CN108874517B - Method for optimizing utilization rate division energy consumption of standby system with fixed priority - Google Patents
Method for optimizing utilization rate division energy consumption of standby system with fixed priority Download PDFInfo
- Publication number
- CN108874517B CN108874517B CN201810365257.5A CN201810365257A CN108874517B CN 108874517 B CN108874517 B CN 108874517B CN 201810365257 A CN201810365257 A CN 201810365257A CN 108874517 B CN108874517 B CN 108874517B
- Authority
- CN
- China
- Prior art keywords
- task
- processor
- execution
- main
- priority
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—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
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5022—Mechanisms to release resources
-
- 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
- G06F9/52—Program synchronisation; Mutual exclusion, e.g. by means of semaphores
- G06F9/526—Mutual exclusion algorithms
-
- 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
Abstract
The invention discloses a method for optimizing utilization rate division energy consumption of a standby system with fixed priority, which comprises the following steps of distributing a standby system resource limited period task set to a main processor and a backup processor by a utilization rate division method; determining a processor speed switching overhead; calculating the lowest speed S executed by the main task by utilizing the feasible sufficient conditions of the monotonic rate strategy scheduling and the speed lower limit of the resource limited period task modelM(ii) a Determining backup task execution speed SB(ii) a Scheduling tasks of a main processor and a backup processor by using a fixed double-priority strategy; and idle time generated by the system is recovered, and the energy consumption of the system is reduced by using a DVS technology and a DPM technology. The method of the invention allocates tasks by a utilization rate division method, ensures that resources can be mutually exclusive used, and effectively reduces the energy consumption of the system while improving the reliability of the system.
Description
Technical Field
The invention relates to low-energy-consumption real-time scheduling of a resource limited period task of a fixed priority standby system in the field of embedded real-time systems, in particular to a method for optimizing utilization rate division energy consumption of the fixed priority standby system.
Background
The embedded real-time system not only requires the task to be executed within a specified time, but also ensures the execution result to be correct. Therefore, the real-time performance is extremely strict. In addition, embedded real-time systems are usually powered by batteries, and the battery development technology is lagging, and the battery has limited capacity and weight. In recent years, with the development of processor technology, the size of the processor is continuously reduced, the energy consumption is higher and higher, and the high energy consumption not only affects the service life of the system, but also reduces the reliability of the system, and more importantly, causes damage to the environment. Therefore, real-time performance, reliability and low power consumption become important factors that restrict the development of embedded systems.
The standby system is an important technology for improving the reliability of the system and consists of a main processor and a standby processor. The main task and the corresponding backup task can be distributed to different processors for execution, when the task of one processor fails to execute, the task of the other processor can continue to execute, and thus the reliability of the system can be improved. At present, the research work of the energy consumption optimization method for the standby system is less, only a few researches mainly aim at the system of the dynamic priority strategy and cannot be suitable for the application of the fixed priority, and the energy consumption of the researches is higher and the occupation overhead is overlarge.
Disclosure of Invention
The invention mainly aims to overcome the defects in the prior art and provides a method for optimizing the utilization rate division energy consumption of a standby and standby system with fixed priority.
The invention adopts the following technical scheme:
the utilization rate of a standby system with fixed priority divides the energy consumption optimization method, the standby system is provided with two processors which are a main processor and a standby processor respectively, and the method is characterized in that:
distributing the resource limited period task set of the standby system to a main processor and a backup processor by a utilization rate division method;
determining a processor speed switching overhead;
scheduling feasible sufficiency conditions by using monotonic rate strategy and speed lower limit S of resource-limited periodic task modelHCalculating the minimum speed S of the execution of the main taskM;
Determining backup task execution speed SB;
Scheduling tasks of a main processor and a backup processor by using a fixed double-priority strategy;
and idle time generated by the standby system is recovered, and the energy consumption of the system is reduced by using the DVS technology and the DPM technology.
The resource-limited periodic task set is provided with n periodic task groups, each periodic task group is provided with a main task with the same parameters and a backup task corresponding to the main task, and each periodic task is used according to the utilization rate u of the periodic taskiOrdering from high to low; distributing the main tasks to the main processor and the backup processor in sequence according to the utilization rate from high to low; if the main tasks sharing the same resource are mapped to the same processor, the main tasks are immediately and forcibly distributed to other processors; when the primary task is assigned, its corresponding backup task is assigned to the other processor.
Determining processor speed switching overhead τi(ii) a The processing steps are as follows:
τi=Oi+ω
wherein O isiIs the processor speed conversion overhead, ω is the time overhead of the management task, i is an integer, and the value range is 1 to n.
Lowest speed S of execution of the main taskMThe calculation method is as follows:
SM=min{ST,SH}
wherein SHIs the lower speed limit, S, of the resource-constrained periodic task modelTThe lowest execution speed of the periodic task set under the limitation of sufficient conditions that the monotonic rate strategy scheduling is feasible; sTCalculated from the following formula:
ST=LSRS+SNRS
wherein LSRSIs the lowest execution speed, S, of the resource demanding task setNRSIs the lowest execution speed for a task set without resource requirements.
The execution speed of the backup task is calculated by the following formula:
SB=Smax
wherein SmaxIs the maximum speed that the processor can provide.
The fixed dual-priority policy comprises two priorities, an initial priority and an execution priority; the initial priority is distributed by a monotonic rate strategy, and the smaller the period of the task is, the higher the priority is; the execution priority is determined in the task execution process, the execution priority is the maximum initial priority of the tasks sharing the same resource, and the task TiPreemption task TkIf and only if task TiIs greater than task TkThe execution priority of (1); and scheduling the main processor task according to a fixed double-priority strategy: calculating delayed execution time Y of backup taskiIf the main task T of the main processoriSuccessfully complete execution and cancel its backup task B in the standby processoriIf backup task B of the main processor is executedkSuccessfully complete execution and cancel the main task T of the standby processorkI and k are integers, the value range is 1-n, and i is not equal to k.
The fixed dual priority policy scheduling refers to: calculating delayed execution time Y of backup taskiIf the primary task T of the standby processoriSuccessfully completes execution and cancels the backup task B of the main processoriIf backup task B of the standby processor is executedkSuccessfully complete execution and cancel the main task T of the main processorkIs performed.
The idle time comprises idle time generated by the task completing execution in advance, reserved time for the cancelled task to be released and time when the task does not release the processor to be in an idle state, and the idle time is used for reducing the execution speed of the main task by using a DVS technology; switching the processor to a low power state using DPM techniques reduces power consumption if and only if the processor is in an idle state.
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) compared with the conventional standby system periodic task scheduling method, the method of the invention saves about 8.15% of energy consumption;
(2) the method can ensure that the periodic task is executed within the deadline of the periodic task, and can ensure that resources are mutually exclusive to be used;
(3) the energy consumption of the system is reduced, the production cost of the product can be reduced, the service time of equipment is prolonged, and the replacement period of the battery is shortened;
(4) the system reliability is effectively improved.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention;
fig. 2 is a graph of the results of a simulation experiment of normalized energy consumption versus worst-time to best-time ratio according to an embodiment of the present invention.
Detailed Description
The invention is further described below by means of specific embodiments.
Referring to fig. 1, the method for optimizing energy consumption division by using the utilization ratio of the standby system with fixed priority provided by the invention comprises the following steps:
step 101: and distributing the standby system resource limited period task set to the main processor and the backup processor by a utilization rate division method.
The standby system consists of two processors, namely a main processor and a standby processor; the resource-limited periodic task set consists of n periodic tasks, each periodic task TiComposed of triads (e)i,ri,pi) Composition, i is an integer with a value ranging from 1 to n, eiIs task TiWorst case execution time, riIs task TiResource requirement of piIs task TiA period of (a); the parameters of the corresponding backup tasks are completely the same as those of the main tasks, and each periodic task is sequenced from high to low according to the utilization rate of the periodic task; utilization ui=ei/piAfter sorting u1≥u2≥...≥un(ii) a Allocating the main tasks to the main processor and the backup processor according to the sequence from high utilization rate to low utilization rate, and once the main tasks sharing the same resource are found to be allocated to the same processOn the processor, forcibly distributing the main task to another processor immediately, and after the main task is distributed, distributing the corresponding backup task to another processor; i.e. first will task T1Assigned to the main processor, its corresponding backup task B1Distributing to a backup processor; task T2Distributing to the backup processor to make its corresponding backup task B2Distributing the data to a main processor; by analogy, suppose task Tk(2<k ≦ n) should be assigned to the primary processor (backup processor) but will be assigned to the backup processor (primary processor) upon detection of a finding that the primary processor (backup processor) has assigned a task sharing the same resources as the primary processor.
Step 102: determining processor speed switching overhead τi。
The calculation method is as follows:
τi=Oi+ω
where ω is the time overhead of the management task, OiIs the processor speed translation overhead, which is calculated as follows:
Oi=K·|Si-Si-1|
where K is a constant associated with the standby system, SiAnd Si-1Respectively, the speed that the processor is capable of providing.
Step 103: calculating the lowest speed S executed by the main task by utilizing the feasible sufficient conditions of the monotonic rate strategy scheduling and the speed lower limit of the resource limited period task modelM。
Lowest speed S of execution of main taskMThe calculation method is as follows:
SM=min{ST,SH}
wherein SHThe lower limit of the speed of the resource-limited periodic task model is as follows:
wherein k and n are integers, GkIs task TkMaximum blocking time of τiTask TiF (k) is an upper utilization bound for the monotonic rate strategy to schedule k cycles of tasks feasible, which is calculated by the following equation:
STthe lowest execution speed of the periodic task set under the limitation of sufficient conditions that the monotonic rate strategy scheduling is feasible; sTCalculated from the following formula:
ST=LSRS+SNRS
wherein LSRSIs the lowest execution speed of the resource demanding task set, which is calculated by:
wherein r isiIs task TiResource requirement of SRS(i) Is using a resourceThe lowest operating speed of; the value is calculated by:
wherein e isiIs task TiIn the worst case execution time, GiIs task TiMaximum blocking time of (c), hp (T)i) Is the priority ratio task TiOf a high priority task, τiAnd τjAre respectively task TiAnd TjL is a real number; sNRSIs the lowest execution speed for a task set without resource requirements, whose value is calculated by:
where NRS is a set of tasks that do not use resources, uiIs task TiF (n) is an upper utilization bound for the monotonic rate strategy to schedule n cycles of the task, and its value is calculated by the following formula:
wherein n is an integer.
Step 104: determining backup task execution speed SB。
To improve the reliability of the system, the execution speed of the backup task is calculated by the following formula:
SB=Smax
wherein SmaxIs the maximum speed that the processor can provide.
Step 105: tasks of the primary processor and the backup processor are scheduled using a fixed dual priority policy.
The fixed double-priority strategy consists of two priorities, namely an initial priority and an execution priority; the initial priority is distributed by a monotonic rate strategy, and the smaller the period of the task is, the higher the priority is; the execution priority is determined in the task execution process, the execution priority is the maximum initial priority of the tasks sharing the same resource, and the task TiPreemption task TkIf and only if task TiIs greater than task TkThe execution priority of (1);
and scheduling the main processor task according to a fixed double-priority strategy: calculating delayed execution time Y of backup taskiIf the main task T of the main processoriSuccessfully complete execution and cancel its backup task B in the standby processoriIf backup task B of the main processor is executedkSuccessfully complete execution and cancel the main task T of the standby processorkExecution of (1);
and the standby processor task is scheduled according to a fixed double-priority strategy: for computing backup tasksDelaying execution time YiIf the primary task T of the standby processoriSuccessfully completes execution and cancels the backup task B of the main processoriIf backup task B of the standby processor is executedkSuccessfully complete execution and cancel the main task T of the main processorkExecution of (1);
backup task BiDelayed execution time Y ofiThe calculation method of (2) is as follows:
Yi=Di-γi-t
wherein D isiIs task TiIs the current time, gammaiIs task TiThe worst response time, gamma, is calculated by an iterative methodi:
Where m is an integer representing the number of iterations, GiIs task TiThe maximum blocking time of (2) is calculated as follows:
wherein r isiIs task TiResource requirement of rjIs task TjResource requirement of ejIs task TjA worst case execution time; phi (T)i) Is a function of a value 0 or 1, phi (T)i) The calculation method of (2) is as follows:
wherein r isiIs task TiResource requirement of rjIs task TjResource requirement of tjIs task TjStart execution time of (rt)iIs task TiThe release time of (c); that is to say phi(Ti) Equal to 1 and only if task TiIs tasked with TjBlocking; remkIs task TkIs left over execution time, tauiAnd τkAre respectively task TiAnd TkIs the processor speed switching overhead, hp (T)i) Is the priority ratio task TiSet of high priority tasks of, eiIs task TiOf the worst case execution time, SiIs task TiThe execution speed of (2).
Step 106: and idle time generated by the system is recovered, and the energy consumption of the system is reduced by using a DVS technology and a DPM technology.
Idle time generated by the system mainly comprises idle time generated by the task completing execution in advance, reserved time released by the cancelled task and time when the task does not release the processor to be in an idle state, and the idle time is used for reducing the execution speed of the main task by using a DVS (dynamic video streaming) technology so as to reduce the energy consumption of the processor; the idle time is recovered by establishing an idle time recovery queue, the recovered task completes the idle time generated by the execution in advance and the reserved time ST released by the cancelled taskiCalculated from the following formula,
wherein remkIs task TkIs the remaining execution time of, wkIs task TkRemaining worst case execution time of ekIs task TkIn the worst case of execution time, fkIs task TkTime already executed, whose value satisfies 0 ≦ fk≤ek,hp(Ti) Is the priority ratio task TiSet of high priority tasks, xkIs a constant, x when the task is successfully completedk1 is ═ 1; otherwise, xk0; reduced execution speed S of main task by DVS technologyMICalculated from the following formula:
wherein remiFor task TiIs the remaining execution time of, wiFor task TiRemaining worst case execution time of eiFor task TiWorst case execution time, STiIs task TiDynamic idle time of; the time ID when a task does not release the processor to be in an idle state is calculated by:
ID=next_arrive_time-t
where next _ arrival _ time is the release time of the last task and t is the current time; and switching the processor to the low power consumption state by using the DPM technology to reduce the energy consumption if and only if the processor is in the idle state and the time ID when the task does not release the processor to be in the idle state is larger than the processor state switching overhead.
As shown in fig. 2, in the present embodiment, each cycle set includes 8 cycle tasks. Periodic task set sharing two resources R1And R2And whether the task has resource requirements is randomly selected. Task T of each periodiIn the period of [2.4,9.6 ]]Of which the worst-case execution time is randomly selected in the range of 0.035 to its period. The system utilization is set to be 0.5, the influence of the ratio of the worst time to the best time on the algorithm energy consumption is examined, the ratio of the worst time to the best time is from 1 to 10, and the step size is 1.
Three methods are compared in fig. 2. First, the BS (fixed priority approach without power saving techniques) method, the task is always executed at maximum processor speed. Second, FPMPSA (uses DVS and DPM techniques to save energy, but cannot use dynamic idle time to reduce energy consumption). Thirdly, the method of the invention (energy saving by using the DVS technique and the DPM technique, and energy consumption reduction by using dynamic idle time). It can be seen from fig. 2 that the normalized energy consumption of all methods is affected by the ratio of the worst time to the best time. The normalized energy consumption of all methods decreases as the ratio of worst time to best time increases. This is because the higher the ratio of the worst time to the best time, the shorter the execution time of the task, and therefore the lower the system power consumption. The normalized energy consumption of the method of the invention is lower than that of the BS and FPMPSA methods. The process of the invention saves energy consumption by about 48.29% and 8.15% compared to the BS and FPMPSA processes, respectively.
The above description is only an embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of infringing the present invention.
Claims (4)
1. The utilization rate of a standby system with fixed priority divides the energy consumption optimization method, the standby system is provided with two processors which are a main processor and a standby processor respectively, and the method is characterized in that:
distributing the resource limited period task set of the standby system to a main processor and a backup processor by a utilization rate division method; the resource-limited periodic task set is provided with n periodic task groups, each periodic task group is provided with a main task with the same parameters and a backup task corresponding to the main task, and each periodic task is used according to the utilization rate u of the periodic taskiOrdering from high to low; distributing the main tasks to the main processor and the backup processor in sequence according to the utilization rate from high to low; if the main tasks sharing the same resource are mapped to the same processor, the main tasks are immediately and forcibly distributed to other processors; after the main task is distributed, the corresponding backup task is distributed to another processor;
determining a processor speed switching overhead;
scheduling feasible sufficiency conditions by using monotonic rate strategy and speed lower limit S of resource-limited periodic task modelHCalculating the minimum speed S of the execution of the main taskM(ii) a Lowest speed S of execution of the main taskMThe calculation method is as follows:
SM=min{ST,SH}
wherein SHIs the lower speed limit, S, of the resource-constrained periodic task modelTThe lowest execution speed of the periodic task set under the limitation of sufficient conditions that the monotonic rate strategy scheduling is feasible; sTCalculated from the following formula:
ST=LSRS+SNRS
wherein LSRSIs the lowest execution speed, S, of the resource demanding task setNRSIs the lowest execution speed for a task set without resource requirements;
determining backup task execution speed SB;
Scheduling tasks of a main processor and a backup processor by using a fixed double-priority strategy;
the fixed dual-priority policy comprises two priorities, an initial priority and an execution priority; the initial priority is distributed by a monotonic rate strategy, and the smaller the period of the task is, the higher the priority is; the execution priority is determined in the task execution process, the execution priority is the maximum initial priority of the tasks sharing the same resource, and the task TiPreemption task TkIf and only if task TiIs greater than task TkThe execution priority of (1); and scheduling the main processor task according to a fixed double-priority strategy: calculating delayed execution time Y of backup taskiIf the main task T of the main processoriSuccessfully complete execution and cancel its backup task B in the standby processoriIf backup task B of the main processor is executedkSuccessfully complete execution and cancel the main task T of the standby processorkI and k are integers, the value ranges are 1-n, and i is not equal to k;
the fixed dual priority policy scheduling refers to: calculating delayed execution time Y of backup taskiIf the primary task T of the standby processoriSuccessfully completes execution and cancels the backup task B of the main processoriIf backup task B of the standby processor is executedkSuccessfully complete execution and cancel the main task T of the main processorkExecution of (1);
and idle time generated by the standby system is recovered, and the energy consumption of the system is reduced by using the DVS technology and the DPM technology.
2. The fixed priority standby system utilization partitioning energy consumption optimization method of claim 1, characterized in thatCharacterized in that: determining processor speed switching overhead τi(ii) a The processing steps are as follows:
τi=Oi+ω
wherein O isiIs the processor speed conversion overhead, ω is the time overhead of the management task, i is an integer, and the value range is 1 to n.
3. The fixed priority standby system utilization partitioning energy consumption optimization method of claim 1, wherein: the execution speed of the backup task is calculated by the following formula:
SB=Smax
wherein SmaxIs the maximum speed that the processor can provide.
4. The fixed priority standby system utilization partitioning energy consumption optimization method of claim 1, wherein: the idle time comprises idle time generated by the task completing execution in advance, reserved time for the cancelled task to be released and time when the task does not release the processor to be in an idle state, and the idle time is used for reducing the execution speed of the main task by using a DVS technology; switching the processor to a low power state using DPM techniques reduces power consumption if and only if the processor is in an idle state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810365257.5A CN108874517B (en) | 2018-04-19 | 2018-04-19 | Method for optimizing utilization rate division energy consumption of standby system with fixed priority |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810365257.5A CN108874517B (en) | 2018-04-19 | 2018-04-19 | Method for optimizing utilization rate division energy consumption of standby system with fixed priority |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108874517A CN108874517A (en) | 2018-11-23 |
CN108874517B true CN108874517B (en) | 2021-11-02 |
Family
ID=64327165
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810365257.5A Active CN108874517B (en) | 2018-04-19 | 2018-04-19 | Method for optimizing utilization rate division energy consumption of standby system with fixed priority |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108874517B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109613971B (en) * | 2018-12-04 | 2022-03-04 | 华侨大学 | Low-energy-consumption method for allocating idle time with lowest utilization rate |
CN114578943B (en) * | 2022-02-21 | 2023-05-26 | 华侨大学 | Fixed-priority inaccurate mixed critical task scheduling method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6981133B1 (en) * | 1997-02-14 | 2005-12-27 | Xyron Corporation | Zero overhead computer interrupts with task switching |
CN1851677A (en) * | 2005-11-25 | 2006-10-25 | 华为技术有限公司 | Embedded processor system and its data operating method |
US7631135B2 (en) * | 2006-03-13 | 2009-12-08 | Fujitsu Limited | Processor access control device |
CN103164274A (en) * | 2013-02-18 | 2013-06-19 | 华东师范大学 | Fixed priority real-time task static scheduling method based on temperature constraint |
CN107329817A (en) * | 2017-06-28 | 2017-11-07 | 华侨大学 | A kind of stand-by system mixing divides reliability and perceives energy consumption optimization method |
-
2018
- 2018-04-19 CN CN201810365257.5A patent/CN108874517B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6981133B1 (en) * | 1997-02-14 | 2005-12-27 | Xyron Corporation | Zero overhead computer interrupts with task switching |
CN1851677A (en) * | 2005-11-25 | 2006-10-25 | 华为技术有限公司 | Embedded processor system and its data operating method |
US7631135B2 (en) * | 2006-03-13 | 2009-12-08 | Fujitsu Limited | Processor access control device |
CN103164274A (en) * | 2013-02-18 | 2013-06-19 | 华东师范大学 | Fixed priority real-time task static scheduling method based on temperature constraint |
CN107329817A (en) * | 2017-06-28 | 2017-11-07 | 华侨大学 | A kind of stand-by system mixing divides reliability and perceives energy consumption optimization method |
Non-Patent Citations (4)
Title |
---|
A Low Power Scheduling Algorithm with Balanced Factor for Periodic Tasks;Wu Haotian等;《2017 10th International Conference on Intelligent Computation Technology and Automation (ICICTA)》;20171010;全文 * |
Reliability-aware low energy scheduling in real time systems with shared resources;ZhangYi-wen等;《Microprocessors and Microsystems》;20170731;全文 * |
可重构系统中实时任务调度算法研究;殷进勇;《中国博士学位论文全文数据库 信息科技辑》;20110715;全文 * |
基于RM策略的资源受限偶发任务调度算法;张忆文等;《华中科技大学学报(自然科学版)》;20170714;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN108874517A (en) | 2018-11-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108762896B (en) | Hadoop cluster-based task scheduling method and computer equipment | |
CN111399989B (en) | Container cloud-oriented task preemption and scheduling method and system | |
CN110825520B (en) | Cluster extremely-fast elastic telescoping method for realizing efficient resource utilization | |
US8056083B2 (en) | Dividing a computer job into micro-jobs for execution | |
US8812639B2 (en) | Job managing device, job managing method and job managing program | |
CN109582448B (en) | Criticality and timeliness oriented edge calculation task scheduling method | |
CN109564528B (en) | System and method for computing resource allocation in distributed computing | |
CN110308977B (en) | Low-energy-consumption method for updating mixed key accidental tasks by dynamic utilization rate | |
CN103179048A (en) | Method and system for changing main machine quality of service (QoS) strategies of cloud data center | |
CN112162835A (en) | Scheduling optimization method for real-time tasks in heterogeneous cloud environment | |
CN111984389B (en) | Resource sharing hybrid critical period task energy consumption optimization method based on deadline | |
CN108874517B (en) | Method for optimizing utilization rate division energy consumption of standby system with fixed priority | |
CN107329817B (en) | Standby standby system mixed partitioning reliability perception energy consumption optimization method | |
Li et al. | Task scheduling algorithm for heterogeneous real-time systems based on deadline constraints | |
CN106445659A (en) | Periodic hybrid random task scheduling method for spacecraft | |
CN110048966B (en) | Coflow scheduling method for minimizing system overhead based on deadline | |
CN113672391B (en) | Parallel computing task scheduling method and system based on Kubernetes | |
CN113535356B (en) | Energy-aware hierarchical task scheduling method and device | |
CN109491775B (en) | Task processing and scheduling method used in edge computing environment | |
CN110850954B (en) | Energy consumption optimization method based on fixed priority event triggering mixed key accidental tasks | |
CN111210286A (en) | Tax control server-based efficient invoice issuing method and system | |
CN106354555A (en) | Operation system process scheduling calculation method | |
CN105955816A (en) | Event scheduling method and device | |
CN113986484B (en) | Task processing global scheduling method of social software | |
CN110647393A (en) | Elastic process management system and method |
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 |