CN115243319A

CN115243319A - Load balancing processing method and device and network equipment

Info

Publication number: CN115243319A
Application number: CN202110444176.6A
Authority: CN
Inventors: 朱中杰; 拜鹏飞; 刘婷婷; 杨晨阳; 索士强; 黄远芳
Original assignee: Datang Mobile Communications Equipment Co Ltd
Current assignee: Datang Mobile Communications Equipment Co Ltd
Priority date: 2021-04-23
Filing date: 2021-04-23
Publication date: 2022-10-25

Abstract

The invention provides a load balancing processing method, a device and electronic equipment, wherein the method comprises the following steps: the network equipment predicts a first cell to which the terminal is to move after a first time; the network equipment predicts a first load amount of the first cell and a second load amount of a second cell under the condition that the terminal moves to the first cell; wherein the first cell is adjacent to the second cell; and if the network equipment determines that the triggering condition of load imbalance is met between the first cell and the second cell according to the first load capacity and the second load capacity, carrying out load balancing processing. The invention can solve the problem that the service quality of a user is continuously deteriorated before switching possibly because the switching is carried out only after the load imbalance is detected in the current load balancing switching strategy, thereby increasing the interruption rate of the user.

Description

Load balancing processing method and device and network equipment

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a load balancing method, an apparatus, and a network device.

Background

With the deployment of the ultra-dense cell and the movement of the user, there are phenomena of frequent user handover and unbalanced load, which results in the performance degradation of the network and the reduction of the user satisfaction. Therefore, how to quickly and accurately implement a handover decision, so as to effectively balance cell loads and reduce user handover times, which becomes a key factor affecting system performance and user experience.

The conventional handover strategy for mobility management mainly aims to solve handover failure existing in an LTE or 5G system, and reduce handover rate and ping-pong effect. The conventional handover strategy performs handover after detecting load imbalance, and needs to continuously observe TTT time, and the service quality of the user will continuously deteriorate before performing handover, thereby increasing the user outage rate.

Disclosure of Invention

The invention provides a load balancing processing method, a load balancing processing device and network equipment, and aims to solve the problem that the service quality of a user is continuously deteriorated before switching possibly caused by the fact that the switching is performed only after the load imbalance is detected in the conventional load balancing switching strategy, so that the user interruption rate is increased.

An embodiment of the present invention provides a load balancing processing method, including:

the network equipment predicts a first cell to which the terminal is to move after a first time;

the network equipment predicts a first load amount of the first cell and a second load amount of a second cell under the condition that the terminal moves to the first cell; wherein the first cell is adjacent to the second cell;

and if the network equipment determines that the triggering condition of load imbalance is met between the first cell and the second cell according to the first load capacity and the second load capacity, carrying out load balancing processing.

Optionally, the predicting, by the network device, a first cell to which the terminal is to move after the first time includes:

the network equipment predicts a second movement track of the terminal after the first moment according to a first movement track of the terminal before the first moment;

and the network equipment predicts a first cell to which the terminal is to move after the first moment according to the second movement track.

Optionally, the predicting, by the network device, the first cell to which the terminal is to move after the first time according to the second movement trajectory includes:

the network equipment determines the channel gain of the terminal corresponding to the second moving track according to a channel information table; the channel information table is used for indicating the channel information values of the terminal at different positions;

and the network equipment predicts a first cell to which the terminal moves after the first time according to the channel gain.

Optionally, the predicting, by the network device, load amounts of the first cell and the second cell when the terminal moves to the first cell includes:

the network equipment determines a first load capacity of the first cell by predicting the number of resources required by the terminal in the first cell under the condition that the terminal moves to the first cell and the total number of available resources of a system;

and the network equipment determines a second load amount of the second cell by predicting the number of resources required by the terminal in the second cell under the condition that the terminal moves to the first cell and the total number of available resources of the system.

Optionally, if it is determined that the triggering condition of load imbalance is satisfied between the first cell and the second cell according to the first load amount and the second load amount, the network device performs load balancing processing, including:

if the network device determines that the triggering condition of load imbalance is met between the first cell and the second cell at a second moment according to a first load amount and a second load amount at the second moment after the first moment, judging whether the triggering condition of load imbalance is met between the first cell and the second cell within a first time period from the second moment according to the first load amount and the second load amount after the second moment;

and if the network equipment determines that the triggering conditions of the load imbalance are met between the first cell and the second cell in the first time period, performing load balancing processing.

Optionally, if it is determined that the triggering condition of load imbalance is satisfied between the first cell and the second cell according to the first load amount and the second load amount, the network device performs load balancing, including:

if the network equipment determines that the triggering condition of load imbalance is met between the first cell and the second cell at a second moment according to a first load capacity and a second load capacity at the second moment after the first moment, determining a user type to which the terminal belongs by predicting the strength of a received signal corresponding to the terminal; wherein the user types include a center user and an edge user;

and the network equipment performs load balancing processing according to the user type.

Optionally, determining the user type to which the terminal belongs according to the received signal strength corresponding to the terminal includes:

predicting a first received signal strength of the terminal in a first cell and a second received signal strength of the terminal in a second cell;

if the difference value between the first received signal strength and the second received signal strength is greater than a first threshold, determining that the user type of the terminal is a central user;

and if the difference value between the first received signal strength and the second received signal strength is smaller than or equal to the first threshold, determining that the user type of the terminal is an edge user.

Optionally, the network device performs load balancing processing according to the user type, including:

aiming at a first terminal of which the user type is a central user, the network equipment determines to maintain the connection state of the first terminal and the first cell;

and aiming at a second terminal with the user type of edge users, the network equipment determines the priority corresponding to the second terminal and performs cell switching on the second terminal according to a switching strategy corresponding to the priority.

Optionally, for a second terminal whose user type is an edge user, the determining, by the network device, a priority corresponding to the second terminal includes:

if the moving direction of the second terminal to be moved to the first cell is from a high-load cell to a low-load cell, the network equipment determines that the second terminal corresponds to a first priority;

if the moving direction of the second terminal is from a low-load cell to a high-load cell, the network equipment determines that the second terminal corresponds to a second priority;

and if the moving direction of the second terminal is from a low-load cell to a low-load cell, or the moving direction is from a high-load cell to a high-load cell, the network equipment determines that the second terminal corresponds to a third priority.

Optionally, performing cell handover on the second terminal according to the handover policy corresponding to the priority, where the cell handover includes:

determining a switching trigger threshold corresponding to the priority according to the priority of the second terminal;

and if the difference between the received signal strengths of the second terminal in the first cell and the second cell is predicted to reach the switching trigger threshold in a second time period, carrying out cell switching on the second terminal.

Optionally, the first handover trigger threshold is smaller than a third handover trigger threshold, and the second handover trigger threshold is larger than the third handover trigger threshold;

wherein the first handover trigger threshold is a handover trigger threshold corresponding to the first priority; the second switching trigger threshold is a switching trigger threshold corresponding to the second priority; the third handover trigger threshold is a handover trigger threshold corresponding to the third priority.

determining a switching moment corresponding to the priority according to the priority corresponding to the second terminal;

and performing cell switching on the second terminal at the switching time.

Optionally, the first switching time is before the third switching time, and the second switching time is after the third switching time;

wherein the first switching time is the switching time corresponding to the first priority; the second switching time is the switching time corresponding to the second priority; the third switching time is the switching time corresponding to the third priority.

Optionally, performing cell handover on the second terminal, including:

predicting a third load amount of the first cell and a fourth load amount of the second cell when the connection state of the second terminal and the first cell is switched to the connection state of the second terminal and the second cell;

and if the load fluctuation amount between the third load amount and the fourth load amount is smaller than a second threshold, switching the connection state of the second terminal and the first cell to the connection state of the second terminal and the second cell.

Optionally, the method further comprises:

the network equipment determines a first resource number required by a central area of each cell according to the resource number required by each terminal in the system and a user type corresponding to the terminal;

the network equipment determines the first resource number as the total number of available resources corresponding to the terminal belonging to the central user in the cell;

and the network equipment determines the total number of available resources corresponding to the terminal belonging to the edge user in the cell according to the first resource number, the total number of resources in the system and the number of cells in the system.

The embodiment of the invention provides a load balancing processing device, which comprises a memory, a transceiver and a processor, wherein the memory is used for storing data;

wherein the memory is used for storing computer programs; the transceiver is used for transceiving data under the control of the processor; the processor is used for reading the computer program in the memory and executing the following operations:

predicting a first cell to which the terminal is to move after a first time;

predicting a first load amount of the first cell and a second load amount of a second cell under the condition that the terminal moves to the first cell; wherein the first cell is adjacent to the second cell;

and if the fact that the triggering condition of load imbalance is met between the first cell and the second cell is determined according to the first load capacity and the second load capacity, carrying out load balancing processing.

Optionally, the processor is configured to read the computer program in the memory and perform the following operations:

predicting a second movement track of the terminal after the first moment according to a first movement track of the terminal before the first moment;

and predicting a first cell to which the terminal is to move after the first time according to the second movement track.

determining the channel gain of the terminal corresponding to the second moving track according to a channel information table; the channel information table is used for indicating the channel information values of the terminal at different positions;

and predicting a first cell to which the terminal is to move after the first time according to the channel gain.

determining a first load capacity of the first cell by predicting the number of resources required by the terminal in the first cell under the condition that the terminal moves to the first cell and the total number of available resources of a system;

and determining a second load amount of the second cell by predicting the number of resources required by the terminal in the second cell under the condition that the terminal moves to the first cell and the total number of available resources of the system.

if it is determined that the triggering condition of load imbalance is met between the first cell and the second cell at a second moment according to a first load amount and a second load amount of the first moment and the second moment, judging whether the triggering condition of load imbalance is met between the first cell and the second cell within a first time period from the second moment according to the first load amount and the second load amount of the second moment;

and if the condition that the first cell and the second cell meet the triggering condition of load imbalance in the first time period is determined, carrying out load balancing processing.

if it is determined that the triggering condition of load imbalance is met between the first cell and the second cell at a second moment according to a first load capacity and a second load capacity at the second moment after the first moment, determining a user type to which the terminal belongs by predicting received signal strength corresponding to the terminal; wherein the user types include a center user and an edge user;

and carrying out load balancing processing according to the user type.

predicting a first received signal strength of the terminal in a first cell and a second received signal strength of the terminal in the second cell;

determining to maintain a connection state of a first terminal and a first cell aiming at the first terminal of which the user type is a central user;

and aiming at a second terminal with the user type of edge users, determining the priority corresponding to the second terminal, and carrying out cell switching on the second terminal according to a switching strategy corresponding to the priority.

if the moving direction of the second terminal to be moved to the first cell is from a high-load cell to a low-load cell, determining that the second terminal corresponds to a first priority;

if the moving direction of the second terminal is from a low-load cell to a high-load cell, determining that the second terminal corresponds to a second priority;

and if the moving direction of the second terminal is from a low-load cell to a low-load cell, or the moving direction is from a high-load cell to a high-load cell, determining that the second terminal corresponds to a third priority.

and performing cell switching on the second terminal at the switching time.

Optionally, the first switching time is before a third switching time, and the second switching time is after the third switching time;

determining a first resource number required by a central area of each cell according to the resource number required by each terminal in a system and a user type corresponding to the terminal;

determining the first resource number as the total number of available resources corresponding to the terminal belonging to the central user in the cell;

and determining the total number of available resources corresponding to the terminal belonging to the edge user in the cell according to the first resource number, the total number of resources in the system and the number of cells in the system.

An embodiment of the present invention provides a network device, including:

a first prediction unit for predicting a first cell to which the terminal is to move after a first time;

a second prediction unit, configured to predict a first load amount of the first cell and a second load amount of a second cell when the terminal moves to the first cell; wherein the first cell is adjacent to the second cell;

and the processing unit is configured to perform load balancing processing if it is determined that a trigger condition of load imbalance is satisfied between the first cell and the second cell according to the first load amount and the second load amount.

Optionally, the first prediction unit is further configured to:

Optionally, the second prediction unit is further configured to:

Optionally, the processing unit is further configured to:

if it is determined that the triggering condition of load imbalance is met between the first cell and the second cell at a second moment after the first moment according to a first load amount and a second load amount at the second moment, judging whether the triggering condition of load imbalance is met between the first cell and the second cell within a first time period starting from the second moment according to the first load amount and the second load amount after the second moment;

Optionally, the processing unit is further configured to:

if the fact that the triggering condition of load imbalance is met between the first cell and the second cell at a second moment is determined according to a first load amount and a second load amount of the second moment after the first moment, determining a user type to which the terminal belongs by predicting the strength of a received signal corresponding to the terminal; wherein the user types include a center user and an edge user;

and carrying out load balancing processing according to the user type.

Optionally, the processing unit is further configured to:

aiming at a first terminal of which the user type is a central user, maintaining the connection state of the first terminal and the first cell;

and aiming at a second terminal with the user type of an edge user, determining the priority corresponding to the second terminal, and performing cell switching on the second terminal according to a switching strategy corresponding to the priority.

Optionally, the processing unit is further configured to:

and at the switching moment, carrying out cell switching on the second terminal.

Optionally, the processing unit is further configured to:

Optionally, the network device further includes:

a first determining unit, configured to determine, according to the number of resources required by each terminal in the system and a user type corresponding to the terminal, a first number of resources required by a central area of each cell;

a second determining unit, configured to determine the first resource number as a total number of available resources corresponding to a terminal belonging to a central user in the cell;

and a third determining unit, configured to determine, according to the first number of resources, the total number of resources in the system, and the number of cells in the system, the total number of available resources corresponding to terminals belonging to the edge user in the cell.

An embodiment of the present application provides a processor-readable storage medium, which stores a computer program, where the computer program is used to enable the processor to execute the load balancing processing method described above.

The technical scheme of the invention has the beneficial effects that: the network equipment predicts a first cell to which a terminal is to move after a first time, and performs load balancing processing when load imbalance occurs between the first cell and a second cell after the first time is determined according to a first load capacity of the first cell and a second load capacity of the second cell under the condition that the terminal is predicted to move to the first cell, so that the problem that switching is performed only after the load imbalance is detected at present, possibly, service quality of a user is continuously deteriorated before switching is performed, and accordingly, the interruption rate of the user is increased is solved.

Drawings

Fig. 1 is a flowchart of a load balancing method according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating predicted movement trajectories according to an embodiment of the invention;

FIG. 3 is a schematic diagram illustrating a structure of predicting a movement trajectory based on a deep neural network according to an embodiment of the present invention;

fig. 4 is a diagram illustrating a cell switching strategy according to an embodiment of the present invention;

fig. 5 is a diagram illustrating a terminal performing cell handover according to an embodiment of the present invention;

FIG. 6 is a block diagram of a load balancing system according to an embodiment of the present invention;

FIG. 7 shows a block diagram of a network device of an embodiment of the invention;

fig. 8 is a block diagram of a load balancing processing apparatus according to an embodiment of the present invention.

Detailed Description

To make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help the full understanding of the embodiments of the present invention. It will therefore be apparent to those skilled in the art that various changes and modifications can be made in the embodiments described herein without departing from the scope and spirit of the invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the execution sequence, and the execution sequence of each process should be determined by the function and the inherent logic of the process, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

In addition, the terms "system" and "network" are often used interchangeably herein.

The technical scheme provided by the embodiment of the application can be suitable for various systems, particularly 5G systems. For example, suitable systems may be global system for mobile communications (GSM) systems, code Division Multiple Access (CDMA) systems, wideband Code Division Multiple Access (WCDMA) General Packet Radio Service (GPRS) systems, long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, long term evolution (long term evolution) systems, LTE-a systems, universal mobile systems (universal mobile telecommunications systems, UMTS), universal internet Access (world interoperability for microwave Access (WiMAX) systems, new Radio interface (NR) systems, etc. These various systems include terminal devices and network devices. The System may further include a core network portion, such as an Evolved Packet System (EPS), a 5G System (5 GS), and the like.

Multiple Input Multiple Output (MIMO) transmission may be performed between the network device and the terminal device by using one or more antennas, where the MIMO transmission may be Single User MIMO (SU-MIMO) or Multi-User MIMO (MU-MIMO). The MIMO transmission may be 2D-MIMO, 3D-MIMO, FD-MIMO, or massive-MIMO, or may be diversity transmission, precoding transmission, beamforming transmission, or the like, depending on the form and number of root antenna combinations.

In the embodiment of the present invention, the term "and/or" describes an association relationship of an associated object, and indicates that three relationships may exist, for example, a and/or B, and may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

In the embodiments of the present application, the term "plurality" means two or more, and other terms are similar thereto.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.

The cell capacity referred to in this application may be characterized by Resource Block Utilization Ratio (RBUR). For example: the resource occupancy is a ratio of the number of actually used Resource Blocks (RBs) of a cell to the number of RBs that can be used by the cell. For a given duration T, the average load of cell i at time T is:

wherein, the first and the second end of the pipe are connected with each other,

is the average load of cell i at time t, N _PRB For the number of RBs that can be used in the system,

the number of RBs is actually used for the cell.

The average load of the network is:

wherein the content of the first and second substances,

n is the average load of the network and is the number of cells.

The standard deviation of the network is:

is the standard deviation of the network.

Considering minimizing the standard deviation of the network load while satisfying the limitation of the number of RBs, the form is as follows: a

When load imbalance exists among cells, the cell load needs TO be adjusted through switching, mainly according TO an A3 event in LTE, and when the A3 event is continuously satisfied within a Time TO Trigger (TTT), switching operation is performed. The trigger conditions of the A3 event are as follows:

Mn+Ofn+Ocn-Hyst>Mp+Ofp+Ocp+Off

mn and Mp represent average received signal strength of the target cell and the source cell, ofn and Ocp represent frequency offset of the target cell and the source cell, ocn and Ocp represent cell independent offset of the target cell and the source cell, hyst is a hysteresis parameter, and Off is A3 event offset of the source cell and the target cell.

The selection of the switching user is determined by an A4 event, and the triggering conditions are as follows:

Mn+Ofn+Ocn-Hyst>Thresh

the whole load balancing process comprises the following steps of firstly, collecting an A3 event measurement report of each Cell, if the Cell meets the conditions in the TTT time, selecting a switching user according to an A4 event, and indirectly changing the coverage range of the Cell by modifying Cell Independent Offset (CIO), hysteresis parameters Hyst and the like, so that the user with poor edge channel quality in the high-load Cell can be switched to an adjacent Cell with good channel condition and load state, thereby relieving the load imbalance among the cells and minimizing the standard deviation of network load.

However, in the above handover method, the handover is performed after the load imbalance is detected, and it is necessary to continuously observe the TTT time, and the service quality of the user is continuously deteriorated before the handover is performed, thereby increasing the user outage rate. When a user moves among cells with different load degrees, frequent switching among the cells can be caused, a ping-pong effect is generated in the moving process of the user, and the switching time and delay are increased. If the user experiences multiple handovers, the handover delays will accumulate, seriously compromising the user experience.

The embodiment of the application provides a load balancing processing method, a load balancing processing device and network equipment, and aims to solve the problem that the current load balancing switching strategy is to switch after load imbalance is detected, which may cause that the service quality of a user is continuously deteriorated before switching is performed, so that the user interruption rate is increased.

The method, the device and the network equipment are based on the same application concept, and because the principles of solving the problems of the method, the device and the network equipment are similar, the implementation of the method, the device and the network equipment can be mutually referred, and repeated parts are not described again.

As shown in fig. 1, an embodiment of the present invention provides a load balancing processing method, which specifically includes the following steps:

step 11: the network device predicts a first cell to which the terminal is to move after a first time.

Optionally, the first time may be the current time, or may be a time after the current time.

Step 12: the network equipment predicts a first load capacity of the first cell and a second load capacity of a second cell under the condition that the terminal moves to the first cell; wherein the first cell is adjacent to the second cell.

Step 13: and if the network equipment determines that the triggering condition of load imbalance is met between the first cell and the second cell according to the first load amount and the second load amount, performing load balancing processing.

In this embodiment, the network device performs load balancing processing when determining that load imbalance will occur between the first cell and the second cell after the first time by predicting the first cell to which the terminal is to move after the first time and according to the predicted first load amount of the first cell and the predicted second load amount of the second cell when the terminal is to move to the first cell, thereby solving the problem that at present, handover is performed after load imbalance is detected, which may cause continuous deterioration of service quality of a user before handover is performed, thereby causing an increase in user outage rate.

For example: at each time T, the base station determines the terminal's T in the past _h In time (T immediately before time T) _h Time period), i.e. a first movement trajectory (a movement trajectory is understood herein to mean a geographical location of the terminal at a plurality of times), predicting the future T of the terminal _p Within time (i.e. T after time T) _p Time period), i.e., the second movement trajectory.

As shown in FIG. 2, the prediction includes a history window and a prediction window, where t is the sum of t _r To t _p Is called a history window, the window length is T _h ＝t _p -t _r Including on the movement trajectory of the terminal

Where Δ is the time interval of adjacent tracks (i.e., the sampling interval, i.e., the frame time interval). The history window trace sequence is marked as x ^His (t)＝[x(t-M+1),…,x(t)] ^T . From t _p To t _q Time series ofCalled prediction window, with window length T _p ＝t _q -t _p . The prediction window comprises the movement track of the terminal

Each position, denoted as x ^Pre (t)＝[x(t+1),…,x(t+N)] ^T . x (t) = (a (t), b (t)) is the position of the user at time t, and a (t) and b (t) represent position coordinates in the horizontal direction and the vertical direction, respectively.

As shown in fig. 3, the movement track of the terminal can be predicted through a deep neural network, which includes two processes of off-line training and on-line prediction. For example, the moving track of the terminal in a research scene can be collected as a sample to train the neural network, and the online prediction stage can be entered after the training is completed. During online prediction, the terminal can upload corresponding position information in real time, and the predictor can predict a future movement track according to historical information uploaded by the terminal (namely the position information uploaded in real time).

Optionally, the predicting, by the network device, a first cell to which the terminal is to move after the first time according to the second movement trajectory includes:

For example: and obtaining a predicted value of the large-scale channel gain according to the predicted moving track (namely the second moving track) after the first moment and a signal Map (Radio Map). Wherein a signal map (i.e., a channel information table) may be measured and stored by the base station in advance, which may characterize the large-scale channel information values (e.g., including path loss and shadow fading) of the terminals at each location accessing the base station. Therefore, the large-scale channel information corresponding to the terminal can be obtained by combining the predicted movement track of the terminal with the signal map, and the movement direction of the terminal in the prediction window can be determined according to the large-scale channel information of the terminal in the prediction window. Wherein the direction of movement may be understood as the direction towards which cell the terminal is moving, i.e. the first cell to which the terminal is to move. For example: under the condition that the large-scale channel information from the target base station to the terminal is continuously increased, the terminal can be determined to move towards the target cell, namely the moving direction corresponding to the terminal.

Optionally, the predicting, by the network device, the load amounts of the first cell and the second cell when the terminal moves to the first cell includes:

For example: and predicting the load capacity of the cell after the first moment (namely predicting the future moment) according to the predicted large-scale channel information of the terminal on the second track (namely the large-scale channel information of the terminal in the prediction window) and the terminal requirement. For example, the number of resources required by the terminal in each cell may be used to measure the load of each cell, where the number of resources required by the terminal is related to the terminal requirement in the cell and the channel information of the terminal, and the base station to which the terminal is connected and the number of resources required may be determined by the predicted position (i.e., the movement trajectory) of the terminal and the predicted large-scale channel gain of the terminal at the corresponding position, so as to predict the load of the cell.

and if the network equipment determines that the triggering conditions of load imbalance are met between the first cell and the second cell in the first time period, performing load balancing processing.

For example: when it is predicted at time t (e.g., the first time) that the trigger condition of load imbalance is met between the first cell and the second cell at time t + i (i.e., the second time), the prediction result after time t + i is continuously observed, where the observation duration is TTT, and if the cell meets the condition of load imbalance within the first time period from time t + i to time t + i + TTT, it is determined that load imbalance occurring at time t + i needs to be processed, so that it is possible to perform load balancing processing without waiting for the time to reach time t + i + TTT, as shown in fig. 4, that is, it is possible to solve the problem that the handover is performed after the load imbalance is detected at present, which may cause the service quality of a user to continuously deteriorate before the handover, thereby increasing the user outage rate.

if the network equipment determines that the triggering condition of load imbalance is met between the first cell and the second cell at a second moment according to a first load amount and a second load amount at the second moment after the first moment, determining a user type to which the terminal belongs by predicting the strength of a received signal corresponding to the terminal; wherein the user types include a center user and an edge user;

For example: and after predicting that the first cell and the second cell meet the triggering condition of load imbalance at the time t + i at the time t, dividing the user types corresponding to the terminals, and determining whether the user type to which the terminal belongs is a center user or an edge user. And load balancing processing is carried out according to the user type of the terminal so as to ensure that the cell load balancing can be converged more quickly and effectively.

For example: and dividing the user types to which the terminal belongs by using the average channel gain difference of the two adjacent cells (which can also characterize the difference of the received signal strengths of the terminal in the two adjacent cells). For one terminal UE _k In other words, the channel gain difference to two adjacent cells can be expressed as:

wherein the content of the first and second substances,

for a terminal UE _k The difference in channel gain to two adjacent cells,

for terminal UE _k To cell BS _i The channel gain of (a) is determined,

for terminal UE _k To cell BS _j The channel gain of (1).

Terminal UE _k The division of the user types to which the terminal UE belongs can be determined according to the difference of the channel gains if the terminal UE _k Corresponding to

If the threshold is larger than the given threshold, the terminal UE is connected _k And dividing the user into a central user, otherwise, dividing the user into an edge user.

and aiming at a second terminal with the user type of an edge user, the network equipment determines the priority corresponding to the second terminal and performs cell switching on the second terminal according to a switching strategy corresponding to the priority.

For example: for the first terminal with the user type as the center user, the first terminal is connected with the base station according to the maximum received signal strength and does not perform switching. For the second terminal with the user type of the edge user, cell switching is needed. Specifically, according to the corresponding priority, different strategies are adopted for cell switching, so that frequent switching and ping-pong effect existing in the process that the terminal moves among the cells are reduced, the interruption probability of the terminal is reduced, and the throughput of the system is improved.

The high-load cell is a cell of which the resource occupancy rate (or the load capacity) of the cell is higher than or equal to a set threshold; the low-load cell is a cell when the resource occupancy rate of the cell is lower than a set threshold.

For example: the second terminal whose user type is an edge user may be further divided according to the predicted moving direction of the terminal: the second terminal is classified as an early handover user (i.e., a first priority terminal) when the second terminal moves from a high load cell toward a low load cell, as a late handover user (i.e., a second priority terminal) when the second terminal moves from a low load cell toward a high load cell, and as a normal handover user (i.e., a third priority terminal) when the second terminal moves between cells having a small load amount (e.g., from one high load cell to another high load cell or from one low load cell to another low load cell).

For example: and aiming at the second terminals with different priorities, determining whether the second terminals meet the condition of cell switching according to different switching trigger thresholds. As an implementation manner, for a terminal of the third priority (i.e. a normal handover user), the handover trigger threshold corresponding to the terminal may be set according to a conventional handover decision threshold. For a terminal with a first priority (i.e. a user is switched in advance), the corresponding switching trigger threshold may be set to be lower than the conventional switching decision threshold (i.e. the first switching trigger threshold is smaller than the third switching trigger threshold). For a terminal of the second priority (i.e., a late handover user), its corresponding handover trigger threshold may be set higher than the conventional handover decision threshold. Of course, the handover trigger thresholds corresponding to different priorities may also be set according to the terminal requirements, which is not limited in this embodiment of the present application.

Optionally, after determining that the terminal satisfies the handover trigger threshold corresponding to the terminal with different priorities according to the handover trigger thresholds corresponding to the terminals with different priorities, to avoid a ping-pong effect, it may be continuously predicted whether the terminal continuously satisfies the handover trigger threshold corresponding to the terminal within a next TTT duration (i.e., a second time period) beginning at a time when the terminal is predicted to satisfy the handover trigger threshold corresponding to the terminal, where the handover trigger threshold may be a threshold of a difference between received signal strengths of the terminal in adjacent cells, that is, it is determined whether the difference between the received signal strengths of the terminal in the adjacent cells satisfies the handover trigger threshold. If the terminal continuously meets the corresponding trigger switching threshold within the time period of the TTT, the cell switching of the terminal is predicted to be needed. Otherwise, the terminal will continue to maintain the original connection state. Thus, if a cell switching operation is performed in the above manner, some terminals belonging to the edge user may be connected to a new base station, thereby determining a final connection state of the terminal. Optionally, the final connection state of the terminal may be compared with the connection state of the previous frame to obtain whether the terminal performs a handover in the frame.

For example: for a terminal with a first priority (i.e. a user who switches in advance), the time when the terminal switches the cell can be set before the time t + i when the load imbalance is predicted; for the terminal of the second priority (i.e. the late handover user), the time when the terminal performs cell handover may be set after the time t + i when the load imbalance is predicted; for the terminal of the third priority (i.e. normal handover user), the time when it performs cell handover may be set to the time t + i when the load imbalance is predicted. Specifically, if it is predicted at the current time t that there is a load imbalance at the time t + i, the handover time at which the terminal belonging to the advanced handover user performs cell handover will be before the time t + i; for the terminal belonging to the delayed handover user, the handover time of the cell handover will be after the time t + i; for a terminal belonging to a normal handover user, the handover time of the terminal performing cell handover will be at time t + i.

Optionally, as an implementation: the switching time corresponding to the terminal can be predicted through the deep neural network, and the off-line training and the on-line prediction are included. Training samples may be generated, for example, from historical data: the method comprises the steps of collecting historical channel information corresponding to a terminal in a research scene as input of a neural network, respectively obtaining different switching moments of an early switching user and a late switching user as output of a model, training the neural network according to a generated training sample, and entering an online prediction stage after training is completed. During online prediction, the terminal can upload real-time historical channel information, so that the predictor can predict the switching time of cell switching at the future time (namely after the first time) according to the historical channel information uploaded by the terminal.

Optionally, the above manner of performing cell handover based on the handover trigger thresholds corresponding to different priorities and the manner of performing cell handover based on the handover moments corresponding to different priorities may be independent; or on the basis of performing cell switching based on the switching trigger thresholds corresponding to different priorities, further performing cell switching based on the switching time corresponding to different priorities. For example: when the deep neural network does not have enough training samples, a cell switching mode can be adopted based on switching trigger thresholds corresponding to different priorities, meanwhile, the training samples of the deep neural network are generated according to a switching decision, further, when the generated training samples meet the requirements of the training samples of the deep neural network, the deep neural network can be trained according to the generated training samples, and therefore the switching time corresponding to the terminal is predicted according to the trained deep neural network.

Optionally, performing cell handover on the second terminal, including:

For example: when it is predicted that cell switching needs to be performed on a part of terminals, the load state of a target cell to which the terminals are switched needs to be considered. Optionally, the resource that needs to be consumed after the user is switched to the target cell is estimated according to the predicted large-scale channel information, and then the load state of the switched target cell is estimated.

If the load between the two cells fluctuates too much after the handover, the handover operation is not executed for the moment until the load fluctuation between the two cells after the handover is smaller than a given threshold (i.e. a second threshold). The terminal maintains a connection state with a source base station until time reaches a predicted handover time of the terminal; when the time reaches the predicted switching time of the terminal, the source base station initiates a switching process, the source base station disconnects the connection with the terminal, and the user is forcibly switched from the source cell to the target cell, so that the terminal keeps the connection state with the target base station. As shown in fig. 5, the user type of UE1 is a late handover user, which will remain connected to the low load cell until reaching late handover point P4; after reaching the hysteresis switch point, it will switch to the high load cell. The user type of UE2 is an advanced handover user, which will remain connected to the high load cell until the advanced handover point P2 is reached, and which will switch to the low load cell after the advanced handover point is reached.

Optionally, the method further comprises:

the network equipment determines a first resource number required by a central area of each cell according to the resource number required by each terminal in the system and the user type corresponding to the terminal;

In this embodiment, on the basis of the division based on the user types, the bandwidth may also be allocated according to the user types. For example: in order to reasonably allocate the bandwidth, the central user and the edge user can be served, and therefore, the bandwidth allocation can be realized in proportion according to the number of required resources of the central user and the edge user.

Optionally, the average data rate of the user can be estimated according to the predicted large-scale channel gain value

The minimum data rate requirement of a user is

The number of resources required by the user

Comprises the following steps:

the RB resource of each region should meet the requirements of all users in the region, wherein the number of the required resources of each region depends on the maximum value of the number of the RBs required by a single user in the region and the average required number of the RBs of all the users. In this way, the total number of RBs required for each of the center region and the edge region of the cell can be further obtained according to the number of RBs required for each user:

thus, the total number of RBs m required according to the central region of the cell ^c And the total RB number m required for the edge region ^e The total number of RBs available for the terminal in the cell center region and the total number of RBs available for the terminal in the edge region may be determined as follows:

N ^c ＝m ^c

wherein N is ^c The total number of RBs respectively available for terminals in the central region,

the total number of RBs available for the terminal in the edge area, G is the number of cells, and N is the total number of RBs in the system.

As shown in fig. 6, an embodiment of the present application provides a framework schematic diagram of a load balancing processing system, where the processing steps of the system to implement load balancing include: carrying out mobility prediction according to the historical movement track of the terminal, and determining a predicted movement track based on machine learning; predicting the moving direction of the terminal according to the predicted moving track, and predicting the predicted channel state of the terminal at a future moment according to the predicted moving track; and predicting the predicted load capacity of the cell at the future moment according to the predicted channel state, and predicting the load balancing condition at the future moment according to the predicted load capacity, so that when load imbalance is predicted, active switching can be performed by determining the corresponding switching moment of the terminal needing cell switching.

In this way, the scheme introduces the track prediction and the moving direction prediction into a switching strategy of load balancing to realize the prediction of the load capacity of the cell at the future moment so as to realize the switching preparation before the load imbalance condition occurs, thereby being convenient for effectively adjusting the cell load in time; and on the basis of predicting the load of the cell at the future moment and combining the predicted movement track and the movement direction of the terminal, the reasonable active switching can be carried out on different types of terminals before the predicted moment needing load balancing, the load balancing is promoted to autonomously and rapidly converge, and the ping-pong switching times of users are reduced.

Compared with a traditional passive switching strategy, the scheme can actively switch based on the active switching strategy of machine learning, and does not need to switch after the TTT duration is waited again when the load is unbalanced, so that more reasonable switching and faster switching speed can be obtained, seamless connection is realized, and the system can effectively process the problem of unbalanced load among cells in time.

Compared with the traditional switching strategy only considering cell load and user channel quality, the switching time of different types of terminals is optimized by combining the terminal moving direction and the switching self-optimization strategy of a load balancing mechanism and reasonably dividing users, so that frequent switching and ping-pong effect existing in the process of moving the terminals among cells can be effectively reduced, the interruption probability of users is reduced, and the throughput of the system is improved.

The network device according to the embodiment of the present application may be a base station, and the base station may include a plurality of cells for providing services to a terminal. A base station may also be called an access point, or may be a device in an access network that communicates over the air-interface, through one or more sectors, with wireless terminal devices, or by other names, depending on the particular application. The network device may be configured to exchange received air frames with Internet Protocol (IP) packets as a router between the wireless terminal device and the rest of the access network, which may include an Internet Protocol (IP) communication network. The network device may also coordinate attribute management for the air interface. For example, the network device according to the embodiment of the present application may be a Base Transceiver Station (BTS) in a Global System for Mobile communications (GSM) or a Code Division Multiple Access (CDMA), may also be a network device (NodeB) in a Wide-band Code Division Multiple Access (WCDMA), may also be an evolved Node B (eNB or e-NodeB) in a Long Term Evolution (LTE) System, a 5G Base Station (gNB) in a 5G network architecture (next generation System), may also be a Home evolved Node B (HeNB), a relay Node (relay Node), a Home Base Station (femto), a pico Base Station (pico) and the like, and the present application is not limited in this embodiment. In some network configurations, a network device may include Centralized Unit (CU) nodes and Distributed Unit (DU) nodes, which may also be geographically separated.

A terminal as referred to in embodiments of the present application may refer to a device providing voice and/or data connectivity to a user, a handheld device having a wireless connection capability, or other processing device connected to a wireless modem, etc. In different systems, the names of the terminal devices may be different, for example, in a 5G system, the terminal device may be called a User Equipment (UE). A wireless terminal device, which may be a mobile terminal device such as a mobile telephone (or "cellular" telephone) and a computer having a mobile terminal device, e.g., a portable, pocket, hand-held, computer-included or vehicle-mounted mobile device, may communicate with one or more Core Networks (CNs) via a Radio Access Network (RAN), and may exchange language and/or data with the RAN. Examples of such devices include Personal Communication Service (PCS) phones, cordless phones, session Initiation Protocol (SIP) phones, wireless Local Loop (WLL) stations, and Personal Digital Assistants (PDAs). The wireless terminal device may also be referred to as a system, a subscriber unit (subscriber unit), a subscriber station (subscriber station), a mobile station (mobile), a remote station (remote station), an access point (access point), a remote terminal device (remote terminal), an access terminal device (access terminal), a user terminal device (user terminal), a user agent (user agent), and a user device (user device), which are not limited in this embodiment of the present application.

In the above description, the load balancing processing method of the present invention is described, and the following embodiment will further describe the network device corresponding to the load balancing processing method with reference to the drawings.

Specifically, as shown in fig. 7, a network device 700 according to an embodiment of the present invention includes:

a first prediction unit 710 for predicting a first cell to which the terminal is to move after a first time;

a second prediction unit 720, configured to predict a first load amount of the first cell and a second load amount of a second cell when the terminal moves to the first cell; wherein the first cell is adjacent to the second cell;

the processing unit 730 is configured to perform load balancing processing if it is determined that a trigger condition of load imbalance is satisfied between the first cell and the second cell according to the first load amount and the second load amount.

Optionally, the first prediction unit 710 is further configured to:

and predicting a first cell to which the terminal is to move after the first moment according to the second movement track.

Optionally, the first prediction unit 710 is further configured to:

Optionally, the second prediction unit 720 is further configured to:

determining a first load amount of the first cell by predicting the number of resources required by the terminal in the first cell under the condition that the terminal moves to the first cell and the total number of available resources of a system;

and determining a second load capacity of the second cell by predicting the number of resources required by the terminal in the second cell under the condition that the terminal moves to the first cell and the total number of available resources of the system.

Optionally, the processing unit 730 is further configured to:

and carrying out load balancing processing according to the user type.

Optionally, the processing unit 730 is further configured to:

if the difference value between the first received signal strength and the second received signal strength is larger than a first threshold, determining that the user type of the terminal is a central user;

Optionally, the processing unit 730 is further configured to:

Optionally, the network device 700 further includes:

a first determining unit, configured to determine, according to the number of resources required by each terminal in a system and a user type corresponding to the terminal, a first number of resources required by a central area of each cell;

It should be noted that, in the embodiment of the present application, the division of the unit is schematic, and is only one logic function division, and when the actual implementation is realized, another division manner may be provided. In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented as a software functional unit and sold or used as a stand-alone product, may be stored in a processor readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.

It should be noted that, the network device 700 provided in the embodiment of the present invention can implement all the method steps implemented by the method embodiment and achieve the same technical effect, and details of the same parts and beneficial effects as those of the method embodiment in this embodiment are not described herein again.

In order to better achieve the above object, an embodiment of the present invention provides a load balancing processing apparatus, as shown in fig. 8, including a memory, a transceiver 810, a processor 800; wherein the memory 820 is used for storing computer programs; a transceiver 810 for transceiving data under the control of the processor 800; such as transceiver 810, for receiving and transmitting data under the control of processor 800; the processor 800 is configured to read the computer program in the memory and perform the following operations:

predicting a first cell to which the terminal is to move after a first time;

and if the condition that the triggering condition of the load imbalance is met between the first cell and the second cell is determined according to the first load amount and the second load amount, carrying out load balancing processing.

Optionally, the processor 800 is configured to read the computer program in the memory and perform the following operations:

Optionally, the processor 800 is configured to read the computer program in the memory and execute the following operations:

and if the condition that the first cell and the second cell meet the triggering condition of load imbalance in the first time period is determined, performing load balancing processing.

and carrying out load balancing processing according to the user type.

Where in fig. 8, the bus architecture may include any number of interconnected buses and bridges, with various circuits being linked together, particularly one or more processors represented by processor 800 and memory represented by memory 820. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The transceiver 810 may be a number of elements including a transmitter and receiver that provide a means for communicating with various other apparatus over a transmission medium including wireless channels, wired channels, fiber optic cables, and the like. The processor 800 is responsible for managing the bus architecture and general processing, and the memory 820 may store data used by the processor 800 in performing operations.

The processor 800 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or a Complex Programmable Logic Device (CPLD), and may also have a multi-core architecture.

It should be noted that, the apparatus provided in the embodiment of the present invention can implement all the method steps implemented by the method embodiment and achieve the same technical effect, and detailed descriptions of the same parts and beneficial effects as the method embodiment in this embodiment are omitted here.

An embodiment of the present invention further provides a processor-readable storage medium, where a computer program is stored, and the computer program is configured to enable the processor to execute the method for load balancing processing.

The processor-readable storage medium can be any available medium or data storage device that can be accessed by a processor, including, but not limited to, magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid State Disks (SSDs)), etc.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These processor-executable instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Furthermore, it is to be noted that in the device and method of the invention, it is obvious that the individual components or steps can be decomposed and/or recombined. These decompositions and/or recombinations are to be regarded as equivalents of the present invention. Also, the steps of performing the series of processes described above may naturally be performed chronologically in the order described, but need not necessarily be performed chronologically, and some steps may be performed in parallel or independently of each other. It will be understood by those skilled in the art that all or any of the steps or elements of the method and apparatus of the present invention may be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or any combination thereof, which can be implemented by those skilled in the art using their basic programming skills after reading the description of the present invention.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A load balancing processing method is characterized by comprising the following steps:

the network equipment predicts a first load capacity of the first cell and a second load capacity of a second cell under the condition that the terminal moves to the first cell; wherein the first cell is adjacent to the second cell;

2. The method of claim 1, wherein the network device predicting the first cell to which the terminal is to move after the first time comprises:

3. The method according to claim 2, wherein the network device predicts a first cell to which the terminal is to move after the first time according to the second movement trajectory, and comprises:

4. The method of claim 1, wherein the network device predicts a load amount of the first cell and the second cell when the terminal moves to the first cell, and comprises:

the network equipment determines a first load amount of the first cell by predicting the number of resources required by the terminal in the first cell under the condition that the terminal moves to the first cell and the total number of available resources of a system;

and the network equipment determines a second load capacity of the second cell by predicting the number of resources required by the terminal in the second cell under the condition that the terminal moves to the first cell and the total number of available resources of the system.

5. The method according to claim 1, wherein if the network device determines that a trigger condition for load imbalance is satisfied between the first cell and the second cell according to the first load amount and the second load amount, performing load balancing processing includes:

6. The method according to claim 1, wherein if the network device determines that a trigger condition of load imbalance is satisfied between the first cell and the second cell according to the first load amount and the second load amount, performing load balancing processing, includes:

7. The method according to claim 6, wherein determining the user type to which the terminal belongs according to the received signal strength corresponding to the terminal comprises:

8. The method of claim 6, wherein the network device performs load balancing according to the user type, and the method comprises:

for a first terminal with a user type as a center user, the network equipment determines to maintain the connection state of the first terminal and the first cell;

9. The method according to claim 8, wherein for a second terminal whose user type is an edge user, the network device determines a priority corresponding to the second terminal, and includes:

10. The method of claim 9, wherein performing cell handover on the second terminal according to the handover policy corresponding to the priority comprises:

11. The method of claim 10, wherein the first handover trigger threshold is less than a third handover trigger threshold, and wherein the second handover trigger threshold is greater than the third handover trigger threshold;

wherein, the first switching trigger threshold is the switching trigger threshold corresponding to the first priority; the second switching trigger threshold is a switching trigger threshold corresponding to the second priority; the third handover trigger threshold is a handover trigger threshold corresponding to the third priority.

12. The method of claim 9, wherein performing cell handover on the second terminal according to the handover policy corresponding to the priority comprises:

13. The method of claim 12, wherein the first switching time is before a third switching time, and wherein the second switching time is after the third switching time;

14. The method of claim 8, wherein performing the cell handover for the second terminal comprises:

15. The method of claim 1, further comprising:

16. A load balancing processing device is characterized by comprising a memory, a transceiver and a processor;

wherein the memory is used for storing a computer program; the transceiver is used for transceiving data under the control of the processor; the processor is used for reading the computer program in the memory and executing the following operations:

predicting a first cell to which the terminal is to move after a first time;

17. The apparatus of claim 16, wherein the processor is configured to read the computer program in the memory and perform the following operations:

18. The apparatus of claim 17, wherein the processor is configured to read the computer program in the memory and perform the following operations:

19. The apparatus of claim 16, wherein the processor is configured to read the computer program in the memory and perform the following operations:

20. The apparatus of claim 16, wherein the processor is configured to read the computer program stored in the memory and perform the following:

21. The apparatus of claim 16, wherein the processor is configured to read the computer program in the memory and perform the following operations:

and carrying out load balancing processing according to the user type.

22. The apparatus of claim 21, wherein the processor is configured to read the computer program in the memory and perform the following:

23. The apparatus of claim 21, wherein the processor is configured to read the computer program stored in the memory and perform the following:

aiming at a first terminal of which the user type is a central user, determining to maintain the connection state of the first terminal and the first cell;

24. The apparatus of claim 23, wherein the processor is configured to read the computer program stored in the memory and perform the following:

25. The apparatus of claim 24, wherein the processor is configured to read the computer program in the memory and perform the following operations:

26. The apparatus of claim 25 wherein the first handover trigger threshold is less than a third handover trigger threshold and wherein the second handover trigger threshold is greater than the third handover trigger threshold;

27. The apparatus of claim 24, wherein the processor is configured to read the computer program in the memory and perform the following operations:

28. The apparatus of claim 27, wherein the first switching time is before the third switching time, and wherein the second switching time is after the third switching time;

29. The apparatus of claim 23, wherein the processor is configured to read the computer program stored in the memory and perform the following:

30. The apparatus of claim 16, wherein the processor is configured to read the computer program in the memory and perform the following operations:

31. A network device, comprising:

32. A processor-readable storage medium, wherein the processor-readable storage medium stores a computer program for causing a processor to execute the load balancing processing method of any one of claims 1 to 15.