CN106549772A - Resource prediction method, system and capacity management device - Google Patents
Resource prediction method, system and capacity management device Download PDFInfo
- Publication number
- CN106549772A CN106549772A CN201510590666.1A CN201510590666A CN106549772A CN 106549772 A CN106549772 A CN 106549772A CN 201510590666 A CN201510590666 A CN 201510590666A CN 106549772 A CN106549772 A CN 106549772A
- Authority
- CN
- China
- Prior art keywords
- outcome
- service index
- association factor
- predicting
- initial service
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/82—Miscellaneous aspects
- H04L47/822—Collecting or measuring resource availability data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/83—Admission control; Resource allocation based on usage prediction
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of resource prediction method, system and capacity management device, and the method includes：According to traffic forecast algorithm and the historical data of initial service index, the initial service index is predicted, obtains predicting the outcome for the initial service index；The association factor of the initial service index is obtained, and obtains the historical data of the association factor；According to the historical data and traffic forecast algorithm of the association factor, the association factor is predicted, predicting the outcome for the association factor is obtained；According to predicting the outcome for the initial service index and predicting the outcome for the association factor, predicting the outcome for final service index, and predicting the outcome according to the final service index, the resource consumption of predictive server are obtained.Resource prediction method, system and capacity management device that the present invention is provided, it is possible to increase the accuracy of resources.
Description
Technical field
The present invention relates to field of cloud calculation, more particularly to a kind of resource prediction method, system and volume weight tube
Reason device.
Background technology
Capacity management is used for the capacity for assessing existing network office point, that is, gather and analyze in current business gauge
The capacity of CPU, internal memory, storage, network and other resources under mould, and it is based on current business scale
And the sustainable degree in the Trend Prediction system future of portfolio growth.Capacity carry out in advance so as to be supported
Scheduling or dilatation, safeguards system even running.Then need long-term resources and estimation side in one kind
Method.
At present, the resources and estimation to server or service node, are all by predictive server
Resource that the service called by upper business itself is consumed is being predicted, but service impacting money
It is complicated that source consumes, and may be affected by other service calls, therefore current server is pre-
The usual error of result of survey can be more not accurate enough than larger.
The content of the invention
For the problems referred to above, it is an object of the invention to provide considering the incidence relation between service
A kind of resource prediction method, system and capacity management device.
In a first aspect, the invention provides a kind of method of resources, including：
According to traffic forecast algorithm and the historical data of initial service index, to the initial service index
It is predicted, obtains predicting the outcome for the initial service index；
The association factor of the initial service index is obtained, and obtains the history number of the association factor
According to；
According to the historical data and traffic forecast algorithm of the association factor, the association factor is carried out
Prediction, obtains predicting the outcome for the association factor；
According to predicting the outcome for the initial service index and predicting the outcome for the association factor, obtain
Final service index predicts the outcome, and predicting the outcome according to the final service index, prediction clothes
The resource consumption of business device.
With reference in a first aspect, in first aspect in the first possible implementation, described in the acquisition
The association factor of initial service index, specifically includes：The initial service index is obtained from database
Association factor, the association factor determined in deployment services by cloud controller.
With reference in a first aspect, in second possible implementation of first aspect, obtaining described initial
The association factor of operational indicator, specifically includes：The pass of the initial service index is obtained from database
The connection factor, wherein, the association factor is by calling chain apparatus by calling path between Analysis Service
Obtain, it is described to call path to be recorded in log.
With reference in a first aspect, in first aspect in the third possible implementation, when transporting on server
During the multiple business of row, the predicting the outcome and the association factor according to the initial service index
Predict the outcome, obtain predicting the outcome for final service index, and according to the pre- of the final service index
Result is surveyed, the resource consumption of predictive server is specifically included：
According to predicting the outcome for the initial service index and predicting the outcome for the association factor, difference
The final service index for obtaining each business predicts the outcome；
According to predicting the outcome and the corresponding list of each business for the final service index of each business
Position resource consumption value, the resource consumption of predictive server.
Second aspect, the present invention also provide a kind of capacity management device, including：
First prediction module, for the historical data according to traffic forecast algorithm and initial service index,
The initial service index is predicted, predicting the outcome for the initial service index is obtained；
Acquisition module, for obtaining the association factor of the initial service index, and obtains the association
The historical data of the factor；
Second prediction module, for the historical data according to the association factor and traffic forecast algorithm,
The association factor is predicted, and obtains predicting the outcome for the association factor；
3rd prediction module, for according to the initial service index predict the outcome with the association because
Predicting the outcome for son, obtains predicting the outcome for final service index, and according to the final service index
Predict the outcome, the resource consumption of predictive server.
With reference to second aspect, in second aspect in the first possible implementation, acquisition module, tool
, for the association factor of the initial service index is obtained from database, the association factor is by cloud for body
What controller was determined in deployment services.
With reference to second aspect, in second possible implementation of second aspect, acquisition module, tool
Body for the association factor of the initial service index is obtained from database, wherein, the association because
Son is by chain apparatus are called by calling what path obtained between Analysis Service, described to call path to be remembered
Record is in log.
With reference to second aspect, in second aspect in the third possible implementation, the 3rd prediction
Module, specifically for when multiple business are run on server, according to the pre- of the initial service index
Predicting the outcome for result and the association factor is surveyed, the final service index of each business is obtained respectively
Predict the outcome；It is corresponding with each business according to predicting the outcome for the final service index of each business
Unit resource consumption figures, the resource consumption of predictive server.
The third aspect, present invention also offers a kind of resources system, including：Capacity management device
And database, wherein,
The capacity management device, for the history number according to traffic forecast algorithm and initial service index
According to being predicted to the initial service index, obtain the initial service index and predict the outcome；
The association factor of the initial service index is obtained, and obtains the historical data of the association factor；Root
According to the historical data and traffic forecast algorithm of the association factor, the association factor is predicted,
Obtain predicting the outcome for the association factor；According to the initial service index predict the outcome with it is described
Predicting the outcome for association factor, obtains predicting the outcome for final service index, and according to the final industry
Business index predicts the outcome, the resource consumption of predictive server；The database, it is described for storing
Association factor corresponding to the historical data of initial service index, the initial service index and described
The historical data of association factor.
With reference to the third aspect, in the third aspect in the first possible implementation, also include：Call
Chain apparatus, for log is got from the database, analyze the tune in the log
With path, the association factor of initial service index is obtained.
The embodiment of the present invention refers in the initial service that not only only accounts for of the resources for carrying out server
Mark, in addition it is also necessary to consider to affect the association factor of initial service index, be resources so to server
Will more accurately.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be right
Needed for embodiment or description of the prior art, accompanying drawing to be used is briefly described, it is clear that
Ground, drawings in the following description are some embodiments of the present invention, for those of ordinary skill in the art
For, without having to pay creative labor, can be with other according to these accompanying drawings acquisitions
Accompanying drawing.
Fig. 1 is the system framework schematic diagram of resources provided in an embodiment of the present invention；
Fig. 2 is the method flow diagram of resources provided in an embodiment of the present invention；
Fig. 3 is the relation schematic diagram called between service provided in an embodiment of the present invention；
Fig. 4 is the structural representation of capacity management device provided in an embodiment of the present invention；
Fig. 5 is the structural representation of capacity management device provided in an embodiment of the present invention；
Fig. 6 is the structural representation of resources system provided in an embodiment of the present invention.
Specific embodiment
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 entered
Row is clearly and completely described, it is clear that described embodiment is only a part of embodiment of the invention,
Rather than the embodiment of whole.Based on the embodiment in the present invention, those of ordinary skill in the art are not having
There is the every other embodiment obtained under the premise of making creative work, belong to present invention protection
Scope.
A kind of resource prediction method, system and capacity management device are embodiments provided, is used for
The accuracy of the resources of the server in raising cloud computing, is described in detail individually below.
For the ease of understanding the embodiment of the present invention, first to the resources of the embodiment of the present invention it is below
System framework is described.
A network environment schematic diagrames of the Fig. 1 for the embodiment of the present invention, in this system architecture, bag
Include following device, cloud controller 102, Service Source pond 104, service bus 106, capacity management dress
108 are put, calls chain apparatus 110, external system 118 and each database, each database to include
Cloud controller database 112, capacity management database 114 and call chain database 116.Wherein,
By 102 application deployment of cloud controller, an application is made up of one group of service, and during deployment, user is optional
Select these services and which service be relevant, the such as service of ordering needs to associate with database service,
Dispose using after, cloud controller can recorded the incidence relation of each service the cloud controller number of oneself
According in storehouse 112, incidence relation between the service of change is synchronized to capacity by cloud controller server 112
Management database 114.Sky can be searched during 102 application deployment of cloud controller from Service Source pond 104
Not busy service carrys out application deployment, for example：There are resource A, resource B and resource in Service Source pond 104
C, it is of course possible to more than these resources.Sometimes one business may require that calling between several services,
When calling between each service, can search on service bus 106 that destination service is current to be deployed to
Where, such as order service will search billing of services, and service bus returns available billing of services node,
The service of order just can be communicated with billing of services.
Chain apparatus 110 and capacity management device 108 is called to belong to operational system, each service exists
Can record when calling and call daily record, call chain apparatus 108 to collect each service node and call daily record,
Then the call relation of each service is analyzed, and by each service call relation record for analyzing to tune
With in chain database 116.Communicated by service bus 106 between each service node.
Call relation between service, can carry out being deployed in deciding in cloud controller.Because cloud
New service is disposed under scene often, during deployment of new services, keeper specifies this service and other services
Incidence relation, cloud controller record this service which node and this service and other service associate
It is related in Cloud Server database 112, capacity management device can be obtained in cloud controller database 112
The incidence relation between each service is got, such that it is able to cloud system resource is predicted and is estimated.When
So, capacity management device 108 can be with from capacity management database 114 or call chain database 116
It is middle to obtain service incidence relation.Capacity management device 108 and call chain apparatus 110 be integrated in one
Rise, as the hardware of an entirety.
Under normal circumstances, Cloud Server database 112 stores cloud controller 102 and disposes certain service
In the information of which node, and the incidence relation between service, then Cloud Server database 112
Can dispose certain service which node information, and service between incidence relation be synchronized to
In capacity management server 114.Call chain database 116 can will call chain apparatus 110 to analyze
Service between incidence relation be synchronized to capacity management database 114.That is, capacity management
The newest incidence relation between service will be stored in database 114.Under normal conditions, when need
When obtaining the call relation between some services, capacity management device 108 is initially to capacity management number
Go to search according to storehouse 114, if searched less than capacity management device in capacity management database 114
108 will make a look up in cloud controller database 112 or call chain database 116.Certainly it is above-mentioned
Cloud Server database 112, capacity management database 114, call chain database 116 can merge
Into a database, that is, cloud controller 102, capacity management device 108, call chain apparatus 110
A public database is shared, now, all data are stored in capacity management database 114.
External system 118, the service that external system 118 directly can be issued in access system, such as this be
System has issued a WEB service, and external system can access this service by accessing network address.
Fig. 2 is refer to, is a kind of flow chart of the embodiment of the method for resources of the embodiment of the present invention,
Specifically include：
Step 201：Capacity management device determines the operational indicator for affecting the business usage amount on server.
If multiple business have been run on server, capacity management device determines each business respectively
The respective operational indicator of impact business usage amount.
Step 202-204, illustrates the detailed process of a concrete operational indicator prediction of a business,
The prediction process of other operational indicators of one business is similar with 202-204.
Step 202：According to traffic forecast algorithm and the historical data of initial service index, to the first beginning of the school year
Business index is predicted, and obtains predicting the outcome for initial service index.
Service resources prediction algorithm has a lot, and the embodiment of the present invention is come by taking a following specific algorithm as an example
Illustrate, be class to the process that operational indicator is predicted using other service resources prediction algorithms
As.Its process includes：
1, capacity management device carries out automatic detection to the cycle of operational indicator, obtains operational indicator
Cycle.
A range of newest operational indicator is obtained from database, Fast Fourier Transform (FFT) is carried out,
Operational indicator is transformed to into frequency, after Fast Fourier Transform (FFT), the modulus value of each Frequency point is exactly
The maximum point of amplitude characteristic under the frequency values, wherein modulus value is dominant frequency freq, then dominant frequency inverse is
For the cycle, then period m=1/freq.
In practical application scene, the cycle of operational indicator does not elapse substantially or over time business change
And cause mechanical periodicity, forecasting inaccuracy can be caused true by being manually specified；Operational indicator reports system daily
Count and be saved in database, according to the newest operational indicator automatic detection cycle, both reduced artificial
Intervene the situation for being suitable for mechanical periodicity again, increased forecasting accuracy.
2, historical data M of the capacity management device to operational indicatortDo once (m is odd number) or twice
The m phase rolling averages of (m is even number), obtain trend component Tt。
3, rejected trend component data Mt-Tt, and rejecting trend component data Mt-Tt's
On the basis of, the average estimation as i-th time point is taken to i-th time point in whole cycles, is obtained
To seasonal component St。
4, to trend component TtIt is fitted, capacity management device provides various model of fit；And be based on
The curvilinear characteristic and error of fitting of input data, from various (here as a example by 7 kinds) models automatically
The trend prediction model that selection is most matched.
Specifically：Capacity management device selects one most to match operational indicator from multiple model of fit
Trend prediction model.
112 timing of cloud controller database is by each operational indicator data is activation to capacity management database
In 114, capacity management database 114 saves each operational indicator data, that is to say, that business refers to
Target related data is producing new data always, needs to be intended according to a period of time newest data correction
Matched moulds type, concrete time can be set with oneself, such as：One week, one month or a season etc..
Capacity management device 108 obtains the newest industry of a period of time from capacity management database 114
The data of business index；Whether extraction model judging characteristic, judging characteristic are constant, if constant is just
Think and corresponding Model Matching；The judging characteristic of different models is respectively：
Linear feature
Feature1 (i)=L (i+1)-L (i)
Feature1=(Feature1-min (Feature1))/mean (Feature1-min (Feature1))；
Index characteristic
Feature2 (i)=log (L (i+1))-log (L (i))；
Feature2=(Feature2-min (Feature2))/mean (Feature2-min (Feature2))；
Modified index feature：
Feature3 (i)=(L (i+2)-L (i+1))/(L (i+1)-L (i))；
Compertz curvilinear characteristics：
Feature4 (i)=(log (L (i+2))-log (L (i+1)))/(log (L (i+1))-log (L (i)))；
S curve feature：
Feature5 (i)=((1/L (i+2))-(1/L (i+1)))/((1/L (i+1))-(1/L (i)))；
Conic section feature：
Feature6 (i)=Feature1 (i+1)-Feature1 (i)；
Feature6=(Feature6-min (Feature6))/mean (Feature6-min (Feature6))；
Logarithmic curve feature：
Feature7 (i)=(L (i+1)-L (i))/(log (i+1)-log (i))
If all aspects of model are not complyed with, carry out curve fitting by different models respectively, one by one
R side's value of each model is checked, r side is better closer to 1 explanation models fitting, selects r side closest
In 1 model as trend prediction model.
So, carried out curve fitting using above-mentioned 7 kinds of models respectively, select optimal from 7 kinds of models
Model as trend prediction model, the degree of accuracy of such prediction can be higher.
5, according to the trend prediction model for selecting, it is fitted the trend component of service decomposition indexAnd will
The trend component of the service decomposition index of predictionRecorded in database.
With the development of business, the trend prediction model of fitting may change, such as in the development rank of business
Section, is presented exponential increase, fit indices forecast model, but many periods of expansion enter the stage of stable development, can
Linear forecast model can be fitted, so prediction is required for amendment fitting being gone according to business latest data every time
Trend prediction model.
6, trend component and seasonal component are rejected from initial data, random component is obtained, estimate with
The mean μ and standard deviation sigma of machine component, specially：
7, by the trend component of fitting, the seasonal component and random component of estimation are overlapped, obtain
Forecast model:
8, then the operational indicator data according to forecast model and history, obtain the prediction of operational indicator
As a result
Step 203：The association factor of the initial service index is obtained from database, and obtains institute
State the historical data of association factor.
Under complicated application scenarios, such as：Under telecommunication service scene, have between many operational indicators
There is incidence relation, an operational indicator depends on another operational indicator or multiple operational indicators,
Depend on multiple dependent variables, thus operational indicator cycle and trend be multiple dependent variables superposition,
Without obvious characteristic, directly this operational indicator is predicted, forecasting inaccuracy can be caused true.In order to
Such case is solved, is needed first to isolate dependent variable, dependent variable is predicted, then by each dependent variable
Predicted value be overlapped, calculate prediction index predicted value, can so increase the degree of accuracy of prediction.
Incidence relation between operational indicator can be embodied by association factor, such as：Business
Index 2 is the association factor of operational indicator 1, therefore, if the second operational indicator affects the first business
Index, then the second operational indicator is the association factor of the first operational indicator.In embodiments of the present invention,
Operational indicator can be specially the service involved by certain business, such as, in following example, clothes
Business A is the first operational indicator, services the association factor that B is the first operational indicator, services C, service
D is the association factor for servicing B.
Under distributed, large-scale cluster system scene, Jing often disposes new service, between service
Incidence relation needs Jing often to update, it is difficult to manual go to safeguard.And distributed, large-scale cluster system field
Under scape, once request can trigger calling for hundreds of front and back ends, multi-level service call, it is difficult to use
Manpower goes to find out the incidence relation between service.
Wherein key point is the acquisition of the association factor of operational indicator, that is, the association obtained between service is closed
System, the embodiment of the present invention propose two kinds of solutions, can automatically analyze and record the association between service
Relation, one kind are that one kind is obtained by calling chain apparatus by obtaining during cloud controller deployment services.
Below both acquisition modes are introduced respectively：
First kind of way：By obtaining during cloud controller deployment services.Because under cloud scene often
The new service of deployment, during deployment of new services, user specifies the incidence relation of the service and other services, cloud
Controller stores the incidence relation between the service and other services in cloud controller database, cloud
Controller database can store the incidence relation between service in capacity management database.Specifically
Process it is as follows：
, by cloud controller deployment services A, configuration service A is with other services (such as keeper：Clothes
Business B, service C) incidence relation；Cloud controller can search available resources in Service Source pond,
Service A is deployed in into the above-mentioned available resources for finding up.After cloud controller has disposed new demand servicing, will
Which service node service A is deployed on, the information such as incidence relation of this service A and other services
It is saved in cloud controller database.Cloud controller database will be these incidence relations between servicing same
Walk in capacity management database.Then capacity management device just buret can be obtained in managing database calmly
Get the incidence relation between service A and other services.
The second way：Obtained by calling chain apparatus.
Under distributed, large-scale cluster system scene, once request can trigger the clothes of hundreds of front and back ends
Calling between business, these some problems called can affect current request, some steps drag slow whole
Individual handling process, needs how many machines distributed to application cluster in the peak traffic phase of large-scale festivals or holidays,
These are all that O＆M needs to consider, but the complexity of transfer environment, it is difficult to be done with manpower
Accurately analyze and have evaluated；In the face of the daily record of magnanimity, it would be desirable to be able to automatically once ask in be related to
Different components " isolated " daily record string together, restore more valuable information, aid in
Problem delimits positioning, capacity planning and stability analysis.That is, clothes are obtained by call chain
Relation between business.Detailed process is as follows：
Assume there are three kinds of services, front end services, the first back-end services, the second back-end services, this three
Class service is all the service issued in Service Source pond.Now, when certain external request accesses front end
During service, front end services also need to call back-end services 1 and back-end services 2, can just complete outside asking
Ask requirement.With calling between each service, each service recorded invoked procedure in daily record,
Then by log collection, and the daily record collected is aggregated into and is called in catenary system.
Then chain apparatus are called to be analyzed daily record, analysis calls path to process, between being serviced
Call source, and the incidence relation between each service, and recorded in call chain database.
Can record in the invoked procedure of each service and call daily record, including track identification (TraceID),
Sequence number (SeqNo), calls the information such as service and called service.Wherein, TraceID is outside
Request accesses generated during front end services unique mark ID, the TraceID in whole call chain
It is constant.A sequencing is buried in SeqNo mark call chains, SeqNo is the unfixed character string of length,
Form is：X.X....X.X, wherein：Each X correspondence one-level is called, and the number of X is calls depth
Degree；Same level calls middle X by calling sequencing to start to be incremented by from 1；Call chain root node (is produced
The node of raw TraceID) SeqNo be 1.Service call responds SeqNo and corresponding with service is called
The SeqNo of request is identical.Each service log calls the form of daily record to be:TraceID | SeqNo | Business Streams
The called side of journey | called side |.
For example, as shown in figure 3, for the schematic diagram of the call relation between service, service A is front end
Service, services B, and it is back-end services to service C, service D and service E.In an operation flow,
Service A have received a request of applications, and it is 1 for 100001, SeqNo to generate TraceID,
The daily record of record is:100001 | 1 | operation flow A | applications | service A；Service A needs to call
Service B, then be revised as 1.1 by SeqNo, and the daily record of record is:100001 | 1.1 | operation flows A | service
A | service B, further, service B also needs to call service E, then SeqNo is revised as 1.1.2,
The daily record of record:100001 | 1.1.2 | operation flows A | service B | service E.Above-mentioned each log
All store in call chain database.
When needing to analyze the call relation between each service of certain business, chain apparatus are called from tune
With get in chain database the concrete business of said one each service between log, and point
Above-mentioned day is analysed, wherein, TraceID identicals are a same calling services, then according to SeqNo just
Know, for example：By analyzing daily record, can know that TraceID for 10001 is
Same calling service, then can know the precedence relationship of SeqNo：1,1.1,1.1.2, so
It has been known that service A calls service B, service B to call service E.The industry can thus be got
Call relation between each service of business.
After calling chain apparatus to get the call relation between service, the association between above-mentioned service is closed
System is synchronized in capacity management database, and such capacity management device just can manage database by buret calmly
In get service between call relation.
So, after capacity management device gets the association factor of operational indicator, from capacity management number
According to the historical data that association factor is got in storehouse.
Step 204：According to the historical data and traffic forecast algorithm of association factor, association factor is entered
Row prediction, obtains predicting the outcome for association factor, the initial service index predicted according to step 202
Predicting the outcome for the association factor for predicting the outcome and predicting, calculates the predicted value for obtaining operational indicator, and
The predicted value of the operational indicator of prediction is stored in capacity management database.
So according to the process of step 202-204, it is predicted that the prediction knot of the operational indicator of each business
Really
Step 205：From capacity management database, the industry of each business run on server is obtained
Business index predicts the outcome, the resource consumption of predictive server.
, often by multiple business joint effect, each service period, trend, busy period are each for server resource
Differ, after impact superposition of each business to server resource, the cycle of server resource and trend are not
Substantially, directly system resource is predicted, forecasting inaccuracy can be caused true.
Fish stock assessment models are pre-build according to telecommunication service feature：For example
St=a × M1t+b×M2t+c×M3t+ d, S are system resource index, and M1, M2, M3 represent each industry
Business index, a, b, c, d represent the resource consumption value of constituent parts business, and meter is needed before each stock assessment
Calculate and correct each service unit resource consumption value；That is, according to service decomposition index and multinomial
The model evaluator factor, such as St=a × M1t+b×M2t+c×M3t+ d, wherein factor of a polynomial have
4, therefore need to only obtain 4 groups of newest service decomposition indexs, you can calculate the resource of constituent parts business
Consumption figures.
The embodiment of the present invention refers in the initial service that not only only accounts for of the resources for carrying out server
Mark, in addition it is also necessary to consider to affect the association factor of initial service index, be resources so to server
Will more accurately.Further, prediction algorithm of the invention is optimized to existing scheme,
Increase cycle automatic detection, trend fitting model selection function, save human cost, reduce it is artificial because
Element interference, in the case of mechanical periodicity, Long-term change trend, increases the accuracy of prediction.In actual feelings
Under condition, by Multiple factors collective effect, cycle and trend is not obvious for prediction index, direct predicated error compared with
Greatly, in order to solve such case, business model is designed according to telecommunication service feature, increases coupling index
Prediction and calculation of natural resources function, increased forecasting accuracy.
As shown in figure 4, a kind of capacity management device that the present invention is provided, including：
First prediction module 41, for the history number according to traffic forecast algorithm and initial service index
According to being predicted to the initial service index, obtain the initial service index and predict the outcome；
Acquisition module 42, for obtaining the association factor of the initial service index, and obtains the pass
The historical data of the connection factor；
Second prediction module 43, calculates for the historical data according to the association factor and traffic forecast
Method, is predicted to the association factor, and obtains predicting the outcome for the association factor；
3rd prediction module 44, for predicting the outcome and the association according to the initial service index
Predicting the outcome for the factor, obtains predicting the outcome for final service index, and is referred to according to the final service
Target predicts the outcome, the resource consumption of predictive server.
Optionally, acquisition module 42, specifically for the initial service index is obtained from database
Association factor, the association factor are determined in deployment services by cloud controller.
Optionally, acquisition module 42, specifically for the initial service index is obtained from database
Association factor, wherein, the association factor is by calling chain apparatus by calling road between Analysis Service
What footpath obtained, it is described to call path to be recorded in log.
Optionally, the 3rd prediction module 44, specifically for when multiple business are run on server, root
According to predicting the outcome for the initial service index and predicting the outcome for the association factor, obtain respectively every
The final service index of individual business predicts the outcome；According to the final service index of each business
Predict the outcome and the corresponding unit resource consumption figures of each business, the resource consumption of predictive server.
The embodiment of the present invention refers in the initial service that not only only accounts for of the resources for carrying out server
Mark, in addition it is also necessary to consider to affect the association factor of initial service index, be resources so to server
Will more accurately.
It should be noted that in the embodiment of the present invention to the division of modules be it is schematic, only
For a kind of division of logic function, when actually realizing, there can be other dividing mode, in addition, at this
Apply each functional module in each embodiment can be integrated in a processing module in, or it is each
Individual module is individually physically present, it is also possible to which two or more modules are integrated in a module.On
State integrated module both to realize in the form of hardware, it would however also be possible to employ the shape of software function module
Formula is realized.
If the integrated module is realized and as independent product using in the form of software function module
When sale or use, can be stored in a computer read/write memory medium.Based on such reason
Solution, part or the skill that the technical scheme of the application is substantially contributed to prior art in other words
The all or part of art scheme can be embodied in the form of software product, the computer software product
It is stored in a storage medium, uses so that a computer equipment (can be including some instructions
Personal computer, server, or network equipment etc.) or processor (processor) perform this Shen
Please each embodiment methods described all or part of step.And aforesaid storage medium includes：USB flash disk,
Portable hard drive, read-only storage (ROM, Read-Only Memory), random access memory
(RAM, Random Access Memory), magnetic disc or CD etc. are various can be with storage program
The medium of code.
The embodiment of the present invention additionally provides a kind of capacity management device, as shown in figure 5, Fig. 5 is this
The structural representation of capacity management device in bright embodiment, the capacity management device include processor 51
With memory 52.Wherein, processor 51 is connected with memory 52.Do not limit in the embodiment of the present invention
Concrete connection medium between fixed above-mentioned part.The embodiment of the present invention selects processor 51 in Figure 5
Connected by bus 53 and memory 52 between, bus is represented with thick line in Figure 5, other parts
Between connected mode, be only to be schematically illustrated, do not regard it as and be limited.The bus can be divided
For address bus, data/address bus, controlling bus etc..For ease of representing, only with a thick line in Fig. 5
Represent, it is not intended that only one bus or a type of bus.
Memory 52 in the embodiment of the present invention, for storing the program code of the execution of processor 51, deposit
Reservoir 52 can be volatile memory (English：Volatile memory), such as arbitrary access is deposited
Reservoir (English：Random-access memory, abbreviation：RAM)；Memory 52 can also be
Nonvolatile memory (English：Non-volatile memory), such as read-only storage (English：
Read-only memory, abbreviation：ROM), flash memory (English：Flash memory),
Hard disk (English：Hard disk drive, abbreviation：HDD) or solid state hard disc (English：solid-state
Drive, abbreviation：SSD) or memory 52 can be used for carrying or store have instruction or
Data structure form expect program code and can by any other memory of computer access, but
Not limited to this.Additionally, memory 52 can also be the combination of above-mentioned any memory.
In the embodiment of the present invention, processor 51, for calling what is stored in memory 52 by bus
Program code, and performed by performing the program code for calling：
According to traffic forecast algorithm and the historical data of initial service index, to the initial service index
It is predicted, obtains predicting the outcome for the initial service index；Obtain the initial service index
Association factor, and obtain the historical data of the association factor；According to the history number of the association factor
According to traffic forecast algorithm, the association factor is predicted, the prediction of the association factor is obtained
As a result；According to predicting the outcome for the initial service index and predicting the outcome for the association factor, obtain
Obtain predicting the outcome for final service index, and predicting the outcome according to the final service index, prediction
The resource consumption of server.
Processor 51 in the embodiment of the present invention, can be a CPU (English：central
Processing unit, abbreviation CPU).
The embodiment of the present invention additionally provides a kind of resources system, as shown in fig. 6, including capacity management
Device 61 and database 62, wherein,
The capacity management device 61, for the history according to traffic forecast algorithm and initial service index
Data, are predicted to the initial service index, obtain predicting the outcome for the initial service index；
The association factor of the initial service index is obtained, and obtains the historical data of the association factor；Root
According to the historical data and traffic forecast algorithm of the association factor, the association factor is predicted,
Obtain predicting the outcome for the association factor；According to the initial service index predict the outcome with it is described
Predicting the outcome for association factor, obtains predicting the outcome for final service index, and according to the final industry
Business index predicts the outcome, the resource consumption of predictive server；
The database 62, for the historical data for storing the initial service index, the just beginning of the school year
The historical data of association factor and the association factor corresponding to business index.
Optionally, the system, also includes：Chain apparatus 63 are called, for obtaining from the database
To log, the path of calling in the log is analyzed, the association of initial service index is obtained
The factor.
Those skilled in the art it should be appreciated that embodiments of the invention can be provided as method, system,
Or computer program.Therefore, the present invention can be implemented using complete hardware embodiment, complete software
Example, or with reference to the form of the embodiment in terms of software and hardware.And, the present invention can be using at one
Or it is multiple wherein include computer usable program code computer-usable storage medium (include but not
Be limited to magnetic disc store, CD-ROM, optical memory etc.) on the computer program implemented
Form.
The present invention is with reference to method according to embodiments of the present invention, equipment (system), and computer journey
The flow chart and/or block diagram of sequence product is describing.It should be understood that can be realized by computer program instructions
Each flow process and/or square frame and flow chart and/or block diagram in flow chart and/or block diagram
In flow process and/or square frame combination.Can provide these computer program instructions to all-purpose computer,
The processor of special-purpose computer, Embedded Processor or other programmable data processing devices is producing one
Individual machine so that by the instruction of computer or the computing device of other programmable data processing devices
Produce for realizing in one square frame or many of one flow process of flow chart or multiple flow processs and/or block diagram
The device of the function of specifying in individual square frame.
These computer program instructions may be alternatively stored in and can guide at computer or other programmable datas
In the computer-readable memory that reason equipment is worked in a specific way so that be stored in the computer-readable
Instruction in memory produces the manufacture for including command device, and the command device is realized in flow chart one
The function of specifying in individual flow process or one square frame of multiple flow processs and/or block diagram or multiple square frames.
These computer program instructions can also be loaded into computer or other programmable data processing devices
On so that series of operation steps is performed on computer or other programmable devices to produce computer
The process of realization, so as to the instruction performed on computer or other programmable devices is provided for realizing
Specify in one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or multiple square frames
Function the step of.
, but those skilled in the art once know although preferred embodiments of the present invention have been described
Basic creative concept, then can make other change and modification to these embodiments.So, appended power
Profit requires to be intended to be construed to include preferred embodiment and fall into the had altered of the scope of the invention and change.
Obviously, those skilled in the art the embodiment of the present invention can be carried out it is various change and modification and
Without departing from the spirit and scope of the embodiment of the present invention.So, if these modifications of the embodiment of the present invention
Belong within the scope of the claims in the present invention and its equivalent technologies with modification, then the present invention is also intended to bag
Containing including these changes and modification.
Claims (10)
1. a kind of method of resources, it is characterised in that include：
According to traffic forecast algorithm and the historical data of initial service index, to the initial service index
It is predicted, obtains predicting the outcome for the initial service index；
The association factor of the initial service index is obtained, and obtains the history number of the association factor
According to；
According to the historical data and traffic forecast algorithm of the association factor, the association factor is carried out
Prediction, obtains predicting the outcome for the association factor；
According to predicting the outcome for the initial service index and predicting the outcome for the association factor, obtain
Final service index predicts the outcome, and predicting the outcome according to the final service index, prediction clothes
The resource consumption of business device.
2. resource prediction method according to claim 1, it is characterised in that the acquisition institute
The association factor of initial service index is stated, is specifically included：
The association factor of the initial service index is obtained from database, the association factor is by cloud control
What device processed was determined in deployment services.
3. resource prediction method according to claim 1, it is characterised in that the acquisition institute
The association factor of initial service index is stated, is specifically included：
The association factor of the initial service index is obtained from database, wherein, the association factor
It is by chain apparatus are called by calling what path obtained between Analysis Service, described to call path to be recorded
In log.
4. resource prediction method according to claim 1, it is characterised in that when on server
When running multiple business, the predicting the outcome and the association factor according to the initial service index
Predict the outcome, obtain final service index and predict the outcome, and according to the final service index
Predict the outcome, the resource consumption of predictive server is specifically included：
According to predicting the outcome for the initial service index and predicting the outcome for the association factor, difference
The final service index for obtaining each business predicts the outcome；
According to predicting the outcome and the corresponding list of each business for the final service index of each business
Position resource consumption value, the resource consumption of predictive server.
5. a kind of capacity management device, it is characterised in that include：
First prediction module, for the historical data according to traffic forecast algorithm and initial service index,
The initial service index is predicted, predicting the outcome for the initial service index is obtained；
Acquisition module, for obtaining the association factor of the initial service index, and obtains the association
The historical data of the factor；
Second prediction module, for the historical data according to the association factor and traffic forecast algorithm,
The association factor is predicted, and obtains predicting the outcome for the association factor；
3rd prediction module, for according to the initial service index predict the outcome with the association because
Predicting the outcome for son, obtains predicting the outcome for final service index, and according to the final service index
Predict the outcome, the resource consumption of predictive server.
6. capacity management device according to claim 5, it is characterised in that the acquisition mould
Block, the association factor specifically for the initial service index is obtained from database, the association because
What son was determined in deployment services by cloud controller.
7. capacity management device according to claim 5, it is characterised in that the acquisition mould
Block, the association factor specifically for the initial service index is obtained from database, wherein, it is described
Association factor is by chain apparatus are called by calling what path obtained between Analysis Service, described to call road
Footpath is recorded in log.
8. capacity management device according to claim 5, it is characterised in that the described 3rd is pre-
Module is surveyed, specifically for when multiple business are run on server, according to the initial service index
Predict the outcome and the association factor predicts the outcome, obtain the final service index of each business respectively
Predict the outcome；According to predicting the outcome and each business pair for the final service index of each business
The unit resource consumption figures answered, the resource consumption of predictive server.
9. a kind of resources system, it is characterised in that include：Capacity management device and database,
Wherein,
The capacity management device, for the history number according to traffic forecast algorithm and initial service index
According to being predicted to the initial service index, obtain the initial service index and predict the outcome；
The association factor of the initial service index is obtained, and obtains the historical data of the association factor；Root
According to the historical data and traffic forecast algorithm of the association factor, the association factor is predicted,
Obtain predicting the outcome for the association factor；According to the initial service index predict the outcome with it is described
Predicting the outcome for association factor, obtains predicting the outcome for final service index, and according to the final industry
Business index predicts the outcome, the resource consumption of predictive server；
The database, for the historical data for storing the initial service index, the initial service
The historical data of association factor and the association factor corresponding to index.
10. resources system as claimed in claim 9, it is characterised in that also include：Call
Chain apparatus, for log is got from the database, analyze the tune in the log
With path, the association factor of initial service index is obtained.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510590666.1A CN106549772B (en) | 2015-09-16 | 2015-09-16 | Resource prediction method, system and capacity management device |
| PCT/CN2016/089927 WO2017045472A1 (en) | 2015-09-16 | 2016-07-13 | Resource prediction method and system, and capacity management apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510590666.1A CN106549772B (en) | 2015-09-16 | 2015-09-16 | Resource prediction method, system and capacity management device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106549772A true CN106549772A (en) | 2017-03-29 |
| CN106549772B CN106549772B (en) | 2019-11-19 |
Family
ID=58288140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510590666.1A Active CN106549772B (en) | 2015-09-16 | 2015-09-16 | Resource prediction method, system and capacity management device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106549772B (en) |
| WO (1) | WO2017045472A1 (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346472A (en) * | 2017-06-29 | 2017-11-14 | 人民法院信息技术服务中心 | A kind of method and device that operation/maintenance data is handled by line modeling |
| CN107943579A (en) * | 2017-11-08 | 2018-04-20 | 深圳前海微众银行股份有限公司 | Resource bottleneck Forecasting Methodology, equipment, system and readable storage medium storing program for executing |
| CN108984304A (en) * | 2018-07-11 | 2018-12-11 | 广东亿迅科技有限公司 | Server expansion calculation method and device based on regression equation |
| CN109271453A (en) * | 2018-10-22 | 2019-01-25 | 阿里巴巴集团控股有限公司 | A kind of determination method and apparatus of database volume |
| CN109510715A (en) * | 2017-09-14 | 2019-03-22 | 中国电信股份有限公司 | Bandwidth allocation methods, device, data center and storage medium |
| CN109543891A (en) * | 2018-11-09 | 2019-03-29 | 深圳前海微众银行股份有限公司 | Method for building up, equipment and the computer readable storage medium of capacity prediction model |
| CN110019110A (en) * | 2017-07-28 | 2019-07-16 | 腾讯科技（深圳）有限公司 | A kind of capacity management methods of operation system, device, equipment and operation system |
| CN110058939A (en) * | 2018-12-27 | 2019-07-26 | 阿里巴巴集团控股有限公司 | System Expansion method, device and equipment |
| CN110096423A (en) * | 2019-05-14 | 2019-08-06 | 深圳供电局有限公司 | Server storage capacity analysis and prediction method based on big data analysis |
| CN110109800A (en) * | 2019-04-10 | 2019-08-09 | 网宿科技股份有限公司 | A kind of management method and device of server cluster system |
| CN110321240A (en) * | 2019-06-28 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of business impact assessment method and apparatus based on time series forecasting |
| CN111611517A (en) * | 2020-05-13 | 2020-09-01 | 咪咕文化科技有限公司 | Index monitoring method and device, electronic equipment and storage medium |
| CN111985713A (en) * | 2020-08-19 | 2020-11-24 | 中国银行股份有限公司 | Data index waveform prediction method and device |
| CN112559191A (en) * | 2020-12-23 | 2021-03-26 | 平安银行股份有限公司 | Method and device for dynamically deploying GPU (graphics processing Unit) resources and computer equipment |
| CN112702345A (en) * | 2020-12-24 | 2021-04-23 | 福建技术师范学院 | Information vulnerability risk assessment method and device based on data element characteristics |
| CN112734195A (en) * | 2020-12-31 | 2021-04-30 | 平安科技（深圳）有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112766698A (en) * | 2021-01-13 | 2021-05-07 | 中国工商银行股份有限公司 | Application service pressure determining method and device |
| CN112860523A (en) * | 2021-03-16 | 2021-05-28 | 中国工商银行股份有限公司 | Fault prediction method and device for batch job processing and server |
| CN113703974A (en) * | 2021-08-27 | 2021-11-26 | 深圳前海微众银行股份有限公司 | Method and device for predicting server capacity |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109446041B (en) * | 2018-09-25 | 2022-10-28 | 平安普惠企业管理有限公司 | Server pressure early warning method and system and terminal equipment |
| CN111181875B (en) * | 2018-11-12 | 2022-12-27 | 中移（杭州）信息技术有限公司 | Bandwidth adjusting method and device |
| CN111400147B (en) * | 2019-01-02 | 2023-05-05 | 中国移动通信有限公司研究院 | Service quality testing method, device and system |
| CN110109750B (en) * | 2019-04-03 | 2023-08-18 | 平安科技（深圳）有限公司 | Virtual resource acquisition method, device, computer equipment and storage medium |
| CN110348684B (en) * | 2019-06-06 | 2023-07-18 | 创新先进技术有限公司 | Service call risk model generation method, prediction method and respective devices |
| CN111352733A (en) * | 2020-02-26 | 2020-06-30 | 北京奇艺世纪科技有限公司 | Capacity expansion and reduction state prediction method and device |
| CN112685173A (en) * | 2020-12-22 | 2021-04-20 | 中通天鸿（北京）通信科技股份有限公司 | Intelligent route distribution system based on rich media |
| CN113762688A (en) * | 2021-01-06 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Business analysis system, method and storage medium |
| CN112965956A (en) * | 2021-03-18 | 2021-06-15 | 上海东普信息科技有限公司 | Database horizontal capacity expansion method, device, equipment and storage medium |
| CN113220299A (en) * | 2021-05-28 | 2021-08-06 | 北京达佳互联信息技术有限公司 | Graphical display method and device |
| CN113923099B (en) * | 2021-09-03 | 2022-12-27 | 华为技术有限公司 | Root cause positioning method for communication network fault and related equipment |
| CN115080363B (en) * | 2022-08-23 | 2022-11-15 | 中国中金财富证券有限公司 | System capacity evaluation method and device based on service log |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102082703A (en) * | 2009-11-26 | 2011-06-01 | 中国移动通信集团贵州有限公司 | Method and device for monitoring equipment performance of service supporting system |
| CN102103714A (en) * | 2009-12-22 | 2011-06-22 | 阿里巴巴集团控股有限公司 | Real-time processing platform for predicting service data and predicting method |
| CN103490956A (en) * | 2013-09-22 | 2014-01-01 | 杭州华为数字技术有限公司 | Self-adaptive energy-saving control method, device and system based on traffic predication |
| US20140095537A1 (en) * | 2012-09-28 | 2014-04-03 | Oracle International Corporation | Real-time business event analysis and monitoring |
| CN104125584A (en) * | 2013-04-27 | 2014-10-29 | 中国移动通信集团福建有限公司 | Service index realization prediction method aiming at network service and apparatus thereof |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103685347B (en) * | 2012-09-03 | 2017-01-18 | 阿里巴巴集团控股有限公司 | Method and device for allocating network resources |
| CN103903069A (en) * | 2014-04-15 | 2014-07-02 | 广东电网公司信息中心 | Storage capacity predication method and storage capacity predication system |
-
2015
- 2015-09-16 CN CN201510590666.1A patent/CN106549772B/en active Active
-
2016
- 2016-07-13 WO PCT/CN2016/089927 patent/WO2017045472A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102082703A (en) * | 2009-11-26 | 2011-06-01 | 中国移动通信集团贵州有限公司 | Method and device for monitoring equipment performance of service supporting system |
| CN102103714A (en) * | 2009-12-22 | 2011-06-22 | 阿里巴巴集团控股有限公司 | Real-time processing platform for predicting service data and predicting method |
| US20140095537A1 (en) * | 2012-09-28 | 2014-04-03 | Oracle International Corporation | Real-time business event analysis and monitoring |
| CN104125584A (en) * | 2013-04-27 | 2014-10-29 | 中国移动通信集团福建有限公司 | Service index realization prediction method aiming at network service and apparatus thereof |
| CN103490956A (en) * | 2013-09-22 | 2014-01-01 | 杭州华为数字技术有限公司 | Self-adaptive energy-saving control method, device and system based on traffic predication |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346472A (en) * | 2017-06-29 | 2017-11-14 | 人民法院信息技术服务中心 | A kind of method and device that operation/maintenance data is handled by line modeling |
| CN110019110A (en) * | 2017-07-28 | 2019-07-16 | 腾讯科技（深圳）有限公司 | A kind of capacity management methods of operation system, device, equipment and operation system |
| CN110019110B (en) * | 2017-07-28 | 2022-11-18 | 腾讯科技（深圳）有限公司 | Capacity management method, device and equipment of service system and service system |
| CN109510715A (en) * | 2017-09-14 | 2019-03-22 | 中国电信股份有限公司 | Bandwidth allocation methods, device, data center and storage medium |
| CN109510715B (en) * | 2017-09-14 | 2022-02-08 | 中国电信股份有限公司 | Bandwidth allocation method and device, data center and storage medium |
| CN107943579A (en) * | 2017-11-08 | 2018-04-20 | 深圳前海微众银行股份有限公司 | Resource bottleneck Forecasting Methodology, equipment, system and readable storage medium storing program for executing |
| CN107943579B (en) * | 2017-11-08 | 2022-01-11 | 深圳前海微众银行股份有限公司 | Resource bottleneck prediction method, device, system and readable storage medium |
| CN108984304A (en) * | 2018-07-11 | 2018-12-11 | 广东亿迅科技有限公司 | Server expansion calculation method and device based on regression equation |
| CN109271453B (en) * | 2018-10-22 | 2021-08-27 | 创新先进技术有限公司 | Method and device for determining database capacity |
| CN109271453A (en) * | 2018-10-22 | 2019-01-25 | 阿里巴巴集团控股有限公司 | A kind of determination method and apparatus of database volume |
| CN109543891A (en) * | 2018-11-09 | 2019-03-29 | 深圳前海微众银行股份有限公司 | Method for building up, equipment and the computer readable storage medium of capacity prediction model |
| CN109543891B (en) * | 2018-11-09 | 2022-02-01 | 深圳前海微众银行股份有限公司 | Method and apparatus for establishing capacity prediction model, and computer-readable storage medium |
| CN110058939A (en) * | 2018-12-27 | 2019-07-26 | 阿里巴巴集团控股有限公司 | System Expansion method, device and equipment |
| CN110109800A (en) * | 2019-04-10 | 2019-08-09 | 网宿科技股份有限公司 | A kind of management method and device of server cluster system |
| CN110096423A (en) * | 2019-05-14 | 2019-08-06 | 深圳供电局有限公司 | Server storage capacity analysis and prediction method based on big data analysis |
| CN110321240A (en) * | 2019-06-28 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of business impact assessment method and apparatus based on time series forecasting |
| CN111611517B (en) * | 2020-05-13 | 2023-07-21 | 咪咕文化科技有限公司 | Index monitoring method and device, electronic equipment and storage medium |
| CN111611517A (en) * | 2020-05-13 | 2020-09-01 | 咪咕文化科技有限公司 | Index monitoring method and device, electronic equipment and storage medium |
| CN111985713A (en) * | 2020-08-19 | 2020-11-24 | 中国银行股份有限公司 | Data index waveform prediction method and device |
| CN111985713B (en) * | 2020-08-19 | 2023-08-18 | 中国银行股份有限公司 | Data index waveform prediction method and device |
| CN112559191A (en) * | 2020-12-23 | 2021-03-26 | 平安银行股份有限公司 | Method and device for dynamically deploying GPU (graphics processing Unit) resources and computer equipment |
| CN112702345A (en) * | 2020-12-24 | 2021-04-23 | 福建技术师范学院 | Information vulnerability risk assessment method and device based on data element characteristics |
| CN112734195A (en) * | 2020-12-31 | 2021-04-30 | 平安科技（深圳）有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112734195B (en) * | 2020-12-31 | 2023-07-07 | 平安科技（深圳）有限公司 | Data processing method, device, electronic equipment and storage medium |
| CN112766698A (en) * | 2021-01-13 | 2021-05-07 | 中国工商银行股份有限公司 | Application service pressure determining method and device |
| CN112766698B (en) * | 2021-01-13 | 2024-02-09 | 中国工商银行股份有限公司 | Application service pressure determining method and device |
| CN112860523A (en) * | 2021-03-16 | 2021-05-28 | 中国工商银行股份有限公司 | Fault prediction method and device for batch job processing and server |
| CN112860523B (en) * | 2021-03-16 | 2024-06-25 | 中国工商银行股份有限公司 | Batch job processing fault prediction method, device and server |
| CN113703974A (en) * | 2021-08-27 | 2021-11-26 | 深圳前海微众银行股份有限公司 | Method and device for predicting server capacity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106549772B (en) | 2019-11-19 |
| WO2017045472A1 (en) | 2017-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106549772A (en) | Resource prediction method, system and capacity management device | |
| CN104123214B (en) | The method and system of tasks carrying progress metrics and displaying based on runtime data | |
| CN108345958A (en) | Order meal delivery time prediction model construction method, prediction method, model and device | |
| CN103778474A (en) | Resource load capacity prediction method, analysis prediction system and service operation monitoring system | |
| CN110400022A (en) | Self-help teller machine cash dosage prediction technique and device | |
| CN110019401A (en) | Part amount prediction technique, device, equipment and its storage medium | |
| CN104424598A (en) | Cash demand quantity predicating device and method | |
| CN107239846B (en) | Parking lot berth prediction processing method and device | |
| CN109741177A (en) | Appraisal procedure, device and the intelligent terminal of user credit | |
| CN108960520A (en) | Power load prediction method, system, computer equipment and medium | |
| CN111401801B (en) | Processing system and method for determining decentralized storage of target object warehouse | |
| CN109992866A (en) | Training method, device, readable medium and the electronic equipment of load forecasting model | |
| CN110309947A (en) | Complete vehicle logistics order forecast method and device, logistics system and computer-readable medium | |
| CN107015900A (en) | A kind of service performance Forecasting Methodology of video website | |
| CN110633863A (en) | Bank note distribution prediction method and device based on GBDT algorithm | |
| CN109816157A (en) | Project plan optimization method, device, computer equipment and storage medium | |
| CN113837383B (en) | Model training method and device, electronic equipment and storage medium | |
| CN110263136B (en) | Method and device for pushing object to user based on reinforcement learning model | |
| CN105787136A (en) | Data mining method and data mining device | |
| CN110532156A (en) | A kind of capacity prediction methods and device | |
| CN110069692A (en) | A kind of resource updates time forecasting methods and system towards open source information collection | |
| CN110032750A (en) | A kind of model construction, data life period prediction technique, device and equipment | |
| CN110858355A (en) | Project budget balance prediction method and device | |
| CN110309948A (en) | Complete vehicle logistics order forecast method and device, logistics system and computer-readable medium | |
| CN113962741B (en) | Coal sales data prediction method, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |