CN109803285A - A kind of cell processing method, device and the network equipment - Google Patents
A kind of cell processing method, device and the network equipment Download PDFInfo
- Publication number
- CN109803285A CN109803285A CN201711145499.5A CN201711145499A CN109803285A CN 109803285 A CN109803285 A CN 109803285A CN 201711145499 A CN201711145499 A CN 201711145499A CN 109803285 A CN109803285 A CN 109803285A
- Authority
- CN
- China
- Prior art keywords
- user
- target cell
- cell
- probability
- business
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of cell processing method, device and the network equipment, wherein, the cell processing method includes: the state according to the current location of user and the currently used business of user, prediction user is located at portfolio when Target cell, it is located at portfolio when Target cell according to the user, the Target cell is switched to power save mode.The solution of the present invention, cell energy-saving processing can be carried out based on customer analysis, it realizes when carrying out energy-efficient treatment to Target cell, consider that user enters under current practice, be resident and leave influence of the Target cell to cell business volume, to the future network load of more accurate understanding Target cell, the accuracy rate of cell energy-saving is improved, the probability for deviation occur is reduced, improves network performance and user experience.
Description
Technical field
The present invention relates to field of communication technology more particularly to a kind of cell processing methods, device and the network equipment.
Background technique
Energy consumption is reduced, reducing CO2 emission is one of target of sustainable development of modern society.Wireless communication
Network will usually dispose a large amount of base station, these base stations are usually to work without interruption for 24 hours, therefore, daily mobile radio communication
The base station of network will consume a large amount of energy.In order to reduce energy consumption, green communications network is realized, in LTE (Long Term
Evolution, long term evolution) and LTE-A (LTE-Advanced, senior long term evolution) system in have been introduced into power-saving mechanism,
Principle is to close the cell of portion of base stations when network load is lighter, provides service using other base station cells, reaches energy conservation
Purpose.
Specifically, at present frequently with cell energy-saving scheme be, based on the prediction of cell own service amount, if prediction obtains
Cell own service amount is smaller, then switching cell enters power save mode；And if predict to obtain cell own service amount larger, protect
Card cell is in normal operating conditions.
But since prediction cell own service amount is usually to be predicted according to cell history data, there is no consider
Influence of the current practice to cell own service amount, therefore usually there is deviation in existing cell energy-saving scheme, thus shadow
Ring network performance and user experience.
Summary of the invention
The embodiment of the present invention provides a kind of cell processing method, device and the network equipment, to solve existing cell energy-saving
The problem of usually there is deviation in scheme, influences network performance and user experience.
In a first aspect, the embodiment of the invention provides a kind of cell processing methods, comprising:
According to the state of the current location of user and the currently used business of user, industry when user is located at Target cell is predicted
Business amount；
It is located at portfolio when Target cell according to the user, the Target cell is switched to power save mode.
Second aspect, the embodiment of the invention also provides a kind of cell handling devices, comprising:
Prediction module predicts that user is located at for the state according to the current location of user and the currently used business of user
Portfolio when Target cell；
The Target cell is switched to by processing module for being located at portfolio when Target cell according to the user
Power save mode.
The third aspect the embodiment of the invention also provides a kind of network equipment, including memory, processor and is stored in institute
State the computer program that can be run on memory and on the processor, wherein the computer program is by the processor
The step of above-mentioned cell processing method is realized when execution.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program, wherein the computer program realizes the step of above-mentioned cell processing method when being executed by processor.
In embodiments of the present invention, pass through the state according to the current location of user and the currently used business of user, prediction
User is located at portfolio when Target cell, and portfolio when Target cell is located at according to user, Target cell is switched to section
Energy state can carry out cell energy-saving processing based on customer analysis, realize when carrying out energy-efficient treatment to Target cell, consider to work as
User enters, is resident and leaves influence of the Target cell to cell business volume under preceding actual conditions, thus more accurate understanding
The future network of Target cell loads, and improves the accuracy rate of cell energy-saving, reduces the probability for deviation occur, improve network performance and
User experience.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will make below to required in the embodiment of the present invention
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 shows the schematic diagrames of the grid map of the embodiment of the present invention；
The trajectory predictions model of Fig. 2 expression embodiment of the present invention uses schematic diagram；
The traffic forecast model of Fig. 3 expression embodiment of the present invention uses schematic diagram；
Fig. 4 indicates the flow chart of the cell processing method of the embodiment of the present invention；
Fig. 5 indicates the schematic diagram of the resource utilization mapping model of the embodiment of the present invention；
Fig. 6 indicates the flow chart of the cell treatment process of the embodiment of the present invention；
One of the structural schematic diagram of cell handling device of Fig. 7 expression embodiment of the present invention；
Fig. 8 shows the second structural representations of the cell handling device of the embodiment of the present invention；
Fig. 9 indicates the structural schematic diagram of the network equipment of the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment to facilitate the understanding of the present invention, first to the present embodiments relate to the following contents explain
It is bright.
Target cell: the process object of the embodiment of the present invention, predicted whether by customer analysis wake up or close
Cell.
User presence information: indicating the relationship between user and Target cell, i.e. user is located at Target cell, or
User is not located at Target cell.For example, if the present embodiments relate to user quantity be m, user presence information
It is described using matrix E:Wherein such as e1Indicate depositing between a kind of m user and Target cell
In state relation.In another example if m is equal to 4, e1It may be expressed as:It illustrates that user 1,2 and 3 is located at Target cell, uses
Family 4 is not located at (or leaving) Target cell；Alternatively, e1It may be expressed as:It illustrates that user 1 and 3 is located at Target cell,
User 2 and 4 is not located at (or leaving) Target cell；Etc..
Trajectory predictions model: is pre-established according to the track data (position data) of user's history, adjacent track number
There are prefixed time intervals between.For the embodiment of the present invention using cell granularity as minimum grid unit, include in cell is all
Location point all regards a node (Node) as.Map minimum particle size (N number of cell face of acquisition trajectories data is used for by setting
Product), sizing grid and tracking quantity can be changed.When map grid is bigger, the area of each grid node is bigger, history
Otherness between track is with regard to smaller.For example, as shown in Figure 1, when grid map includes cell Node n1To n7When, track T1It can
{ n is expressed as using cell Node1,n2,n3,n6}。
In order to guarantee the accuracy rate of trajectory predictions model, in acquisition trajectories data, for being less than or waiting in every track
It can be deleted in the track of 2 nodes.Since within the scope of a step, user can be only moved to several cells of surrounding, therefore, right
In can not the cell that reaches of a step be, for example, to Missing Data Filling, fill method can be carried out inquire existing track, if having one it is complete
Contain the reachable path between two cell Nodes in whole track, and the similar track ratio including this section of path is high, then it will be by
The filling of this path, this includes reverse track.
Specifically, trajectory predictions model can be based on Bayesian inference frame, basic ideas have currently been sent out based on user
Raw trip track TpUsing the destination of bayesian algorithm prediction user, wherein the destination of user is njProbability are as follows:
Wherein, G indicates the destination sum of user.Destination can be more than certain thresholding by screening user's residence time
The region of (such as 1h) identifies that the residence time the long more is likely to be destination, but may miss brief stay.
P(d∈nj) indicate that destination is njPrior probability, numerical value passes through counting user destination whithin a period of time
In njHistorical track number ratio obtain, i.e., Indicate that destination locations are located at njInterior history rail
Mark sum, StotalIndicate the total number of tracks of all historical datas of user.The only priori of destination that once reached of user is general
Rate is just not zero, that is to say, that the grid node that only user once reached is possible to be predicted to be the current purpose of user
Ground.It should be noted that prior probability be with time correlation, when data volume is larger, can distinguish counting user working day and
The track at weekend.
P(Tp|d∈nj) it is posterior probability, indicate that known destination is njWhen have passed through track TpProbability, in other words,
Expression destination is grid node njWhen, entire trip track can be with current track Tp(i.e. trip track is by current for stapled section
Track Tp) probability.Specifically, posterior probability P (Tp|d∈nj) may be expressed as:Wherein
Refer to that destination is njTotal number of tracksIn contain track TpTrack number.
It should be pointed out that being probability in all purposes ground of user according to the destination that trajectory predictions model prediction obtains
Supreme good.After being predicted using destination of the trajectory predictions model to user, the optional mesh for predicting to obtain
Underground the highest track of switching probability, next location point of track is exactly future position (i.e. Target cell).
It is shown in Figure 2, it can using the process that trajectory predictions model obtains the probability that user reaches future position are as follows:
Step 21: obtaining the track data of user, i.e. position data is single in detail；
Step 22: according to the track data of user, utilizing the destination of trajectory predictions model prediction user；
Step 23: (next location point of current point is the different tracks from user current point to destination in this track
Future position) in, select the maximum track of cell transition probability；
Step 24: being based on the maximum track of cell transition probability, determine that user reaches the probability of future position.
For example, it is assumed that user is in current point nc, predict that its destination is nj, user has different from current point to destination
Track (current point n in this trackcNext location point be future position), if from ncTo njDifferent tracks in cell transfer
The track of maximum probability are as follows: P (nc→nj)=P (nc→nc+1)·P(nc+1→nc+2)····P(nJ=1→nj), then it can determine
User is from current point ncThe probability for reaching future position is P (nc→nc+1)。
For the transition probability between adjacent two cell Node, obtained using Markov transition probabilities model.Such as it is small
Area node naTo nbTransition probability can be equal to, in historical trajectory data library include cell Node { na,nbTrace number divided by
All includes cell Node naTrace number.Therefore, it for each pair of adjacent mesh in grid map, estimated can calculate
Their transition probability, and these transition probabilities are stored in a two-dimensional transfer matrix, wherein one-dimensional correspond to grid
Current state, another dimension correspond to next state.If using symbol MijIndicate transfer matrix, then the corresponding transfer matrix of Fig. 1
Are as follows:
Wherein, in MijIn, p12Indicate cell Node n1To n2Transition probability, p54Indicate cell Node n5To n4Transfer
Probability, etc..
Traffic forecast model: is pre-established according to the business datum of user's history.
It should be noted that the type of service of user typically is provided with following two features: it is sudden, user at a time certain
A place is to have stronger rule under compared with Long grain time (being greater than 30min) than more random using the behavior of which APP
Property, for example see that video class business is more at home user's every night, see that news is relatively more in subway, but in shorter granularity
Time (do not have predictability under 1min to 5min), but with user current state and mood depending on, type of service
Sudden and randomness it is larger；Duration, user is changeable using the time span of certain APP, from several seconds to several
Hour be likely to, the type of service that current time uses is relevant with previous moment, such as certain user when commuting daily all
TV play is seen in subway, and from the beginning sees tail in riding process, and for another example certain user checks wechat every night, and every
The secondary duration is 1 to 2 hour, for this kind of user, it is easy to predict to obtain subsequent time from the type of service of previous moment
The type of service of (such as 15min).It therefore, can be by the service class of user according to the sudden and duration of customer service type
Business diagnosis under business diagnosis and stationary state that type prediction is divided under motion state.
Specifically, the traffic forecast model in the embodiment of the present invention can be divided into the traffic forecast model under user movement state
With the traffic forecast model under user's stationary state.According to traffic forecast model carry out traffic forecast when, first according to
Family historical behavior habit and real-time track data judge the state of user, judge that it is motion state or static shape
State.Under default situations, user is kept in motion, except non-user reaches some destination, then when determining that user enters destination
Enter stationary state.
Under motion state, the type of service that user uses is related to the transfer of its track.Business under user movement state
After the state and user of prediction model and the currently used business of user are switched to next future position from current location, business shape
State switching probability is related.For example, big city opens video and watches movie after on a user to subway (cell switching), arrive
Turn off video after standing to get off.The probability that this event follows single user to occur is very high.It is used when if defining user location variation
The state switching probability of certain type of service a isThenIt may be expressed as:
Wherein,Indicate that user generates the thing switched using service condition when position changes
Number of packages, N (ni→ni+1) indicate that user is switched to the event number of next future position from current location.It is general according to service condition switching
Rate, in conjunction with the currently used type of service of user, user uses the probability of certain type of service after predictable prefixed time interval.
According to the duration of business, the traffic forecast model under user's stationary state is model relevant to timing, with
The probability of business is used in current location after prefixed time interval in the current location at family, prefixed time interval and user's history
Correlation, can be predicted user preset time interval after use certain type of service probability.If certain user is in daily fixed time period
It is more consistent using recording for app, then it is assumed that the user has preferable duration, the user strong for duration, to history service
Type gives higher weight, otherwise it is assumed that previous time period weight is larger.In this way, under static state, prefixed time interval
User may be expressed as: using the probability of certain type of service a afterwards
Wherein, Ni,t,aIndicate user in position ni+1The event number of type of service a is used with prefixed time interval t, A is indicated
The sum of type of service corresponding to user.
It is shown in Figure 3, it can using the process of the type of service of user after traffic forecast model prediction prefixed time interval
Are as follows:
Step 31: obtaining the current location of user and the state of currently used business, i.e. business datum is single in detail；
Step 32: according to user's history behavioural habits and real-time track data, judging that user is motion state or static
State；
Step 33: when the user is at rest, based on the traffic forecast model under user's stationary state, predicting user
Type of service after prefixed time interval；
Step 34: when user is kept in motion, based on the traffic forecast model under user movement state, in conjunction with user
Present type of service predicts the type of service after user preset time interval.
Below in conjunction with attached drawing, description is described in detail to the embodiment of the present invention.
Shown in Figure 4, the embodiment of the invention provides a kind of cell processing methods, are applied to the network equipment, the network
Equipment is for handling cell.The cell processing method includes the following steps:
Step 401: according to the state of the current location of user and the currently used business of user, it is small to predict that user is located at target
Portfolio when area.
It should be noted that the user in this step is specifically related at least one user.
Wherein, predict user be located at Target cell when portfolio when, may be with Target cell phase in order to sufficiently choose
The user of pass can first determine that target area, and the user's (one or more) being currently in target area be determined as
Analyze user.The target area generally includes at least the adjacent area of Target cell and Target cell, in this way in target area
User can be with Target cell strong correlation, and there are entrance, resident and a possibility that leave Target cell.Corresponding, step 401 can wrap
It includes:
Determine at least one user being currently in target area；
It is every after prediction prefixed time interval according to the track data of each of at least one user received user
One user is located at the probability of Target cell；
According to the shape of the position of Target cell, the current location of each user and the currently used business of each user
State predicts portfolio when each user is located at Target cell after prefixed time interval.
Step 402: being located at portfolio when Target cell according to user, Target cell is switched to power save mode.
In the embodiment of the present invention, Target cell is switched to energy conservation by portfolio when being located at Target cell according to user
When state, it can be considered based on pre-set business amount threshold value.Pre-set business amount threshold value is pre- according to the practical business situation of Target cell
First it is arranged, such as when the total traffic of Target cell is greater than pre-set business amount threshold value, it is ensured that Target cell, which is in, to be waken up
State, and when the total traffic of Target cell is less than or equal to pre-set business amount threshold value, Target cell can be switched to energy conservation
State.
Specifically, step 402 can include:
It is located at the probability of Target cell according to user presence information, each user and each user is located at target
Portfolio when cell determines that the total traffic of Target cell is greater than the probability of pre-set business amount threshold value；
It, will when the total traffic of Target cell is greater than the probability of pre-set business amount threshold value less than the first predetermined probabilities threshold value
Target cell is switched to power save mode.
Wherein, each user refers to the user being located in target area.First predetermined probabilities threshold value is according to target
The practical business situation of cell is pre-set, may be, for example, 2%, 3% etc., only guaranteed when the total traffic of Target cell is big
When the probability is relatively small for pre-set business amount threshold value, influence to user after Target cell energy conservation can be just reduced.And if target is small
The probability that the total traffic in area is greater than pre-set business amount threshold value is greater than or equal to the first predetermined probabilities threshold value, then to make Target cell
It is normal operating conditions in waking up.
The cell processing method of the embodiment of the present invention, portfolio when by determining that user is located at Target cell, works as user
When portfolio when positioned at Target cell meets preset condition, Target cell is switched to power save mode, it can be based on user point
Analysis carry out cell energy-saving processing, realize to Target cell carry out energy-efficient treatment when, consider current practice under user enter,
It is resident and leaves influence of the Target cell to cell business volume, so that the future network of more accurate understanding Target cell is negative
It carries, improves the accuracy rate of cell energy-saving, reduce the probability for deviation occur, improve network performance and user experience.
In the embodiment of the present invention, the probability that user is located at Target cell can be carried out pre- based on preset trajectory predictions model
It surveys.Therefore each after prediction prefixed time interval according to the track data of each user received in the embodiment of the present invention
The process that a user is located at the probability of Target cell can are as follows:
According to the track data of each user received and preset trajectory predictions model, each use is predicted
The destination at family；
It calculates each user and arrives at the destination possible a variety of cell transition probabilities from current location, and from a variety of cells
Maximum cell transition probability is selected in transition probability；
According to maximum cell transition probability, determine that each user is located at the probability of Target cell.
Optionally, portfolio when user is located at Target cell can be predicted based on preset traffic forecast model.Cause
In this embodiment of the present invention, according to the position of the Target cell, each user current location and each described in
The state of the currently used business of user predicts industry when each described user after the prefixed time interval is located at Target cell
The process of business amount can are as follows:
Currently made according to the position of the Target cell, the current location of each user and each described user
State and preset traffic forecast model with business, each described user is located at after predicting the prefixed time interval
The probability of various businesses type is used when Target cell；
Using the probability of various businesses type when being located at Target cell according to user described in each, and according to history number
Generated flow, calculates each described user and is located at mesh when according to each obtained described user using various businesses type
Mark portfolio when cell.
Wherein, preset traffic forecast model can be the traffic forecast model or the static shape of user under user movement state
Traffic forecast model under state, depending on the virtual condition of user.Traffic forecast model under user movement state is worked as with user
After preceding state and user using business is switched to next future position from current location, service condition switching probability is related.With
Preset time in the current location of traffic forecast model and user under the stationary state of family, prefixed time interval and user's history
The probability correlation of business is used behind interval in current location.In this way, considering that user makes under motion state and under static state
The case where with business, predictablity rate can be improved.
In the embodiment of the present invention, when multiple users are related to Target cell, according to user presence information, each
The probability that user is located at Target cell is located at portfolio when Target cell with each user, determines the total business of Target cell
The process that amount is greater than the probability of pre-set business amount threshold value can are as follows:
It is located at the probability of Target cell according to user presence information, each user and each user is located at target
Portfolio when cell, calculates a variety of possible total traffics of Target cell and each possible total traffic is corresponding general
Rate；
According to a variety of possible total traffics of Target cell and the corresponding probability of each possible total traffic, calculate
The total traffic of Target cell is greater than the probability of pre-set business amount threshold value.
In the following, illustrating that the total traffic for calculating Target cell is greater than the probability of pre-set business amount threshold value by specific example
Process.
For example, if pre-set business amount threshold value is vTh, the number of users being currently in target area is m, each user
The number for the business of can be used is s i.e. type of service s kind, vijIndicate that user i uses type of service app's (j) in Target cell
Flow, then the traffic matrix V of m user may be expressed as:
uijIndicate that user i uses the probability of type of service app (j) in Target cell, then the probability matrix U of m user can
It indicates are as follows:
wiIndicate portfolio when user i is located at Target cell, then the traffic matrix W of m user are as follows:
State matrix E of the m user in Target cell are as follows:
piIndicate that user i is located at the probability of Target cell, then the probability matrix P of m user are as follows:
Therefore, the total traffic matrix S of Target cell are as follows:
That is, the possible total traffic of Target cell shares 2 in this examplemKind.Wherein, 2mKind total traffic is corresponding
Probability matrix be p (ei)=E*p.
Should be noted is, as calculating p (ei) when, not simple matrix calculates.For example, if number of users m is equal to 4,
Then S1Corresponding Probability p (e1) are as follows: p (e1)=p1·p2·p3(1-p4)。
That is the total traffic matrix of Target cell and its corresponding relationship of probability are as follows:
Based on this, the total traffic of Target cell is greater than Probability p (S > V of pre-set business amount threshold valueTH) are as follows:
Total traffic in the embodiment of the present invention, when carrying out energy-efficient treatment to Target cell, in addition to considering Target cell
Outside probability greater than pre-set business amount threshold value, further it is also possible to consider the resource utilizations of Target cell, only small in target
The resource utilization of probability and Target cell that the total traffic in area is greater than pre-set business amount threshold value all meets the feelings of preset condition
Under condition, Target cell is just switched to power save mode.
In the resource utilization for determining Target cell, can be determined based on preset resource utilization mapping model.
The preset resource utilization mapping model is obtained using historical data training, shown in Figure 5, and input parameter is at least wrapped
Cell total traffic, community user number, cell history Reference Signal Received Power RSRP average value and temporal information are included (when current
Between, week, holiday information) etc., output parameter be local resource utilization rate.Wherein, when model training, training data can be according to
Fixed cycle updates, and corresponding model also will be updated.Due to user demand portfolio it is certain in the case where, the location of user
Signal strength will affect its signal-to-noise ratio for receiving signal, and then influence its resource occupation to wireless network, for example, LTE system
In, more Physical Resource Block (physical can be distributed in the case that user demand portfolio is certain, when user's noise is poor
Resource block, abbreviation PRB), to guarantee that subscriber traffic demand is met, therefore, when by cell total traffic
When size is mapped to 2/3/4G resource utilization ratio, needs to consider the current signal strength of user, ideally should
Modeling training, but complexity and calculation amount in view of realizing are carried out in the history RSRP of each cell to each user, it can benefit
With all user's histories of cell (such as one month) RSRP average value.
Specifically, calculating a variety of possible total traffics of Target cell and the corresponding probability of each total traffic
On the basis of, the process that Target cell is switched to power save mode can are as follows:
The total traffic of maximum probability in a variety of possible total traffics of Target cell is determined as the total of Target cell
Portfolio；
According to the historical data of Target cell, the number of users and Target cell after prefixed time interval in Target cell are predicted
RSRP average value；
According to the RSRP average value of number of users, Target cell in the total traffic of Target cell, Target cell and preset
Temporal information and preset resource utilization mapping model after time interval, determine the resource utilization of Target cell；
When the total traffic of Target cell is greater than the probability of pre-set business amount threshold value less than the first predetermined probabilities threshold value, and mesh
When marking the resource utilization of cell less than the second predetermined probabilities threshold value, Target cell is switched to power save mode.
Wherein, the second default resource utilization threshold is preset according to the practical business situation of Target cell.
In the following, being handled in conjunction with Fig. 6 from cell of two angles of off-line learning and on-line prediction to the embodiment of the present invention
Process is illustrated.
Off-line learning: firstly, obtaining historical position data, history service data and cell history respectively from the detailed list of data
RSRP, KPI, the data in the detailed list of the data can real-time update；Then, feature training is carried out to historical position data, obtains rail
Mark prediction model, and feature training is carried out to history service data, traffic forecast model is obtained, and to cell history RSRP, KPI
Cell business volume is carried out to the training of resource utilization mapping model, obtains resource utilization mapping model.
On-line prediction: firstly, obtaining real time position data and real time traffic data respectively from the detailed list of data；Secondly, root
According to real time position data and trajectory predictions model, user trajectory prediction is carried out, and according to real time traffic data and business
Prediction model carries out subscriber traffic prediction；Again, summarize each user in predicting, carry out the prediction of target cell traffic amount, i.e., in advance
The total traffic for surveying Target cell is greater than the probability of pre-set business amount threshold value；Then, according to the total traffic of Target cell, and
Resource utilization mapping model predicts the resource utilization of Target cell；Finally, being preset when the total traffic of Target cell is greater than
The probability of traffic volume threshold is less than the first predetermined probabilities threshold value, and the resource utilization of Target cell is less than the second predetermined probabilities threshold
When value (meeting preset condition), Target cell is switched to power save mode.
Cell processing method of the invention is illustrated in above-described embodiment, below in conjunction with embodiment and attached drawing to this
The cell handling device of invention is illustrated.
Shown in Figure 7, the embodiment of the invention also provides a kind of cell handling devices, comprising:
Prediction module 71 predicts user position for the state according to the current location of user and the currently used business of user
Portfolio when Target cell；
Processing module 72 switches the Target cell for being located at portfolio when Target cell according to the user
To power save mode.
The cell handling device of the embodiment of the present invention, portfolio when by determining that user is located at Target cell, works as user
When portfolio when positioned at Target cell meets preset condition, Target cell is switched to power save mode, it can be based on user point
Analysis carry out cell energy-saving processing, realize to Target cell carry out energy-efficient treatment when, consider current practice under user enter,
It is resident and leaves influence of the Target cell to cell business volume, so that the future network of more accurate understanding Target cell is negative
It carries, improves the accuracy rate of cell energy-saving, reduce the probability for deviation occur, improve network performance and user experience.
Optionally, shown in Figure 8 in the embodiment of the present invention, the prediction module 71 includes:
First determination unit 711, for determining at least one user being currently in target area；
First predicting unit 712, the track for each of at least one user user according to receiving
Data, each described user is located at the probability of Target cell after predicting prefixed time interval；
Second predicting unit 713, for according to the position of the Target cell, the current location of each user and
The state of each currently used business of user, each described user is located at target after predicting the prefixed time interval
Portfolio when cell.
Further, shown in Figure 4, the processing module 72 includes:
Second determination unit 721, for being located at Target cell according to user presence information, each described user
Probability and each described user are located at portfolio when Target cell, and it is default to determine that the total traffic of the Target cell is greater than
The probability of traffic volume threshold；
Processing unit 722, the probability for being greater than pre-set business amount threshold value for the total traffic when the Target cell are less than
When the first predetermined probabilities threshold value, the Target cell is switched to power save mode.
Optionally, second determination unit 721 is specifically used for:
It is located at probability and each described user of Target cell according to user presence information, each described user
Portfolio when positioned at Target cell calculates a variety of possible total traffics of the Target cell and each possible total industry
The corresponding probability of business amount；
According to a variety of possible total traffics of the Target cell and the corresponding probability of each possible total traffic,
The total traffic for calculating the Target cell is greater than the probability of pre-set business amount threshold value.
Optionally, the processing unit 722 is specifically used for:
The total traffic of maximum probability in a variety of possible total traffics of the Target cell is determined as the target
The total traffic of cell；
According to the historical data of the Target cell, the user after the prefixed time interval in the Target cell is predicted
Several and the Target cell Reference Signal Received Power RSRP average value；
According to the RSRP of number of users, the Target cell in the total traffic of the Target cell, the Target cell
Temporal information and preset resource utilization mapping model after average value and the prefixed time interval, determine the mesh
Mark the resource utilization of cell；
When the total traffic of the Target cell is greater than the probability of pre-set business amount threshold value less than the first predetermined probabilities threshold value,
And the resource utilization of the Target cell less than the second predetermined probabilities threshold value when, the Target cell is switched to energy saving shape
State.
Optionally, first predicting unit 712 is specifically used for:
According to the track data of each user received and preset trajectory predictions model, predict each
The destination of a user；
It calculates each described user and arrives at the destination possible a variety of cell transition probabilities from current location, and from described
Maximum cell transition probability is selected in a variety of cell transition probabilities；
According to the maximum cell transition probability, determine that each described user is located at the probability of Target cell.
Optionally, second predicting unit 713 is specifically used for:
Currently made according to the position of the Target cell, the current location of each user and each described user
State and preset traffic forecast model with business, each described user is located at after predicting the prefixed time interval
The probability of various businesses type is used when Target cell；
Using the probability of various businesses type when being located at Target cell according to user described in each, and according to history number
Generated flow, calculates each described user and is located at mesh when according to each obtained described user using various businesses type
Mark portfolio when cell.
Optionally, the preset traffic forecast model be user movement state under traffic forecast model or user it is quiet
The only traffic forecast model under state；The state of traffic forecast model and the currently used business of user under user movement state,
And after user is switched to next future position from current location, service condition switching probability is related；Industry under user's stationary state
In current location after prefixed time interval in the current location of business prediction model and user, prefixed time interval and user's history
Use the probability correlation of business.
In addition, the embodiment of the invention also provides a kind of network equipment, including memory, processor and it is stored in described deposit
On reservoir and the computer program that can run on the processor, wherein the computer program is executed by the processor
When can realize each process of above-mentioned cell processing method embodiment, and identical technical effect can be reached, to avoid repeating, this
In repeat no more.
Specifically, the embodiment of the invention also provides a kind of network equipment, the network equipment includes total referring to shown in 9
Line 91, transceiver 92, antenna 93, bus interface 94, processor 95 and memory 96.
In the embodiment of the present invention, the network equipment further include: be stored on memory 96 and can be transported on processor 95
Capable computer program, wherein the computer program can realize following steps when being executed by processor 95:
According to the state of the current location of user and the currently used business of user, industry when user is located at Target cell is predicted
Business amount；
It is located at portfolio when Target cell according to the user, the Target cell is switched to power save mode.
In Fig. 9, bus architecture (is represented) with bus 91, bus 91 may include any number of interconnection bus and
Bridge, bus 91 will include the one or more processors represented by processor 95 and the various electricity of memory that memory 96 represents
Road links together.Bus 91 can also be by the various other of such as peripheral equipment, voltage-stablizer and management circuit or the like
Circuit links together, and these are all it is known in the art, and therefore, it will not be further described herein.Bus connects
Mouth 94 provides interface between bus 91 and transceiver 92.Transceiver 92 can be an element, be also possible to multiple element, than
Such as multiple receivers and transmitter, the unit for communicating over a transmission medium with various other devices is provided.Through processor 95
The data of processing are transmitted on the radio medium by antenna 93, and further, antenna 93 also receives data and by data transmission
To processor 95.
Processor 95 is responsible for management bus 91 and common processing, can also provide various functions, including timing, periphery connects
Mouthful, voltage adjusting, power management and other control functions.And memory 96 can be used for storage processor 95 and execute behaviour
Used data when making.
Optionally, processor 95 can be CPU, ASIC, FPGA or CPLD.
The embodiment of the present invention also provides a kind of computer readable storage medium, is stored thereon with computer program, wherein institute
The each process for realizing above-mentioned cell processing method embodiment when computer program is executed by processor is stated, and can be reached identical
Technical effect, to avoid repeating, which is not described herein again.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media, can be by any side
Method or technology realize that information stores.Information can be computer readable instructions, data structure, the module of program or other numbers
According to.The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory
(SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory techniques, CD-ROM are read-only
Memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or
Other magnetic storage devices or any other non-transmission medium, can be used for storage can be accessed by a computing device information.According to
Herein defines, and computer-readable medium does not include temporary computer readable media (transitory media), such as modulation
Data-signal and carrier wave.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, computer, clothes
Business device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (11)
1. a kind of cell processing method characterized by comprising
According to the state of the current location of user and the currently used business of user, business when user is located at Target cell is predicted
Amount；
It is located at portfolio when Target cell according to the user, the Target cell is switched to power save mode.
2. the method according to claim 1, wherein described currently used according to the current location of user and user
The state of business, prediction user are located at portfolio when Target cell, comprising:
Determine at least one user being currently in target area；
The track data of each of at least one user user according to receiving is predicted every after prefixed time interval
One user is located at the probability of Target cell；
According to the position of the Target cell, the current location of each user and each described currently used industry of user
The state of business predicts portfolio when each described user after the prefixed time interval is located at Target cell.
3. according to the method described in claim 2, it is characterized in that, business when being located at Target cell according to the user
Amount, is switched to power save mode for the Target cell, comprising:
It is located at the probability of Target cell according to user presence information, each described user and each described user is located at
Portfolio when Target cell determines that the total traffic of the Target cell is greater than the probability of pre-set business amount threshold value；
It, will when the total traffic of the Target cell is greater than the probability of pre-set business amount threshold value less than the first predetermined probabilities threshold value
The Target cell is switched to power save mode.
4. according to the method described in claim 3, it is characterized in that, described according to user presence information, described in each
The probability that user is located at Target cell is located at portfolio when Target cell with each described user, determines the Target cell
Total traffic be greater than pre-set business amount threshold value probability, comprising:
It is located at the probability of Target cell according to user presence information, each described user and each described user is located at
Portfolio when Target cell calculates a variety of possible total traffics of the Target cell and each possible total traffic
Corresponding probability；
According to a variety of possible total traffics of the Target cell and the corresponding probability of each possible total traffic, calculate
The total traffic of the Target cell is greater than the probability of pre-set business amount threshold value.
5. according to the method described in claim 4, it is characterized in that, described preset when the total traffic of the Target cell is greater than
When the probability of traffic volume threshold is less than the first predetermined probabilities threshold value, the Target cell is switched to power save mode, comprising:
The total traffic of maximum probability in a variety of possible total traffics of the Target cell is determined as the Target cell
Total traffic；
According to the historical data of the Target cell, predict number of users after the prefixed time interval in the Target cell and
The Reference Signal Received Power RSRP average value of the Target cell；
It is average according to the RSRP of number of users, the Target cell in the total traffic of the Target cell, the Target cell
Temporal information and preset resource utilization mapping model after value and the prefixed time interval, determine that the target is small
The resource utilization in area；
When the total traffic of the Target cell is greater than the probability of pre-set business amount threshold value less than the first predetermined probabilities threshold value, and institute
When stating the resource utilization of Target cell less than the second predetermined probabilities threshold value, the Target cell is switched to power save mode.
6. according to the method described in claim 2, it is characterized in that, at least one described user that the basis receives
The track data of each user, each described user is located at the probability of Target cell after predicting prefixed time interval, comprising:
According to the track data of each user received and preset trajectory predictions model, each institute is predicted
State the destination of user；
It calculates each described user and arrives at the destination possible a variety of cell transition probabilities from current location, and from described a variety of
Maximum cell transition probability is selected in cell transition probability；
According to the maximum cell transition probability, determine that each described user is located at the probability of Target cell.
7. according to the method described in claim 2, it is characterized in that, the position according to the Target cell, each institute
The current location of user and the state of each currently used business of user are stated, is predicted each after the prefixed time interval
A user is located at portfolio when Target cell, comprising:
According to the position of the Target cell, the current location of each user and each described currently used industry of user
The state of business and preset traffic forecast model, each described user is located at target after predicting the prefixed time interval
The probability of various businesses type is used when cell；
Using the probability of various businesses type when being located at Target cell according to user described in each, and obtained according to historical data
Generated flow when each arrived user uses various businesses type, calculating each described user, to be located at target small
Portfolio when area.
8. the method according to the description of claim 7 is characterized in that the preset traffic forecast model is user movement state
Under traffic forecast model or the traffic forecast model under user's stationary state；
Wherein, the state of the traffic forecast model under user movement state and the currently used business of user and user are from current
After position is switched to next future position, service condition switching probability is related；
It is pre- in the current location of traffic forecast model and user under user's stationary state, prefixed time interval and user's history
If the probability correlation of business is used after time interval in current location.
9. a kind of cell handling device characterized by comprising
Prediction module predicts that user is located at target for the state according to the current location of user and the currently used business of user
Portfolio when cell；
The Target cell is switched to energy conservation for being located at portfolio when Target cell according to the user by processing module
State.
10. a kind of network equipment, including memory, processor and it is stored on the memory and can transports on the processor
Capable computer program, which is characterized in that such as claim 1 to 8 is realized when the computer program is executed by the processor
Any one of described in cell processing method the step of.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
It realizes when being executed by processor such as the step of cell processing method described in any item of the claim 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711145499.5A CN109803285A (en) | 2017-11-17 | 2017-11-17 | A kind of cell processing method, device and the network equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711145499.5A CN109803285A (en) | 2017-11-17 | 2017-11-17 | A kind of cell processing method, device and the network equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109803285A true CN109803285A (en) | 2019-05-24 |
Family
ID=66555111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711145499.5A Pending CN109803285A (en) | 2017-11-17 | 2017-11-17 | A kind of cell processing method, device and the network equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109803285A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954732A (en) * | 2019-12-10 | 2021-06-11 | 中国移动通信有限公司研究院 | Network load balancing method, device, equipment and storage medium |
| CN113132945A (en) * | 2019-12-30 | 2021-07-16 | 中国移动通信集团辽宁有限公司 | Energy-saving scheduling method and system for railway private network base station cell |
| CN113766523A (en) * | 2020-06-02 | 2021-12-07 | 中国移动通信集团河南有限公司 | Network resource utilization rate prediction method and device for serving cell and electronic equipment |
| WO2022001565A1 (en) * | 2020-06-30 | 2022-01-06 | 华为技术有限公司 | Communication prediction-based energy saving method and apparatus |
| CN114980282A (en) * | 2021-02-24 | 2022-08-30 | 上海华为技术有限公司 | Power adjustment method and network management server |
| CN115022965A (en) * | 2022-07-25 | 2022-09-06 | 中国联合网络通信集团有限公司 | Cell positioning method, device, electronic equipment and storage medium |
| US11576118B1 (en) | 2021-08-04 | 2023-02-07 | Nokia Solutions And Networks Oy | Optimizing usage of power using switch off of cells |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5572221A (en) * | 1994-10-26 | 1996-11-05 | Telefonaktiebolaget Lm Ericsson | Method and apparatus for detecting and predicting motion of mobile terminals |
| CN102137404A (en) * | 2010-01-26 | 2011-07-27 | 中兴通讯股份有限公司 | Method and system for realizing energy saving of wireless communication network |
| CN102196460A (en) * | 2010-03-11 | 2011-09-21 | 三星电子株式会社 | Apparatus and method for reducing energy consumption in wireless communication system |
| CN102740426A (en) * | 2012-06-05 | 2012-10-17 | 中兴通讯股份有限公司 | Base station energy-saving method, device and system |
| CN103889001A (en) * | 2014-03-13 | 2014-06-25 | 南京邮电大学 | Method for self-adaptive load balancing based on future load prediction |
-
2017
- 2017-11-17 CN CN201711145499.5A patent/CN109803285A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5572221A (en) * | 1994-10-26 | 1996-11-05 | Telefonaktiebolaget Lm Ericsson | Method and apparatus for detecting and predicting motion of mobile terminals |
| CN102137404A (en) * | 2010-01-26 | 2011-07-27 | 中兴通讯股份有限公司 | Method and system for realizing energy saving of wireless communication network |
| CN102196460A (en) * | 2010-03-11 | 2011-09-21 | 三星电子株式会社 | Apparatus and method for reducing energy consumption in wireless communication system |
| CN102740426A (en) * | 2012-06-05 | 2012-10-17 | 中兴通讯股份有限公司 | Base station energy-saving method, device and system |
| CN103889001A (en) * | 2014-03-13 | 2014-06-25 | 南京邮电大学 | Method for self-adaptive load balancing based on future load prediction |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112954732A (en) * | 2019-12-10 | 2021-06-11 | 中国移动通信有限公司研究院 | Network load balancing method, device, equipment and storage medium |
| CN112954732B (en) * | 2019-12-10 | 2023-04-07 | 中国移动通信有限公司研究院 | Network load balancing method, device, equipment and storage medium |
| CN113132945A (en) * | 2019-12-30 | 2021-07-16 | 中国移动通信集团辽宁有限公司 | Energy-saving scheduling method and system for railway private network base station cell |
| CN113766523A (en) * | 2020-06-02 | 2021-12-07 | 中国移动通信集团河南有限公司 | Network resource utilization rate prediction method and device for serving cell and electronic equipment |
| CN113766523B (en) * | 2020-06-02 | 2023-08-01 | 中国移动通信集团河南有限公司 | Method and device for predicting network resource utilization rate of serving cell and electronic equipment |
| WO2022001565A1 (en) * | 2020-06-30 | 2022-01-06 | 华为技术有限公司 | Communication prediction-based energy saving method and apparatus |
| CN114980282A (en) * | 2021-02-24 | 2022-08-30 | 上海华为技术有限公司 | Power adjustment method and network management server |
| CN114980282B (en) * | 2021-02-24 | 2024-04-09 | 上海华为技术有限公司 | Power adjustment method and network management server |
| US11576118B1 (en) | 2021-08-04 | 2023-02-07 | Nokia Solutions And Networks Oy | Optimizing usage of power using switch off of cells |
| EP4132120A1 (en) * | 2021-08-04 | 2023-02-08 | Nokia Solutions and Networks Oy | Optimizing usage of power using switch off of cells |
| CN115022965A (en) * | 2022-07-25 | 2022-09-06 | 中国联合网络通信集团有限公司 | Cell positioning method, device, electronic equipment and storage medium |
| CN115022965B (en) * | 2022-07-25 | 2024-04-09 | 中国联合网络通信集团有限公司 | Cell positioning method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109803285A (en) | A kind of cell processing method, device and the network equipment | |
| CN104931041B (en) | A kind of location sequence Forecasting Methodology based on user trajectory data | |
| Liu et al. | Toward QoI and energy-efficiency in Internet-of-Things sensory environments | |
| Obaidat et al. | Smart cities and homes | |
| Stojmenovic | Fog computing: A cloud to the ground support for smart things and machine-to-machine networks | |
| Reddy et al. | A genetic algorithm for energy efficient fog layer resource management in context-aware smart cities | |
| Jan et al. | PASCCC: Priority-based application-specific congestion control clustering protocol | |
| Marjanović et al. | Energy-aware and quality-driven sensor management for green mobile crowd sensing | |
| CN105009475B (en) | In view of the ambulant method and system predicted for admission control and Resource Availability of user equipment (UE) | |
| Fouad et al. | Distributed and scalable computing framework for improving request processing of wearable IoT assisted medical sensors on pervasive computing system | |
| Tan et al. | Energy harvesting aware topology control with power adaptation in wireless sensor networks | |
| EP2905931B1 (en) | Method and apparatus for determining data flow rate of service access port | |
| CN110430583A (en) | A kind of SSB beam optimization configuration method and device | |
| Pino-Povedano et al. | Selective forwarding for energy-efficient target tracking in sensor networks | |
| Ashraf et al. | Energy management in harvesting enabled sensing nodes: Prediction and control | |
| Wala et al. | Energy efficient data collection in smart cities using iot | |
| Jaitawat et al. | Battery and supercapacitor imperfections modeling and comparison for RF energy harvesting wireless sensor network | |
| Said | A bandwidth control scheme for reducing the negative impact of bottlenecks in IoT environments: simulation and performance evaluation | |
| Essalhi et al. | A new clustering‐based optimised energy approach for fog‐enabled IoT networks | |
| Sun et al. | QoI-aware energy management in Internet-of-Things sensory environments | |
| Lovén et al. | A dark and stormy night: Reallocation storms in edge computing | |
| Surenther et al. | Enhancing data transmission efficiency in wireless sensor networks through machine learning-enabled energy optimization: A grouping model approach | |
| Lee et al. | BUCKET: scheduling of solar-powered sensor networks via cross-layer optimization | |
| Le et al. | A power manager with balanced quality of service for energy-harvesting wireless sensor nodes | |
| CN115099476B (en) | Electric power Internet of things asynchronous scheduling method based on cyclic difference theory |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190524 |
|
| RJ01 | Rejection of invention patent application after publication |