CN104468257B - Cloud application availability Forecasting Methodology and system based on mobile subscriber's time-space behavior - Google Patents
Cloud application availability Forecasting Methodology and system based on mobile subscriber's time-space behavior Download PDFInfo
- Publication number
- CN104468257B CN104468257B CN201410598622.9A CN201410598622A CN104468257B CN 104468257 B CN104468257 B CN 104468257B CN 201410598622 A CN201410598622 A CN 201410598622A CN 104468257 B CN104468257 B CN 104468257B
- Authority
- CN
- China
- Prior art keywords
- time
- cloud application
- user
- availability
- network
- 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.)
- Active
Links
Landscapes
- Telephonic Communication Services (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a kind of cloud application availability Forecasting Methodology and system based on mobile subscriber's time-space behavior.This method is：1) intelligent movable equipment end chooses user cloud application to be predicted and its use time t, i.e. user's use pattern, are sent to mobile subscriber's time-space behavior data collector of the intelligent movable equipment end；2) mobile subscriber's time-space behavior data collector is by the user's use pattern information received, and the electric quantity consumption statistical information and network state mode statistical information of the intelligent movable equipment end are sent to high in the clouds；3) data that the high in the clouds is sended over according to mobile subscriber's time-space behavior data collector calculate availability of the cloud application to be predicted in setting usage time interval, and result of calculation is sent into the intelligent movable equipment end.The present invention can help the availability of cloud application on its mobile device of user in predicting future time section, provide convenient for user's application；Meanwhile, also help mobile cloud application provider or service provider's optimization service.
Description
Technical field
The invention belongs to mobile internet technical field, and in particular to a kind of intelligence based on user's time-space behavior pattern analysis
Energy mobile device cloud application availability Forecasting Methodology and system, it is possible to achieve cloud application on the mobile terminal device such as smart mobile phone
Availability is analyzed and predicted, mobile subscriber can be helped to predict the availability of cloud application on its mobile device of future time section, be
Make user more rationally comfortable convenient using application offer according to the custom of oneself；Meanwhile, also help mobile cloud application provider or
Service provider is accustomed to analyzing the availability of its cloud application on the mobile apparatus according to user's time-space behavior, to optimize service.
Background technology
Consumption mode and abundant infrastructure resources that cloud computing mode is with the ease for use of its height, payable at sight, just
Change the mode of people's use information service.Meanwhile, the mobile terminal using smart mobile phone as representative should by feature-rich
With software, the every aspect in people's life has been deep into rapidly, is gradually replaced tradition PC to turn into and is most widely used internet
The mode of service.Counted according to Chinese Network Information Centre, China cell phone netizen has reached 500,000,000 people within 2013, accounts for internet
The 81% of user.With the quick popularization and a wide range of covering of mobile network of mobile intelligent terminal, video is downloaded, IMU
The multi-field Mobile solution sustainable growths such as letter, mobile phone games and shopping at network.On the one hand, the interconnection that mobile terminal is enriched constantly
Network service, diversified media application need to carry out the computation-intensives such as natural language processing, speech recognition, image recognition times
Business, this proposes requirements at the higher level to mobile device performance；On the other hand, mobile terminal exists again calculates and storage resource is limited, battery
The limitation such as cruising time is limited, communication capacity is limited.The mobile cloud meter that mobile terminal ability is combined and proposed with cloud computing mode
Calculate the contradiction for alleviating these two aspects to a certain extent.Mobile terminal cloud application is calculated using the resource processing of cloud computing platform appoints
Business, and with mobile terminal communication or it is synchronous so as to user mutual, both make use of mobile terminal it is ubiquitous, it is easy-to-use the advantages of, and can solve
The problem of resource requirement.According to market report, the expense for being used to move cloud computing service to the whole world in 2016 is up to 64.7 hundred million U.S.s
Member, mobile cloud application extreme enrichment, is that daily life brings huge facility.
But, compared with conventional cloud is applied, mobile cloud application has mobility, resource-constrained (such as battery), network unstable
The features such as fixed (such as wifi network is unavailable, 3G signal blind spots), its service availability is more fragile, and computing resource is provided and industry
The regular failure of business service or inaccessible.And the first element experienced as QoS of customer, the service of cloud application can use
Property directly reflects the service quality of cloud application, is user's concern the most, while being also that mobile cloud application provider is excellent
Change its application product and the emphasis of service.
Mobile terminal cloud application has the characteristics that：1) position dynamic：The dynamic change of mobile end position directly affects
The type of its network connection, such as 3G network or different wifi connections, and different network connection types also brings cloud and answered
With different Quality of Service Experience, such as stable wifi connections can ensure the high availability of media class cloud application；2) time dynamic
Property：The service condition and environment of mobile terminal cloud application are with time dynamic, and determinant is the behavior pattern of user, such as use
Music class application is commonly used at family before sleeping, then applies the period before sleeping to require high availability for music class；3) resource-constrained
Property：The resource-constrained of mobile terminal is mainly reflected in the continuous electric time, and the continuous electric time assuming that under air time same case with
There is incidence relation using the custom of cloud application in network connection and user；Therefore, mobile terminal cloud application availability mainly by
The influence of following factor：1) network connection (relevant with geographical position), with the transfer in user geographical position, residing for user
Network state is shifted therewith, and the change of network state directly affects mobile terminal cloud application availability and influences mobile terminal mobile phone indirectly
Power consumption.2) user's use time is distributed (relevant with application use pattern), and user has necessarily relative using mobile cloud application
Stable Annual distribution, the distribution directly affects the actual mobile cloud application availability experienced of user.3) the electric time is continued (with answering
It is relevant with use pattern), the availability of mobile cloud application is directly affected using the dump energy of power consumption and certain moment of application, with this
Meanwhile, the two factors are closely related with the use pattern of user.
Therefore, enriching, it is necessary to be that mobile subscriber and cloud application provider provide a kind of availability with mobile cloud application
Analysis method and system, so that obtaining user obtains more preferable Quality of Service Experience, these to move the raising of cloud application provider
Its application availability turns into a urgent need to solve the problem, and according to the personalized time-space behavior pattern of mobile subscriber to cloud application
Availability be predicted and analyze as a kind of new approaches.
The content of the invention
The problem of existing for prior art, the present invention proposes a kind of based on the personalized time-space behavior pattern of mobile subscriber
The analysis of cloud application availability and Forecasting Methodology and the system of analysis, it is therefore intended that improve cloud application clothes for Intelligent mobile equipment user
Business quality of experience, helps cloud application provider to optimize its application product.The present invention is from time and two, space dimension to user's row
To be described, the time describes use wish and custom of the user to cloud application, the transfer of spatial description user locations and network rings
Border, by the analysis of mobile subscriber's time-space behavior pattern to cloud application, with reference to energy consumption of mobile equipment and network connection state
The availability of change in time and space, analysis and prediction cloud application in mobile terminal.
The technical scheme that the present invention is provided is：
A kind of mobile device end cloud application availability analysis and Forecasting Methodology and system, as shown in Figure 1.The system is contained
Intelligent movable equipment end and high in the clouds two parts.
Intelligent movable equipment end main modular has：Cloud application equipment end, user interface, time-based cloud application uses mould
Formula logging modle, the monitoring of time-based electric quantity consumption and statistical module, network connection type monitoring based on geographical position with
Statistical module and mobile subscriber's time-space behavior data collector：
1) user interface, major function is to provide mobile terminal and the interaction of mobile subscriber.User can be referred to by interface
The fixed cloud application for wishing analysis and prediction, selection wish uses the period of cloud application；Meanwhile, user interface provides user and checked
The availability functionality of cloud application, and provide data support to the time-based cloud application use pattern logging modle of lower floor.
2) time-based cloud application use pattern logging modle, function is to record meaning of the mobile subscriber to certain cloud application
It is willing to use time (being obtained from user interface, specified by user), to be to be counted in the cycle for a period of time, and statistical result is passed
Pass mobile subscriber time-space behavior data collector.
3) time-based electric quantity consumption monitoring and statistical module, monitor, generate in real time to user's mobile device end electricity
Tuple { time, battery }, the tuple represents the correspondence of certain moment and dump energy, equivalent to relational database during storage
One list item.Meanwhile, monitoring result is finally passed to mobile use by test user using the power consumption speed of mobile cloud device procedures
Family time-space behavior data collector.
4) the network connection type monitoring based on geographical position and statistical module, the network state to user are supervised in real time
Survey and counted with one day for the cycle, statistical result is finally passed to mobile subscriber's time-space behavior data collector.User
Network state be divided into four types：3g networks, wifi network, no network, 3g and wifi network can use simultaneously.
5) mobile subscriber's time-space behavior data collector, collects user's use pattern from three above module, and electricity disappears
Consumption and real-time condition and network state pattern, three is arranged and transmitted to high in the clouds.
6) cloud application equipment end, refers to the equipment end application program of to be analyzed and monitoring mobile cloud application, mainly with app
The cloud application equipment end that client form, i.e. user interface are chosen.This module is directly reacted primarily as monitored object
User behavior and cloud application performance.
Counted, for sake of convenience, given tacit consent to one day for the cycle, one day time slice based on the time with upper module.Set up
Daily monitoring result is recorded as the number of times in each mapping status by user network state with the mapping of period.
Mobile high in the clouds facing cloud application provider, is responsible for dividing user's time-space behavior pattern that mobile device end is counted
Analysis and prediction, and with mobile device end interaction.Mobile high in the clouds is included with lower module：Cloud application high in the clouds, cloud application availability management
Interface, cloud application availability model module, mobile subscriber's time-space behavior data sink, based on mobile subscriber's time-space behavior pattern
Cloud application availability analysis and prediction module：
1) cloud application availability management interface, predominantly cloud application provider provide visual user's behavior pattern and available
Character condition, and availability prediction and analysis result are passed into user interface.
2) mobile subscriber's time-space behavior data sink, receives mobile subscriber's time-space behavior data of intelligent movable equipment end
The data of collector transmission, and by data preparation, pass to the cloud application availability point based on mobile subscriber's time-space behavior pattern
Analysis and prediction module.
3) cloud application availability model module, deposits simple cloud application availability model, and to based on mobile subscriber's space-time
The analysis of cloud application availability and the prediction module of behavior pattern transmit naive model parameter, such as four kinds networks are in physical condition
Probability of availability on (as disposed, signal covering etc.).This module deposits the availability parameters unrelated with user's time-space behavior, deposits
It is placed on high in the clouds.
4) the cloud application availability analysis based on mobile subscriber's time-space behavior pattern and prediction module, from mobile subscriber's space-time
Behavioral data receiver and cloud application availability model module receive parameters, set up user's time-space behavior model and by one
Determine algorithm cloud application availability is analyzed and predicted.
5) cloud application high in the clouds, refers to the high in the clouds part that cloud application provides service.This module is used as a part for system, its function
It is same cloud application equipment end interaction, and considers the change in availability that its interaction is brought by other modules.Meanwhile, cloud application
Provider can optimize according to analysis result to this module.
Compared with prior art, the positive effect of the present invention is：
System and method can help the availability of user in predicting future time section mobile device end application, be user more
It is rationally comfortable to provide help using application；System and method can help the behavioural habits of cloud application provider analysis customer group
And the application availability of user's real experiences, help application provider's optimization product.
Brief description of the drawings
The cloud application availability analysing and predicting system structure based on mobile subscriber's time-space behavior pattern that Fig. 1 is the present invention is shown
It is intended to.
Fig. 2 is schematic flow sheet in embodiment.
Embodiment
Below by specific embodiments and the drawings, the present invention will be further described.
The present invention is based on the analysis to user's time-space behavior pattern, using monitoring and statistical, calculates and predicts
Cloud application availability.Main feature has following three aspect：
1st, the focus of system and method is the availability of Intelligent mobile equipment end application, and angle is from user behavior
Pattern analysis.
2nd, user behavior is described in terms of time and two, space for system and method, and the time describes user and used
Wish and custom, the transfer of spatial description user locations and use environment.
3rd, system and method is main to obtain Intelligent mobile equipment consumption by the monitoring and acquisition to user behavior and wish
The change in time and space of electricity and network connection state, calculates the availability for obtaining more actual accurately Intelligent mobile equipment end application.
Fig. 1 is the prediction of the Intelligent mobile equipment cloud application availability based on the mobile subscriber's time-space behavior pattern system of the present invention
The structural representation of system.The system is built using modular mode, is interacted and transmitted by interface between disparate modules and disappears
There is relative independence between breath, each module and accomplish the loose coupling of intermodule.As shown in figure 1, wherein mobile device end bag
Include cloud application mobile terminal, user interface, time-based cloud application use pattern logging modle, time-based electric quantity consumption inspection
Survey and statistical module, the network connection type monitoring based on geographical position is received with statistical module and mobile subscriber's time-space behavior data
Storage；Mobile high in the clouds (mainly facing cloud application provider) includes cloud application, cloud application availability management interface, mobile subscriber
Time-space behavior data sink, the analysis of cloud application availability and prediction module based on mobile subscriber's time-space behavior pattern, Yun Ying
Use availability model.Different modules is specifically described separately below.
1. mobile device end
Mobile device end is statistics and the monitoring center of whole system, and it is realized to the qualitative of user's time-space behavior pattern
And quantitative statistical analysis, interaction and data packing with user are delivered to the function in high in the clouds.Mould is divided according to functional characteristic
Block simultaneously designs interaction path, and the service condition and environment to cloud application carry out comprehensive Simultaneous Monitoring.
Mobile device end contains the specific support and embodiment to this method and system core thought, mainly including cloud application
Mobile terminal, user interface, time-based cloud application use pattern logging modle, time-based electric quantity consumption monitoring and statistics
Module, network connection type monitoring and statistical module and mobile subscriber's time-space behavior data collector six based on geographical position
Module.Modules all complete allomeric function by carrying out information exchange with other correlation modules and mobile high in the clouds.Explain below
State the major function of each module.
1>User interface
User interface be the directly visual operable module of user there is provided major function include user should to wish monitoring cloud
Selection function, user is to feedback of the usability results to user obtained by the specified function of wish usage time interval and calculating
Function.
The realization of user interface includes display layout based on app interfaces, mainly and operation is laid out, and can use mobile terminal
Operating system DLL is realized.As that in android system, can use textview, the component such as bar.
2>Time-based cloud application use pattern logging modle
Time-based cloud application use pattern logging modle major function is the cloud application specified to user and should
Wish usage time interval is recorded and (obtained from user interface), and passes to mobile subscriber's time-space behavior Data Collection
Device.
Recording method is, by time slice, two marks (such as shaping variable) to be maintained to each period, are represented respectively
It is following that in the period, whether wish is used and the conventional number of times used in the period wish.
3>Time-based electric quantity consumption monitoring and statistical module
Time-based electric quantity consumption monitoring and statistical module mainly realize two functions：Calculate mobile terminal power consumption and record
Real time electrical quantity.Mobile terminal power consumption measuring and calculating point two parts, Part I is system power consumption, that is, the power consumption speed of mobile cloud application is not used
Rate；Part II is using power consumption speed during mobile cloud application.The measuring and calculating method of mobile terminal cloud application power consumption speed has a variety of,
By taking android system as an example, or even there are part Android flavors to carry using power consumption detection.Conveniently way is
Battery log file (internal bags are used such as in API) is read, cpu distribution during mobile cloud application operation can also be read
Time, the percentage of its use time is therefrom obtained, and represented with (total power consumption * percentages/total time).When user wishes system
When predicting availability, this module obtains current electric quantity and consigns to mobile subscriber's time-space behavior data collector.
Because power consumption is closely related with network state, it is necessary to be surveyed respectively to the power consumption speed under heterogeneous networks state
Calculate.In the network connection type monitoring and statistical module based on geographical position, network state is divided into four types, then calculates speed
Rate has four values to be corresponded with network state.
4>Network connection type monitoring and statistical module based on geographical position
Network connection type monitoring based on geographical position is network state with statistical module focus.This module is net
Network state is divided into four kinds：3g, wifi, 3g with wifi and no 3g with no wifi, time slice, set up record
(table 1).
Table 1 is based on time-space behavior statistical form
Blank cell representative office is in the statistics number under certain period and certain network state in table 1.To user network state
Monitoring can be that (being to be segmented by the hour here) obtains current network state at regular intervals, and having in such as Android exploitations can
Judge network type with API；Trigger, the change of monitoring network state can also be set.Here, it is necessary to the problem solved
It is unstable networks situation.When network state continuously changes in the short time, generally there are two reasons：First, network signal is weak；
Second, mobile device end breaks down.For both of these case, the using effect card either event of mobile cloud application
Barrier, therefore can will directly be divided into no 3g with no wifi, i.e. network down state this period.
5>Mobile subscriber's time-space behavior data collector
The major function of mobile subscriber's time-space behavior data collector be collect three monitoring modulars data, and by its with
Certain data structure is sent to mobile subscriber's time-space behavior data sink in high in the clouds.This module undertakes two functions, to data
Packing function and data flow sending function.Meanwhile, this module is responsible for ensureing the stable transmission of data, record Monitoring Data
Transmission state and realizing is retransmitted, and the function such as resumes.
6>Cloud application mobile terminal
Cloud application mobile terminal is the object of monitoring and the analysis of system and method, is the application journey of intelligent movable equipment end
Sequence.
2. move high in the clouds
Mobile high in the clouds main function is for cloud application provider to provide the pattern analysis of user's time-space behavior and during based on user
The cloud application availability of empty behavior pattern.It covers almost all of evaluation work, and calculates user's reality according to certain algorithm
The cloud application availability of border experience.Mobile high in the clouds includes cloud application, cloud application availability management interface, mobile subscriber's time-space behavior
Data sink, the analysis of cloud application availability and prediction module based on mobile subscriber's time-space behavior pattern, cloud application availability
Model.
1>Mobile subscriber's time-space behavior data sink
Mobile subscriber's time-space behavior data sink is as interactive module of the high in the clouds with intelligent movable equipment end is moved, mainly
Function is exactly to obtain the information of mobile subscriber's time-space behavior data collector and be subject to Simple Calculation and structuring.
The information that this module is received has four parts：(time-based user intention uses secondary cloud application use pattern record
Number and user specify times for using of wish), cloud application power consumption speed, current real time electrical quantity and the network based on time-space behavior
Type state statistic record.Processing computational methods to information are as follows：
Assuming that：With one day for the cycle, time t scope is interval (0:01,24:00).When user intention uses cloud application
Between u (t) (value for 0 or 1 piecewise function), i.e., in t, if user intention, functional value is set to 1 if, on the contrary to be set to 0；Letter
Number Nu (t) represents the wish access times in the cloud application user of t, herein due to being that time slice is recorded, then letter
Number is piecewise function, and value is integer；System power consumption speed in the case of heterogeneous networks is b1,b2,b3,b4；Cloud application power consumption speed
Rate is B1,B2,B3,B4；Current real time electrical quantity Bn；The number of times statistics that different network type state is in t is function Nn1
(t),Nn2(t),Nn3(t),Nn4(t), this four functions are equally piecewise functions and value is shaping.
Calculate：For function Nu (t), in units of hour, it is intended that user intention is participated in as a weighting parameters
Availability calculations process, therefore we define probability density function f (t) and are：
MeetHerein, f (t) value is determined by Nu (t).
For function Nn1(t),Nn2(t),Nn3(t),Nn4(t), equally with one day for the cycle, in units of hour, we
Calculate the user network state distribution probability density function based on space-time：
Wherein i ∈ { 1,2,3,4 }, meet
Finally, mobile subscriber's time-space behavior data sink is available to the cloud application based on mobile subscriber's time-space behavior pattern
Property analysis with prediction module transmission data u (t), f (t), Bi, bi, Bn, pi(t), wherein i ∈ { 1,2,3,4 }.
2>Cloud application availability model
Cloud application availability model preserves the simple availability calculations model in part, and main function is to based on mobile subscriber
The analysis of cloud application availability and the prediction module of time-space behavior pattern provide call parameter.Parameter mainly includes：In four kinds of nets
Mobile cloud application availability A under network type statei, wherein i ∈ { 1,2,3,4 }；The availability that cloud application provider is ensured
(the high availability index as described in SLA SLA) As.
3>The analysis of cloud application availability and prediction module based on mobile subscriber's time-space behavior pattern
The analysis of cloud application availability and core of the prediction module as mobile high in the clouds based on mobile subscriber's time-space behavior pattern
The heart, major function is the parameter according to acquisition, and analysis calculates cloud application availability and result is fed back into cloud application provider.
Wherein, availability analysis calculating is described as follows：
First, the parameter that this module is obtained from other modules is listed below：
User intention uses cloud application time u (t)；T at the time of user sets wish use time0；User intention is used
The probability function f (t) of frequency；User network state distribution probability function p based on space-timei(t)；System power consumption speed bi；Yun Ying
With power consumption speed BiCurrent real time electrical quantity Bn；Rely on the mobile cloud application availability A of network statei；Cloud application provider is ensured
Availability indexes As；Wherein, i ∈ { 1,2,3,4 }.Defined parameters P { battery_charge>0 } mobile end-cell electricity is represented
Measure available probability.
Step1：Obviously, pi(t) separate with f (t), both simultaneous probability are pi(t) * f (t), the event is general
Rate distribution function is：
With one day for the cycle, in units of hour, the value that we calculate the function is as follows：
F is abbreviated as belowi。
Step2：Assuming that user t at the time of wish use time is set0Afterwards until using finishing and will not be charged.Meter
Calculate to try to achieve according to user's requirement and user's time-space behavior custom and expend electricity and pot life in theory, method is following (with pseudo- generation
Representation), wherein initializing variable t is t0。
Assuming that user wishes that the future time period of prediction is T0(being herein one day), above false code is finished note
Record gained moment t is a numerical value, is represented in future time, according to user intention, and prediction gained mobile device electricity exhausts
Moment or at the time of pass through a time cycle, it is designated as T.Calculate user is desirable for before moment T time Tb and user
It is Tt that the total time being desirable for, which is assumed, (in units of hour, both are numerical value)：
Calculate P { battery_charge>0 }=Tb/Tt
Step3：The final computational methods of availability for cloud application are as follows：
We represent mobile cloud application availability with Probability Forms that availability includes two aspects：Mobile cloud application system
Availability AmobileWith mobile terminal battery electric quantity availability Abattery。
In Step2, P { battery_charge>0 } calculating is by representing the P that user behavior is accustomed toiIt is common with power consumption speed
It is same to determine, therefore AbatteryP { battery_charge can directly be taken>0 } as rational characterising parameter.
For Amobile, it is understood that calculating gained F in Step1iDescription is directed to four kinds of different network states, user's
The comprehensive probability of availability of use pattern and user intention in time is (it is to be understood that user anticipates in the range of one day
It is willing to use and residing geographical position meets i-th of network-like probability of state), when calculating user intention f (t) to it in time
Mapped to interval (0,1), calculate network state p residing for useri(t) it is spatially mapped to interval (0,1) when, i.e., at certain
Four kinds of network states are calculated F by one moment with probability description so working asiWhen, we integrate in time to it obtains based on use
The probability of availability of family time-space behavior pattern.Mathematically have：
We provide brief logical and proved：
Due toTherefore t at any time, hasHave againThen it is reciprocity
Formula both sides be integrated for：
According to the addition property of integration, we extract superposition number：
I.e.：
Card is finished.
AiAvailability of four kinds of networks on physical condition (as disposed, signal covering etc.) is represented, these parameters should from cloud
Obtained with availability model module.Ai*FiThe usable probability under certain network condition based on user behavior pattern is represented, while I
Also need to consider the availability indexes As, final A that cloud application provider is ensuredmobileBe calculated as follows formula：
Finally, we integrate mobile cloud application system availability AmobileWith mobile terminal battery electric quantity availability ABattery,From
And obtain the final mobile cloud application availability based on user's time-space behavior pattern：
4>Cloud application availability management interface
Cloud application availability management interface main function is to provide visualization data and result for cloud application provider.Together
When, availability prediction and analysis result are passed to user interface by it, to provide the user the services such as suggestion push.
5>Cloud application
Cloud application module is the analysis object of system and method, and it is the high in the clouds part of cloud application of interest, main to make
With service is provided the user, with certain function.
Illustrate whole system flow below by instantiation：
Whole system flow is as shown in Fig. 2 first, user selects cloud application to be predicted by user interface, and specifies
The time of the cloud application is desirable in the following time.Time-based cloud application use pattern logging modle obtains user
The information and record of setting, pass to mobile subscriber's time-space behavior data collector afterwards.Meanwhile, time-based electric quantity consumption
Network connection type monitoring of the monitoring with statistical module and based on geographical position is with statistical module to mobile subscriber's time-space behavior number
The information for each monitoring and recording is transmitted according to collector.
The data of acquisition are packed and arranged by mobile subscriber's time-space behavior data collector, by network transmission to high in the clouds, and
Transmitting procedure is monitored and fault-tolerant processing.When data transfer is finished, mobile subscriber's time-space behavior data collector is to data
Simple process and calculating are carried out, meanwhile, cloud application availability model prepares the parameter of its preservation, afterwards, and two modules will be available
Property calculate needed for each item data and parameter be transferred to cloud application availability analysis based on mobile subscriber's time-space behavior pattern with
Prediction module.
The analysis of cloud application availability and data of the prediction module according to acquisition based on mobile subscriber's time-space behavior pattern, lead to
Cross parser and calculate the cloud application availability based on user's time-space behavior pattern, and result is transferred to cloud application availability pipe
Manage interface.Cloud application availability management interface can mainly be interacted with integrated multiple function with cloud application provider, meanwhile,
As a result user interface is transferred to, this process is also a network transmission process, data volume is smaller.
An application example is provided below.
In daily life, video/audio class movement cloud application is as a kind of integration of Internet resources, extreme enrichment people
Life.However, the mobile cloud application use environment of the behavior pattern based on user is but restricted by each side, such as network
Environment, battery electric quantity etc..So, in many cases, it can not but be used when user is desirable for cloud application, cause cloud application can use
Property greatly by user's conditioning.
It is desirable that setting up a video/audio class movement cloud application availability analysis system, purport on intelligent family moving platform
Providing the user availability analysis and forecast model for itself custom, be user's reasonable arrangement using the cloud application time with
Place provides help；Simultaneously, it is intended that by the analysis to user behavior pattern and mobile cloud application availability, cloud application is carried
The actual availability of its cloud application service can be obtained for business, and analyzes user behavior pattern distribution, for optimization cloud application service
Data are provided to support.
Based on this method and system, the characteristics of moving cloud application for video/audio class, we have done two aspects to system
Modification.First, the use of video/audio class cloud application requires very high to fluency, fluency be availability determinant it
One.Therefore, we divide 3g network states into unavailable in cloud application availability model is set, and concrete reason is two sides
Face：First, 3g network signals and level of coverage are not reaching to the requirement for seeing video；Secondly, economically see, use 3g flows
Downloading video files cost is too high, therefore almost nobody sees video using 3g networks.Second, general video/audio class cloud application
Download caching function is provided with, if so that network state is unavailable but local when having cached, cloud application is to user
For still can use.So, we add caching push function, i.e., user specify be desirable for the time of this application after, be
The migration and variation united according to user network state in one day, finds out the time that user is desirable for applying but network state does not allow
Section, shifts to an earlier date PUSH message to user and informs that user should be downloaded or caching to audio files in advance.
The characteristic that this application moves cloud application for video/audio class in design builds a set of overall availability parameters
Collect, analyze and prediction scheme.By the monitoring to user behavior pattern, cloud application is more preferably experienced for user suggestion push is provided
And cloud application provider is designed service provision for customer group behavior pattern, cloud application availability is carried in user level
Rise.
The above embodiments are merely illustrative of the technical solutions of the present invention rather than is limited, the ordinary skill of this area
Personnel can modify or equivalent substitution to technical scheme, without departing from the spirit and scope of the present invention, this
The protection domain of invention should be to be defined described in claim.
Claims (6)
1. a kind of cloud application availability Forecasting Methodology based on mobile subscriber's time-space behavior, its step is：
1) intelligent movable equipment end chooses user cloud application to be predicted and its use time t, i.e. user's use pattern, send
Mobile subscriber's time-space behavior data collector to the intelligent movable equipment end；
2) mobile subscriber's time-space behavior data collector is by the user's use pattern information received, the intelligent movable equipment end
Electric quantity consumption statistical information and network state mode statistical information be sent to high in the clouds；
3) data that the high in the clouds is sended over according to mobile subscriber's time-space behavior data collector calculate the cloud to be predicted
The availability in setting usage time interval is applied, and result of calculation is sent to the intelligent movable equipment end；
Wherein, the high in the clouds is according to formulaProbability density function f (t) is calculated, and according to formulaCalculate a user network state distribution probability density function pi(t)；Wherein,Nu (t) is represented
In the wish access times of the cloud application user of t, T1 is the use time cycle, and i-th of network type shape is in t
The number of times statistics of state is function Nni(t), network state sum is n；Then according to formulaCalculate the shifting
The mobile cloud application system availability A at dynamic smart machine endmobile, and calculate the battery electric quantity of the intelligent movable equipment end can
The property used Abattery；According to formula A=Amobile*AbatteryCalculating obtains the prediction that each cloud application to be predicted is selected in user
Availability in time；Wherein, Abattery=Tb/Tt, Tt are the total time that user is desirable for, and Tb is the intelligent movable of prediction
User before equipment electricity exhausts is desirable for the time；The availability indexes that As is ensured by cloud application provider, AiFor the shifting
Dynamic smart machine end is in the probability of availability in i-th kind of network state, FiFor in the range of a cycle user intention use and
Residing geographical position meets i-th of network-like probability of state,AndN is that network state is total
Number.
2. the method as described in claim 1, it is characterised in that the electric quantity consumption statistical information is united including system power consumption speed
Information is counted, cloud application power consumption speed and electricity monitor two tuples { time, battery } in real time；Wherein, time represents certain moment,
Battery represents dump energy.
3. the method as described in claim 1, it is characterised in that the network state mode statistical information is included in a cycle
The network state statistical information of each period；Wherein network state includes：3g networks can use, and wifi network can use, no network
It can use, 3g and wifi network can use simultaneously.
4. a kind of cloud application availability forecasting system based on mobile subscriber's time-space behavior, it is characterised in that including being connected by network
The intelligent movable equipment end connect and high in the clouds；The intelligent movable equipment end includes time-based cloud application use pattern and records mould
Block, time-based electric quantity consumption monitoring and statistical module, network connection type monitoring and statistical module based on geographical position,
Mobile subscriber's time-space behavior data collector；The high in the clouds includes mobile subscriber's time-space behavior data sink；Wherein,
The time-based cloud application use pattern logging modle, for the cloud application to be predicted for choosing user and its is used
Time t, i.e. user's use pattern, are sent to mobile subscriber's time-space behavior data collector；
The time-based electric quantity consumption monitoring and statistical module, the electricity for monitoring the intelligent movable equipment end in real time
Amount, generates electric quantity consumption statistical information, and send it to mobile subscriber's time-space behavior data collector；
The network connection type monitoring and statistical module based on geographical position, for monitoring the intelligent movable equipment in real time
The network state pattern at end, generates network state mode statistical information, and send it to mobile subscriber's time-space behavior number
According to collector；
Mobile subscriber's time-space behavior data collector, for the user's use pattern information that will be received, the intelligent movable is set
The electric quantity consumption statistical information and network state mode statistical information at standby end are sent to mobile subscriber's time-space behavior data
Receiver；
The data that the high in the clouds is received according to mobile subscriber's time-space behavior data sink, calculate the cloud application to be predicted
In the availability of setting usage time interval, and result of calculation is sent to the intelligent movable equipment end；
Wherein, the high in the clouds is according to formulaProbability density function f (t) is calculated, and according to formulaCalculate a user network state distribution probability density function pi(t)；Wherein,Nu (t) is represented
In the wish access times of the cloud application user of t, T1 is the use time cycle, and i-th of network type shape is in t
The number of times statistics of state is function Nni(t), network state sum is n；Then according to formulaCalculate the shifting
The mobile cloud application system availability A at dynamic smart machine endmobile, and calculate the battery electric quantity of the intelligent movable equipment end can
The property used Abattery；According to formula A=Amobile*AbatteryCalculating obtains the prediction that each cloud application to be predicted is selected in user
Availability in time；Wherein, Abattery=Tb/Tt, Tt are the total time that user is desirable for, and Tb is the intelligent movable of prediction
User before equipment electricity exhausts is desirable for the time；The availability indexes that As is ensured by cloud application provider, AiFor the shifting
Dynamic smart machine end is in the probability of availability in i-th kind of network state, FiFor in the range of a cycle user intention use and
Residing geographical position meets i-th of network-like probability of state,AndN is that network state is total
Number.
5. system as claimed in claim 4, it is characterised in that the electric quantity consumption statistical information is united including system power consumption speed
Information is counted, cloud application power consumption speed and electricity monitor two tuples { time, battery } in real time；Wherein, time represents certain moment,
Battery represents dump energy.
6. system as claimed in claim 4, it is characterised in that the network state mode statistical information is included in a cycle
The network state statistical information of each period；Wherein network state includes：3g networks can use, and wifi network can use, no network
It can use, 3g and wifi network can use four kinds of states simultaneously.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410598622.9A CN104468257B (en) | 2014-10-30 | 2014-10-30 | Cloud application availability Forecasting Methodology and system based on mobile subscriber's time-space behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410598622.9A CN104468257B (en) | 2014-10-30 | 2014-10-30 | Cloud application availability Forecasting Methodology and system based on mobile subscriber's time-space behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104468257A CN104468257A (en) | 2015-03-25 |
| CN104468257B true CN104468257B (en) | 2017-10-31 |
Family
ID=52913664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410598622.9A Active CN104468257B (en) | 2014-10-30 | 2014-10-30 | Cloud application availability Forecasting Methodology and system based on mobile subscriber's time-space behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104468257B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899303A (en) * | 2015-06-10 | 2015-09-09 | 杭州祥声通讯股份有限公司 | Cloud big data analysis system applied to rail transportation means |
| CN106227844A (en) * | 2016-07-27 | 2016-12-14 | 深圳市金立通信设备有限公司 | The method of a kind of application recommendation and terminal |
| CN107395404B (en) * | 2017-07-07 | 2018-10-30 | 腾讯科技（深圳）有限公司 | The method and apparatus for prompting network environment for network application, predicting service quality |
| EP3428793A1 (en) | 2017-07-10 | 2019-01-16 | Siemens Aktiengesellschaft | Method for supporting a user in the creation of a software application and computer program using an implementation of the method and programming interface which can be used in such a method |
| CN107682178A (en) * | 2017-08-30 | 2018-02-09 | 国信优易数据有限公司 | A kind of mobile subscriber's online operation behavior Forecasting Methodology and device |
| CN113673080B (en) * | 2021-07-15 | 2023-08-18 | 北京奇艺世纪科技有限公司 | Method, device, equipment and medium for predicting duration of application and training model |
| CN113282518B (en) * | 2021-07-22 | 2021-12-10 | 广州市玄武无线科技股份有限公司 | Method and device for tracking and displaying form behaviors of mobile terminal in real time |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0849909A2 (en) * | 1996-12-18 | 1998-06-24 | Nortel Networks Corporation | Communications network monitoring |
| CN1529959A (en) * | 2000-09-01 | 2004-09-15 | �����շ�������˹�� | System and method for measuring wireless device and network usage and performance metrics |
| CN1629870A (en) * | 2003-06-30 | 2005-06-22 | 微软公司 | Methods and architecture for providing status and forecasts of a user's preference and availability |
| CN101248680A (en) * | 2005-07-05 | 2008-08-20 | 凯锐恩Iq公司 | Rule based data collection and management in a wireless communications network |
| CN102739838A (en) * | 2011-04-06 | 2012-10-17 | 北京双迪广告有限公司 | User behavior analysis method of smart mobile phone application |
-
2014
- 2014-10-30 CN CN201410598622.9A patent/CN104468257B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0849909A2 (en) * | 1996-12-18 | 1998-06-24 | Nortel Networks Corporation | Communications network monitoring |
| CN1529959A (en) * | 2000-09-01 | 2004-09-15 | �����շ�������˹�� | System and method for measuring wireless device and network usage and performance metrics |
| CN1629870A (en) * | 2003-06-30 | 2005-06-22 | 微软公司 | Methods and architecture for providing status and forecasts of a user's preference and availability |
| CN101248680A (en) * | 2005-07-05 | 2008-08-20 | 凯锐恩Iq公司 | Rule based data collection and management in a wireless communications network |
| CN102739838A (en) * | 2011-04-06 | 2012-10-17 | 北京双迪广告有限公司 | User behavior analysis method of smart mobile phone application |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104468257A (en) | 2015-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104468257B (en) | Cloud application availability Forecasting Methodology and system based on mobile subscriber's time-space behavior | |
| KR102083766B1 (en) | Providing per-application resource usage information | |
| US8909358B2 (en) | Method and system for complex smart grid infrastructure assessment | |
| US9148458B2 (en) | Network server arrangement for processing non-parametric, multi-dimensional, spatial and temporal human behavior or technical observations measured pervasively, and related method for the same | |
| CN105760449B (en) | A kind of cloud method for pushing towards multi-source heterogeneous data | |
| Rui et al. | Architecture design of the Internet of Things based on cloud computing | |
| CN105069025A (en) | Intelligent aggregation visualization and management control system for big data | |
| CN109636481A (en) | User's portrait construction method and device towards domestic consumer | |
| CN107562953A (en) | A kind of river information system based on GIS geographical information technologies | |
| CN103336493A (en) | An energy management system | |
| CN109088747A (en) | The management method and device of resource in cloud computing system | |
| CN107820214A (en) | A kind of user trajectory analysis system based on time suboptimal control | |
| CN108829704A (en) | A kind of big data distributed libray Analysis Service technology | |
| CN106354797A (en) | Data recommendation method and device | |
| CN105955715A (en) | Information processing method, device and intelligent terminal | |
| CN103209102B (en) | The Distributed Measurement System of Web service quality and method | |
| CN112464123A (en) | Water quality monitoring data visualization system and method based on micro-service | |
| CN106547622B (en) | Network resource situation presentation data optimization processing method based on computing module | |
| CN104254083B (en) | Predict the method and device of traffic hotspots | |
| Yang et al. | Participant service quality aware data collecting mechanism with high coverage for mobile crowdsensing | |
| Jia et al. | A privacy-sensitive service selection method based on artificial fish swarm algorithm in the internet of things | |
| CN111209329A (en) | Dynamic analysis method, device and system based on full-service volume price change path | |
| CN110445753A (en) | The partition method and device of terminal device abnormal access | |
| CN108171538A (en) | User data processing method and system | |
| Obaidat et al. | Context-aware middleware architectural framework for intelligent smart grid data management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |