CN115794404B - Method for determining UE (user equipment) unavailable period by 5GS (gallium arsenide) network and method for optimizing system by UE - Google Patents
Method for determining UE (user equipment) unavailable period by 5GS (gallium arsenide) network and method for optimizing system by UE Download PDFInfo
- Publication number
- CN115794404B CN115794404B CN202211576861.5A CN202211576861A CN115794404B CN 115794404 B CN115794404 B CN 115794404B CN 202211576861 A CN202211576861 A CN 202211576861A CN 115794404 B CN115794404 B CN 115794404B
- Authority
- CN
- China
- Prior art keywords
- period
- information
- amf
- duration
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- JBRZTFJDHDCESZ-UHFFFAOYSA-N AsGa Chemical compound [As]#[Ga] JBRZTFJDHDCESZ-UHFFFAOYSA-N 0.000 title description 2
- 229910001218 Gallium arsenide Inorganic materials 0.000 title description 2
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000003111 delayed effect Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 17
- 238000004590 computer program Methods 0.000 description 9
- 230000009286 beneficial effect Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
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
- Telephonic Communication Services (AREA)
Abstract
The application discloses a method for determining a UE unavailable period by a 5GS network and a method for optimizing a system by the UE, wherein the method for determining the UE unavailable period by the 5GS network comprises the following steps: the UE initiates capability negotiation supporting the capability of the service unavailability period to the AMF when initially registering; AMF initiates an analysis request for subscribing the UE unavailable period to NWDAF; the NWDAF acquires the state data of the UE according to the time interval; the UE downloads an update file from the AF download system; the UE determines whether the current state data meets the preconfigured state data of the update file and judges whether to delay updating according to a determination result; the UE initiates a mobile/periodical registration update request to the AMF; the AMF forwards the information of the update request to an NWDAF, and the NWDAF predicts the duration by using configuration information of a plurality of UE, updated file information and the duration of the updated file, or simultaneously predicts a proper period of the UE unavailable period by using the historical state data of the current UE and feeds the proper period back to the AMF; the AMF responds to the update request of the UE based on the information of the UE's unavailability period.
Description
Technical Field
The application relates to the technical field of 5GS, in particular to a method for determining a UE (user equipment) unavailable period by a 5GS network and a method for optimizing a system by the UE.
Background
With the rapid development of 5G networks, users can enjoy various services on the UE, however, the service types are increasing, so that some functions or modes of the UE cannot adapt to the system inevitably, and thus, problems in aspects of system loopholes, compatibility, stability and the like are caused, and bad use experience is caused to the users. Therefore, the UE needs to update the system of the UE irregularly to repair system loopholes, optimize partial functions and perfect the UE system, so that the UE system has better safety, compatibility and stability, the system operates more smoothly, and a user obtains better experience.
Generally, when the UE needs to perform system optimization, firstly, a system upgrade file, a patch file or other update files are downloaded from a network end, and after the downloading is completed, the upgrade update can be performed locally, and on one hand, the UE upgrade update may need related operations of a user; on the other hand, since the UE cannot immediately perform the system upgrade update due to insufficient battery power or insufficient storage capacity, etc., a delay is required for performing the related operation. However, whenever the UE performs an upgrade update operation, the UE becomes unavailable for a period of time, i.e., the UE cannot interact with the 5GS for a period of time.
In the prior art, the 5GS cannot acquire the state information that the UE is about to interact with the 5GS for some deterministic reason (such as system upgrade update, etc.) or for a period of time in the future, if the UE is suddenly in an unavailable state without the 5GS acquiring the information in advance, the 5GS cannot take effective measures in time, so that the key service related to the UE in progress in the 5GS is suddenly interrupted, and some important data may be lost. Therefore, before the UE performs the upgrade and update, the UE needs to make the 5GS perceive that the UE needs to perform the upgrade and update operation in advance, so that the 5GS takes corresponding measures to adjust the key service in the UE, in this process, the determination of the UE unavailability period is particularly important, if the UE unavailability period determined by the 5GS is inaccurate, even if the 5GS takes corresponding measures, unnecessary signaling may be caused for the 5GS, normal operation of the service cannot be ensured, and meanwhile, bad user experience may be brought.
Therefore, it is necessary to provide a method for determining the UE unavailability period by the 5GS network so that the 5GS network takes corresponding measures to ensure that the service is performed normally.
Disclosure of Invention
The present application is directed to a method and a computer-readable storage medium for determining a UE unavailability period by a 5GS network, which are beneficial to more accurately determining the UE unavailability period. .
Another object of the present application is to provide a method and a computer-readable storage medium for system optimization by a UE, so that a 5GS network can take corresponding measures to ensure normal operation of a service according to an unavailability period of the UE.
To achieve the above object, the present application provides a method for determining a UE unavailability period by a 5GS network, including:
the UE performs initial registration and initiates capability negotiation supporting the capability of the service unavailability period to the AMF during the initial registration;
the AMF initiates an analysis request for subscribing the unavailable period of the UE to the NWDAF according to the received request of the UE, wherein a request message of the analysis request comprises a time interval for acquiring the state data of the UE;
the NWDAF responds to the AMF request and acquires the state data of the UE according to the time interval;
the UE downloads an update file from the AF download system;
after the downloading is completed, the UE determines whether the current state data meets the preset state data of the update file and judges whether to delay updating according to a determination result;
the UE initiates a mobile/periodical registration update request to the AMF, and a judgment result of whether to delay updating, configuration information of the UE and the pre-configuration state data are carried in a message of the update request;
the AMF forwards the information of the update request to an NWDAF, and the NWDAF predicts the duration of the UE unavailable period by using the configuration information, the updated file information and the duration of the updated file of a plurality of UE stored in a database according to the judging result of whether to delay the update, or simultaneously predicts the duration of the UE unavailable period by using the historical state data of the current UE to obtain proper time periods meeting the preconfigured state data and the duration of the UE unavailable period, and feeds the proper time periods back to the AMF;
the AMF responds to the update request of the UE based on the information of the UE unavailable period.
Optionally, the status data includes battery level and ROM data;
the configuration information of the UE comprises UE hardware information and current system information.
Optionally, the predicting, using the historical state data of the current UE, the suitable period of time to satisfy the preconfigured state data and the duration of the UE non-availability period includes:
preprocessing historical state data of the UE to obtain standard data and dividing the standard data into a training set and a testing set;
training the first prediction model by using standard data in the training set;
verifying the trained first prediction model by using standard data in the test set;
predicting by using the first prediction model passing verification and inversely normalizing the prediction result to obtain state data of a future time point of the UE;
when it appears that status data of a plurality of consecutive future time points all satisfy the preconfigured status data and a time period defined by the plurality of consecutive future time points satisfies a duration of the UE non-availability period, the time period is determined as an appropriate period of the UE non-availability period.
Optionally, the first prediction model is a GRU model, and the calculation formula is as follows:
r=σ(w r [x t ,h t-1 ])
z=σ(w z [x t ,h t-1 ])
h'=tanh(w[x t ,h t-1 ])
wherein r is a reset gate, x t H is the standard data currently input t-1 For the output of a time step on the GRU model, z is an update gate, h t-1 'is the hidden state of the previous time step, h' is the hidden state of the current time step, h t For the output of the GRU model in the current time step, sigma is a sigmoid function, tanh is an activation function, and w r 、w z W is a weight matrix.
Optionally, predicting the duration of the UE unavailable period by using the configuration information, the updated file information, and the duration of the updated file of the plurality of UEs stored in the database includes:
preprocessing each piece of configuration information and updated file information of a plurality of UE respectively to obtain index data, preprocessing the duration of updated files of a plurality of UE to obtain label data, and dividing the index data and the label data into a training set and a testing set;
training a second prediction model by using the training set;
verifying the trained second prediction model by using the test set;
and predicting by using the index data of the current UE and the second prediction model passing verification, and processing the prediction result to obtain the duration of the UE unavailable period.
Optionally, the configuration information of the UE includes UE hardware information and current system information;
the UE hardware information comprises multi-category hardware information, and the current system information comprises current system type and current system version information;
the index data acquisition method comprises the following steps:
respectively setting scoring rules for each type of hardware information;
calculating the score of each piece of hardware information of each UE according to the scoring rule and summing to obtain the total score of each UE;
classifying each UE according to a score interval in which the total score of each UE is located, and setting different values representing the classifications as index data;
different values representing the current system type and the current system version information are set as index data.
Optionally, the AMF responding to the update request of the UE based on the information of the UE unavailability period includes:
transmitting the duration of the UE unavailable period to the UE; or alternatively
Setting a delay timer according to a suitable period of the UE unavailability period;
transmitting the delay timer and the duration of the UE unavailable period to a UE;
when the UE receives the duration of the UE unavailable period, entering an updating flow;
and when the UE receives the delay timer and the duration of the UE unavailable period, entering an updating flow when the delay timer expires.
To achieve the above object, the present application also provides a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements a method for determining a UE unavailability period by a 5GS network as described above.
The present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer readable storage medium and executes the computer instructions to cause the electronic device to perform the method of determining the UE unavailability of the 5GS network as described above.
In the method, the NWDAF obtains the state data of the UE according to the time interval, and can obtain the judging result of whether the UE is delayed to update, the configuration information of the UE and the preconfigured state data of the update file, and the configuration information of a plurality of UEs, the updated file information, the duration of the updated file and the like are stored in the database, so that the NWDAF can predict and obtain the duration of the UE unavailable period based on the related data or obtain the duration of the UE unavailable period and the proper period simultaneously through prediction, thereby being beneficial to more accurately determining the UE unavailable period.
To achieve the above another object, the present application provides a method for performing system optimization for a UE, including a method for determining a UE unavailability period by using a 5GS network as described above, where after the AMF responds to an update request of the UE based on information of the UE unavailability period, the method for performing system optimization for the UE further includes:
the UE initiates a de-registration request to the AMF or initiates the de-registration request in a delayed manner according to the information of the UE unavailable period;
the AMF responds to the de-registration request of the UE and stores the UE context;
the UE installs the update file;
after the UE finishes updating, the UE initiates an initial registration request to the AMF, and the AMF restores the context according to the request of the UE.
To achieve the above object, the present application also provides a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements a method for system optimization of a UE as described above.
The present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer readable storage medium and executes the computer instructions to cause the electronic device to perform the method of system optimization of the UE as described above.
In the method, the 5GS acquires the duration that the UE is about to become unavailable or is unavailable for a period of time in the future, namely the UE unavailable period, so that the 5GS reserves the context information for the UE before the UE enters the actual unavailable period, and therefore, the situation that the 5GS interrupts key services and loses important data in the UE due to the fact that the UE is unavailable under unknown conditions is prevented, and normal operation of the services is ensured. In addition, the 5GS can accurately determine the unavailability period of the UE by utilizing the collected data set, so that the problem that resources cannot be timely and reasonably allocated by the 5GS when the UE interacts with the 5GS again after the advanced upgrade and update is completed is avoided.
Drawings
Fig. 1 is a flowchart of a method for determining a UE unavailability period by the GS network according to embodiment 5 of the present application.
Fig. 2 is a schematic diagram of a DNN model employed in an embodiment of the present application.
Fig. 3 is a flowchart of a method for system optimization by a UE according to an embodiment of the present application.
Detailed Description
In order to describe the technical content, constructional features, achieved objects and effects of the present application in detail, the following description is made in connection with the embodiments and the accompanying drawings.
For ease of understanding the present application, the relevant terms presented herein are explained as follows:
UE: user Equipment, i.e. terminals
5GS:5G System
RAN: radio Access Network radio access networks, i.e. base stations
AMF: access and Mobility Management Function access and mobility management functions
5G MM:5G mobility management 5G mobility management
AF: application Function application function
NWDAF: network Data Application Function network data analysis function
CPU: central Processing Unit central processing unit
GPU: graphics Processing Unit graphic processor
RAM: random acess memory random access memory
ROM: read-Only Memory
Modem: modulator, abbreviations for Modulator and Demodulator
GRU: gated Recurrent Unit gating circulation unit
Example 1
Referring to fig. 1, the present application discloses a method for determining a UE unavailability period by a 5GS network, including:
1. the UE performs initial registration and initiates capability negotiation to the AMF to support its use of the unavailable period capability at the initial registration. Further, for the UE, the method for determining the UE unavailability period by the GS network of the present application 5 may be performed.
Specifically, the UE indicates, in a 5G MM capability cell requesting information, the AMF to support its capability to use the unavailable period, thereby initiating capability negotiation to the current network. The AMF would indicate in the registration accept response message that the current network supports the UE's capability to use the unavailability period in 5 GS.
2. The AMF initiates an analysis request for subscribing the unavailable period of the UE to the NWDAF according to the received request of the UE, wherein a request message of the analysis request comprises a time interval for acquiring the state data of the UE.
For example, the time interval may be set to 5 minutes, i.e. set to NWDAF to acquire the status data of the UE every five minutes.
The status data of the UE may include battery level and ROM data, etc.
3. The NWDAF responds to the request of the AMF and acquires the status data of the UE at intervals. The state data of the UE are continuously acquired according to the time interval, so that the state data can be used as historical state data for prediction later.
4. The UE downloads the update file from the AF download system.
In particular, the update file may be a system update file, a patch file, or other update file, or the like.
5. After the downloading is completed, the UE determines whether the current state data meets the preset state data of the update file and judges whether to delay updating according to the determination result. If the current state data all meet the preconfigured state data of the update file, delay update is not needed, and if the current state data do not all meet the preconfigured state data of the update file, delay update is needed.
Specifically, when downloading a system update file, a patch file, or other update files to the AF, the UE may acquire the requirements of the preconfigured battery power, the preconfigured memory allowance, and the like of different update files, and update the predicted duration, for example: the UE obtains that the battery power of the XX version system is required to be updated by more than or equal to 50%, the memory margin is required to be more than or equal to 5G, and the updating time is expected to be twenty minutes.
If the current battery power of the UE is greater than or equal to the preconfigured battery power (i.e., the current state data satisfies the corresponding preconfigured state data), the current memory margin of the UE is greater than or equal to the preconfigured memory margin (i.e., the current state data satisfies the corresponding preconfigured state data), and if other state data also included also satisfies the corresponding preconfigured state data, the UE does not need to perform delay update, otherwise, the UE needs to perform delay update.
6. The UE initiates a mobile/periodical registration update request to the AMF, and a judgment result of whether to delay updating, configuration information of the UE and pre-configuration state data are carried in a message of the update request.
Specifically, the configuration information of the UE includes UE hardware information and current system information.
UE hardware information may include CPU, GPU, RAM, modem, etc.
The current system information may include a current system type and current system version information.
7. The AMF forwards the information of the update request to the NWDAF, the NWDAF predicts the duration of the UE unavailable period (current UE) by using the configuration information, the updated file information and the duration of the updated file of a plurality of UEs stored in a database according to the judging result of whether to delay the update, or simultaneously predicts the proper period (namely, the duration of the UE unavailable period and the proper period of the UE unavailable period) meeting the preset state data and the duration of the UE unavailable period by using the historical state data of the current UE, and feeds back to the AMF.
It is understood that the pre-configured status data is satisfied, i.e., the pre-configured status data is satisfied within the appropriate period, for example, in the case that the status data includes a battery power and a memory margin, the battery power is required to be equal to or greater than the pre-configured battery power and the memory margin is required to be equal to or greater than the pre-configured memory margin throughout the period. A suitable period that satisfies the duration of the UE's unavailability period refers to a period that is sufficient for the update file to complete the update.
Specifically, the updated file information may be the size of the updated file, which may be carried in the update request message when each UE initiates the mobile/periodic registration update request to the AMF, or may be reported to the current network after each UE completes the update, where the current network stores the update request in the database.
Specifically, the duration of the updated file, that is, the duration of the actual update of each updated file, may be reported to the current network after each UE completes the update, and the current network stores the updated file in the database.
More specifically, when the UE does not need to delay updating, the NWDAF does not need to predict a suitable period of the UE's unavailability based on the current UE's historical state data, but only needs to predict the duration of the UE's unavailability. When the UE needs to be updated with a delay, the NWDAF needs to predict both a suitable period of the UE's unavailable period and a duration of the UE's unavailable period based on the current UE's historical state data.
In some embodiments, predicting, using the historical state data of the current UE, a suitable period of time that satisfies the preconfigured state data and the duration of the UE's non-availability period includes:
preprocessing the historical state data of the UE to obtain standard data and dividing the standard data into a training set and a testing set. Specifically, the state data such as the battery power, the memory allowance and the like of each time interval are preprocessed to obtain standardized data so that training, verification and prediction can be performed by using the first prediction model, and further the state data such as the battery power, the memory allowance and the like of the future time point can be obtained.
The first predictive model is trained using standard data in the training set.
And verifying the trained first prediction model by using standard data in the test set.
And predicting by using the first prediction model passing verification and inversely normalizing the prediction result to obtain the state data of the future time point of the UE.
When it appears that the status data of a consecutive plurality of future time points all satisfy the preconfigured status data and that the time period defined by the consecutive plurality of future time points satisfies the duration of the UE non-availability period, the time period is determined as a suitable period of the UE non-availability period.
After the state data (battery power, memory margin, etc.) of the future time point are obtained, the state data are compared with the pre-configured state data, if each state data does not meet the pre-configured state data (for example, the battery power is greater than or equal to the pre-configured power and the memory margin is greater than or equal to the pre-configured memory margin, etc.), the time point is not met, and if each state data meets the pre-configured state data (for example, the battery power is greater than or equal to the pre-configured power and the memory margin is greater than or equal to the pre-configured memory margin, etc.), the time point is met. If it appears that the status data of a consecutive plurality of future time points all meet the preconfigured status data, indicating that the time period defined by the consecutive plurality of future time points meets the preconfigured status data, then when this time period meets the duration of the unavailability period (ensures that a time period of sufficient update file installation is obtained), it is determined as a suitable time period for the UE's unavailability period.
Taking a time point of 5 minutes as an example, the prediction result shows that the time points of 10, 15, 20, and 25 satisfy the above comparison condition (the status data of each time point can be regarded as an average value of the data of the previous 5 minutes), the AMF can determine that the 20 minutes is a suitable period of the UE's non-availability period.
The first prediction model is a GRU model, and the calculation formula is as follows:
r=σ(w r [x t ,h t-1 ])
z=σ(w z [x t ,h t-1 ])
h'=tanh(w[x t ,h t-1' ])
wherein r is a reset gate, x t For the current input standard data, h t-1 For the output of a time step on the GRU model, z is an update gate, h t-1 'is the hidden state of the previous time step, h' is the hidden state of the current time step, h t For the output of the GRU model in the current time step, sigma is a sigmoid function, the data is converted into a value in the range of 0-1, the value is used as a gating signal, tanh is an activation function, the data is scaled to a value between-1 and 1, and w r 、w z W is a weight matrix, and is used for the weight matrix,representing the multiplication of the matrix corresponding elements.
Specifically, the number of hidden units in the GRU model, namely the number of hidden neurons, is searched from [2,10] with the step length as 1 by using a grid search method, a cross entropy loss function is adopted, a random gradient descent method is used for optimizing an objective function, and the learning rate is 0.03.
In some embodiments, predicting the duration of the UE unavailable period using the configuration information, the updated file information, and the duration of the updated file of the plurality of UEs stored in the database includes:
preprocessing each configuration information and updated file information of a plurality of UE respectively to obtain index data, preprocessing the duration of updated files of a plurality of UE to obtain tag data (output), and dividing the index data and the tag data into a training set and a testing set;
training the second prediction model by using the training set;
verifying the trained second prediction model by using the test set;
and predicting by using the index data of the current UE and the second prediction model passing verification, and processing the prediction result to obtain the duration of the UE unavailable period.
Specifically, the configuration information of the UE includes UE hardware information and current system information;
the UE hardware information includes multi-category hardware information (UE model, RAM, CPU, GPU, etc.), and the current system information includes a current system type (android system, apple, hong, etc.) and current system version information;
the index data acquisition method comprises the following steps:
scoring rules are set for each category of hardware information. For example, scoring rules are 1-10 points, such as: some UE model scores 6 points, RAM scores 8 points, CPU scores 8 points, GPU scores 7 points (only 4 indices are listed here, more indices may be included).
And calculating the score of each piece of hardware information of each UE according to the scoring rule and summing to obtain the total score of each UE. For the above example, the sum of the scores of the respective hardware information of the UE is 27 scores.
Classifying each UE according to a score interval in which the total score of each UE is located, and setting different values representing the respective classifications as index data. For example, UEs with a total score of less than 40% of full score may be classified into a first class; the UEs with total score higher than 40% of full score and lower than 60% of full score are classified into a second class; UEs with total score higher than 60% of full score and lower than 80% of full score are classified into a third class; UEs with a score higher than 80% of full score are classified into a fourth class, and these four classes may be represented by 1, 2, 3, and 4, respectively, so as to facilitate prediction as index data.
Different values representing the current system type and the current system version information are set as index data.
Specifically, the current system type and the current system version information can be comprehensively considered to convert the current system information into numerical values, for example, an android system can be divided into two categories according to the version, 1 and 2 can be used for representing the two categories, an apple system can be divided into two categories according to the version, 3 and 4 can be used for representing the two categories, and a hong Mongolian system can be divided into two categories according to the version, and 5 and 6 can be used for representing the two categories. Then, the current system information can be divided into six categories in the above manner and represented by 1-6, respectively, above.
Specifically, when the updated file information is the size of the updated file, the sizes of the file are required to be unified, such as unified MB unit, so as to avoid that different sizes affect the prediction result of the model.
Referring to fig. 2, specifically, the second prediction model is a DNN model, and the calculation formula is as follows:
Z 1 =f(W 1 X+b)
Z 2 =f(W 2 Z 1 +b)
y=f(W 3 Z 2 +b)
wherein X is index data, y is output data, W is a parameter, and b is a bias term.
In this specific example, the number of hidden layers in DNN is 2, the first hidden layer has 128 neurons, the second hidden layer has 64 neurons, the loss function is a cross entropy loss function, and the Adam optimizer is used to optimize the objective function, and the learning rate is 0.01.
8. The AMF responds to the update request of the UE based on the information of the UE's unavailability period. And the UE may enter the update procedure immediately or with a delay based on the information of the UE's unavailability period.
In some embodiments, the AMF responding to the update request of the UE based on the information of the UE's unavailable period comprises:
transmitting the duration of the UE unavailable period to the UE; or alternatively
Setting a delay timer according to a proper period of the UE unavailable period;
the delay timer and the duration of the UE unavailability period are sent to the UE.
And when the UE receives the duration of the UE unavailable period, entering an updating flow. That is, when the current network only calculates the duration of the UE unavailable period, the sent information of the UE unavailable period is mainly the duration, and when the UE receives the duration of the UE unavailable period, the UE can enter the update procedure.
And when the UE receives the delay timer and the duration of the UE unavailable period, entering an updating flow when the delay timer expires. That is, when the current network calculates the duration of the UE's unavailable period and the appropriate period at the same time, the UE enters the update procedure when the appropriate period is reached or about to be reached.
It should be noted that if the user of the UE sets an update period (for example, only updates between 23 hours at night and 6 hours in the morning), it is not necessary to immediately determine whether the current status data satisfies the preconfigured status data of the update file after the downloading is completed, and it may be determined whether the current status data satisfies the preconfigured status data of the update file and perform the subsequent steps when the update period set by the user arrives.
In the method, the NWDAF obtains the state data of the UE according to the time interval, and can obtain the judging result of whether the UE is delayed to update, the configuration information of the UE and the preconfigured state data of the update file, and the configuration information of a plurality of UEs, the updated file information, the duration of the updated file and the like are stored in the database, so that the NWDAF can predict and obtain the duration of the current UE unavailable period based on the related data or simultaneously obtain the duration of the UE unavailable period and the proper period through prediction, thereby being beneficial to more accurately determining the unavailable period.
Example two
The application discloses a computer readable storage medium having a program stored thereon, which when executed by a processor implements a method for determining UE unavailability by a 5GS network according to embodiment one.
Example III
Embodiments of the present application disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the electronic device to perform the method for determining the UE unavailability period by the 5GS network as described in embodiment one.
Example IV
Referring to fig. 3, the present application discloses a method for system optimization of UE, which includes a method for determining UE unavailability period by the 5GS network according to the first embodiment,
after the AMF responds to the update request of the UE based on the information of the unavailability period, the method for performing system optimization by the UE further includes:
9. the UE initiates a deregistration request to the AMF or delays initiating the deregistration request according to the information of the unavailability period. Specifically, the reason for the request may be indicated as a software update in the message of the deregistration request.
10. The AMF responds to the de-registration request of the UE and saves the UE context.
11. The UE performs the installation of the update file.
12. After the UE finishes updating, the UE initiates an initial registration request to the AMF, and the AMF restores the context according to the request of the UE.
In the method, the 5GS acquires the duration that the UE is about to become unavailable or is unavailable for a period of time in the future, namely the UE unavailable period, so that the 5GS reserves the context information for the UE before the UE enters the actual unavailable period, and therefore, the situation that the 5GS interrupts key services and loses important data in the UE due to the fact that the UE is unavailable under unknown conditions is prevented, and normal operation of the services is ensured. In addition, the 5GS can accurately determine the unavailability period of the UE by utilizing the collected data set, so that the problem that resources cannot be timely and reasonably allocated by the 5GS when the UE interacts with the 5GS again after the advanced upgrade and update is completed is avoided.
Example five
The application discloses a computer readable storage medium having a program stored thereon, which when executed by a processor implements a method for system optimization by a UE according to the fourth embodiment.
Example six
Embodiments of the present application disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the method for system optimization by the UE according to the fourth embodiment.
It should be appreciated that in embodiments of the present application, the processor may be a central processing module (CentralProcessing Unit, CPU), which may also be other general purpose processors, digital signal processors (DigitalSignal Processor, DSP), application specific integrated circuits (Application SpecificIntegrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Those skilled in the art will appreciate that the processes implementing all or part of the methods of the above embodiments may be implemented by hardware associated with computer program instructions, and the program may be stored in a computer readable storage medium, where the program when executed may include processes of embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a Random access memory (Random AccessMemory, RAM), or the like.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
The foregoing disclosure is only illustrative of the preferred embodiments of the present application and is not intended to limit the scope of the claims hereof, as defined by the equivalents of the claims.
Claims (10)
1. A method for determining a UE unavailability period by a 5GS network, comprising:
the UE performs initial registration and initiates capability negotiation supporting the capability of the service unavailability period to the AMF during the initial registration;
the AMF initiates an analysis request for subscribing the unavailable period of the UE to the NWDAF according to the received request of the UE, wherein a request message of the analysis request comprises a time interval for acquiring the state data of the UE;
the NWDAF responds to the AMF request and acquires the state data of the UE according to the time interval;
the UE downloads an update file from the AF download system;
after the downloading is completed, the UE determines whether the current state data meets the preset state data of the update file and judges whether to delay updating according to a determination result;
the UE initiates a mobile/periodical registration update request to the AMF, and a judgment result of whether to delay updating, configuration information of the UE and the pre-configuration state data are carried in a message of the update request;
the AMF forwards the information of the update request to an NWDAF, and the NWDAF predicts the duration of the UE unavailable period by using the configuration information, the updated file information and the duration of the updated file of a plurality of UE stored in a database according to the judging result of whether to delay the update, or simultaneously predicts the duration of the UE unavailable period by using the historical state data of the current UE to obtain proper time periods meeting the preconfigured state data and the duration of the UE unavailable period, and feeds the proper time periods back to the AMF;
the AMF responds to the update request of the UE based on the information of the UE unavailable period.
2. The method for determining the UE unavailability of the 5GS network according to claim 1, wherein,
the status data includes battery power and ROM data;
the configuration information of the UE comprises UE hardware information and current system information.
3. The method for determining the UE unavailability of the 5GS network according to claim 1, wherein,
the predicting, using the historical state data of the current UE, a suitable period of time to satisfy the preconfigured state data and the duration of the UE non-availability period includes:
preprocessing historical state data of the UE to obtain standard data and dividing the standard data into a training set and a testing set;
training the first prediction model by using standard data in the training set;
verifying the trained first prediction model by using standard data in the test set;
predicting by using the first prediction model passing verification and inversely normalizing the prediction result to obtain state data of a future time point of the UE;
when it appears that status data of a plurality of consecutive future time points all satisfy the preconfigured status data and a time period defined by the plurality of consecutive future time points satisfies a duration of the UE non-availability period, the time period is determined as an appropriate period of the UE non-availability period.
4. The method for determining the UE unavailability of the 5GS network according to claim 3, wherein,
the first prediction model is a GRU model, and the calculation formula is as follows:
r=σ(w r [x t ,h t-1 ])
z=σ(w z [x t ,h t-1 ])
h'=tanh(w[x t ,h t-1’ ])
wherein r is a reset gate, x t H is the standard data currently input t-1 For the output of a time step on the GRU model, z is an update gate, h t-1 'is the hidden state of the previous time step, h' is the hidden state of the current time step, h t For the output of the GRU model in the current time step, sigma is a sigmoid function, tanh is an activation function, and w r 、w z W is a weight matrix.
5. The method for determining the UE unavailability of the 5GS network according to claim 1, wherein,
the predicting the duration of the UE unavailable period by using the configuration information, the updated file information, and the duration of the updated file stored in the database includes:
preprocessing each piece of configuration information and updated file information of a plurality of UE respectively to obtain index data, preprocessing the duration of updated files of a plurality of UE to obtain label data, and dividing the index data and the label data into a training set and a testing set;
training a second prediction model by using the training set;
verifying the trained second prediction model by using the test set;
and predicting by using the index data of the current UE and the second prediction model passing verification, and processing the prediction result to obtain the duration of the UE unavailable period.
6. The method for determining the UE unavailability of the 5GS network of claim 5,
the configuration information of the UE comprises UE hardware information and current system information;
the UE hardware information comprises multi-category hardware information, and the current system information comprises current system type and current system version information;
the index data acquisition method comprises the following steps:
respectively setting scoring rules for each type of hardware information;
calculating the score of each piece of hardware information of each UE according to the scoring rule and summing to obtain the total score of each UE;
classifying each UE according to a score interval in which the total score of each UE is located, and setting different values representing the classifications as index data;
different values representing the current system type and the current system version information are set as index data.
7. The method for determining the UE unavailability of the 5GS network of claim 5,
the AMF responding to the update request of the UE based on the information of the UE unavailable period comprises the following steps:
transmitting the duration of the UE unavailable period to the UE; or alternatively
Setting a delay timer according to a suitable period of the UE unavailability period;
transmitting the delay timer and the duration of the UE unavailable period to a UE;
when the UE receives the duration of the UE unavailable period, entering an updating flow;
and when the UE receives the delay timer and the duration of the UE unavailable period, entering an updating flow when the delay timer expires.
8. A computer readable storage medium having stored thereon a program, which when executed by a processor implements a method of determining UE unavailability according to the 5GS network of any of claims 1 to 7.
9. A method for system optimization of a UE, comprising a method for determining a UE unavailability period in a 5GS network according to any of claims 1 to 7,
after the AMF responds to the update request of the UE based on the information of the UE unavailability period, the method for performing system optimization by the UE further includes:
the UE initiates a de-registration request to the AMF or initiates the de-registration request in a delayed manner according to the information of the UE unavailable period;
the AMF responds to the de-registration request of the UE and stores the UE context;
the UE installs the update file;
after the UE finishes updating, the UE initiates an initial registration request to the AMF, and the AMF restores the context according to the request of the UE.
10. A computer readable storage medium, on which a program is stored, characterized in that the program, when being executed by a processor, implements a method for system optimization of a UE according to claim 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211576861.5A CN115794404B (en) | 2022-12-08 | 2022-12-08 | Method for determining UE (user equipment) unavailable period by 5GS (gallium arsenide) network and method for optimizing system by UE |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211576861.5A CN115794404B (en) | 2022-12-08 | 2022-12-08 | Method for determining UE (user equipment) unavailable period by 5GS (gallium arsenide) network and method for optimizing system by UE |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115794404A CN115794404A (en) | 2023-03-14 |
CN115794404B true CN115794404B (en) | 2023-08-01 |
Family
ID=85418093
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211576861.5A Active CN115794404B (en) | 2022-12-08 | 2022-12-08 | Method for determining UE (user equipment) unavailable period by 5GS (gallium arsenide) network and method for optimizing system by UE |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115794404B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115988550B (en) * | 2022-12-16 | 2023-10-24 | 广州爱浦路网络技术有限公司 | UE (user equipment) unavailable period acquisition method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018131984A1 (en) * | 2017-01-16 | 2018-07-19 | 엘지전자(주) | Method for updating ue configuration in wireless communication system and apparatus for same |
CN113301630A (en) * | 2020-02-21 | 2021-08-24 | 联发科技(新加坡)私人有限公司 | Method and apparatus for user equipment reachability after notification in mobile communication |
CN114143805A (en) * | 2020-08-12 | 2022-03-04 | 苹果公司 | Network operation to update user equipment parameters |
-
2022
- 2022-12-08 CN CN202211576861.5A patent/CN115794404B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018131984A1 (en) * | 2017-01-16 | 2018-07-19 | 엘지전자(주) | Method for updating ue configuration in wireless communication system and apparatus for same |
CN113301630A (en) * | 2020-02-21 | 2021-08-24 | 联发科技(新加坡)私人有限公司 | Method and apparatus for user equipment reachability after notification in mobile communication |
CN114143805A (en) * | 2020-08-12 | 2022-03-04 | 苹果公司 | Network operation to update user equipment parameters |
Non-Patent Citations (1)
Title |
---|
面向5G的无线侧网络切片发展与研究;刘珊;韩潇;黄蓉;;邮电设计技术(第01期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN115794404A (en) | 2023-03-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106878952B (en) | Regional personnel number prediction method and device | |
CN108399564B (en) | Credit scoring method and device | |
CN115794404B (en) | Method for determining UE (user equipment) unavailable period by 5GS (gallium arsenide) network and method for optimizing system by UE | |
CN110991875A (en) | Platform user quality evaluation system | |
CN110471671A (en) | Using dispositions method, device, system, equipment and computer readable storage medium | |
CN108805332B (en) | Feature evaluation method and device | |
CN114614989A (en) | Feasibility verification method and device of network service based on digital twin technology | |
CN115705282A (en) | Cell network anomaly detection method and device and computer readable storage medium | |
CN111291868A (en) | Network model training method, device, equipment and computer readable storage medium | |
CN111399875A (en) | Gray scale upgrade control method and device, electronic equipment and storage medium | |
CN115423201A (en) | Method, device and equipment for predicting power generation capacity data and computer readable storage medium | |
CN115827232A (en) | Method, device, system and equipment for determining configuration for service model | |
CN115915237A (en) | Energy-saving measuring and calculating method and device for base station equipment and calculating equipment | |
CN115955700B (en) | Method for enhancing continuity of network slice service and computer readable storage medium | |
CN112652399A (en) | Old man mental state detection terminal and old man mental state detection system | |
CN111381959A (en) | Capacity expansion method and device | |
CN108874431B (en) | Method and device for updating application | |
CN116993396B (en) | Risk early warning method based on vehicle user tag and computer equipment | |
CN112153685B (en) | RRC fault detection method and device | |
CN117726195B (en) | City management event quantity change prediction method, device, equipment and storage medium | |
US20240129801A1 (en) | Systems and methods for determining, monitoring, and predicting application capacity in multiple radio access networks | |
CN112806045B (en) | Pseudo base station identification method, pseudo base station identification device, electronic equipment and computer readable storage medium | |
CN114980304A (en) | Positioning method, equipment, device and storage medium based on measurement report | |
CN112766350A (en) | Method, device and equipment for constructing two-classification model and computer readable storage medium | |
CN116843203A (en) | Service access processing method, device, equipment, medium and product |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |