CN101615135A - The method and apparatus that a kind of smoothed data is handled - Google Patents

The method and apparatus that a kind of smoothed data is handled Download PDF

Info

Publication number
CN101615135A
CN101615135A CN 200910089782 CN200910089782A CN101615135A CN 101615135 A CN101615135 A CN 101615135A CN 200910089782 CN200910089782 CN 200910089782 CN 200910089782 A CN200910089782 A CN 200910089782A CN 101615135 A CN101615135 A CN 101615135A
Authority
CN
China
Prior art keywords
task
time
data processing
execution time
fitting function
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
Application number
CN 200910089782
Other languages
Chinese (zh)
Other versions
CN101615135B (en
Inventor
龚力
李蕊
杨建军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZTE Corp
Original Assignee
ZTE Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ZTE Corp filed Critical ZTE Corp
Priority to CN200910089782.XA priority Critical patent/CN101615135B/en
Publication of CN101615135A publication Critical patent/CN101615135A/en
Priority to PCT/CN2010/073664 priority patent/WO2011009345A1/en
Application granted granted Critical
Publication of CN101615135B publication Critical patent/CN101615135B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements

Abstract

The invention discloses the method that a kind of smoothed data is handled, comprising: according to the expection execution time of task, and the data processing amount that sets the tasks by fitting function; Execution according to determined data processing amount control task.The device that the present invention also provides a kind of smoothed data to handle.The present invention passes through the prediction to the data processing amount of task, realizes the control to the task processing time, has reduced the undulatory property that task is carried out, and helps improving the stability and the predictability of hicap data processing.

Description

The method and apparatus that a kind of smoothed data is handled
Technical field
The present invention relates to the data processing technique of the communications field, relate in particular to the method and apparatus that a kind of smoothed data is handled.
Background technology
In intelligent net system, often need carry out the processing of user data, as deletion of logging off users information or the like at the backstage of system configuration task.In jumbo system, because the user data total amount is very big, these task consumed time are very many often, and the load of system also can be very big.In the intelligent net system of commercialization; because user's use habit; usually can produce a large amount of disposable data on the special dates such as the end of month or red-letter days; cause the data volume big rise and fall of system's odd-numbered day processing; the processing time fluctuation is violent; system stability and predictability that this and commercial system require produce contradiction, need take measures level and smooth this fluctuation.
Summary of the invention
In view of this, fundamental purpose of the present invention is to provide a kind of method and apparatus of smoothed data processing, with the fluctuation in data processing amount in the level and smooth intelligent net system and processing time.
For achieving the above object, technical scheme of the present invention is achieved in that
The invention provides the method that a kind of smoothed data is handled, this method comprises:
According to the expection execution time of task, and the data processing amount that sets the tasks by fitting function;
Control described task executions according to determined data processing amount.
Wherein, described fitting function is in order to the funtcional relationship of data of description treatment capacity and data processing time, and is corresponding, with the described fitting function of expection execution time substitution of described task, promptly obtains and corresponding data processing amount of described expection execution time.
This method further comprises: preestablish the pressure concluding time of task, and judge in described task implementation whether task execution time exceeds the described pressure concluding time; Judging that described task execution time exceeds pressure during the concluding time, forces to end task.
This method further comprises: carries out when finishing in described task, and the physical end time of logger task, and described fitting function is revised according to the physical end time of record.
Wherein, the expection execution time of described task is determined according to the described task executions time of historical record, is perhaps determined by the expection concluding time of setting of task and the difference of current time.
The device that the present invention also provides a kind of smoothed data to handle, this device comprises:
The data processing amount determination module is used for the expection execution time according to task, and the data processing amount that sets the tasks by fitting function;
Task is carried out control module, is used for controlling described task executions according to determined data processing amount.
Described fitting function is in order to the funtcional relationship of data of description treatment capacity and data processing time, accordingly, described data processing amount determination module is further used for, and with the described fitting function of expection execution time substitution of described task, obtains and corresponding data processing amount of described expection execution time.
This device further comprises: judge module is used for judging in described task implementation whether task execution time exceeds the predetermined pressure concluding time, and when judgement exceeds, notifies described task to carry out control module and force to end task.
This device further comprises: the function correcting module, be used for when described task is carried out end, the physical end time of logger task, described fitting function is revised according to the physical end time of record, and revised fitting function is offered the data processing amount determination module.
Wherein, the expection execution time of described task is by the execution time of historical record, or determined by the expection concluding time of setting of task and the difference of current time.
The method and apparatus that a kind of smoothed data provided by the present invention is handled, utilize the time that the data treatment capacity is predicted, according to expecting that the processing time calculates the suitable data treatment capacity, can play the purpose of smoothing processing data, and realization expects the processing time actual treatment of data to the control in task processing time around; Fitting function is proposed, and according to the actual treatment time to carrying out online correction, realized the self-adaptation of system, reduced the undulatory property that task is carried out, help improving the stability and the predictability of hicap data processing.
Description of drawings
The method flow diagram that Fig. 1 handles for a kind of smoothed data of the present invention;
Fig. 2 is the composition structural representation of the device of a kind of smoothed data processing of the present invention.
Embodiment
The technical solution of the present invention is further elaborated below in conjunction with the drawings and specific embodiments.
For realizing level and smooth data processing, core concept of the present invention is: according to the expection execution time of task, and the data processing amount that sets the tasks by fitting function, again according to the execution of determined data processing amount control task, thereby realize control to the task handling time.Wherein, fitting function is in order to the funtcional relationship of data of description treatment capacity and data processing time, and is corresponding, with the expection execution time substitution fitting function of task, can obtain and expects corresponding data processing amount of execution time.Preferable, carry out when finishing in task, the physical end time that can logger task, and fitting function is revised according to the physical end time of record, the fitting function of revising is applied to follow-up task handles; By such cycling, can realize dynamic self-adapting adjustment, to reach the purpose of the undulatory property that the reduction task carries out to fitting function.
In actual applications, the expection execution time of task can be the absolute time that the user sets, and is promptly determined the expection execution time of the task that obtains by the difference of expection concluding time of task and current time; Certainly, also can obtain the expection execution time of task, for example: the expection execution time of determining this subtask according to the task executions time of historical record according to certain specific algorithm.
Based on above-mentioned thought, the method that a kind of smoothed data provided by the present invention is handled as shown in Figure 1, mainly may further comprise the steps:
Step 101, the expection concluding time of setting task.
The expection concluding time of the task setting correspondence that the user carries out as required.
Step 102 is obtained the expection concluding time of task and the difference of current time, is designated as Δ t.
The expection concluding time of setting subtracted each other with the current time obtain Δ t, Δ t is the expection execution time of task, in order to span expeced time of expression task execution.
Step 103, the expection execution time Δ t substitution fitting function with obtaining draws data processing amount.
This fitting function is designated as F (), and F () will can obtain the corresponding data processing amount with Δ t in order to the funtcional relationship of data of description treatment capacity and data processing time among the Δ t substitution F ().Wherein, F () can provide an empirical value in the concrete process of implementing, and revises in follow-up operation; And F () is not limited only to function, also can be realized by computation processing methods such as processes.
The data processing amount that the present invention calculates fitting function F () is as the real data treatment capacity of task, and with the actual execution time of this control task, thereby improves the stability and the predictability of data processing.
Step 104, according to the execution of the data processing amount control task that draws, and the logger task execution time.
Execute the task according to the data processing amount that draws, and when the real data treatment capacity of task reached above-mentioned data processing amount, the control task executable operations finished.
Step 105 compares the task execution time of record and default pressure concluding time, judges whether task execution time exceeds the pressure concluding time, if exceed, then execution in step 106; Otherwise, execution in step 107.
Step 106 is judged that task execution time exceeds the pressure concluding time, and is forced to end task, and forwards step 107 to.
The present invention is by set forcing the concluding time, and the pressure that exceeds setting at task execution time was forced to end task during the concluding time, thereby realizes definitely controlled to task execution time.
Step 107, during task termination, the physical end time of logger task, and revise fitting function according to physical end time of task.
Time when physical end time of task and task are begun to carry out subtracts each other, and obtains the actual execution time of task, and according to the actual execution time of task and the funtcional relationship of data processing amount, fitting function is revised.By using actual execution time dynamically to revise fitting function, can make fitting function in time follow the tracks of actual situation, thus the funtcional relationship of more effective fitting data processing time and data processing amount.The dynamic self-adapting correction of fitting function can be adopted but be not limited only to the mode of linear fit.
When follow-up task is carried out, repeat the operation of above-mentioned steps 101~107, just will use revised fitting function.This shows, by such cycling, can realize dynamic self-adapting adjustment, thereby draw the fitting function that tallies with the actual situation more, better to reach the purpose of the undulatory property that the reduction task carries out fitting function.
Be the method that realizes that above-mentioned smoothed data is handled, the device that the present invention also provides a kind of smoothed data to handle, as shown in Figure 2, this device comprises: data processing amount determination module 10 and task are carried out control module 20.Wherein, data processing amount determination module 10 is used for the expection execution time according to task, and the data processing amount that sets the tasks by fitting function; This fitting function is in order to the funtcional relationship of data of description treatment capacity and data processing time, and is corresponding, and data processing amount determination module 10 is the expection execution time substitution fitting function of task, promptly obtains and expects corresponding data processing amount of execution time.Task is carried out control module 20, connects data processing amount determination module 10, is used for the execution according to data processing amount determination module 10 determined data processing amount control tasks.
Preferable, this device further comprises judge module 30 and function correcting module 40 on the basis of above-mentioned module.Judge module 30, the connection task is carried out control module 20, is used for judging in the task implementation whether task execution time exceeds the predetermined pressure concluding time, and when judgement exceeds, the notice task is carried out control module 20 and is forced to end task, to realize definitely controlled to task execution time.Function correcting module 40, connect data processing amount determination module 10 and task and carry out control module 20, be used for when task is carried out end, the physical end time of logger task, the physical end time according to record is revised fitting function, and revised fitting function offered data processing amount determination module 10, thereby realize dynamic self-adapting adjustment to fitting function.The dynamic self-adapting correction of fitting function can be adopted but be not limited only to the mode of linear fit.
In sum, method and apparatus of the present invention utilizes the time that the data treatment capacity is predicted, according to expecting that the processing time calculates the suitable data treatment capacity, can play the purpose of smoothing processing data, and realization expects the processing time actual treatment of data to the control in task processing time around; Fitting function is proposed, and according to the actual treatment time to carrying out online correction, realized the self-adaptation of system, reduced the undulatory property that task is carried out, help improving the stability and the predictability of hicap data processing.
The above is preferred embodiment of the present invention only, is not to be used to limit protection scope of the present invention.

Claims (10)

1, a kind of method of smoothed data processing is characterized in that this method comprises:
According to the expection execution time of task, and the data processing amount that sets the tasks by fitting function;
Control described task executions according to determined data processing amount.
2, the method for handling according to the described smoothed data of claim 1, it is characterized in that, described fitting function is in order to the funtcional relationship of data of description treatment capacity and data processing time, accordingly, with the described fitting function of expection execution time substitution of described task, promptly obtain and corresponding data processing amount of described expection execution time.
3, the method for handling according to the described smoothed data of claim 1 is characterized in that this method further comprises: preestablish the pressure concluding time of task, and judge in described task implementation whether task execution time exceeds the described pressure concluding time; Judging that described task execution time exceeds pressure during the concluding time, forces to end task.
4, the method for handling according to the described smoothed data of claim 1, it is characterized in that, this method further comprises: carries out when finishing in described task, and the physical end time of logger task, and described fitting function is revised according to the physical end time of record.
5, the method for handling according to each described smoothed data in the claim 1 to 4, it is characterized in that, the expection execution time of described task is determined according to the described task executions time of historical record, is perhaps determined by the expection concluding time of setting of task and the difference of current time.
6, a kind of device of smoothed data processing is characterized in that this device comprises:
The data processing amount determination module is used for the expection execution time according to task, and the data processing amount that sets the tasks by fitting function;
Task is carried out control module, is used for controlling described task executions according to determined data processing amount.
7, the device of handling according to the described smoothed data of claim 6, it is characterized in that, described fitting function is in order to the funtcional relationship of data of description treatment capacity and data processing time, accordingly, described data processing amount determination module is further used for, with the described fitting function of expection execution time substitution of described task, obtain and corresponding data processing amount of described expection execution time.
8, the device of handling according to the described smoothed data of claim 6, it is characterized in that, this device further comprises: judge module, be used for judging in described task implementation whether task execution time exceeds the predetermined pressure concluding time, and when judgement exceeds, notify described task to carry out control module and force to end task.
9, the device of handling according to the described smoothed data of claim 6, it is characterized in that, this device further comprises: the function correcting module, be used for when described task is carried out end, the physical end time of logger task, the physical end time according to record is revised described fitting function, and revised fitting function is offered the data processing amount determination module.
10, the device of handling according to each described smoothed data in the claim 6 to 9 is characterized in that, the expection execution time of described task is by the execution time of historical record, or is determined by the expection concluding time of setting of task and the difference of current time.
CN200910089782.XA 2009-07-23 2009-07-23 A kind of method and apparatus of smoothed data process Active CN101615135B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN200910089782.XA CN101615135B (en) 2009-07-23 2009-07-23 A kind of method and apparatus of smoothed data process
PCT/CN2010/073664 WO2011009345A1 (en) 2009-07-23 2010-06-08 Method and device for smoothing data processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN200910089782.XA CN101615135B (en) 2009-07-23 2009-07-23 A kind of method and apparatus of smoothed data process

Publications (2)

Publication Number Publication Date
CN101615135A true CN101615135A (en) 2009-12-30
CN101615135B CN101615135B (en) 2015-08-12

Family

ID=41494793

Family Applications (1)

Application Number Title Priority Date Filing Date
CN200910089782.XA Active CN101615135B (en) 2009-07-23 2009-07-23 A kind of method and apparatus of smoothed data process

Country Status (2)

Country Link
CN (1) CN101615135B (en)
WO (1) WO2011009345A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011009345A1 (en) * 2009-07-23 2011-01-27 中兴通讯股份有限公司 Method and device for smoothing data processing
CN113296874A (en) * 2020-05-29 2021-08-24 阿里巴巴集团控股有限公司 Task scheduling method, computing device and storage medium

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100257613B1 (en) * 1996-10-15 2000-06-01 모리시타 요이찌 Video and audio coding method, coding apparatus, and coding program recording medium
US6928398B1 (en) * 2000-11-09 2005-08-09 Spss, Inc. System and method for building a time series model
JP4071668B2 (en) * 2003-04-16 2008-04-02 富士通株式会社 Apparatus and method for adjusting system resources
CN101459605B (en) * 2008-12-31 2012-03-21 成都市华为赛门铁克科技有限公司 Method and device for flow control
CN101615135B (en) * 2009-07-23 2015-08-12 中兴通讯股份有限公司 A kind of method and apparatus of smoothed data process

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011009345A1 (en) * 2009-07-23 2011-01-27 中兴通讯股份有限公司 Method and device for smoothing data processing
CN113296874A (en) * 2020-05-29 2021-08-24 阿里巴巴集团控股有限公司 Task scheduling method, computing device and storage medium

Also Published As

Publication number Publication date
WO2011009345A1 (en) 2011-01-27
CN101615135B (en) 2015-08-12

Similar Documents

Publication Publication Date Title
Quevedo et al. Stochastic stability of event-triggered anytime control
Visioli A new design for a PID plus feedforward controller
CN104879888A (en) Device and method for automatically setting parameters of household appliances
US10736032B2 (en) Method for cloudlet-based optimization of energy consumption
CN102110015B (en) Method and device for determining task progress and task processing time
CN105338188A (en) Schedule prompting method and mobile terminal
GB0329221D0 (en) Session control in a communication system
CN104239130B (en) Control method and terminal for responding to operation instruction by human-computer interaction interface
CN110631221A (en) Control method and device of air conditioner, terminal and storage medium
CN101615135A (en) The method and apparatus that a kind of smoothed data is handled
Khuzani et al. On optimal online power policies for energy harvesting with finite-state Markov channels
KR101387769B1 (en) Scheduling method, system, and computer-readable recording medium for reducing power consumption of smart device
CN110925936A (en) Air conditioner control method and device, computer equipment and storage medium
CN107529209A (en) Control the method and its device of WIFI hot spot power saving
CN108667463A (en) Monitoring data compression method
CN107133741A (en) Pending tasks processing method, device, readable storage medium storing program for executing and electronic equipment
CN105827543A (en) Traffic control method and electronic device
CN115096033A (en) Refrigeration strategy generation method, system, terminal and medium based on body temperature change
CN105259752B (en) Load distribution method, device and system for equipment group
CN109340094A (en) A kind of air compressor energy-saving control method based on load
CN109059219B (en) Control method of WIFI module of air conditioner, air conditioner and storage medium
CN105916203A (en) Method and system for improving scheduling capability of control plane in LTE system
CN108027593A (en) Method and apparatus for running technology system
CN110149685B (en) Grant free transmission power control method and equipment under multi-beam configuration
JP2004509420A5 (en)

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant