CN113316087B - Dynamic paging method based on terminal position prediction in LTE system - Google Patents
Dynamic paging method based on terminal position prediction in LTE system Download PDFInfo
- Publication number
- CN113316087B CN113316087B CN202110567526.8A CN202110567526A CN113316087B CN 113316087 B CN113316087 B CN 113316087B CN 202110567526 A CN202110567526 A CN 202110567526A CN 113316087 B CN113316087 B CN 113316087B
- Authority
- CN
- China
- Prior art keywords
- core network
- information
- paging
- user side
- prediction
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W68/00—User notification, e.g. alerting and paging, for incoming communication, change of service or the like
- H04W68/02—Arrangements for increasing efficiency of notification or paging channel
Abstract
The invention belongs to the field of communication, and particularly relates to a dynamic paging method based on terminal position prediction in an LTE (Long term evolution) system, which comprises the following steps: acquiring information of a user side in real time, inputting the acquired information into a trained deep learning model, and predicting a moving path of the user side; sending the path to a core network; the user side detects the current position information in real time, and when the position information is consistent with the predicted path sent to the core network, the core network sends a paging signaling to the predicted position to complete the paging process; when the user terminal detects that the deviation exists between the cell where the user terminal is located and the prediction path, the user terminal initiates a tracking area updating process, the updated tracking area is sent to a core network, and the core network executes a dynamic paging mode when falling back after receiving information to complete a paging process; the invention predicts the moving path of the user terminal, and the core network only sends signaling to the predicted cell after the prediction is correct, thereby effectively reducing the paging signaling overhead of mobility management in the IDLE state.
Description
Technical Field
The invention belongs to the field of communication, and particularly relates to a dynamic paging method based on terminal position prediction in an LTE (Long term evolution) system.
Background
Mobile communication systems require appropriate mechanisms for mobility management of the terminals in order to communicate messages to the terminals as soon as possible when there is a page. Typical flows of mobility management include location updates and paging. With the rapid development of mobile communication and the popularization of intelligent terminals, the signaling overhead of the related flow of the mobile terminal is greatly increased, it is very important to manage the signaling consumption in the mobile communication to prevent the channel resource from being consumed, and it is important to study how to reduce the signaling consumption in the mobility management.
In the LTE system, mobility management is handled by a mobility management entity in a non-access stratum, and mainly includes two procedures, namely Tracking Area Update (TAU) and Paging (Paging). In current LTE systems, if a UE in IDLE (IDLE mode) state leaves a currently stored TAL, the UE initiates a TAU procedure to the core network, informing the core network of the new location and requesting the network to reallocate the TAL. When paging needs to be transmitted to a mobile user, a core network requires all cells in a TAL where the mobile user is located to send paging signaling, the paging mode can page the UE within the first time under the condition that no extra information about the UE exists, but only one signaling is responded finally because the UE is only possibly in one cell in the TAL, and other signaling has no effect, so that the resource waste of an LTE system is caused.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a dynamic paging method based on terminal position prediction in an LTE system, which comprises the following steps: acquiring information of a user side in real time, inputting the acquired information into a trained deep learning model, and predicting a moving path of the user side; sending the predicted moving path to a core network of the LTE system; the user side detects the current position information in real time, when the detected position information is consistent with the predicted path sent to the core network, the user side does not carry out any processing, and the core network sends a paging signaling to the predicted position to complete the paging process; when the user terminal detects that the deviation exists between the cell where the user terminal is located and the prediction path, the user terminal initiates a tracking area updating process and sends the updated tracking area to the core network, and the core network executes a dynamic paging mode during fallback after receiving information to complete a paging process.
Preferably, the acquired user side information includes the position information and time of the user side; the location information is the cell ID where the ue is currently located.
Preferably, the process of predicting the moving path of the user terminal includes: firstly, setting a threshold value at a user side; and when the cell ID information and the time stamp information collected by the user side are greater than a set threshold value, calculating the path prediction so as to obtain a path prediction result.
Furthermore, a model for predicting the path is a dynamic Bayesian model; the process of making the prediction includes: acquiring the position information of the current user side in real time, and inputting the current position information into a trained dynamic Bayesian model to predict the movement path of the user side; the process of training the dynamic Bayesian model comprises the following steps: acquiring a historical input sequence of a user side, wherein the sequence comprises historical position information and a historical moving path of the user side; inputting the historical input sequence into a dynamic Bayesian model to preprocess the input data, and linearizing the position information; constructing a conditional probability table according to the preprocessing result; respectively constructing two neural networks according to the conditional probability table, wherein the first neural network is a model obtained from a historical input sequence, the input information of an input layer of the model is linearized original information, and an output layer outputs a predicted position; the second neural network is a model from a real position to an end position, the input information of the model is a plurality of pairs of original positions and end positions, and the output layer outputs the predicted position information; and performing weighted summation on the output values of the two neural networks to obtain a sequence of predicted positions.
Preferably, the information of the user terminal and the process of training the model are all completed at the user terminal.
Preferably, the process of updating the tracking area by the user side includes: when the terminal detects that the current position corresponds to the predicted position, the tracking area is updated according to the predicted position, otherwise, the user terminal initiates a position updating request signaling to the core network, after the core network receives the position updating request signaling sent by the terminal, the core network replies a position updating receiving signaling, and the signaling comprises a new tracking area list distributed by the core network for the terminal and is synchronized with the core network again.
Preferably, the process of the core network performing the dynamic paging mode in the fallback includes: after the last paging or tracking area updating, the core network determines the cell where the user terminal UE is located, and the cell is taken as a relevant cell; at the moment, the user terminal UE enters an idle mode and freely moves; when the UE leaves the current tracking area list, initiating a tracking area update command, and updating the relevant cells through the command; if the moving amplitude of the UE is smaller, the paging is directly carried out in the related cell of the UE, if the paging does not obtain the response, the paging is carried out in other cells of the TA where the related cell is located, and if the paging does not obtain the response, the paging is carried out in all the cells of other TAs of the current TAL.
The invention predicts the moving path of the user terminal, and the core network only sends signaling to the predicted cell after the prediction is correct, thereby effectively reducing the paging signaling overhead of mobility management in the IDLE state.
Drawings
Fig. 1 is a schematic diagram of the division of tracking areas of a non-access stratum of an LTE system according to the present invention;
fig. 2 is a flowchart of a fallback mode in an LTE system according to the present invention;
fig. 3 is a flowchart of a prediction model in an LTE system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In a tracking area division structure of a non-access stratum of an LTE system, as shown in fig. 1, an area covered by one base station is called a Cell (Cell), and each Cell has a unique Cell number. Several adjacent cells form a Tracking Area (TA), and each Tracking Area has a unique identification number. The plurality of adjacent Tracking areas together further form a Tracking Area List (TAL, Tracking Area List), the two Tracking Area lists are allowed to have overlapped parts, and the Tracking Area List stored in the mobile terminal should contain the Tracking Area where the Tracking Area is located.
A dynamic paging method based on terminal position prediction in an LTE system comprises the following steps: acquiring information of a user side in real time, inputting the acquired information into a trained deep learning model, and predicting a moving path of the user side; sending the predicted moving path to a core network of the LTE system; the user side detects the current position information in real time, when the detected position information is consistent with the predicted path sent to the core network, the user side does not carry out any processing, and the core network sends a paging signaling to the predicted position to complete the paging process; when the user terminal detects that the deviation exists between the cell where the user terminal is located and the prediction path, the user terminal initiates a tracking area updating process and sends the updated tracking area to the core network, and the core network executes a dynamic paging mode during fallback after receiving information to complete a paging process.
The prediction part aims at predicting the future position of the UE through the historical information of the UE by using an algorithm based on deep learning and training, the algorithm proposes to use a dynamic Bayesian model (DBN), the invention does not use a specific algorithm to realize the function of the prediction part, but provides a reasonable scheme to fuse the algorithm into a frame of mobility management, and the scheme can unload huge calculation in the training process to the terminal and reduce the operation burden of a core network.
Preferably, the model for predicting the path is a dynamic Bayesian model; the process of making the prediction includes: acquiring the position information of the current user side in real time, and inputting the current position information into a trained dynamic Bayesian model to predict the movement path of the user side; the process of training the dynamic Bayesian model comprises the following steps: acquiring a historical input sequence of a user side, wherein the sequence comprises historical position information and a historical moving path of the user side; the method comprises the steps of inputting a historical input sequence into a dynamic Bayesian model, preprocessing input data, linearizing position information because the position information is generally nonlinear, carrying out Taylor expansion on the sequence, and then obtaining linearized data by disassembling sub-polynomials by using a method of logarithm solving two sides of an equation. The result of the preprocessing is then used to obtain a conditional probability table, for example, to determine the probability that the next state will appear at location B under the condition of location a. Two neural networks are respectively constructed according to the conditional probability table, wherein the neural network comprises an input layer, a hidden layer and an output layer, the first network refers to a model obtained from a historical input sequence, the input layer of the neural network is original information after linearization, and the output layer outputs a predicted position. The second network is a model from a real position to an end position, a plurality of pairs of original positions and end positions are input into an input layer, and predicted position information is output from an output layer. And then, carrying out weighted summation on the output values of the two neural networks to obtain a sequence of the predicted position, wherein the weighted value is dynamically changed in training, the maximum likelihood error is calculated each time during training to judge the accuracy of the current model, then the weighted values of the two neural networks are dynamically adjusted, and the obtained weighted value is the final result when the maximum likelihood error is less than 0.01.
A specific implementation mode for training a deep learning algorithm is disclosed, wherein the algorithm model is a dynamic Bayesian model, and the method comprises the following steps: and giving a historical input sequence, and inputting the given historical input sequence into a dynamic Bayesian model to estimate the condition distribution of the terminal at a certain moment. Here the conditional distribution of the terminal position at a certain time instant is recursively calculated by means of a recursive bayesian estimation, i.e. given a historical input sequence. In the estimation process of the input sequence by adopting a recursive Bayesian estimation method, a target is not directly estimated, but is estimated by taking the target as the condition distribution of the terminal position; representing a final target by weighting two neural networks in the process of carrying out condition distribution estimation, wherein the first network refers to a model obtained from a historical input sequence, and the second network refers to a model from a real position to an end position of the model; the two networks are connected together, effectively making the two neural networks as a whole a feed-forward recurrent neural network. The hidden state characterization of the image is learned by inputting raw data into a feed-forward recurrent neural network and can be used as a network memory for passing from one time step to the next.
The fallback part is used for enabling a fallback mechanism to enable the system to continue to operate normally when the prediction provided by the prediction part is wrong. When the prediction fails, the UE predicts again and needs a certain time to collect the required information, and in the vacuum period, the invention adopts a dynamic paging mode to process paging, and the dynamic paging mode can effectively reduce the consumption of paging signaling under the condition that the UE has small moving amplitude.
As shown in fig. 2, the moving range of the mobile terminal is usually not large for a limited time, and if the core network directly instructs all cells in the TAL to send paging signaling when paging the UE, a certain amount of waste is caused. Thus, in the present invention, a new paging scheme is employed. After paging or TAU, the core network determines the cell where the UE is located, which is referred to herein as the relevant cell. The UE thereafter enters the IDLE state and is free to move. If the UE leaves the current TAL, it initiates a tracking area update command TAU, and the relevant cell is updated accordingly. As shown in fig. 2, the location information about the UE known by the core network includes: if the mobility amplitude of the UE is not large, the cell related to the UE and the TAL where the UE is located may be directly paged first, and if no response is obtained, the cell is paged next to other cells in the tracking area TA where the cell related is located, and if no response is still obtained, the cell is paged in all cells of other TAs of the current TAL. According to the paging method, the required signaling quantity does not exceed the traditional mode, and the signaling loss is effectively reduced.
The prediction frame in the invention aims to accurately locate the cell where the UE is located when the paging arrives, if the prediction is correct, the core network only needs to send a paging signaling to complete the paging process, thereby effectively reducing the signaling consumption, and the flow chart of the prediction part is shown in figure 3.
The prediction mechanism adopted by the invention can be divided into two parts, namely a part at the UE side and a part at the core network side. On the UE side, the UE needs to collect information that helps the prediction analysis, such as the geographical location, time, etc. of the user. The geographic location can be represented by longitude and latitude, but in the LTE system, the prediction only needs to be accurate to the cell level, so the mobile terminal only needs to collect the cell ID when collecting the geographic information, which can reduce the cost when transmitting the prediction information to the core network.
After enough information is collected, the UE starts to train by using a preset algorithm, a path which the UE possibly travels is predicted after the training is finished, the path comprises J cells, and the result is transmitted to a core network after the prediction is finished. After that, the UE detects whether the current actual location is consistent with the predicted location sent to the core network, and if so, the prediction is correct, and at this time, the UE does not perform any processing. If the UE detects that the deviation exists between the cell where the UE is located and the predicted cell, the prediction is wrong, the UE initiates a TAU flow at the moment, the prediction before the core network is informed of being invalid, and the system falls back to the dynamic paging mode.
On the other hand, after the core network receives the prediction information transmitted by the UE, the core network starts a prediction mode, the core network only monitors a new tracking area update message at the moment, when the core network is in the prediction mode, if the core network does not receive any message transmitted by the UE, the default prediction position of the core network is correct, and the core network considers that the prediction cell is the cell where the UE is located at the moment. If the core network receives the TAU sent by the UE, indicating that the prediction is wrong, then the mobility management returns to the dynamic paging mode and considers the last cell with correct prediction to be the relevant cell.
Under the prediction framework, information acquisition and training of the prediction model are completed on the UE side, and the participation of a core network is not needed during the information acquisition and training, so that a training link with higher complexity is independently completed by the UE, and thus, the calculation amount of the core network can be effectively reduced, and the signaling interaction between the UE and the core network can be reduced. In addition, the chip manufacturing process of the UE is getting smaller and smaller nowadays, so that the UE can save certain power consumption while having stronger computing power, and the prediction mode can effectively utilize resources in various aspects.
The above-mentioned embodiments, which further illustrate the objects, technical solutions and advantages of the present invention, should be understood that the above-mentioned embodiments are only preferred embodiments of the present invention, and should not be construed as limiting the present invention, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. A dynamic paging method based on terminal position prediction in an LTE system is characterized by comprising the following steps: acquiring information of a user side in real time, inputting the acquired information into a trained deep learning model, and predicting a moving path of the user side; sending the predicted moving path to a core network of the LTE system; the user side detects the current position information in real time, when the detected position information is consistent with the predicted path sent to the core network, the user side does not carry out any processing, and the core network sends a paging signaling to the predicted position to complete the paging process; when the user side detects that the deviation exists between the cell where the user side is located and the prediction path, the user side initiates a tracking area updating process and sends the updated tracking area to the core network, and the core network executes a dynamic paging mode during fallback after receiving information to complete a paging process;
the process of predicting the moving path of the user terminal comprises the following steps: firstly, setting a threshold value at a user side; the method comprises the steps that a user side collects cell ID information and timestamp information of the user side in the moving process, and when the cell ID information and the timestamp information collected by the user side are larger than a set threshold value, path prediction calculation is carried out, so that a path prediction result is obtained; the process of performing the calculation of the path prediction includes: acquiring the position information of the current user side in real time, and inputting the current position information into a trained dynamic Bayesian model to predict the movement path of the user side; the process of training the dynamic Bayesian model comprises the following steps: acquiring a historical input sequence of a user side, wherein the sequence comprises historical position information and a historical moving path of the user side; inputting the historical input sequence into a dynamic Bayesian model to preprocess the input data, and linearizing the position information; constructing a conditional probability table according to the preprocessing result; respectively constructing two neural networks according to the conditional probability table, wherein the first neural network is a model obtained from a historical input sequence, the input information of an input layer of the model is linearized original information, and an output layer outputs a predicted position; the second neural network is a model from a real position to an end position, the input information of the model is a plurality of pairs of original positions and end positions, and the output layer outputs predicted position information; carrying out weighted summation on the output values of the two neural networks to obtain a sequence of predicted positions;
the process of the core network executing the dynamic paging mode when falling back comprises the following steps: after the last paging or tracking area updating, the core network determines the cell where the user terminal UE is located, and the cell is taken as a relevant cell; at the moment, the user terminal UE enters an idle mode and freely moves; when the UE leaves the current tracking area list, initiating a tracking area updating command, and updating the relevant cells through the command; if the moving amplitude of the UE is smaller, the paging is directly carried out in the related cell of the UE, if the paging does not obtain the response, the paging is carried out in other cells of the TA where the related cell is located, and if the paging does not obtain the response, the paging is carried out in all the cells of other TAs of the current TAL.
2. The dynamic paging method based on terminal location prediction in LTE system according to claim 1, wherein the obtained ue information includes location information and time of the ue; the location information is the cell ID where the user terminal is currently located.
3. The dynamic paging method based on terminal location prediction in the LTE system as claimed in claim 1, wherein the processes of obtaining the information of the user end and training the model are both performed at the user end.
4. The dynamic paging method based on terminal location prediction in LTE system as claimed in claim 1, wherein the process of updating tracking area at the ue comprises: when the terminal detects that the current position corresponds to the predicted position, the tracking area is updated according to the predicted position, otherwise, the user terminal initiates a position updating request signaling to the core network, after the core network receives the position updating request signaling sent by the terminal, the core network replies a position updating receiving signaling, and the signaling comprises a new tracking area list distributed by the core network for the terminal and is synchronized with the core network again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567526.8A CN113316087B (en) | 2021-05-24 | 2021-05-24 | Dynamic paging method based on terminal position prediction in LTE system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567526.8A CN113316087B (en) | 2021-05-24 | 2021-05-24 | Dynamic paging method based on terminal position prediction in LTE system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113316087A CN113316087A (en) | 2021-08-27 |
| CN113316087B true CN113316087B (en) | 2022-05-10 |
Family
ID=77374556
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110567526.8A Active CN113316087B (en) | 2021-05-24 | 2021-05-24 | Dynamic paging method based on terminal position prediction in LTE system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113316087B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117255409A (en) * | 2022-06-10 | 2023-12-19 | 展讯通信（上海）有限公司 | Paging method and device, terminal equipment, network equipment and chip |
| CN115225140B (en) * | 2022-07-15 | 2023-05-05 | 广州爱浦路网络技术有限公司 | Satellite paging method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106851604A (en) * | 2015-12-07 | 2017-06-13 | 中国联合网络通信集团有限公司 | A kind of Traffic prediction method and device of mobile communications network |
| WO2018024131A1 (en) * | 2016-08-03 | 2018-02-08 | Huawei Technologies Co., Ltd. | Location tracking in wireless networks |
| CN111095821A (en) * | 2017-08-01 | 2020-05-01 | 维尔塞特公司 | Handover based on predicted network conditions |
| WO2020114606A1 (en) * | 2018-12-07 | 2020-06-11 | Telefonaktiebolaget Lm Ericsson (Publ) | User equipment tracking and paging area selection in wireless communication systems |
| CN112243590A (en) * | 2018-06-07 | 2021-01-19 | 华为技术有限公司 | Method for mobility based on prediction and pre-preparation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109479256B (en) * | 2016-07-12 | 2021-10-26 | 瑞典爱立信有限公司 | Method and apparatus for including data in paging messages |
-
2021
- 2021-05-24 CN CN202110567526.8A patent/CN113316087B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106851604A (en) * | 2015-12-07 | 2017-06-13 | 中国联合网络通信集团有限公司 | A kind of Traffic prediction method and device of mobile communications network |
| WO2018024131A1 (en) * | 2016-08-03 | 2018-02-08 | Huawei Technologies Co., Ltd. | Location tracking in wireless networks |
| CN111095821A (en) * | 2017-08-01 | 2020-05-01 | 维尔塞特公司 | Handover based on predicted network conditions |
| CN112243590A (en) * | 2018-06-07 | 2021-01-19 | 华为技术有限公司 | Method for mobility based on prediction and pre-preparation |
| WO2020114606A1 (en) * | 2018-12-07 | 2020-06-11 | Telefonaktiebolaget Lm Ericsson (Publ) | User equipment tracking and paging area selection in wireless communication systems |
Non-Patent Citations (4)
| Title |
|---|
| 《An Adaptive Wireless Paging Scheme Using Bayesian Network Location Prediction Model》;Yao Yuan;《2009 IEEE 70th Vehicular Technology Conference Fall》;20100112;全文 * |
| R2-168546 "DL data transmission in RRC_INACTIVE";Huawei等;《3GPP tsg_ran\WG2_RL2》;20161104;全文 * |
| TD-LTE系统TA及TAlist规划原则;吕邦国等;《电信工程技术与标准化》;20130615(第06期);全文 * |
| 一种基于用户行为预测的群移动性管理模型;林晓勇等;《电信科学》;20170820(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113316087A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113316087B (en) | Dynamic paging method based on terminal position prediction in LTE system | |
| CN107466103B (en) | Terminal positioning method and network equipment | |
| EP3847841B1 (en) | Procedure for optimization of self-organizing network | |
| Wan et al. | Cost reduction in location management using semi‐realtime movement information | |
| CN111629319B (en) | Position prediction method and device | |
| CN113328784B (en) | Paging method, system, device and medium for low-orbit satellite based on 5G core network | |
| CN108900980B (en) | Resource allocation optimization method based on mobility prediction in heterogeneous network | |
| US11818684B2 (en) | User equipment tracking and paging area selection in wireless communication systems | |
| CN111343680B (en) | Switching time delay reduction method based on reference signal received power prediction | |
| CN101938814B (en) | Mobile terminal paging method and mobile call center equipment | |
| WO2018082323A1 (en) | Method and device for optimizing paging | |
| CN114071661A (en) | Base station energy-saving control method and device | |
| CN113904948B (en) | 5G network bandwidth prediction system and method based on cross-layer multidimensional parameters | |
| US11546821B2 (en) | Methods and systems for selecting a gateway node to support handover in a wireless communication network | |
| US8634824B2 (en) | Method for updating a monitoring list of information identifying cells transferred by a base station of a wireless telecommunication network in a cell managed by the base station | |
| CN116321374A (en) | Base station energy-saving turn-off method, equipment and storage medium | |
| WO2023052010A1 (en) | Trajectory data collection in mobile telecommunication systems | |
| CN102158872B (en) | Method and device for replanning TA (Tracking Area) | |
| WO2017071282A1 (en) | Method of realizing mobility management and network element | |
| CN110121891B (en) | Method and apparatus for predicting mobility of a mobile communication device in a cellular communication network | |
| US10306488B2 (en) | Controller node, method and computer programrat | |
| WO2023185716A1 (en) | Terminal information prediction method and apparatus, and network element | |
| CN108810937A (en) | A kind of the control plane optimization method and controller of mobile management | |
| TWI814629B (en) | Mobile network user handover prediction and anomaly prediction system and method | |
| WO2023184411A1 (en) | Data collection method for beam management based on machine learning and wireless communication device |
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 |