CN106020988A - Off-line task scheduling method and device for intelligent video monitoring system - Google Patents
Off-line task scheduling method and device for intelligent video monitoring system Download PDFInfo
- Publication number
- CN106020988A CN106020988A CN201610391312.9A CN201610391312A CN106020988A CN 106020988 A CN106020988 A CN 106020988A CN 201610391312 A CN201610391312 A CN 201610391312A CN 106020988 A CN106020988 A CN 106020988A
- Authority
- CN
- China
- Prior art keywords
- task
- processor
- time
- monitoring system
- intelligent video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5044—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering hardware capabilities
-
- 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]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
- G06F9/5088—Techniques for rebalancing the load in a distributed system involving task migration
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention discloses an off-line task scheduling method and device for an intelligent video monitoring system. The off-line task scheduling method for the intelligent video monitoring system is applied to a server in the video monitoring system. The video monitoring system further comprises a plurality of processors used for processing off-line tasks of the intelligent video monitoring system and a processing capability model pre-established for the processors. The method comprises the steps that an off-line task request of the intelligent video monitoring system is received, and the task request comprises at least one task to be processed; the weighting time length of each task to be processed is calculated; according to the processing capability model, the time needed for processing all the tasks to be processed at present of each processor is calculated; according to the weighting time length and the time, the tasks to be processed in the task request are scheduled to the processors. By means of the off-line scheduling method and device, the loads of the processors can be balanced..
Description
Technical field
The present invention relates to intelligent video monitoring system off-line task technical field, particularly to a kind of intelligent video
Monitoring system off-line method for scheduling task and device.
Background technology
When in the face of substantial amounts of monitor video, traditional offline video processing system, although employ intelligence and regard
Frequency analysis (IVA) technology, due to the restriction of unit computing capability, generally cannot meet the time in customer requirement
Inside completing monitor video and process task, for this, we introduce distributed proccessing.In Distributed Calculation,
Task management, task scheduling and resource management are three big basic functions of system, and wherein task scheduling is impact
The importance that systematic function is good and bad.Task scheduling is the important component part of operating system, and in real time
Operating system, task scheduling directly affects its real-time performance.Task scheduling algorithm can be divided into event: drives and adjusts
Degree algorithm, according to the priority of event and the execution of the prioritization schemes task of task;Clock drives scheduling to calculate
Method, is generally used for periodic duty.
Traditional distributed task dispatching method has Min-Min, Max-Min etc..Min-Min dispatching algorithm
Thought is as far as possible each task to be distributed to use the earliest and perform the fastest processor.Min-Min algorithm
Based on minimum completion time, and it is considered that whole unappropriated task is due to often in mapping each time
Secondary is all that task is distributed to perform the fastest processor, so easily causes the serious uneven of resource load
Weighing apparatus, resource cannot be fully used.
Traditional distributed task dispatching method is knowledge deterministic algorithm mostly, it is desirable to system resource and use
Family task has the knowledge of an overall determination.Owing to the operation time of intelligent video process task in advance cannot
Know, and the change over time of the disposal ability of intelligent video analysis server (IVU) and change, can
Seeing, the method for scheduling task of traditional distributed, when applying to intelligent video monitoring system, easily causes process
Device cluster load imbalance, the utilization of resources are insufficient, it is impossible to meet present intelligent monitoring video processing duties
Demand.
Summary of the invention
The purpose of the embodiment of the present invention be to provide a kind of intelligent video monitoring system off-line method for scheduling task and
Device, so that processor load equilibrium.
For reaching above-mentioned purpose, the embodiment of the invention discloses a kind of intelligent video monitoring system off-line task and adjust
Degree method, the server being applied in intelligent video monitoring system, described intelligent video monitoring system also comprises
Multiple processors for processing intelligent video monitoring system off-line task, pre-build for described processor
Disposal ability model, method includes:
Receive intelligent video monitoring system off-line task requests, described task requests comprises at least one and waits to locate
Reason task;
Calculate the weight temporal length of each waiting task;
According to described disposal ability model, calculate each processor and process self currently pending all task institute
The time needed;
According to described weight temporal length and described time, the waiting task in described task requests is adjusted
Degree is to processor.
It is also preferred that the left described disposal ability model is:
Wherein, describedFor the weight temporal length of currently pending for a processor i task, described vlastFor
The latest computed speed of pre-recorded processor i, describedFor the variation tendency of processor i disposal ability, institute
Stating t is that processor i processes this required by task time.
It is also preferred that the left it is described according to described weight temporal length and described time, by described task requests
Waiting task is scheduled to processor, including:
For each processor, it is judged that process whether self currently pending all required by task time is not more than
Preset first threshold value;
If it is, by waiting task corresponding for maximum weight temporal length, be scheduled to required time minimum
Processor.
It is also preferred that the left it is described according to described weight temporal length and described time, by described task requests
Waiting task is scheduled to processor, also includes:
Self currently pending all required by task time is processed more than described default first threshold at each processor
In the case of value, calculate the difference of maximum required time and minimum required time;
Judge that whether described difference is more than presetting Second Threshold;
If it is, by task corresponding for weight temporal length immediate with described difference, be scheduled to minimum institute
The processor of the correspondence that takes time.
It is also preferred that the left described weight temporal is a length of:
Wherein, described JLFor the weight temporal length of each waiting task, described n is each described task
The number of the data block comprised, described LiFor the time span of data block described in i-th, described Li=qm* t,
I ∈ [1, n], described qmThe quality corresponding for i-th data block divides weights, and described t is the end of described data block
Only time and the difference of initial time.
For reaching above-mentioned purpose, the invention also discloses a kind of intelligent video monitoring system off-line task scheduling dress
Putting, the server being applied in intelligent video monitoring system, described intelligent video monitoring system also comprises multiple
For processing the processor of intelligent video monitoring system off-line task, pre-build the place for described processor
Reason capability model, device includes:
Receiver module, is used for receiving intelligent video monitoring system off-line task requests, wraps in described task requests
Containing at least one waiting task;
First computing module, for calculating the weight temporal length of each waiting task;
Second computing module, for according to described disposal ability model, calculates the process of each processor and self works as
The time of front pending all required by task;
Scheduler module, for according to described weight temporal length and described time, by described task requests
Waiting task be scheduled to processor.
It is also preferred that the left described disposal ability model is:
Wherein, describedFor the weight temporal length of currently pending for a processor i task, described vlastFor
The latest computed speed of pre-recorded processor i, describedFor the variation tendency of processor i disposal ability, institute
Stating t is that processor i processes this required by task time.
It is also preferred that the left described scheduler module, including:
First judging unit, for for each processor, it is judged that process self currently pending all task
Whether required time is not more than preset first threshold value;
First scheduling unit, in the case of described first judging unit judged result is for being, by maximum
Waiting task corresponding to weight temporal length, be scheduled to the processor that required time is minimum.
It is also preferred that the left described scheduler module, also include:
Computing unit, for being more than in each processor self currently pending all required by task time of process
In the case of described preset first threshold value, calculate the difference of maximum required time and minimum required time;
Second judging unit, is used for judging that whether described difference is more than presetting Second Threshold;
Second scheduling unit, is used in the case of described second judging unit judged result is for being, will be with institute
State the task that difference immediate weight temporal length is corresponding, be scheduled to the processor that minimum required time is corresponding.
It is also preferred that the left described weight temporal is a length of:
Wherein, described JLFor the weight temporal length of each waiting task, described n is each described task
The number of the data block comprised, described LiFor the time span of data block described in i-th, described Li=qm* t,
I ∈ [1, n], described qmThe quality corresponding for i-th data block divides weights, and described t is the end of described data block
Only time and the difference of initial time.
As seen from the above technical solutions, a kind of intelligent video monitoring system off-line that the embodiment of the present invention provides
Method for scheduling task and device, receive intelligent video monitoring system off-line task requests, in described task requests
Comprise at least one waiting task;Calculate the weight temporal length of each waiting task;According to described place
Reason capability model, calculates each processor and processes the time of self currently pending all required by task;According to
Described weight temporal length and described time, it is scheduled to the waiting task in described task requests process
Device.
Visible, pre-build the disposal ability model for described processor, carry out task according to described model
Scheduling, so that processor load balance, makes full use of processor resource, processes task efficiently, fill
The advantage of Distributed Calculation is waved in distribution.
Certainly, arbitrary product or the method for implementing the present invention must be not necessarily required to reach above-described institute simultaneously
There is advantage.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to enforcement
In example or description of the prior art, the required accompanying drawing used is briefly described, it should be apparent that, describe below
In accompanying drawing be only some embodiments of the present invention, for those of ordinary skill in the art, do not paying
On the premise of going out creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The stream of a kind of intelligent video monitoring system off-line method for scheduling task that Fig. 1 provides for the embodiment of the present invention
Journey schematic diagram;
The knot of a kind of intelligent video monitoring system off-line task scheduling apparatus that Fig. 2 provides for the embodiment of the present invention
Structure schematic diagram.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clearly
Chu, be fully described by, it is clear that described embodiment be only a part of embodiment of the present invention rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
The every other embodiment obtained under property work premise, broadly falls into the scope of protection of the invention.
The embodiment of the invention discloses a kind of intelligent video monitoring system off-line method for scheduling task and device, with
Lower it is described in detail respectively.
It should be noted that the embodiment of the present invention is preferably applied to the server in intelligent video monitoring system,
In actual applications, intelligent video monitoring system also comprises multiple for processing intelligent video monitoring system off-line
The processor of task, pre-builds the disposal ability model for processor.
See a kind of intelligent video monitoring system off-line task scheduling that Fig. 1, Fig. 1 provide for the embodiment of the present invention
The schematic flow sheet of method, comprises the steps:
S101, receives intelligent video monitoring system off-line task requests, comprises at least one in described task requests
Individual waiting task;
Wherein, waiting task is pending intelligent video monitoring system off-line task.
Wherein, server can be: intelligent video Processing Algorithm dispatch server, and processor can be: intelligence
Energy video analytics server (IVU), task requests can be: intelligent video monitoring system off-line task and use
The process request at family.
In a specific implementation, user submits an intelligent monitoring video to and processes request.According to
The process request at family, is divided into several data blocks such as by intelligent video, for avoiding the communication between IVU,
By multiple relevant data block one intelligent video monitoring system off-line task of composition, such as, divide video into
39 data blocks, from video beginning to ending, 3 the most adjacent data blocks one tasks of composition, totally 13
Task.Server receives task requests, comprises 13 pending intelligent video monitoring systems in task requests
Off-line task.
S102, calculates the weight temporal length of each waiting task;
Wherein, the weight temporal of each waiting task is a length of:
Wherein, JLFor the weight temporal length of each waiting task, n is that each waiting task comprises
The number of data block, LiFor the weight temporal length of i-th data block, Li=qm* t, i ∈ [1, n], qmFor i-th
The quality division initial weight that data block is corresponding, t is the termination time difference with initial time of data block.In reality
In the application of border, can ask according to the process of user, intelligent monitoring video be carried out quality division, and then obtains
Quality to each data block divides initial weight.
S103, according to described disposal ability model, calculates each processor process self currently pending all
The time of required by task;
Wherein, the disposal ability model for processor is:
Wherein,For the weight temporal length of currently pending for a processor i task, vlastFor remembering in advance
The latest computed speed of the processor i of record,For the variation tendency of processor i disposal ability, t is processor i process
This required by task time.
In actual applications, according to the disposal ability model pre-build, processor i can be calculated and process certainly
The time of each required by task in the currently pending all tasks of body, so obtain processor i process self work as
The time of front pending all required by task.
Wherein, the process pre-building the disposal ability model for processor can be:
After receiving the intelligent video monitoring system off-line task process request that user submits to first, calculate each
The weight temporal length of waiting task, according to size order, joins in task queue by each task,
In actual applications, task queue is not essential, specifically can set up disposal ability model with realization and be as the criterion;
τ task scheduling of η * front in task queue is processed by server to τ processor, has often processed an intelligence
Video monitoring system off-line task, processor is by actual treatment time feedbacking to server, and wherein, η is positive even
Integer thresholds, controls the quantity of scheduler task first, can arrange voluntarily according to the sum of waiting task, example
As: giving 3 processor A, B and C process by front 9 task schedulings, each processor comprises 3 tasks;
The actual treatment time needed for weight temporal length according to task and process, set up n unit linear function
Group, equation group is:
Its coefficient matrix is:
Wherein, TnThe actual treatment time of the n-th required by task, t is processed for processornnIt is in the n-th task
Beginning and ending time of nth data block poor.
The solution of n unit linear function group is:
qm=ξ1+ξ2+…+ξn-r
ξ1、ξ2、ξn-rIt is the basic course laboratory of n unit linear function group, r=r (D);
Calculate each video quality and divide qmAccurate weights, and be each qmOne set is set for protecting
Deposit the result of every time calculating, and will in set the meansigma methods of data as qmAccurate weights;
Calculate processing speed V of each processor, the processing speed of up-to-date for processor three times is put into set M
In, wherein, V=JL/ T, described M={Vt1,Vt2,Vt3, t1、t2、t3Represent and calculate described processing speed time institute
In the moment at place, T is the actual treatment time that processor processes a required by task;
According to set M, calculate the process acceleration a of each processor, as the change of processor disposal ability
Change trend;
Weight temporal length, the processing speed of processor and process acceleration according to task, sets up for often
The disposal ability model of one processor.
S104, according to described weight temporal length and described time, pending by described task requests
Task scheduling is to processor.
Concrete, according to described weight temporal length and described time, treating in described task requests is located
Reason task scheduling to processor, can be for each processor, it is judged that process self currently pending all
Whether business required time is not more than preset first threshold value;If if it is, server also having unscheduled to place
The waiting task of reason device, by waiting task corresponding for maximum weight temporal length, is scheduled to be taken
Between smallest processor.
Concrete, in actual applications, process self currently pending all required by task at each processor
Time is more than in the case of preset first threshold value, it is also possible to calculate maximum required time and minimum required time
Difference;Judge that whether this difference is more than presetting Second Threshold;If it is if it is, the most unscheduled in server
To the waiting task of processor, by task corresponding for weight temporal length immediate with this difference, scheduling
Give the processor that minimum required time is corresponding.
Exemplary, in a specific implementation, video monitoring system comprises 3 for processing video
Processor A, B, C of task, corresponding process all required by task time is respectively 10s, 15s, 18s,
Preset first threshold value is 13s, and default Second Threshold is 6s.Server also has the most unscheduled waiting task 1,
2,3 and 4, corresponding weight temporal length is respectively 12s, 7.5s, 9s and 10s.For processor A institute
Take time no more than preset first threshold value, then the task 1 that weight temporal length is maximum is scheduled to place by server
Reason device A process;For processor B required time more than preset first threshold value, calculate maximum required time 18s
Being 8s with the difference of minimum required time 10s, this difference, more than presetting Second Threshold, also has in server and does not adjusts
The waiting task 2,3 and 4 of degree, it is known that weight temporal length 7.5s of waiting task 2 is closest to difference
8s, then unscheduled waiting task 2 is scheduled to processor B process by server;For processor C institute
Taking time more than preset first threshold value, the difference calculating maximum 18s and minimum task time 10s task time is
8s, this difference, more than presetting Second Threshold, also has unscheduled waiting task 3 and 4 in server, corresponding
Weight temporal length be respectively 9s and 10s, it is known that the weight temporal length of waiting task 3 is closest to poor
Value, then unscheduled waiting task 3 is scheduled to processor C process by server.Continue executing with next round
Scheduling, until not having unscheduled waiting task in server.
Visible, pre-build the disposal ability model for processor, carry out task according to disposal ability model
Scheduling, so that processor load balance, makes full use of processor resource, processes task efficiently, fill
The advantage of Distributed Calculation is waved in distribution.
A kind of intelligent video monitoring system off-line task that seeing Fig. 2, Fig. 2 provides for the embodiment of the present invention is adjusted
The structural representation of degree device, this task scheduling apparatus is applied to the server in intelligent video monitoring system,
Described intelligent video monitoring system also comprises multiple process for processing intelligent video monitoring system off-line task
Device, pre-builds the disposal ability model for described processor, corresponding with the flow process shown in Fig. 1, should
Task scheduling apparatus can include receiver module the 201, first computing module the 202, second computing module 203,
Scheduler module 204.
Wherein, receiver module 201, it is used for receiving intelligent video monitoring system off-line task requests, described task
Request comprises at least one waiting task;
First computing module 202, for calculating the weight temporal length of each waiting task;
Second computing module 203, for according to described disposal ability model, calculates each processor and processes self
The time of currently pending all required by task;
Scheduler module 204, for according to described weight temporal length and described time, by described task requests
In waiting task be scheduled to processor.
Concrete, described disposal ability model is:
Wherein,For the weight temporal length of currently pending for a processor i task, vlastFor remembering in advance
The latest computed speed of the processor i of record,For the variation tendency of processor i disposal ability, t is processor i process
This required by task time.
Concrete, described scheduler module, may include that the first judging unit and the first scheduling unit are (in figure
Not shown);
First judging unit, for for each processor, it is judged that process self currently pending all task
Whether required time is not more than preset first threshold value;
First scheduling unit, in the case of described first judging unit judged result is for being, by maximum
Waiting task corresponding to weight temporal length, be scheduled to the processor that required time is minimum.
Concrete, described scheduler module, it is also possible to including: computing unit, the second judging unit and second are adjusted
Degree unit (not shown);
Computing unit, for being more than in each processor self currently pending all required by task time of process
In the case of described preset first threshold value, calculate the difference of maximum required time and minimum required time;
Second judging unit, is used for judging that whether described difference is more than presetting Second Threshold;
Second scheduling unit, is used in the case of described second judging unit judged result is for being, will be with institute
State the task that difference immediate weight temporal length is corresponding, be scheduled to the processor that minimum required time is corresponding.
Concrete, described weight temporal is a length of:
Wherein, described JLFor the number that described n is the data block that each described task comprises, described LiFor
The time span of data block described in i-th, described Li=qm* t, i ∈ [1, n], described qmFor i-th data block
Corresponding quality divides weights, and described t is the termination time difference with initial time of described data block.
Visible, pre-build the disposal ability model for described processor, carry out task according to described model
Scheduling, so that processor load balance, makes full use of processor resource, processes task efficiently, fill
The advantage of Distributed Calculation is waved in distribution.
It should be noted that in this article, the relational terms of such as first and second or the like be used merely to by
One entity or operation separate with another entity or operating space, and not necessarily require or imply these
Relation or the order of any this reality is there is between entity or operation.And, term " includes ", " comprising "
Or its any other variant is intended to comprising of nonexcludability, so that include the mistake of a series of key element
Journey, method, article or equipment not only include those key elements, but also other including being not expressly set out
Key element, or also include the key element intrinsic for this process, method, article or equipment.Do not having
In the case of more restrictions, statement " including ... " key element limited, it is not excluded that including described wanting
Process, method, article or the equipment of element there is also other identical element.
Each embodiment in this specification all uses relevant mode to describe, phase homophase between each embodiment
As part see mutually, what each embodiment stressed is the difference with other embodiments.
For device embodiment, owing to it is substantially similar to embodiment of the method, so the comparison described
Simply, relevant part sees the part of embodiment of the method and illustrates.
One of ordinary skill in the art will appreciate that all or part of step realizing in said method embodiment
The program that can be by completes to instruct relevant hardware, and described program can be stored in computer-readable
Take in storage medium, the storage medium obtained designated herein, such as: ROM/RAM, magnetic disc, CD etc..
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit protection scope of the present invention.
All any modification, equivalent substitution and improvement etc. made within the spirit and principles in the present invention, are all contained in
In protection scope of the present invention.
Claims (10)
1. an intelligent video monitoring system off-line method for scheduling task, is applied in intelligent video monitoring system
Server, it is characterised in that described intelligent video monitoring system also comprises multiple for processing intelligent video
The processor of monitoring system off-line task, pre-builds the disposal ability model for described processor;Described
Method includes:
Receive intelligent video monitoring system off-line task requests, described task requests comprises at least one and waits to locate
Reason task;
Calculate the weight temporal length of each waiting task;
According to described disposal ability model, calculate each processor and process self currently pending all task institute
The time needed;
According to described weight temporal length and described time, the waiting task in described task requests is adjusted
Degree is to processor.
Method the most according to claim 1, it is characterised in that described disposal ability model is:
Wherein,For the weight temporal length of currently pending for a processor i task, vlastFor remembering in advance
The latest computed speed of the processor i of record,For the variation tendency of processor i disposal ability, t is processor i process
This required by task time.
Method the most according to claim 1, it is characterised in that described according to described weight temporal length
And described time, the waiting task in described task requests is scheduled to processor, including:
For each processor, it is judged that process whether self currently pending all required by task time is not more than
Preset first threshold value;
If it is, by waiting task corresponding for maximum weight temporal length, be scheduled to required time minimum
Processor.
Method the most according to claim 3, it is characterised in that described according to described weight temporal length
And described time, the waiting task in described task requests is scheduled to processor, also includes:
Self currently pending all required by task time is processed more than described default first threshold at each processor
In the case of value, calculate the difference of maximum required time and minimum required time;
Judge that whether described difference is more than presetting Second Threshold;
If it is, by task corresponding for weight temporal length immediate with described difference, be scheduled to minimum institute
The processor of the correspondence that takes time.
Method the most according to claim 1, it is characterised in that described weight temporal is a length of:
Wherein, described JLFor the weight temporal length of each waiting task, described n is each described task
The number of the data block comprised, described LiFor the time span of data block described in i-th, described Li=qm* t,
I ∈ [1, n], described qmThe quality corresponding for i-th data block divides weights, and described t is the end of described data block
Only time and the difference of initial time.
6. an intelligent video monitoring system off-line task scheduling apparatus, is applied in intelligent video monitoring system
Server, it is characterised in that described intelligent video monitoring system also comprises multiple for processing intelligent video
The processor of monitoring system off-line task, pre-builds the disposal ability model for described processor;Described
Device includes:
Receiver module, is used for receiving intelligent video monitoring system off-line task requests, wraps in described task requests
Containing at least one waiting task;
First computing module, for calculating the weight temporal length of each waiting task;
Second computing module, for according to described disposal ability model, calculates the process of each processor and self works as
The time of front pending all required by task;
Scheduler module, for according to described weight temporal length and described time, by described task requests
Waiting task be scheduled to processor.
Device the most according to claim 6, it is characterised in that described disposal ability model is:
Wherein,For the weight temporal length of currently pending for a processor i task, vlastFor remembering in advance
The latest computed speed of the processor i of record,For the variation tendency of processor i disposal ability, t is processor i process
This required by task time.
Device the most according to claim 6, it is characterised in that described scheduler module, including:
First judging unit, for for each processor, it is judged that process self currently pending all task
Whether required time is not more than preset first threshold value;
First scheduling unit, in the case of described first judging unit judged result is for being, by maximum
Waiting task corresponding to weight temporal length, be scheduled to the processor that required time is minimum.
Device the most according to claim 8, it is characterised in that described scheduler module, also includes:
Computing unit, for being more than in each processor self currently pending all required by task time of process
In the case of described preset first threshold value, calculate the difference of maximum required time and minimum required time;
Second judging unit, is used for judging that whether described difference is more than presetting Second Threshold;
Second scheduling unit, is used in the case of described second judging unit judged result is for being, will be with institute
State the task that difference immediate weight temporal length is corresponding, be scheduled to the processor that minimum required time is corresponding.
Device the most according to claim 6, it is characterised in that described weight temporal is a length of:
Wherein, described JLFor the weight temporal length of each waiting task, described n is each described task
The number of the data block comprised, described LiFor the time span of data block described in i-th, described Li=qm* t,
I ∈ [1, n], described qmThe quality corresponding for i-th data block divides weights, and described t is the end of described data block
Only time and the difference of initial time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610391312.9A CN106020988B (en) | 2016-06-03 | 2016-06-03 | A kind of offline method for scheduling task of intelligent video monitoring system and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610391312.9A CN106020988B (en) | 2016-06-03 | 2016-06-03 | A kind of offline method for scheduling task of intelligent video monitoring system and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106020988A true CN106020988A (en) | 2016-10-12 |
CN106020988B CN106020988B (en) | 2019-03-15 |
Family
ID=57089481
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610391312.9A Active CN106020988B (en) | 2016-06-03 | 2016-06-03 | A kind of offline method for scheduling task of intelligent video monitoring system and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106020988B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110545242A (en) * | 2018-05-29 | 2019-12-06 | 杭州海康威视数字技术股份有限公司 | target analysis method and intelligent analysis equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102831012A (en) * | 2011-06-16 | 2012-12-19 | 日立(中国)研究开发有限公司 | Task scheduling device and task scheduling method in multimode distributive system |
CN102902587A (en) * | 2011-07-28 | 2013-01-30 | 中国移动通信集团四川有限公司 | Distribution type task scheduling method, distribution type task scheduling system and distribution type task scheduling device |
CN103226467A (en) * | 2013-05-23 | 2013-07-31 | 中国人民解放军国防科学技术大学 | Data parallel processing method and system as well as load balancing scheduler |
-
2016
- 2016-06-03 CN CN201610391312.9A patent/CN106020988B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102831012A (en) * | 2011-06-16 | 2012-12-19 | 日立(中国)研究开发有限公司 | Task scheduling device and task scheduling method in multimode distributive system |
CN102902587A (en) * | 2011-07-28 | 2013-01-30 | 中国移动通信集团四川有限公司 | Distribution type task scheduling method, distribution type task scheduling system and distribution type task scheduling device |
CN103226467A (en) * | 2013-05-23 | 2013-07-31 | 中国人民解放军国防科学技术大学 | Data parallel processing method and system as well as load balancing scheduler |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110545242A (en) * | 2018-05-29 | 2019-12-06 | 杭州海康威视数字技术股份有限公司 | target analysis method and intelligent analysis equipment |
Also Published As
Publication number | Publication date |
---|---|
CN106020988B (en) | 2019-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sprunt et al. | Aperiodic task scheduling for hard-real-time systems | |
CN106981221A (en) | The airport break indices method and system decomposed based on time space dimension | |
CN103324525B (en) | Method for scheduling task under a kind of cloud computing environment | |
US20130007753A1 (en) | Elastic scaling for cloud-hosted batch applications | |
CN104657220A (en) | Model and method for scheduling for mixed cloud based on deadline and cost constraints | |
CN104657221A (en) | Multi-queue peak-alternation scheduling model and multi-queue peak-alteration scheduling method based on task classification in cloud computing | |
Nguyen et al. | A hybrid scheduling algorithm for data intensive workloads in a mapreduce environment | |
CN109783225B (en) | Tenant priority management method and system of multi-tenant big data platform | |
CN102243598A (en) | Task scheduling method and system in distributed data warehouse | |
CN104023042B (en) | Cloud platform resource scheduling method | |
CN104580306A (en) | Multi-terminal backup service system and task scheduling method thereof | |
CN109861850A (en) | A method of the stateless cloud workflow load balance scheduling based on SLA | |
CN104035819B (en) | Scientific workflow scheduling method and device | |
CN113918314A (en) | Task processing method, edge computing device, computer device, and medium | |
Raj et al. | Effective cost mechanism for cloudlet retransmission and prioritized VM scheduling mechanism over broker virtual machine communication framework | |
CN110099083A (en) | A kind of load equilibration scheduling method and device for server cluster | |
Sharma et al. | An improved task allocation strategy in cloud using modified k-means clustering technique | |
CN103699448A (en) | Scheduling method based on time limit and budget in cloud computing environment | |
CN106020988A (en) | Off-line task scheduling method and device for intelligent video monitoring system | |
CN103842955B (en) | A kind of job flow control method, device and system | |
CN116302404B (en) | Resource decoupling data center-oriented server non-perception calculation scheduling method | |
Naik et al. | Scheduling tasks on most suitable fault tolerant resource for execution in computational grid | |
CN107329817A (en) | A kind of stand-by system mixing divides reliability and perceives energy consumption optimization method | |
Kim et al. | Virtual machines placement for network isolation in clouds | |
CN103678000A (en) | Computational grid balance task scheduling method based on reliability and cooperative game |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |