CN109583742A - A kind of phased array radar resource regulating method based on the distribution of two sub-priorities - Google Patents
A kind of phased array radar resource regulating method based on the distribution of two sub-priorities Download PDFInfo
- Publication number
- CN109583742A CN109583742A CN201811415307.2A CN201811415307A CN109583742A CN 109583742 A CN109583742 A CN 109583742A CN 201811415307 A CN201811415307 A CN 201811415307A CN 109583742 A CN109583742 A CN 109583742A
- Authority
- CN
- China
- Prior art keywords
- task
- time
- scheduling
- enabled
- formula
- 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.)
- Pending
Links
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
- G06Q10/06—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
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a kind of phased array radar resource regulating methods based on the distribution of two sub-priorities, including initiation parameter；Select executable set of tasks Ap, obtain the task queue of comprehensive priority；ID is updated according to successful task type is dispatched；Judge whether to meet time-constrain and energy constraint condition, if being unsatisfactory for its time-constrain or energy constraint condition, i=i+1 is enabled to carry out the next task in this scheduling interval；If i > Np, illustrate that the task analysis in this scheduling interval terminates, pointer p enabled to be directed toward next scheduling interval；As p > tendTerminate.Dispatching method of the invention considers priority and the off period of task simultaneously, has carried out two times scheduling on the basis of primary scheduling；By dispatching twice, guarantee more to go scheduler task in the case where radar system resource makes full use of, improve the time availability of system, reduce the Loss Rate of task, keep scheduling strategy more perfect.
Description
Technical field
The present invention relates to phased array radar control technology fields, and in particular to a kind of based on the phased of two sub-priorities distribution
Radar resource dispatching method.
Background technique
In Phased Array Radar Resource Scheduling, usually according to the priority of task working method come the task of distributing, preferentially
The high task of grade is first scheduled, and the low task of priority is finally scheduled.Such way, will lead to even if in radar resource
Relatively in the case where abundance, it can also make the task of low priority and be dropped because of temporal conflict, in turn result in task
Time availability decline, task Loss Rate increases, while wasting the consequence of system resource.In the prior art with regard to scheduling of resource
Preceding strategy distribution is studied, but considers only the priority of task or the off period of task；The money of radar system
Source, which is appointed, can not so make full use of, and the time availability of system is lower, and task Loss Rate is higher.
Summary of the invention
The object of the present invention is to provide a kind of phased array radar resource regulating methods based on the distribution of two sub-priorities.
In order to achieve the above object, providing a kind of phased thunder based on the distribution of two sub-priorities in one embodiment of the present of invention
Up to resource regulating method, comprising the following steps:
Step 1: initiation parameter, the parameter include time indicator p, energy state vector E, time state vector φΔt
(k) and marking variable ID, wherein p >=t0；
Step 2: judgementIt whether is 0；
IfThe executing the time in task requests the latest less than p of the task is then deleted, goes to step 3；
IfIt is not 0；P=p+ Δ t is enabled, is rejudged；
Step 3: the set of tasks A that current time can execute is selected from task requestspIf the set task number is
Np, the higher task of comprehensive priority is selected by the sequence to two times scheduling task priority, therefore can obtain comprehensive preferential
The task queue that grade arranges from high to low, is denoted asMission number i=1；
Step 4: from set ApIn select i-th of task, be denoted as Ti；
If flag=1,5 are gone to step, execution chained list is otherwise put it into, enables sti=p, and it is deleted from application chained list
It removes；ID is updated and according to formula (4-8) and formula (4-24) update φ according to successful task type is dispatchedΔt(k) and Ei(k)；If appointing
Be engaged in TiFor search mission, then p=p+ld is enabledi；If dispatching tracing task, p=p+ Δ t is enabled, goes to step 6；
The algorithm of above-mentioned formula (4-8) and formula (4-24) are as follows:
Step 5: judging whether to meet time-constrain and energy constraint condition, if being unsatisfactory for its time-constrain or energy about
Beam condition then enables i=i+1 carry out the next task in this scheduling interval；If i > Np, illustrate the task in this scheduling interval
Analysis terminates, and pointer p is enabled to be directed toward next scheduling interval, i.e. p=p+ Δ t goes to step 6, otherwise return step 5；
Step 6: as p > tend, 7 are gone to step, otherwise return step 2；
Step 7: emulation terminates.
In conclusion the invention has the following advantages that
Dispatching method of the invention considers priority and the off period of task simultaneously, carries out on the basis of primary scheduling
Two times scheduling；By dispatching twice, guarantee more to go scheduler task in the case where radar system resource makes full use of,
The time availability for improving system reduces the Loss Rate of task, keeps scheduling strategy more perfect.
Detailed description of the invention
Fig. 1 is the flow diagram of one embodiment of the invention；
Fig. 2 a is inventive algorithm A and algorithm B regulation index search mission Loss Rate comparison diagram；
Fig. 2 b is inventive algorithm A and algorithm B regulation index search mission Loss Rate comparison diagram；
Fig. 2 c is inventive algorithm A and algorithm B regulation index tracing task Loss Rate comparison diagram；
Fig. 2 d is inventive algorithm A and algorithm B regulation index task Loss Rate comparison diagram；
Fig. 2 e is inventive algorithm A and algorithm B regulation index time availability comparison diagram；
Fig. 2 f is inventive algorithm A and algorithm B regulation index capacity usage ratio comparison diagram.
Specific embodiment
The present invention provides a kind of phased array radar resource regulating methods based on the distribution of two sub-priorities, including following step
It is rapid:
Step 1: initiation parameter, the parameter include time indicator p, energy state vector E, time state vector φΔt
(k) and marking variable ID, wherein p >=t0；
Step 2: judgementIt whether is 0；
IfThe executing the time in task requests the latest less than p of the task is then deleted, goes to step 3；
IfIt is not 0；P=p+ Δ t is enabled, is rejudged；
Step 3: the set of tasks A that current time can execute is selected from task requestspIf the set task number is
Np, the higher task of comprehensive priority is selected by the sequence to two times scheduling task priority, therefore can obtain comprehensive preferential
The task queue that grade arranges from high to low, is denoted asMission number i=1；
Step 4: from set ApIn select i-th of task, be denoted as Ti；
If flag=1,5 are gone to step, execution chained list is otherwise put it into, enables sti=p, and it is deleted from application chained list
It removes；ID is updated and according to formula (4-8) and formula (4-24) update φ according to successful task type is dispatchedΔt(k) and Ei(k)；If appointing
Be engaged in TiFor search mission, then p=p+ld is enabledi；If dispatching tracing task, p=p+ Δ t is enabled, goes to step 6；
The algorithm of above-mentioned formula (4-8) and formula (4-24) are as follows:
Step 5: judging whether to meet time-constrain and energy constraint condition, if being unsatisfactory for its time-constrain or energy about
Beam condition then enables i=i+1 carry out the next task in this scheduling interval；If i > Np, illustrate the task in this scheduling interval
Analysis terminates, and pointer p is enabled to be directed toward next scheduling interval, i.e. p=p+ Δ t goes to step 6, otherwise return step 5；
Step 6: as p > tend, 7 are gone to step, otherwise return step 2；
Step 7: emulation terminates.
A specific embodiment of the invention are as follows:
The present invention is the algorithm that pulse interlacing is introduced on the basis of time indicator, and the two is combined as a kind of new
Dispatching algorithm most suitable resident task is selected for each moment by time indicator.The method of sliding-model control is answered
With on the time span Δ t of system, then the sliding step of time indicator is Δ t and is successively directed toward these discrete at the time of points.
Pulse interlacing cannot be carried out between resident task due to searching for, needs to introduce marking variable ID, is judged with this
Pulse interlacing can be carried out at the time of current, remember ID={ flag, p, dmax, wherein the value of flag ∈ { 0,1 } is 0 or 1, and p is
It is directed toward the time indicator at current time.As flag=1, it was demonstrated that the previous resident task that this moment executes can carry out pulse
Staggeredly, i.e., previous task is tracing task, otherwise flag=0；dmaxTo have dispatched institute in successful task on a timeline
The maximum moment value occupied, is denoted as:
Wherein, N is scheduled successful number of tasks, stkIt indicates to dispatch successfully resident real time, ldkExpression is scheduled to
The resident physical length of function.If the task at current time is search mission and p < dmax, then search mission cannot be held at this moment
Row.
In order to judge on the time point of various discrete whether the existing pulse by successful dispatch, introduce time state to
Flow function φΔt(k), φ is initializedΔt(k)=0, when event is scheduled successfully, then according to following formula renewal function:
Wherein, k={ 1,2,3 ... } is time interval number,φ is worked as in formula (4-8) expressionΔt(k)
When=1, k-th of moment existing pulse, this moment cannot execute task requests, then time indicator refers to according to sliding step Δ t
To next moment, judge next moment point with the presence or absence of capable of executing at current time for task.
There are two critically important constraint conditions in scheduling process, and need to meet this constraint condition just can smoothly carry out
Scheduling, i.e. time constraint condition and energy constraint condition.
(1) time constraint condition
It is assumed that p is current time indicator, TiFor the scheduler task at moment pointed by p pointer, TiTo have dispatched success
Task, need interpretation TiIt can execute, be needed to T at current timeiAnd TkStaggeredly analyzed.It is analyzed from beam angle, such as
Fig. 1 provides two kinds of staggeredly modes that may be present, [o1,o2] be two tasks resident overlay region, wherein o1And o2Meet such as
Lower time-constrain:
Introduce marking variable PT, for analyze need the dispatching of the task whether meet more than time-constrain.PT is used to divide
The pulse for analysing the task and task of dispatching successfully for needing to dispatch at this time receives whether the phase meets the requirements with the transmitting phase, i.e., cannot
Overlapping.It is denoted as:
PT={ x1,x2,r1,r2,s} (4-11)
Wherein x1And r1Respectively transmitting pulse initial time for receiving pulse corresponding with its of task, x2And r2Respectively
For transmitting pulse finish time for receiving pulse corresponding with its of task, s is the number of the pulse.
As task TiWith TkTransmitting pulse or receive between pulse when having overlapping, i.e. TiIt is unsatisfactory for time-constrain, is not handed over
Mistake success.In order to more easily judge, TiWith TkWhether conflict in time, it can be by TiWith TkTransmitting pulse and corresponding
Pulse is received to be expressed asWithThen:
Wherein siAnd skRespectively represent task TiWith TkIn resident overlay region [o1,o2] in transmitting or receive pulse compile
Number.Since resident task is there are two types of staggeredly mode, then siAnd skValue range also there are two types of, discuss respectively to it.In formula
Under the conditions of (4-9) and formula (4-10), siAnd skValue range it is as follows:
If Fig. 1 knows, there are three types of overlap modes for the pulse of two resident tasks: being overlapped between (A) transmitting pulse；(B) arteries and veins is received
It is overlapped between punching；(C) transmitting pulse and reception pulse overlap.Assuming that:
So, it can be obtained by formula (4-12)~(4-16), the time constraint condition of three kinds of overlap modes are as follows:
If the transmitting pulse or reception pulse of current time task are unsatisfactory for (4-14)~(4-19), indicate that this is resident
Task TiIt is unsatisfactory for time constraint condition, then cannot be dispatched at this moment, continues to judge whether other task can expire at this moment
The time-constrain being enough.If current task meets time constraint condition, then continue to judge whether the task is also able to satisfy energy
Amount constraint.
(2) energy constraint condition
Energy constraint is divided into stable state and transient energy constraint again.Due to the real-time of scheduling, so main research wink herein
State energy constraint.Since transmitting pulse can consume energy, cause the temperature of system that can rise, when its temperature is more than that system can be held
It will result in the damage of system by the range of, so the trouble-free operation in order to guarantee system, needs to limit the wink of system
State energy.System is indicated in the transient energy of t moment are as follows:
In formula, p (x) is system power function；τ is parameter, reflects the performance of system self-radiating.The cooling time of system
It can be by system consumption energy by maximum value EmaxWith normal value EnomalTo indicate.If the energy of the t at current time is E (t), then
It is obtained according to (4-20) in t+t0Energy value consumed by moment are as follows:
If E (t)=Emax, E (t+t0)=Enormal, it can obtain:
Wherein t0The time of required cooling when being restored to normal value for energy, it can thus be concluded that cooling velocity are as follows:
Ei-1Be denoted as: task i is before successful dispatch, the energy state vector of system consumption, if task TiIt dispatches successfully,
Then system capacity state vector parameter updates according to the following formula (4-24):
Wherein,For radar transmission power, tpiFor the fire pulse width of task i, Δ t is discrete time intervals length,
t0To dispatch initial time,For the pulse number of the task i in k-th of time interval, M is total discrete time intervals number,It can be calculated by formula (4-25):
As the E obtained by formula (4-24)i(k) meet E (t)≤EmaxWhen, i.e. task TiMeet transient energy constraint.
In conclusion if the task T of schedulingiBoth meet time-constrain, also meet transient energy constraint, then the task schedule
Success.
Methods herein is the current time pointed by time indicator analysis.Assuming that in [t0,tend] there is N in the time
A task needs to dispatch, wherein t0For the initial time of scheduling interval, tendFor the finish time of scheduling interval.The pulse of optimization
The step of alternate algorithm, is described as follows:
Step 1: initiation parameter, including time indicator p, energy state vector E, time state vector φΔt(k) it and marks
Know variable ID, wherein p >=t0。
Step 2: ifIt then deletes and executes the time in task requests the latest less than p task, go to step 3；It is no
Then p=p+ Δ t, return step 2.
Step 3: the set of tasks A that current time can execute is selected from task requestspIf the set task number is
Np, the higher task of comprehensive priority is selected by the sequence to two times scheduling task priority, therefore can obtain comprehensive preferential
The task queue that grade arranges from high to low, is denoted asMission number i=1.
Step 4: from set ApIn select i-th of task, be denoted as TiIf flag=1,5 are gone to step, otherwise puts it into and holds
Row chained list, enables sti=p, and it is deleted from application chained list.ID is updated and according to formula according to successful task type is dispatched
(4-8) and formula (4-24) update φΔt(k) and Ei(k).If task TiFor search mission, then p=p+ldi；If scheduling tracking is appointed
Business, then p=p+ Δ t, goes to step 6.
Step 5: judging whether to meet time-constrain and energy constraint condition, if being unsatisfactory for its time-constrain or energy about
Beam condition then enables i=i+1 carry out the next task in this scheduling interval.If i > Np, illustrate the task in this scheduling interval
Analysis terminates, and pointer p is enabled to be directed toward next scheduling interval, i.e. p=p+ Δ t goes to step 6, otherwise return step 5.
Step 6: as p > tend, 7 are gone to step, otherwise return step 2.
Step 7: emulation terminates.
Simulation analysis:
Simulating scenes include that range searching, verifying, low priority tracking, the tracking of middle priority and high priority track five kinds
The task of type, all types of number of tasks generate at random, and task relevant parameter is as shown in the table:
| Task type | Priority | Pulse number | Pulse width | Pulse period | Time window | Transmission power |
| Verifying | 5 | 26 | 0.03 | 0.3 | 10 | 5 |
| High priority tracking | 4 | 21 | 0.02 | 0.2 | 10 | 5 |
| Middle priority tracking | 3 | 21 | 0.03 | 0.3 | 20 | 5 |
| Low priority tracking | 2 | 15 | 0.02 | 0.2 | 30 | 5 |
| Range searching | 1 | 18 | 0.02 | 0.2 | - | 5 |
A length of 600ms when emulation, the mean power of transmitter are 400w, and transient energy constrains threshold values Emax=6J.It will be herein
The optimization algorithm (hereinafter referred to as calculation A) and original pulse interlacing dispatching algorithm as a comparison for proposing pulse interlacing scheduling are (hereafter
Referred to as algorithm B) it compares.The average result of 100 emulation is given below.
For the Loss Rate of search mission it can be seen from Fig. 2 (a), algorithm B is 8 or so in number of tasks, begins to lose
Task, and algorithm A is the task of substantially few loss within 40 in number of tasks.With the increase of number of tasks, algorithm A's
Task Loss Rate is significantly lower than the task Loss Rate of algorithm B, and the task of algorithm A loses speed and is also far smaller than algorithm B.Together
Reason, for Fig. 2 (b) and Fig. 2 (c), i.e. tracing task also has similar result with the Loss Rate of general assignment.This is because due to
Time indicator is introduced, the free time of system is fully utilized.Algorithm A, which is that each time point selection is suitable, to be appointed
Business, thus takes full advantage of free time, and then improve search/tracing task success rate.
In Fig. 2 (d), it can be seen that the average time offset rate of algorithm A is basically stable at 0.45 or so, is because of algorithm
A, which only considered, is directed toward the suitable task of at the time of point selection for each time indicator, does not consider this factor of expected time, institute
It is more stable with average time offset rate.Compared with algorithm A, algorithm B considers average time offset rate, which makes to appoint
The actual execution time of business executes the time as close as expectation.Its average time offset rate increases with the increase of number of tasks
Greatly, this is because with number of tasks increase, the competition of time resource is more and more fierce.
In Fig. 2 (e), Fig. 2 (f) as can be seen that within number of tasks is less than 40, time/energy of algorithm A and algorithm B
Utilization rate is essentially identical.But with the increase of number of tasks, two kinds of resources utilization rate (time availability and the energy benefit of algorithm B
With rate) it is lower than algorithm A.This is because algorithm A utilizes time indicator, it is followed successively by each time point and selects suitable task, fill
Divide the free time for the system that is utilized, and then improves task schedule success rate, therefore energy resource has also obtained sufficient benefit
With.
Claims (1)
1. a kind of phased array radar resource regulating method based on the distribution of two sub-priorities, which comprises the following steps:
Step 1: initiation parameter, the parameter include time indicator p, energy state vector E, time state vector φΔt(k) and
Marking variable ID, wherein p >=t0；
Step 2: judgementIt whether is 0；
IfThe executing the time in task requests the latest less than p of the task is then deleted, goes to step 3；
IfIt is not 0；P=p+ Δ t is enabled, is rejudged；
Step 3: the set of tasks A that current time can execute is selected from task requestspIf the set task number is Np, lead to
It crosses and the higher task of comprehensive priority is selected to the sequence of two times scheduling task priority, therefore comprehensive priority can be obtained by height
To the task queue of low arrangement, it is denoted asMission number i=1；
Step 4: from set ApIn select i-th of task, be denoted as Ti；
If flag=1,5 are gone to step, execution chained list is otherwise put it into, enables sti=p, and it is deleted from application chained list；Root
ID is updated and according to formula (4-8) and formula (4-24) update φ according to successful task type is dispatchedΔt(k) and Ei(k)；If task TiFor
Search mission then enables p=p+ldi；If dispatching tracing task, p=p+ Δ t is enabled, goes to step 6；
The algorithm of above-mentioned formula (4-8) and formula (4-24) are as follows:
Step 5: judging whether to meet time-constrain and energy constraint condition, if being unsatisfactory for its time-constrain or energy constraint item
Part then enables i=i+1 carry out the next task in this scheduling interval；If i > Np, illustrate the task analysis in this scheduling interval
Terminate, pointer p is enabled to be directed toward next scheduling interval, is i.e. p=p+ Δ t goes to step 6, otherwise return step 5；
Step 6: as p > tend, 7 are gone to step, otherwise return step 2；
Step 7: emulation terminates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811415307.2A CN109583742A (en) | 2018-11-26 | 2018-11-26 | A kind of phased array radar resource regulating method based on the distribution of two sub-priorities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811415307.2A CN109583742A (en) | 2018-11-26 | 2018-11-26 | A kind of phased array radar resource regulating method based on the distribution of two sub-priorities |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109583742A true CN109583742A (en) | 2019-04-05 |
Family
ID=65924491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811415307.2A Pending CN109583742A (en) | 2018-11-26 | 2018-11-26 | A kind of phased array radar resource regulating method based on the distribution of two sub-priorities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583742A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717651A (en) * | 2019-09-10 | 2020-01-21 | 北方信息控制研究院集团有限公司 | Space situation perception phased array radar task planning method based on variable data rate |
| CN114237842A (en) * | 2021-12-02 | 2022-03-25 | 电子科技大学 | Phased array radar self-adaptive task scheduling method based on typical parameter limitation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831009A (en) * | 2012-08-24 | 2012-12-19 | 电子科技大学 | Phased array radar task scheduling method |
| US20140067483A1 (en) * | 2012-08-30 | 2014-03-06 | Electronics And Telecommunications Research Institute | Apparatus and method for constructing radar chart |
| CN106682820A (en) * | 2016-12-14 | 2017-05-17 | 中国人民解放军空军工程大学 | Optimized radar task scheduling method of digital array based on pulse interlacing |
-
2018
- 2018-11-26 CN CN201811415307.2A patent/CN109583742A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831009A (en) * | 2012-08-24 | 2012-12-19 | 电子科技大学 | Phased array radar task scheduling method |
| US20140067483A1 (en) * | 2012-08-30 | 2014-03-06 | Electronics And Telecommunications Research Institute | Apparatus and method for constructing radar chart |
| CN106682820A (en) * | 2016-12-14 | 2017-05-17 | 中国人民解放军空军工程大学 | Optimized radar task scheduling method of digital array based on pulse interlacing |
Non-Patent Citations (1)
| Title |
|---|
| 刘岩: ""相控阵雷达资源调度优化算法的研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717651A (en) * | 2019-09-10 | 2020-01-21 | 北方信息控制研究院集团有限公司 | Space situation perception phased array radar task planning method based on variable data rate |
| CN110717651B (en) * | 2019-09-10 | 2023-04-28 | 北方信息控制研究院集团有限公司 | Space situation awareness phased array radar task planning method based on variable data rate |
| CN114237842A (en) * | 2021-12-02 | 2022-03-25 | 电子科技大学 | Phased array radar self-adaptive task scheduling method based on typical parameter limitation |
| CN114237842B (en) * | 2021-12-02 | 2023-09-05 | 电子科技大学 | Phased array radar self-adaptive task scheduling method based on typical parameter definition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Online multi-workflow scheduling under uncertain task execution time in IaaS clouds | |
| CN109783218B (en) | Kubernetes container cluster-based time-associated container scheduling method | |
| CN102831009B (en) | Phased array radar task scheduling method | |
| CN101237469B (en) | Method for optimizing multi-QoS grid workflow based on ant group algorithm | |
| CN112416585B (en) | Deep learning-oriented GPU resource management and intelligent scheduling method | |
| CN109709535B (en) | Beam resident scheduling method for cooperative distributed system | |
| CN110287003A (en) | The management method and management system of resource | |
| CN104765640A (en) | Intelligent service scheduling method | |
| EP3221666B1 (en) | Automatic system for monitoring electric power consumption | |
| CN104915251A (en) | Task scheduling method and device | |
| CN107370799B (en) | A kind of online computation migration method of multi-user mixing high energy efficiency in mobile cloud environment | |
| CN109583742A (en) | A kind of phased array radar resource regulating method based on the distribution of two sub-priorities | |
| CN103257900B (en) | Real-time task collection method for obligating resource on the multiprocessor that minimizing CPU takies | |
| CN105487920A (en) | Ant colony algorithm based optimization method for real-time task scheduling of multi-core system | |
| CN104834564A (en) | Task scheduling method and device | |
| CN103473122A (en) | Workflow system resource scheduling method in cloud computing environment | |
| CN109857532A (en) | DAG method for scheduling task based on the search of Monte Carlo tree | |
| CN116069512B (en) | Serverless efficient resource allocation method and system based on reinforcement learning | |
| CN106648831B (en) | Cloud workflow schedule method based on glowworm swarm algorithm and dynamic priority | |
| CN112332404A (en) | Intelligent management system and method for heating service | |
| CN110113212B (en) | Relay satellite single-address antenna scheduling method suitable for breakpoint continuous transmission | |
| CN110928666B (en) | Method and system for optimizing task parallelism based on memory in Spark environment | |
| CN112860390A (en) | Job scheduling program, information processing apparatus, and job scheduling method | |
| CN103902385A (en) | Priori knowledge based phase array radar self-adaption task scheduling method | |
| Wu et al. | Utility accrual scheduling under arbitrary time/utility functions and multi-unit resource constraints |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190405 |
|
| WD01 | Invention patent application deemed withdrawn after publication |