the lower its priority; the deadline is the same, and the earlier the release time is, the higher the priority is; the later the release time, the lower its priority; when the deadline is the same as the priority, the lower the task index is, the higher the priority is; tasks with high priority are scheduled preferentially;
the stack resource protocol ensures resource mutual exclusion access, and comprises the following steps:
when the task is executed without accessing the resource, the priority of the task is kept unchanged; when a resource is accessed, its priority becomes the highest priority for the task using that resource; after the task releases the resources, the priority of the task is restored to the original priority;
the computing system generated dynamic idle time, I, is represented by:
I＝Ih+Ic
wherein, IcIdle time generated for the server; i ishThe idle time generated for the early completion of the periodic task,
Ihrepresented by the formula:
Figure FDA0002885628990000021
wherein M isiIs task TiIs determined by the remaining execution time, P (T)iT) is task T with priority ratio and having completed execution at time TiA task set with high priority;
the processor speed is switched to a low power consumption state by utilizing a dynamic power consumption management technology, and the processing steps are as follows:
when the processor is in an idle state and the dynamic idle time I is larger than the time overhead of switching the processor state, switching the processor to a low power consumption state by using a dynamic power consumption management technology; otherwise, the processor keeps an idle state;
the resource-limited energy consumption optimum speed SOThe calculation method of (2) is as follows:
So＝max{Scrit,ST}
wherein S iscritThe running speed is the optimal running speed of the energy consumption of the processor; sTFor optimum speed in resource-constrained situations, STThe values of (d) are expressed as:
Figure FDA0002885628990000022
wherein D isminProcessor requirements under resource constraints;
speed of execution S of the periodic taskiThe calculation method of (2) is as follows:
Figure FDA0002885628990000023
wherein, WiFor task TiThe worst-case remaining execution time.
CN201811301749.4A 2018-11-02 2018-11-02 Resource-limited hybrid task energy consumption sensing method Active CN109597378B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811301749.4A CN109597378B (en) 2018-11-02 2018-11-02 Resource-limited hybrid task energy consumption sensing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811301749.4A CN109597378B (en) 2018-11-02 2018-11-02 Resource-limited hybrid task energy consumption sensing method

Publications (2)

Publication Number Publication Date
CN109597378A CN109597378A (en) 2019-04-09
CN109597378B true CN109597378B (en) 2021-03-09

Family

ID=65957484

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811301749.4A Active CN109597378B (en) 2018-11-02 2018-11-02 Resource-limited hybrid task energy consumption sensing method

Country Status (1)

Country Link
CN (1) CN109597378B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110070219A (en) * 2019-04-15 2019-07-30 华侨大学 One kind mixing critical system static state energy consumption optimization method based on deadline
CN111078401B (en) * 2019-12-02 2023-03-10 华侨大学 Periodic task temperature sensing energy consumption optimization method
CN111324197B (en) * 2020-02-07 2023-03-07 华侨大学 Method for reducing system energy consumption based on three-speed periodic task
CN113759833B (en) * 2020-06-05 2023-06-06 航天科工惯性技术有限公司 Multi-sensor acquisition task scheduling method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN105893148A (en) * 2016-03-30 2016-08-24 华侨大学 Low-energy-consumption aporadic task scheduling method based on RM strategy
CN106970835A (en) * 2017-03-20 2017-07-21 华侨大学 Fixed priority resource limited system level energy consumption optimization method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4785142B2 (en) * 2007-01-31 2011-10-05 ルネサスエレクトロニクス株式会社 Data processing device
US20180095792A1 (en) * 2016-10-05 2018-04-05 Mediatek Inc. Multi-core system including heterogeneous processor cores with different instruction set architectures

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN105893148A (en) * 2016-03-30 2016-08-24 华侨大学 Low-energy-consumption aporadic task scheduling method based on RM strategy
CN106970835A (en) * 2017-03-20 2017-07-21 华侨大学 Fixed priority resource limited system level energy consumption optimization method

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
Dynamic Voltage Scaling of Mixed Task Sets in Priority-Driven Systems;Dongkun Shin and Jihong Kim;《IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems》;20060331;第25卷(第3期);论文第1-5页 *
可靠性感知周期任务能耗管理调度算法;张忆文;《计算机科学与探索》;20161207;全文 *
常带宽服务器混合任务低功耗调度算法;张忆文;《计算机研究与发展》;20150915;论文第1-7页 *
资源受限周期任务低能耗调度算法;张忆文;《小型微型计算机系统》;20170515(第5期);论文第1-4页 *
资源受限周期任务双速度调度算法;张忆文;《小型微型计算机系统》;20180915(第9期);全文 *

Also Published As

Publication number Publication date
CN109597378A (en) 2019-04-09

Similar Documents

Publication Publication Date Title
CN109597378B (en) Resource-limited hybrid task energy consumption sensing method
Mei et al. Energy-aware preemptive scheduling algorithm for sporadic tasks on DVS platform
CN106970835B (en) Hierarchical energy consumption optimization method for fixed priority resource-limited system
CN103810026A (en) Mixing scheduling method suitable for real-time system periodic tasks
CN109324880A (en) A kind of low-power consumption scheduling method suitable for real-time system periodic task model
CN107728466B (en) Fixed priority reliability perception energy consumption optimization method suitable for numerical control system
CN109739332B (en) Multi-task general energy consumption optimization method
US20180329750A1 (en) Resource management method and system, and computer storage medium
US9652027B2 (en) Thread scheduling based on performance state and idle state of processing units
CN114710563A (en) Cluster energy saving method and device
CN109918181B (en) Worst response time-based task schedulability analysis method for hybrid critical system
CN114578947B (en) Dynamic priority energy consumption aware inaccurate mixed critical task scheduling method and system
CN109918185B (en) Scheduling method based on virtual task fixed priority mixed key system
Socci et al. Time-triggered mixed-critical scheduler on single and multi-processor platforms
CN111984389B (en) Resource sharing hybrid critical period task energy consumption optimization method based on deadline
CN107329817B (en) Standby standby system mixed partitioning reliability perception energy consumption optimization method
CN108874517B (en) Method for optimizing utilization rate division energy consumption of standby system with fixed priority
CN113590324B (en) Heuristic task scheduling method and system for cloud side-end collaborative computing
US20160179716A1 (en) Timer management apparatus
CN110850954A (en) Energy consumption optimization method based on fixed priority event triggering mixed key accidental tasks
Marinho et al. Job phasing aware preemption deferral
CN107562527B (en) Real-time task scheduling method for SMP (symmetric multi-processing) on RTOS (remote terminal operating system)
Li et al. The improved EDF scheduling algorithm for embedded real-time system in the uncertain environment
CN109656697B (en) Dual-mode resource-limited periodic task energy consumption optimization method
CN115543450B (en) Method for dynamically dormancy of server-free calculation of resource optimization in edge scene and application

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