CN112633589A - Probability model-based hybrid key task energy consumption optimization scheduling method - Google Patents
Probability model-based hybrid key task energy consumption optimization scheduling method Download PDFInfo
- Publication number
- CN112633589A CN112633589A CN202011609560.9A CN202011609560A CN112633589A CN 112633589 A CN112633589 A CN 112633589A CN 202011609560 A CN202011609560 A CN 202011609560A CN 112633589 A CN112633589 A CN 112633589A
- Authority
- CN
- China
- Prior art keywords
- task
- mode
- probability
- energy consumption
- key
- 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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000005457 optimization Methods 0.000 title claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims abstract description 10
- 238000009826 distribution Methods 0.000 claims description 40
- 230000007704 transition Effects 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000000737 periodic effect Effects 0.000 claims description 14
- 238000005315 distribution function Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Public Health (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Water Supply & Treatment (AREA)
- Algebra (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Power Sources (AREA)
Abstract
The invention relates to a probability model-based hybrid key task energy consumption optimization scheduling method, which comprises the following steps of establishing a probability-based hybrid key task scheduling model; calculating the execution time under the worst condition of the task in the low mode by using the probability of mode conversion; respectively calculating the low key level task speed S by using the worst execution time and the feasibility condition of system scheduling in the task low modeLOAnd high key level task speed SHI(ii) a Deducing a probability model of energy consumption by using the probability model of the execution time of the task; and finding out the execution probability of the high-key level task in a high mode, so that the average energy consumption of the system is the lowest. The method of the invention utilizes the probability of the taskAnd the model is used for minimizing the average energy consumption of the system.
Description
Technical Field
The invention relates to low-energy-consumption real-time scheduling of a hybrid key system, in particular to a probability model-based hybrid key task energy consumption optimization scheduling method.
Background
An embedded real-time system formed by integrating multiple applications with different key levels on the same platform becomes a hybrid key system. The hybrid key system has wide application in the aerospace field and the automotive electronics field. Such as aircraft flight control systems, automotive control systems, and cardiac pacemaker control systems. The operating environment of these systems is limited, and some of them operate even in extreme environments, and the energy for driving these systems usually adopts batteries, and because of the limited power supply capacity of the batteries, the energy consumption becomes an important factor that must be considered for designing these systems.
Existing energy consumption studies for hybrid critical systems assume that tasks are always executed at their worst case time, which is too pessimistic because the true execution time of a task tends to be lower than its worst case execution time; this results in wasted system resources. Therefore, the probability model-based hybrid key task energy consumption optimization scheduling method is provided, system resources can be utilized more effectively, and energy consumption is reduced.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a probabilistic model hybrid key task energy consumption optimization scheduling method.
In order to achieve the purpose, the technical scheme of the invention is as follows:
establishing a probability-based mixed key task scheduling model;
calculating the execution time under the worst condition of the task in the low mode by using the probability of mode conversion;
respectively calculating the low key level task speed S by using the worst execution time and the feasibility condition of system scheduling in the task low modeLOAnd high key level task speed SHI;
Deducing a probability model of energy consumption by using the probability model of the execution time of the task;
finding out the execution probability of the high key level task in a high mode to ensure that the average energy consumption of the system is the lowest;
the establishment of the probability-based hybrid key task scheduling model comprises the following steps:
consider a single processor system comprising n mutually independent hybrid key period task models Γ={τ1,τ2,…,τnMix the critical periodic tasks τi(1. ltoreq. i. ltoreq. n, i is an integer) from (T)i,Di,Li,Ci(LO),Ci(HI),PETi) Is represented by the formula, wherein TiAnd DiAre each tauiThe period and relative deadline; l isiIs τiA key hierarchy of value LO (low key hierarchy task) or HI (high key hierarchy task); ci(LO) and Ci(HI) is each τiWorst case execution time in low mode and high mode. PETiIs task τiThe value of the historical execution time information of (2) is represented by a 3 × k matrix:
wherein, Cl(1. ltoreq. l. ltoreq.k) represents task τiExecution time at maximum processor speed; f. ofi(Cl) And Fi(Cl) Respectively represent execution time as ClA probability density function and an empirical distribution function; of particular note is task τiC of (A)i(LO) is not given in advance. There are three modes of the hybrid critical system, low mode, high mode, and transition mode. The low mode refers to all high key hierarchy mixed key period tasks tauiWhen the execution is finished, the execution time does not exceed Ci(LO); so-called high mode is to allow only high key hierarchy mixed key period tasks τiCompleting the execution; the conversion mode refers to a task period task tau with a high key leveliIts execution time exceeds Ci(LO) and the period of time it completes execution; if mixing the critical period task τiFor low key hierarchy tasks, then Ci(HI)=Ci(LO); if mixing the critical period task τiFor high key level tasks, then Ci(HI)>=Ci(LO); the task set is scheduled by using a preemptive fixed priority strategy and is scheduled by using a monotone deadline strategy, and the period of the taskThe smaller, the greater its priority; the larger the period of a task, the smaller its priority.
Preferably, the calculating the worst execution time of the task in the low mode by using the probability of the mode conversion specifically includes:
mixed critical periodic tasks τiThe worst-case execution time in the low mode is calculated by:
wherein,is thatInverse function of empirical distribution function under distribution, PLO→HIIs the probability of a system mode transition,represents the time distribution in different modes, W ∈ { LO, HI, TR } (LO, HI, TR represent low mode, high mode, and transition mode, respectively); task tauiExecution time distribution in low modeGiven by:
wherein [ ] denotes the Hadamard product of the matrix and x denotes Ci(LO) in PETiNumber of columns in (1), TxMeaning that the 3 xk matrix is truncated to a 3 x matrix, with the following extra columns removed, SLOIs the low key level task speed;
wherein K is Ci(LO)/SLO-Ci(LO),T′xIndicating that the 3 xk matrix is truncated to a 3 x (k-x) matrix, with the previous extra columns removed, SHIIs the speed of high key level tasks.
wherein S isHIIs the speed of high key level tasks.
Preferably, the low key level task speed S is respectively calculated by using the worst execution time in the task low mode and the feasibility condition of system schedulingLOAnd high key level task speed SHI(ii) a The method specifically comprises the following steps:
mixed critical periodic tasks τiThe feasibility conditions in the low mode, the high mode and the transition mode are given by:
wherein, Ci(LO) and Ci(HI) is each τiWorst case execution times in low and high modes, hep (i) is the priority ratio of the mixed critical period task τiHigh set of tasks, MjIs mixing of critical period tasks taujThe number of task instances released within its response time; diIs mixing of critical period tasks tauiThe relative deadline of (c); low key hierarchy task speed SLOAnd high key level task speed SHICan be calculated by the above formula.
Preferably, a probability model of energy consumption is deduced by using a probability model of the execution time of the task; the method specifically comprises the following steps:
the energy consumption of the task is determined by power consumption, execution time and execution speed; the power consumption model of the system is given by:
wherein,the maximum dynamic power consumption, the value of which can be normalized to 1; s is the normalized speed of the processor, theta is the ratio of the maximum static power consumption to the maximum dynamic power consumption, and the value of theta is generally 0.2; pindIs processor-independent power consumption, which takes on a value of 0.1;
therefore, the probability distribution of power consumption in the low modeCalculated from the following formula:
probability distribution of energy consumption in transition modeCalculated from the following formula:
preferably, the execution probability of the high key level task in a high mode is found out, so that the average energy consumption of the system is the lowest; the method specifically comprises the following steps:
the average energy consumption of a task is equal to the probability product of the corresponding energy consumption and its corresponding mode, and the probability function f (E') characterizing each mode of the system is calculated by:
whereinIs a high key hierarchy task τiProbability of execution in high mode, PLO→HIIs the probability of a system mode transition,to representThe probability density function in the distribution is,to representThe probability density function in the distribution is,to representA probability density function in the distribution; the average energy consumption E for the task ensemble is therefore calculated by:
wherein,to representThe amount of energy consumed in the distribution,to representThe amount of energy consumed in the distribution,to representEnergy consumption values in the profile; to minimize the average energy consumption E, it is critical to findWhich in turn may pass PLO→HIAnd calculating the relation between the system and the state of the system, wherein the specific calculation method comprises the following steps:
wherein A represents τiThe previous task of (2) is run in high mode; b represents tauiThe execution time of the previous task exceeds the execution time of the worst case in the low mode; c represents tauiAfter the previous task is finished executing, the system is not in an idle state. Events A, B, C may be distributed by time in different patternsTo obtain the compound.
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 comprises the steps of firstly, establishing a probability-based mixed key task scheduling model; calculating the execution time under the worst condition of the task in the low mode by using the probability of mode conversion; respectively calculating the low key level task speed S by using the worst execution time and the feasibility condition of system scheduling in the task low modeLOAnd high key level task speed SHI(ii) a Deducing a probability model of energy consumption by using the probability model of the execution time of the task; finding out the execution probability of the high key level task in a high mode; compared with the conventional method for scheduling the periodic tasks of the hybrid key system, the method disclosed by the invention has the advantages that the average energy consumption of the system is reduced by about 59.03% to the minimum; and can ensure that the periodic task is executed within the deadline of the periodic task; the energy consumption of the hybrid key system is reduced, the production cost of products is reduced, the service time of equipment is prolonged, and the replacement period of batteries is shortened.
The invention is further described in detail with reference to the drawings and the embodiments, but the method for optimally scheduling the energy consumption of the hybrid key tasks based on the probabilistic model is not limited to the embodiments.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
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 optimally scheduling energy consumption of mixed key tasks based on a probabilistic model according to the present invention includes the following steps:
step 101: and establishing a probability-based mixed key task scheduling model.
Consider a single-processor system containing n mutually independent mixed key period task models Γ ═ τ1,τ2,…,τnMix the critical periodic tasks τi(1. ltoreq. i. ltoreq. n, i is an integer) from (T)i,Di,Li,Ci(LO),Ci(HI),PETi) Is represented by the formula, wherein TiAnd DiAre each tauiThe period and relative deadline; l isiIs τiA key hierarchy of value LO (low key hierarchy task) or HI (high key hierarchy task); ci(LO) and Ci(HI) is each τiWorst case execution time in low mode and high mode. PETiIs task τiThe value of the historical execution time information of (2) is represented by a 3 × k matrix:
wherein, Cl(1. ltoreq. l. ltoreq.k) represents task τiExecution time at maximum processor speed; f. ofi(Cl) And Fi(Cl) Respectively represent execution time as ClA probability density function and an empirical distribution function; of particular note is task τiC of (A)i(LO) is not given in advance. There are three modes of the hybrid critical system, low mode, high mode, and transition mode. The low mode refers to all high key hierarchy mixed key period tasks tauiWhen the execution is finished, the execution time does not exceed Ci(LO); so-called high mode is to allow only high key hierarchy mixed key period tasks τiCompleting the execution; the conversion mode refers to a task period task tau with a high key leveliIts execution time exceeds Ci(LO) and the period of time it completes execution; if mixing the critical period task τiFor low key hierarchy tasks, then Ci(HI)=Ci(LO); if mixing the critical period task τiFor high key level tasks, then Ci(HI)>=Ci(LO); the task set is scheduled by using a preemptive fixed priority strategy and is scheduled by using a monotone deadline strategy, wherein the smaller the period of the task is, the larger the priority of the task is; the larger the period of a task, the smaller its priority.
Step 102: and calculating the worst-case execution time of the task in the low mode by using the probability of mode conversion.
Mixed critical periodic tasks τiThe worst-case execution time in the low mode is calculated by:
wherein,is thatInverse function of empirical distribution function under distribution, PLO→HIIs the probability of a system mode transition,represents the time distribution in different modes, W ∈ { LO, HI, TR } (LO, HI, TR represent low mode, high mode, and transition mode, respectively); task tauiExecution time distribution in low modeGiven by:
wherein [ ] denotes the Hadamard product of the matrix and x denotes Ci(LO) in PETiNumber of columns in (1), TxMeaning that the 3 xk matrix is truncated to a 3 x matrix, with the following extra columns removed, SLOIs the low key level task speed;
wherein K is Ci(LO)/SLO-Ci(LO),T′xIndicating that the 3 xk matrix is truncated to a 3 x (k-x) matrix, with the previous extra columns removed, SHIIs the speed of high key level tasks.
wherein S isHIIs the speed of high key level tasks.
Step 103: respectively calculating the low key level task speed S by using the worst execution time and the feasibility condition of system scheduling in the task low modeLOAnd high key level task speed SHI(ii) a The method specifically comprises the following steps:
mixed critical periodic tasks τiThe feasibility conditions in the low mode, the high mode and the transition mode are given by:
wherein, Ci(LO) and Ci(HI) is each τiWorst case execution times in low and high modes, hep (i) is the priority ratio of the mixed critical period task τiHigh set of tasks, MjIs mixing of critical period tasks taujThe number of task instances released within its response time; diIs mixing of critical period tasks tauiThe relative deadline of (c); low key hierarchy task speed SLOAnd high key level task speed SHICan be calculated by the above formula.
Step 104: deducing a probability model of energy consumption by using the probability model of the execution time of the task; the method specifically comprises the following steps:
the energy consumption of the task is determined by power consumption, execution time and execution speed; the power consumption model of the system is given by:
wherein,the maximum dynamic power consumption, the value of which can be normalized to 1; s is the normalized speed of the processor, theta is the ratio of the maximum static power consumption to the maximum dynamic power consumption, and the value of theta is generally 0.2; pindIs processor-independent power consumption, which takes on a value of 0.1;
therefore, power consumption in the low modeProbability distributionCalculated from the following formula:
probability distribution of energy consumption in transition modeCalculated from the following formula:
step 105: and finding out the execution probability of the high-key level task in a high mode, so that the average energy consumption of the system is the lowest.
The average energy consumption of a task is equal to the probability product of the corresponding energy consumption and its corresponding mode, and the probability function f (E') characterizing each mode of the system is calculated by:
whereinIs a high key hierarchy task τiProbability of execution in high mode, PLO→HIIs the probability of a system mode transition,to representThe probability density function in the distribution is,to representThe probability density function in the distribution is,to representA probability density function in the distribution; the average energy consumption E for the task ensemble is therefore calculated by:
wherein,to representThe amount of energy consumed in the distribution,to representThe amount of energy consumed in the distribution,to representEnergy consumption values in the profile; to minimize the average energy consumption E, it is critical to findWhich in turn may pass PLO→HIAnd calculating the relation between the system and the state of the system, wherein the specific calculation method comprises the following steps:
wherein A represents τiThe previous task of (2) is run in high mode; b represents tauiThe execution time of the previous task exceeds the execution time of the worst case in the low mode; c represents tauiAfter the previous task is finished executing, the system is not in an idle state. Events A, B, C may be distributed by time in different patternsTo obtain the compound.
In this embodiment, the mixed-cycle task set Γ ═ τ1,τ2Contains 2 periodic tasks τ1=(30,30,HI,C1(LO),8,PET1),τ2=(30,30,LO,6,6,PET2) The history information of the execution time of the task is as follows:
get PLO→HI=0.05,SHIWhen 1, it is known that1(LO) is 4, and S can be calculated from equations 6-8LO1/3. Therefore, the temperature of the molten metal is controlled,
due to tau2Is a low key hierarchy task and therefore does not have a high mode and a transition modeThe time profile of formula (la); the corresponding energy consumption distribution is as follows:
through calculation, the energy consumption is optimized to be rapidPeriodic task τ1The average energy consumption of (2) is 3.36; periodic task τ2The average energy consumption of (1.65); the total average energy consumption was 5.01; total energy consumption without using the probabilistic model system is 12.23; in the interval [0,30 ]]Scheduling the set of tasks internally saves energy consumption by about 59.03% compared to a method where the tasks are executed at their worst case execution time.
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 (6)
1. A probability model-based hybrid key task energy consumption optimization scheduling method is characterized by comprising the following steps:
establishing a probability-based mixed key task scheduling model;
calculating the execution time under the worst condition of the task in the low mode by using the probability of mode conversion;
respectively calculating the low key level task speed S by using the worst execution time and the feasibility condition of system scheduling in the task low modeLOAnd high key level task speed SHI;
Deducing a probability model of energy consumption by using the probability model of the execution time of the task;
finding out the execution probability of the high key level task in a high mode to ensure that the average energy consumption of the system is the lowest;
2. the method according to claim 1, wherein the establishing of the probability-based hybrid mission critical energy consumption optimized scheduling model comprises:
consider a single-processor system containing n mutually independent mixed key period task models Γ ═ τ1,τ2,…,τnMix key periodic tasks, }, τiI is not less than 1 and not more than n, i is an integer, represented by (T)i,Di,Li,Ci(LO),Ci(HI),PETi) Is represented by the formula, wherein TiAnd DiAre each tauiThe period and relative deadline; l isiIs τiThe value of the key hierarchy of (1) is LO low key hierarchy task or HI high key hierarchy task; ci(LO) and Ci(HI) is each τiWorst case execution time, PET, in low and high modesiIs task τiIs represented by a 3 × k matrix:
wherein, Cl(1. ltoreq. l. ltoreq.k) represents task τiExecution time at maximum processor speed; f. ofi(Cl) And Fi(Cl) Respectively represent execution time as ClA probability density function and an empirical distribution function; the hybrid key system has three modes, namely a low mode, a high mode and a conversion mode; the low mode refers to all high key hierarchy mixed key period tasks tauiWhen the execution is finished, the execution time does not exceed Ci(LO); so-called high mode is to allow only high key hierarchy mixed key period tasks τiCompleting the execution; the conversion mode refers to a task period task tau with a high key leveliIts execution time exceeds Ci(LO) and the period of time it completes execution; if mixing the critical period task τiFor low key hierarchy tasks, then Ci(HI)=Ci(LO); if mixing the critical period task τiFor high key level tasks, then Ci(HI)>=Ci(LO); the task set is scheduled using a preemptive fixed priority policy.
3. The method for optimal scheduling of energy consumption of mixed critical tasks based on a probabilistic model according to claim 1, wherein the calculating of the worst case execution time of the task in the low mode using the probability of mode transformation specifically comprises:
mixed critical periodic tasks τiThe worst-case execution time in the low mode is calculated by:
wherein,is thatInverse function of empirical distribution function under distribution, PLO→HIIs the probability of a system mode transition,represents the time distribution under different modes, W is belonged to { LO, HI, TR }; LO, HI, and TR represent low mode, high mode, and transition mode, respectively; task tauiExecution time distribution in low modeGiven by:
wherein [ ] denotes the Hadamard product of the matrix and x denotes Ci(LO) in PETiNumber of columns in (1), TxMeaning that the 3 xk matrix is truncated to a 3 x matrix, with the following extra columns removed, SLOIs the low key level task speed;
wherein K is Ci(LO)/SLO-Ci(LO),T′xIndicating that the 3 x k matrix is truncated to a 3 x (k-x) matrix with the previous extra columns removed.
wherein S isHIIs the speed of high key level tasks.
4. The method for optimal scheduling of energy consumption of mixed key tasks based on probabilistic model according to claim 1, wherein the low key level task speed S is calculated by using the worst case execution time in task low mode and the feasibility condition of system schedulingLOAnd high key level task speed SHI(ii) a The method specifically comprises the following steps:
mixed critical periodic tasks τiThe feasibility conditions in the low mode, the high mode and the transition mode are given by:
wherein, Ci(LO) and Ci(HI) is each τiWorst case execution times in low and high modes, hep (i) is the priority ratio of the mixed critical period task τiHigh set of tasks, MjIs mixing of critical period tasks taujThe number of task instances released within its response time; diIs mixing of critical period tasks tauiThe relative deadline of (c); sLOLow key level task speed; sHIIs a high key level task speed.
5. The method for energy consumption optimized scheduling of hybrid critical tasks based on probabilistic models as defined in claim 1, wherein the probabilistic model of energy consumption is derived from a probabilistic model of the execution time of the tasks; the method specifically comprises the following steps:
the energy consumption of the task is determined by power consumption, execution time and execution speed; the power consumption model of the system is given by:
wherein,is the maximum dynamic power consumption; s is the normalized speed of the processor, and theta is the ratio of the maximum static power consumption to the maximum dynamic power consumption; pindIs processor independent power consumption。
probability distribution of energy consumption in transition modeCalculated from the following formula:
6. the method for optimal scheduling of energy consumption of hybrid key tasks based on probabilistic models according to claim 1, wherein the execution probability of high key level tasks in a high mode is found to minimize the average energy consumption of the system; the method specifically comprises the following steps:
the average energy consumption of a task is equal to the probability product of the corresponding energy consumption and its corresponding mode, and the probability function f (E') characterizing each mode of the system is calculated by:
wherein P isi HIIs a high key hierarchy task τiProbability of execution in high mode, PLO→HIIs the probability of a system mode transition, fl LO(El LO) To representThe probability density function in the distribution is,to representThe probability density function in the distribution is,to representA probability density function in the distribution; the average energy consumption E for the task ensemble is therefore calculated by:
wherein,to representThe amount of energy consumed in the distribution,to representThe amount of energy consumed in the distribution,to representEnergy consumption values in the profile; to minimize the average energy consumption E, it is critical to find Pi HIWhich in turn may pass through PLO→HIAnd calculating the relation between the state of the system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011609560.9A CN112633589B (en) | 2020-12-30 | 2020-12-30 | Probability model-based hybrid key task energy consumption optimization scheduling method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011609560.9A CN112633589B (en) | 2020-12-30 | 2020-12-30 | Probability model-based hybrid key task energy consumption optimization scheduling method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112633589A true CN112633589A (en) | 2021-04-09 |
CN112633589B CN112633589B (en) | 2022-07-29 |
Family
ID=75286639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011609560.9A Active CN112633589B (en) | 2020-12-30 | 2020-12-30 | Probability model-based hybrid key task energy consumption optimization scheduling method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112633589B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105677461A (en) * | 2015-12-30 | 2016-06-15 | 西安工业大学 | Mixed-criticality tasks scheduling method based on criticality |
CN108983712A (en) * | 2018-06-04 | 2018-12-11 | 华东师范大学 | A kind of optimization mixes the method for scheduling task of crucial real-time system service life |
CN108984292A (en) * | 2018-08-14 | 2018-12-11 | 华侨大学 | Mix critical system fixed priority periodic duty energy consumption optimization method |
CN109739332A (en) * | 2019-01-25 | 2019-05-10 | 华侨大学 | A kind of general energy consumption optimization method of multitask |
CN109918181A (en) * | 2019-01-12 | 2019-06-21 | 西北工业大学 | Mixing critical system task Schedulability Analysis method based on the worst response time |
CN110288153A (en) * | 2019-06-25 | 2019-09-27 | 华侨大学 | A kind of optimal velocity mixing critical cycle task energy consumption optimization method |
CN111736987A (en) * | 2020-05-29 | 2020-10-02 | 山东大学 | Task scheduling method based on GPU space resource sharing |
CN111984389A (en) * | 2020-08-28 | 2020-11-24 | 华侨大学 | Resource sharing mixed key cycle task energy consumption optimization method based on double cutoff time limits |
-
2020
- 2020-12-30 CN CN202011609560.9A patent/CN112633589B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105677461A (en) * | 2015-12-30 | 2016-06-15 | 西安工业大学 | Mixed-criticality tasks scheduling method based on criticality |
CN108983712A (en) * | 2018-06-04 | 2018-12-11 | 华东师范大学 | A kind of optimization mixes the method for scheduling task of crucial real-time system service life |
CN108984292A (en) * | 2018-08-14 | 2018-12-11 | 华侨大学 | Mix critical system fixed priority periodic duty energy consumption optimization method |
CN109918181A (en) * | 2019-01-12 | 2019-06-21 | 西北工业大学 | Mixing critical system task Schedulability Analysis method based on the worst response time |
CN109739332A (en) * | 2019-01-25 | 2019-05-10 | 华侨大学 | A kind of general energy consumption optimization method of multitask |
CN110288153A (en) * | 2019-06-25 | 2019-09-27 | 华侨大学 | A kind of optimal velocity mixing critical cycle task energy consumption optimization method |
CN111736987A (en) * | 2020-05-29 | 2020-10-02 | 山东大学 | Task scheduling method based on GPU space resource sharing |
CN111984389A (en) * | 2020-08-28 | 2020-11-24 | 华侨大学 | Resource sharing mixed key cycle task energy consumption optimization method based on double cutoff time limits |
Non-Patent Citations (6)
Title |
---|
CAO JIE 等: "Dual fault-tolerant scheduling algorithm of periodic and aperiodic hybrid real-time tasks in cloud environment", 《JOURNAL OF COMPUTER APPLICATIONS》 * |
张忆文 等: "实时系统混合任务低功耗调度算法", 《吉林大学学报(工学版)》 * |
张忆文 等: "资源受限周期任务低能耗调度算法", 《小型微型计算机系统》 * |
景维鹏 等: "混合关键任务可靠调度方法与调度性分析", 《西安电子科技大学学报》 * |
赵瑞姣 等: "基于异构多核系统的混合关键任务调度算法", 《计算机工程》 * |
黄丽达 等: "截止时限为关键参数的混合关键级实时任务调度研究", 《计算机研究与发展》 * |
Also Published As
Publication number | Publication date |
---|---|
CN112633589B (en) | 2022-07-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108984292B (en) | Fixed priority periodic task energy consumption optimization method for hybrid key system | |
CN106773711B (en) | A kind of the hybrid tasks scheduling method and model of railway locomotive operation steerable system | |
CN110308977B (en) | Low-energy-consumption method for updating mixed key accidental tasks by dynamic utilization rate | |
CN110165714B (en) | Micro-grid integrated scheduling and control method based on extreme dynamic programming algorithm and computer readable storage medium | |
CN111984389B (en) | Resource sharing hybrid critical period task energy consumption optimization method based on deadline | |
CN112486652B (en) | Non-preemptive fixed priority hybrid critical task energy consumption optimal scheduling method | |
CN109597378B (en) | Resource-limited hybrid task energy consumption sensing method | |
CN115619002A (en) | Flexible dynamic mixed key system scheduling method | |
CN109918185B (en) | Scheduling method based on virtual task fixed priority mixed key system | |
CN111284347B (en) | State clustering coding method in charging station vehicle access control | |
CN110070219A (en) | One kind mixing critical system static state energy consumption optimization method based on deadline | |
CN114578947A (en) | Dynamic priority energy consumption perception non-precise mixed key task scheduling method and system | |
CN112905330B (en) | Fixed priority hybrid key sporadic task energy consumption sensing method | |
CN110288153B (en) | Optimal speed mixed key cycle task energy consumption optimization method | |
CN112633589B (en) | Probability model-based hybrid key task energy consumption optimization scheduling method | |
CN110850954B (en) | Energy consumption optimization method based on fixed priority event triggering mixed key accidental tasks | |
CN116126503A (en) | Dynamic priority semi-perspective inaccurate mixing critical task energy consumption optimization scheduling method | |
Kim et al. | Power guarantee for electric systems using real-time scheduling | |
CN110825504B (en) | Server-based hybrid key accidental task energy consumption optimization method | |
CN114578946A (en) | Non-precise mixed key task non-preemption dynamic priority energy consumption optimization method | |
CN110806795B (en) | Energy consumption optimization method based on dynamic idle time mixed key cycle task | |
CN111954268B (en) | Cooperative resource allocation and system based on small unmanned aerial vehicle | |
CN114578944B (en) | Method and system for sensing energy consumption of mixed critical tasks by updating utilization rate of fixed priority | |
CN110837291B (en) | Energy consumption optimization method based on actual execution time mixed key cycle task | |
CN115016632B (en) | Dynamic priority energy-saving scheduling method based on multiprocessor partition |
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 |