Access cell switching method and apparatus for terminal device, and electronic device
By predicting the signal quality of the target cell and dynamically selecting the access link in the terminal device, the problem of low spectrum resource utilization in satellite communication systems is solved, achieving more efficient spectrum resource utilization and stable communication services.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-20
- Publication Date
- 2026-03-27
AI Technical Summary
Satellite communication systems in related technologies suffer from problems such as low spectrum resource utilization, high latency, coverage blind spots, and limited ability to respond to emergencies, especially when the coordinated scheduling of high-orbit satellites, low-orbit satellites, high-altitude base stations, and ground base stations is insufficient.
The terminal device predicts the signal quality of the target cell, sends a random access request to the target access base station based on the prediction result, and allocates available access resources to the terminal device in the order of high-orbit star link, low-orbit star link and base station link, so as to realize the handover across different types of links and dynamically select the optimal access point.
This improves the utilization rate of spectrum resources, avoids resource waste and uneven load, and ensures the stability and continuity of communication.
Smart Images

Figure CN120980633B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of wireless communication, and more specifically, to a method, apparatus, and electronic device for handing over access cells to a terminal device. Background Technology
[0002] With the continuous growth of global communication demands, satellite communication systems have become a key technology for extending terrestrial network coverage and ensuring communication capabilities in remote areas and mobile environments. However, satellite communication systems in related technologies are typically based on satellites in fixed orbits, which exposes many limitations when facing rapidly increasing data transmission demands and diverse communication scenarios, such as low resource utilization, high latency, coverage blind spots, and limited ability to respond to emergencies. Furthermore, these technologies lack coordinated scheduling among high-orbit satellites, low-orbit satellites, high-altitude base stations, and terrestrial base stations, and do not adequately consider the issue of access failures under coordinated resource scheduling of high- and low-orbit satellites, resulting in low spectrum resource utilization and inadequate handling of handover failures.
[0003] This shows that satellite communication methods in related technologies suffer from the technical problem of low spectrum resource utilization. Summary of the Invention
[0004] This application provides a terminal device access cell handover method, apparatus, and electronic device to at least solve the technical problem of low spectrum resource utilization in satellite communication methods in related technologies.
[0005] According to one aspect of the embodiments of this application, a method for handover of access cell for a terminal device is provided, comprising: when the terminal device is to be handed over from the current cell to a target cell, predicting the signal quality of the target cell based on the signal quality of the target cell monitored by the terminal device; when it is determined that the handover execution conditions are met based on the predicted signal quality of the target cell, sending a random access request to a target access base station, wherein the target access base station is a base station corresponding to the target cell; when a random access response is received from the target access base station and the random access response indicates that the terminal device is allowed to randomly access the target cell, sending a resource allocation request to the target access base station; and when a resource allocation response is received from the target access base station, performing a random access operation according to the target access link indicated by the resource allocation response to perform cell handover, wherein the target access link is an access resource that is available and allocated to the terminal device by the target access base station in the order of high-orbit satellite link, low-orbit satellite link, and base station link.
[0006] According to another aspect of the embodiments of this application, an access cell handover apparatus for a terminal device is also provided, comprising: a prediction unit, configured to predict the signal quality of the target cell based on the signal quality of the target cell monitored by the terminal device when the terminal device is to be handed over from the current cell to the target cell; a first sending unit, configured to send a random access request to a target access base station when the handover execution conditions are determined to be met based on the predicted signal quality of the target cell, wherein the target access base station is the base station corresponding to the target cell; a second sending unit, configured to send a resource allocation request to the target access base station when receiving a random access response from the target access base station and the random access response indicating that the terminal device is allowed to randomly access the target cell; and a first execution unit, configured to perform a random access operation according to the target access link indicated by the resource allocation response to perform cell handover when receiving the resource allocation response from the target access base station, wherein the target access link is an access resource in an available state allocated to the terminal device by the target access base station in the order of high-orbit satellite link, low-orbit satellite link, and base station link.
[0007] In one exemplary embodiment, the apparatus further includes: a second execution unit, configured to continuously monitor the signal quality of the current cell, generate a measurement report, and send the generated measurement report to a current access base station, wherein the current access base station is the base station corresponding to the current cell; and a monitoring unit, configured to continuously monitor the signal quality of the target cell upon receiving a handover command returned by the current access base station based on the measurement report.
[0008] In an exemplary embodiment, the prediction unit includes: a first input module, configured to input a current signal quality sequence into a trained first prediction model to obtain the predicted signal quality, wherein the current signal quality sequence includes the signal quality of the target cell monitored in a continuous set of monitoring times, the first prediction model is a time series model, and the predicted signal quality is the predicted signal quality of the target cell at the time following the last monitoring time in the set of monitoring times; wherein the handover execution condition includes: the signal quality of the cell to be handed over is greater than or equal to a signal quality threshold.
[0009] In an exemplary embodiment, the apparatus further includes: a third execution unit, configured to, after sending a resource allocation request to the target access base station, in response to the received resource allocation request, perform the following link determination operation through the target access base station: if there is an available high-orbit satellite link in a set of high-orbit satellite links of the target cell, determine one available high-orbit satellite link as the target access link; if there is no available high-orbit satellite link in the set of high-orbit satellite links, select the target access link from the set of candidate links based on the link status of candidate links in a set of candidate links, wherein the set of candidate links includes a set of low-orbit satellite links of the target cell and a set of base station links of the target cell.
[0010] In an exemplary embodiment, the third execution unit includes: a second input module, configured to input the current link state information of each candidate link in the set of candidate links into a trained second prediction model to obtain a link prediction result, wherein the current link state information of each candidate link is used to indicate the link state of each candidate link at the current time, and the link prediction result is the predicted candidate link selected from the set of candidate links at the current time; and a determination module, configured to determine the candidate link indicated by the link prediction result as the selected target access link.
[0011] In one exemplary embodiment, the second prediction model is a long short-term memory model. The apparatus further includes: an acquisition unit, configured to acquire a training dataset, wherein one training data point in the training dataset corresponds to a specified time point within a specified time period; each training data point in the training dataset includes state feature information of each of a plurality of training access links at the specified time point corresponding to each training data point, and a training label corresponding to each training data point; the training label corresponding to each training data point is used to indicate which of the plurality of training access links is selected at the specified time point corresponding to each training data point; and a training unit, configured to perform multiple rounds of model training on the second prediction model to be trained using the training dataset to obtain a trained second prediction model.
[0012] In one exemplary embodiment, the apparatus further includes: a fourth execution unit, configured to, before performing a random access operation according to the target access link indicated by the resource allocation response, retain access resources allocated to the terminal device in the current cell through the current access base station, wherein the current access base station is the base station corresponding to the current cell; and an access unit, configured to, after performing a random access operation according to the target access link indicated by the resource allocation response, in the event of a cell handover failure of the terminal device, respond to a fallback request sent by the terminal device and, based on the access resources reserved for the terminal device, re-access the terminal device to the current cell through the current access base station.
[0013] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed by a processor.
[0014] According to another aspect of the embodiments of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform the steps in any of the method embodiments described above.
[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to perform the steps of any of the above method embodiments through the computer program.
[0016] This application allows for the prediction of signal quality in a target cell when a terminal device is waiting to switch from its current cell to a target cell. Based on the signal quality monitored by the terminal device, the signal quality of the target cell is predicted, and future signal quality is predicted based on historically monitored signal quality. This avoids frequent cell handovers and improves the timeliness of cell handovers. If the handover execution conditions are met based on the predicted signal quality of the target cell, a random access request is sent to the target access base station, where the target access base station is the base station corresponding to the target cell. Upon receiving a random access response from the target access base station, and the random access response indicating that the terminal device is allowed to randomly access the target cell, a resource allocation request is sent to the target access base station. Upon receiving a resource allocation response from the target access base station... In this case, a random access operation is performed according to the target access link indicated in the resource allocation reply for cell handover. The target access link is an available access resource allocated to the terminal device by the target access base station in the order of high-orbit satellite link, low-orbit satellite link, and base station link. Since the target access base station can allocate appropriate access resources to the terminal device among the high-orbit satellite link, low-orbit satellite link, and base station link, the terminal device can dynamically select the optimal access point among different links, thereby making full use of the access point and avoiding resource waste and uneven load. Different access points correspond to different spectrum resources, thus achieving the technical effect of improving spectrum resource utilization and solving the technical problem of low spectrum resource utilization in satellite communication methods in related technologies. Attached Figure Description
[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:
[0018] Figure 1 This is a schematic diagram illustrating an application scenario of a terminal device access cell handover method according to an embodiment of this application.
[0019] Figure 2 This is a flowchart illustrating an optional terminal device access cell handover method according to an embodiment of this application.
[0020] Figure 3 This is a schematic diagram of an optional terminal device access cell handover method according to an embodiment of this application.
[0021] Figure 4 This is a schematic diagram of another optional terminal device access cell handover method according to an embodiment of this application.
[0022] Figure 5 This is a schematic diagram of another optional terminal device access cell handover method according to an embodiment of this application.
[0023] Figure 6 This is a schematic diagram of another optional terminal device access cell handover method according to an embodiment of this application.
[0024] Figure 7 It is a C / I CDF diagram using mountain base stations and LSTM to predict channel quality information, and without using mountain base stations.
[0025] Figure 8 This is a structural block diagram of an optional terminal device access cell handover device according to an embodiment of this application.
[0026] Figure 9 This is a computer system architecture block diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation
[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0029] According to one aspect of the embodiments of this application, a method for handing over access cells to a terminal device is provided. Optionally, in this embodiment, the above-described method for handing over access cells to a terminal device may be applied, but is not limited to, to applications such as... Figure 1 The hardware environment shown includes terminal device 102 and base station 104. Base station 104 can be connected to terminal device 102 via a network and can be used to provide communication services to terminal device 102.
[0030] The aforementioned network may include a wireless network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wireless Fidelity (WIFI) and Bluetooth. Terminal device 102 may be, but is not limited to, a personal computer (PC), mobile phone, tablet computer, fixed station, and vehicle-mounted terminal, etc. Base station 104 may be, but is not limited to, a terrestrial base station, satellite base station, mountain base station, or other base station types.
[0031] The access cell handover method for the terminal device in this embodiment can be executed by the terminal device 102, or it can be jointly executed by the base station 104 and the terminal device 102. Taking the execution of the access cell handover method for the terminal device in this embodiment by the terminal device 102 as an example, Figure 2 This is a flowchart illustrating an optional access cell handover method for a terminal device according to an embodiment of this application, as shown below. Figure 2 As shown, the process of this method may include steps S202 to S208.
[0032] Step S202: When the terminal device is about to switch from the current cell to the target cell, the signal quality of the target cell is predicted based on the signal quality of the target cell monitored by the terminal device.
[0033] Step S204: If the handover execution conditions are met based on the predicted signal quality of the target cell, a random access request is sent to the target access base station, where the target access base station is the base station corresponding to the target cell.
[0034] Step S206: Upon receiving a random access response from the target access base station, and the random access response indicating that the terminal device is allowed to randomly access the target cell, a resource allocation request is sent to the target access base station.
[0035] Step S208: Upon receiving the resource allocation response from the target access base station, perform a random access operation according to the target access link indicated in the resource allocation response to perform cell handover. The target access link is an access resource that is available and allocated to the terminal device by the target access base station in the order of high-orbit satellite link, low-orbit satellite link, and base station link.
[0036] The terminal device access cell handover method in this embodiment can be applied to the field of wireless communication, specifically to scenarios where a terminal device switches from its current access cell to a target cell. A cell is the basic unit of a mobile communication network in the communication field, consisting of a geographical area covered by a base station. When a user moves between different cells, the system can automatically switch base stations to ensure communication continuity. Cells are typically in the form of a Tracking Area Code (TAC) grid, and the grid shape can be determined by fixed latitude and longitude intervals or a hexagonal cellular grid, serving as an identifier for locating the user's position.
[0037] With the continuous growth of global communication demands, satellite communication systems have become a key technology for extending terrestrial network coverage and ensuring communication capabilities in remote areas and mobile environments. However, satellite communication systems in related technologies are typically based on satellites in fixed orbits, which exposes many limitations when facing rapidly increasing data transmission demands and diverse communication scenarios, such as low resource utilization, high latency, coverage blind spots, and limited ability to respond to emergencies. Furthermore, these technologies lack coordinated scheduling among high-orbit satellites, low-orbit satellites, high-altitude base stations, and terrestrial base stations. For example, when switching cells, terminal devices can typically only access links of the same type (e.g., switching from one terrestrial base station to another, or from one satellite to another), and cannot switch across different types of links. This also prevents dynamic allocation of spectrum resources, potentially leading to resource overload in some areas and waste in others, resulting in low spectrum resource utilization.
[0038] Furthermore, in related technologies, terminal devices fail to consider future changes in the signal quality of the target cell when switching cells. This may lead to frequent cell switching due to deterioration in the signal quality of the target cell after switching to it, thus affecting the continuity of communication.
[0039] To at least partially solve the above-mentioned technical problems, in this embodiment, the terminal device can predict the signal quality of the target cell and select the target cell to access based on the prediction; the target access base station can select a suitable target access link for the terminal device from a variety of different links in the order of high-orbit satellite link, low-orbit satellite link and base station link, and the terminal device can access the target access link according to the indicated target access link, thereby realizing the handover across different types of links.
[0040] In this embodiment, when a terminal device is about to hand over from its current cell to a target cell, the terminal device can monitor the signal quality of the target cell and predict its future signal quality based on the monitored signal quality. Here, the terminal device can prepare to hand over to the target cell if it detects poor signal in the current cell or receives a handover command. Optionally, the terminal device can predict the signal quality of the target cell using a pre-trained model. The predicted signal quality can be the signal quality of the target cell at a future time or the trend of signal quality changes within a future time period.
[0041] When the handover execution conditions are met based on the predicted signal quality of the target cell, the terminal device can send a random access request to the target access base station, where the target access base station is the base station corresponding to the target cell, and the random access request is used to request random access to the target cell. A random access request is a signal used to initialize the communication link, and its purpose is to request access permission from the target cell. Optionally, the handover execution conditions may be that the predicted signal quality of the target cell remains higher than a preset signal quality threshold in the future time period, or that the predicted signal quality of the target cell is higher than the signal quality of the current cell at a future time, or other handover conditions based on the predicted signal quality indicating a higher target cell signal quality. This embodiment does not limit these conditions.
[0042] After receiving a random access request, the target access base station can return a random access response indication to the terminal device. If the terminal device receives the random access response from the target access base station, and the random access response indication allows the terminal device to randomly access the target cell, the terminal device can send a resource allocation request to the target access base station. This resource allocation request requests the allocation of access resources from the target cell for the terminal device, requesting the target access base station to allocate available access resources to the terminal device in order to establish a stable communication link.
[0043] After receiving a resource allocation request, the target access base station can allocate resources to the terminal device according to preset logic, including selecting a suitable target access link for the terminal device. Here, the target access link can be an available access resource allocated by the target access base station to the terminal device in the order of high-orbit satellite links, low-orbit satellite links, and base station links. High-orbit satellite links provide wide-area coverage, suitable for long-term service for static users and high-demand areas; the target access base station prioritizes allocating available high-orbit satellite links. Low-orbit satellite links provide dynamic coverage, suitable for mobile terminals and short-term high-bandwidth needs; when high-orbit satellite link resources are scarce, the target access base station can prioritize allocating low-orbit satellite link resources. Base station links provide communication signals from base stations; the coverage area of a single base station is usually small, so it is considered the least desirable link. When both high-orbit and low-orbit satellite links are unavailable, the target access base station can allocate base station link resources to the terminal device. Optionally, the target access base station can also select the most suitable target access link for the terminal device from high-orbit satellite links, low-orbit satellite links, and base station links based on the signal quality of each link, avoiding low-quality access and improving communication stability. After the target access base station determines the target access link, it can return a resource allocation response to the terminal device, indicating the target access link and the parameter information required for the terminal device to access the target access link.
[0044] Optionally, the target access base station can adopt a priority resource scheduling mechanism to ensure that high-orbit satellite link resources are preferentially allocated to long-term stable users; and low-orbit satellite links provide dynamic supplementation, with base station links as a backup, forming a multi-level resource scheduling scheme.
[0045] Upon receiving a resource allocation response from the target access base station, the terminal device can perform a random access operation according to the target access link indicated in the resource allocation response to perform cell handover. Optionally, as follows: Figure 3 As shown, the terminal device sends a random access request to the target access base station. The target access base station processes the random access request and sends a random access response. After receiving the random access response, the terminal device submits a resource allocation request to the target access base station. The target access base station performs resource scheduling and evaluation based on access priority and determines a target access link. Here, the access priority is in the order of high-orbit satellite link, low-orbit satellite link, and base station link. After determining the target access link, the target access base station sends a resource allocation response to the terminal device, indicating the target access link. The terminal device can then perform a random access operation based on the resource allocation response to complete access to the target access link in the target cell.
[0046] Optionally, when the target access link of the terminal device is a terrestrial base station, the terminal device can continuously monitor the resources of the low-Earth orbit satellite link, and switch to the available low-Earth orbit satellite link when there are available access resources on the low-Earth orbit satellite link.
[0047] The embodiments provided in this application, when a terminal device is waiting to switch from the current cell to a target cell, predict the signal quality of the target cell based on the signal quality monitored by the terminal device; if the handover execution conditions are met based on the predicted signal quality of the target cell, a random access request is sent to the target access base station, where the target access base station is the base station corresponding to the target cell; if a random access response is received from the target access base station, and the random access response indicates that the terminal device is allowed to randomly access the target cell, a resource allocation request is sent to the target access base station; if a resource allocation response is received from the target access base station, a random access operation is performed according to the target access link indicated in the resource allocation response to perform cell handover, wherein the target access link is an access resource that is available and allocated to the terminal device by the target access base station in the order of high-orbit satellite link, low-orbit satellite link, and base station link. This solves the technical problem of low spectrum resource utilization in satellite communication methods in related technologies and improves the utilization rate of spectrum resources.
[0048] In one exemplary embodiment, the method further includes: continuously monitoring the signal quality of the current cell, generating a measurement report, and sending the generated measurement report to the current access base station, wherein the current access base station is the base station corresponding to the current cell; and continuously monitoring the signal quality of the target cell upon receiving a handover command returned by the current access base station based on the measurement report.
[0049] In related technologies, terminal devices lack effective prediction and verification of the target cell's signal quality during cell handover. Furthermore, the terminal device does not consider channel quality changes during random access, which may lead to a deterioration in signal quality after cell handover, thus affecting communication stability. To at least partially address these issues, in this embodiment, the terminal device continuously monitors the signal quality of the current cell and prepares for handover if the current cell signal is poor. It also continuously monitors the signal quality of the target cell to which it will handover, and only performs the handover operation if the target cell signal is good.
[0050] In this embodiment, the terminal device continuously monitors the signal quality of the current cell, generates a measurement report, and sends the generated measurement report to the current access base station of the current cell. Similar to the target access base station, the current access base station is the base station corresponding to the current cell. Here, the monitored signal quality may include, but is not limited to, all or some of the indicators such as signal strength, signal-to-interference ratio, and bit error rate. Optionally, the terminal device may continuously monitor the signal quality of the current cell, but only generate a measurement report and send the generated measurement report to the current access base station when a handover preparation event is triggered. Here, the handover preparation event can be triggered when the signal quality of the current cell is less than a preset threshold.
[0051] After receiving a detection report, the current cell can send a handover request to the target cell. Upon receiving a response from the target cell, it returns a handover command to the terminal device. Here, the current cell can select a neighboring cell as the target cell. The returned handover command can specify the target cell and include the parameters required for the terminal device to locate it. It should be noted that the operations performed by both the current cell and the target cell are executed by their respective current access base station and target access base station.
[0052] When a terminal device receives a handover command from the currently accessed base station based on a measurement report, the terminal device can continuously monitor the signal quality of the target cell, where the target cell is the cell to which the terminal device is to hand over, as indicated in the handover command. Optionally, monitoring the signal quality of the target cell can be similar to monitoring the signal quality of the current cell, monitoring indicators such as signal strength, signal-to-interference ratio, and bit error rate.
[0053] Subsequently, similar to the aforementioned embodiments, the terminal device can predict the signal quality of the target cell based on the signal quality monitored by the terminal device. If the terminal device determines that the handover execution conditions are met based on the predicted signal quality of the target cell, it can trigger a handover operation to switch the terminal device from the current cell to the target cell. Optionally, the handover execution conditions can be set based on experience. For example, the signal quality of the target cell can reach a preset threshold, or the signal quality of the target cell can be higher than that of the current cell. This embodiment does not limit this. The triggered handover operation includes the random access operation in the aforementioned embodiments, which will not be elaborated here.
[0054] Optionally, such as Figure 4As shown, the terminal device monitors the signal quality of the current cell. When the signal quality falls below a threshold, a preparation event is triggered, and a measurement report is sent to the current cell. The current cell makes a handover decision and sends a handover request to the target cell. Upon receiving the handover request, the target cell assesses the current resource status. If resources are available, it allows the terminal device to handover through admission control and transmits the handover command to the current cell in response to the handover request. Finally, the current cell sends the handover command to the terminal device. After receiving the handover command, the terminal device stores the handover command, monitors the signal quality of the target cell, and assesses the feasibility of the handover operation. If the feasibility is satisfied, the handover execution steps are initiated. During the handover, the terminal device synchronizes with the target cell and initiates random access to complete the handover.
[0055] In this embodiment, the terminal device continuously monitors the network status of the current cell, generates a monitoring report in preparation for cell handover when the signal is poor, and continuously monitors the signal quality of the target cell, which can improve the stability of cell handover and ensure that the signal quality can be improved after the cell handover.
[0056] In an exemplary embodiment, predicting the signal quality of a target cell based on the signal quality of the target cell monitored by the terminal device includes: inputting a current signal quality sequence into a trained first prediction model to obtain a predicted signal quality, wherein the current signal quality sequence includes the signal quality of the target cell monitored in a continuous set of monitoring times, the first prediction model is a time series model, and the predicted signal quality is the predicted signal quality of the target cell at the time following the last monitoring time in the set of monitoring times.
[0057] In this embodiment, the handover execution condition includes: the signal quality of the cell to be handed over to is greater than or equal to a signal quality threshold. Correspondingly, when the predicted signal quality is greater than or equal to the signal quality threshold, the handover execution condition is met, and in this case, the terminal device can send a random access request to the target access base station.
[0058] In related technologies, there is a lack of intelligent prediction capabilities in random access or handover decisions, failing to consider future signal changes. These technologies only trigger handover based on fixed signal thresholds, failing to intelligently predict handover success rates. In this embodiment, a first prediction model can predict the signal quality of the target cell, dynamically assessing the feasibility of handover. The terminal device can then execute the handover based on the prediction results, thereby improving handover stability. Here, the first prediction model is a time series model, which can predict the signal quality of the next moment based on the signal quality of consecutive moments in the past time period. Optionally, the first prediction model can be a Long Short-Term Memory (LSTM) network. LSTM is a time-recurrent neural network that can remember long-term information and is suitable for processing sequential data.
[0059] After receiving a handover command, the terminal device can continuously monitor the signal quality of the target cell and acquire the current signal quality sequence. This current signal quality sequence is then input into a trained first prediction model to obtain the predicted signal quality output by the first prediction model, thus predicting the signal quality at the next moment. The current signal quality sequence includes the signal quality of the target cell monitored over a continuous set of monitoring times. The first prediction model is a time series model, and the predicted signal quality is the signal quality of the target cell at the moment following the last monitoring time in the set of monitoring times. Here, the current signal quality sequence, encompassing the signal quality of the target cell monitored over a continuous set of monitoring times, provides a time window for signal changes, allowing the model to predict trends. After inputting the current signal quality sequence into the trained first prediction model, the first prediction model can capture the trend of signal quality changes over time, predict the change in signal quality at the next moment, and output the predicted signal quality of the target cell at the next moment. Optionally, the predicted signal quality can be represented numerically or probabilistically to indicate the signal quality level of the target cell at the next moment.
[0060] After obtaining the predicted signal quality, it can be determined whether the predicted signal quality of the target cell meets the handover conditions. Here, the handover execution conditions include: the signal quality of the cell to be handed over to is greater than or equal to a signal quality threshold. That is, if the predicted signal quality is greater than or equal to the signal quality threshold, it can be determined that the handover execution conditions are met. Here, the signal quality threshold can be a preset fixed threshold, or it can be a threshold dynamically adjusted based on the current cell's signal quality. For example, the signal quality threshold can be equal to or higher than the current signal quality of the current cell to ensure that the signal quality does not degrade after handover to the target cell.
[0061] In this embodiment, the future signal quality of the target cell is predicted by the first prediction model, and a decision on whether to perform a handover operation is made based on the prediction results. This can improve the accuracy of handover decisions and enhance the stability of communication.
[0062] In an exemplary embodiment, after sending a resource allocation request to the target access base station, the method further includes: in response to the received resource allocation request, performing the following link determination operation through the target access base station: if there is an available high-orbit satellite link in a set of high-orbit satellite links of the target cell, determining the available high-orbit satellite link as the target access link; if there is no available high-orbit satellite link in a set of high-orbit satellite links, selecting the target access link from a set of candidate links based on the link status of candidate links in a set of candidate links, wherein the set of candidate links includes a set of low-orbit satellite links of the target cell and a set of base station links of the target cell.
[0063] Because high-orbit satellite links offer the widest signal coverage and most stable connection, the target access base station can prioritize allocating high-orbit satellite link resources. If high-orbit satellite link resources are unavailable, the target access link can then be selected from a set of alternative links. This set of alternative links includes a set of low-orbit satellite links for the target cell and a set of base station links for the target cell. Optionally, the set of base station links may include a set of mountain base station links and a set of terrestrial base station links. Mountain base station links, deployed in high-altitude areas, can cover terrestrial satellite signal blind spots and serve as priority access when high-orbit and low-orbit satellite link resources are unavailable. Terrestrial base station links can cover the needs of ordinary terrestrial users and provide fallback access capabilities when all satellite links and mountain base station links are unavailable.
[0064] In this embodiment, in response to the received resource allocation request, the target access base station can first determine the available high-orbit satellite links in a group of high-orbit satellite links of the target cell. If there is an available high-orbit satellite link in a group of high-orbit satellite links of the target cell, the target access base station will determine one of the available high-orbit satellite links as the target access link, thereby achieving priority allocation of the high-orbit satellite link.
[0065] If no usable high-orbit satellite link exists in a set of high-orbit satellite links, low-orbit satellite links and base station links are used as supplementary resources. Based on the link status of the candidate links in a set of candidate links, a target access link is selected from the set of candidate links by the target access base station. This set of candidate links includes a set of low-orbit satellite links and a set of base station links of the target cell. Optionally, the link with the best current link status in the set of candidate links can be selected as the target access link. Alternatively, future link status changes can be predicted using a model, and the link with the best future link status can be selected as the target access link to ensure the quality of the selected target access link and ensure that the terminal equipment can obtain stable and efficient communication services.
[0066] In this embodiment, by prioritizing high-orbit satellite links, the terminal equipment can be ensured to obtain the maximum signal coverage, thereby improving the stability and continuity of communication services. By using low-orbit satellite links and base station links as supplements, different types of link resources can be flexibly scheduled, improving the utilization efficiency of different types of link resources.
[0067] In an exemplary embodiment, selecting a target access link from a set of candidate links based on the link status of the candidate links in the set of candidate links includes: inputting the current link status information of each candidate link in the set of candidate links into a trained second prediction model to obtain a link prediction result; and determining the candidate link indicated by the link prediction result as the selected target access link.
[0068] In related technologies, access links are typically selected based on the current instantaneous channel quality, without considering historical trends and predicted future trends, leading to inaccurate selection of target access links. To address this issue, this embodiment utilizes a second prediction model to predict channel quality, assessing the channel availability and link status of each candidate link in advance. This reduces access failures and unnecessary handovers, improves access success rate, and ultimately enhances system stability and user experience. Optionally, the second prediction model can be LSTM.
[0069] In this embodiment, if it is determined that there is no usable high-orbit satellite link in a set of high-orbit satellite links, a target access link can be selected from a set of candidate links. The method for selecting a target access link can be as follows: input the current link state information of each candidate link in the set of candidate links into a trained second prediction model to obtain the link prediction result output by the second prediction model. Here, the current link state information of each candidate link is used to indicate the link state of each candidate link at the current time, and the link prediction result is the predicted candidate link selected from the set of candidate links at the current time.
[0070] Optionally, the link prediction result can be in the form of a probability distribution, indicating the probability of selecting each candidate link. The candidate link with the highest selection probability is the candidate link indicated by the link prediction result. After obtaining the link prediction result, the target access base station can determine the candidate link indicated by the link prediction result as the selected target access link, thus completing the selection of the target access link from the candidate links.
[0071] In this embodiment, by using the prediction results of the second prediction model to select the target access link, future changes in the link status can be taken into account in the link selection, avoiding the selection of links whose signal quality will deteriorate, thereby enhancing the continuity and stability of communication.
[0072] In one exemplary embodiment, the second prediction model is a Long Short-Term Memory (LSTM) model. Correspondingly, the method further includes: acquiring a training dataset, wherein one training data point in the training dataset corresponds to a specified time point within a specified time period, and each training data point in the training dataset includes state feature information of each training access link among multiple training access links at the specified time point corresponding to each training data point, and a training label corresponding to each training data point, wherein the training label corresponding to each training data point is used to indicate which training access link among the multiple training access links is selected at the specified time point corresponding to each training data point.
[0073] Before training the model, it is necessary to obtain the training dataset by collecting channel quality data at multiple times from multiple training access links over a period of time, including signal strength, bit error rate, etc., and then performing the corresponding preprocessing to obtain the training dataset.
[0074] Here, the training dataset is a dataset specifically used for training the second prediction model. It includes the state feature information of each training access link in multiple training access links within a specified time period at each time step. The data has been preprocessed, and each time step has a training label. Optionally, the state feature information of a training access link at a time step may include signal strength, signal-to-interference ratio, bit error rate, throughput, etc. Here, a state feature information can be used as an input feature. The training dataset includes multiple input features xt, and the format of an input feature xt is shown in formula (1):
[0075] xt=[SNR, C / I, BER, Throughput, ...](1)
[0076] Where SNR is signal strength, C / I is signal-to-interference ratio, BER is bit error rate, and Throughput is throughput.
[0077] Here, since the model's prediction objective is to predict the most suitable target access link for access at the next time t+1, there can be N training access links. That is, the target access point has N possible choices, including multiple high-orbit satellite links, multiple low-orbit satellite links, and multiple base station links. The final output of the second prediction model will be the corresponding yt containing N elements, representing the selection probability of each access link.
[0078] After obtaining the above multiple input features xt, the data needs to be preprocessed, such as... Figure 5 As shown, multiple input features can first be segmented into time series, dividing the data into multiple time segments according to time windows. Each time segment contains data from T time steps. For example, if each time window is T time steps in size, the input is a sequence consisting of xt-T+1, xt-T+2 to xt, and a time segment contains the input features of all training access links at all times within that time window.
[0079] To avoid dimensional differences between different features in different ranges, it is necessary to standardize each input feature. For any input feature xt(i), the standardization formula is shown in formula (2):
[0080]
[0081] in, This is the mean of the input feature. The standard deviation of the input feature is given above. The mean and standard deviation are calculated based on all input features within the time period to which the input feature belongs.
[0082] After this, missing values for each input feature can be filled. If an input feature has too many missing values to fill, the input feature can be discarded.
[0083] Finally, label generation is performed. For each time t, a corresponding training label needs to be generated to represent the target training link most suitable for access at that time. That is, the corresponding training label is used to indicate which training access link is selected at a specified time corresponding to each training data among multiple training access links. Here, the training label can be in the form of a one-hot encoded vector. For example, when the target access link at time t is i, the training label at time t is as shown in formula (3):
[0084]
[0085] Here, the i-th value is 1, and yt(i)=1 indicates that the training access link i is the target access link at time t.
[0086] Correspondingly, after obtaining the training dataset, multiple rounds of model training are performed on the second prediction model to be trained using the training dataset to obtain the trained second prediction model.
[0087] Optionally, such as Figure 6 As shown, the structure of the second prediction model is first determined to be an LSTM model, and the LSTM model computation process begins. The LSTM model consists of multiple LSTM units and fully connected layers. Each LSTM unit can update its own state based on the input sequence and past states.
[0088] For time step t, the computation of an LSTM cell includes the forget gate, input gate, output gate, and update of the memory cell state. Here, the forget gate is shown in equation (4):
[0089]
[0090] Where σ is the sigmoid activation function, Wf and bf are the weights and biases of the forget gate, ht−1 is the hidden state at the previous time step, xt is the input at the current time step, and the hidden state is the output of the output gate.
[0091] The input gate is shown in formula (5):
[0092]
[0093] Here, it is the output of the input gate, which determines which information should be written into the memory unit, and Wi and bi are the weights and biases of the input gate.
[0094] Candidate memory units are shown in formula (6):
[0095] t=tanh(Wc*[ht-1,xt]+bc) (6)
[0096] in, t is a candidate memory cell, and Wc and bc are the weights and biases of the candidate memory cell.
[0097] The memory unit is shown in formula (7):
[0098] Ct = ft * Ct - 1 + it * t(7)
[0099] Where Ct is the current state of the memory unit, Ct−1 is the memory unit from the previous time step, ft*Ct−1 controls the forgetting of the previous memory, and it* t controls the addition of new information.
[0100] The output gate is shown in equation (8):
[0101] ot=σ(Wo*[ht-1,xt]+bo)(8)
[0102] Where ot is the output of the output gate, which determines the hidden state ht at the current time step, and it can be used as the input at the next time step. Wo and bo are the weights and biases of the output gate. The hidden state is shown in formula (9):
[0103] ht=ot*tanh(Ct)(9)
[0104] Based on the above update method, the memory unit is updated multiple times in chronological order using the training dataset until all data in the training dataset is used to complete the update of the memory unit.
[0105] The hidden state ht of the output network of the output gate needs to be transformed into a probability distribution as the model output, which represents the selection probability of each training access link. Here, the Softmax function can be used to transform it in the Softmax output layer. Suppose there are N training access links, and the Softmax function is as shown in formula (10):
[0106] =Softmax(Wo*ht+bo) (10)
[0107] in, For the predicted probability distribution, Wo and bo are the weights and biases of the output gate.
[0108] The loss function of the second prediction model can be the cross-entropy loss function, which measures the difference between the predicted target access link and the training label. For each time t, the cross-entropy loss function is calculated as shown in Equation (11):
[0109]
[0110] in, These are training labels. It is the predicted probability distribution.
[0111] Then, the Adam optimizer can be used to perform gradient descent optimization and update the model parameters. The update formula for the Adam optimizer is shown in formula (12):
[0112]
[0113] in, It's the learning rate. and It is an estimate of the gradient's momentum and variance. It is a small constant used to prevent division by zero errors. The overall training process includes forward propagation of the input data through the LSTM model, and computation of the output. The loss function at each time step is calculated using the cross-entropy loss function; the gradient is calculated using the backpropagation algorithm; and the model parameters are updated using the Adam optimizer. The second prediction model is then obtained after training.
[0114] In this embodiment, by using an LSTM model as the second prediction model and training the second prediction model with a training dataset, the accuracy of the second prediction model can be improved.
[0115] In one exemplary embodiment, the method further includes: before performing a random access operation according to the target access link indicated in the resource allocation reply, the method further includes: reserving access resources allocated to the terminal device in the current cell through the current access base station, wherein the current access base station is the base station corresponding to the current cell; after performing a random access operation according to the target access link indicated in the resource allocation reply, the method further includes: in the event of a cell handover failure of the terminal device, in response to a backoff request sent by the terminal device, re-accessing the terminal device to the current cell through the current access base station based on the access resources reserved for the terminal device.
[0116] In related technologies, there are shortcomings in the handover failure handling mechanism. During handover, the cell before the handover does not reserve resources for the outgoing terminal device. In the event of a handover failure, it is impossible to quickly reconnect to the cell before the handover, which may lead to communication interruption. In this embodiment, the current access base station reserves the access resources allocated to the terminal device in the current cell when the terminal device performs a handover. In the event of a handover failure, the terminal device can reconnect to the current cell based on the reserved access resources, ensuring that communication is not interrupted.
[0117] Here, the access resources reserved by the current access base station are the access resources allocated to the terminal device in the current cell. In the event of a handover failure, the terminal device can send a fallback request to the current access base station, which can respond to the fallback request and use the reserved access resources to reconnect the terminal device to the current cell.
[0118] In this embodiment, by introducing resource reservation and failure fallback mechanisms, the current cell reserves access resources for terminal devices before handover, and a re-access method after handover. This allows for a quick fallback to the current cell in case of handover failure, reducing communication interruptions caused by factors such as channel fading and unavailability of the target cell, and improving user experience.
[0119] The following explanation, using optional examples, illustrates the terminal device access cell handover method in this application embodiment. In this optional example, the terminal device access cell handover method is described in an earthquake scenario. In an earthquake scenario, ground base stations are damaged, and user terminals need to prioritize accessing high-orbit satellite links for emergency communication. When high-orbit satellite link resources are scarce, user terminals can sequentially attempt to access low-orbit satellite links and high-altitude base station links. Specific steps include:
[0120] Preparation for event triggering and measurement report transmission: The user terminal monitors the high-orbit satellite link signal and sends a measurement report.
[0121] Handover decision and command issuance: The high-orbit satellite link initiates a handover request to the low-orbit satellite link or the high-mountain base station link, and the low-orbit satellite link or the high-mountain base station link receives and issues a handover command.
[0122] The feasibility of handover is assessed using an LSTM model to evaluate channel quality parameters: the user terminal monitors the signal status of the target cell and performs handover based on the actual situation.
[0123] Random access and resource scheduling: After the handover is completed, the terminal accesses the mountain base station and completes random access. After successful access, the channel quality continues to be monitored.
[0124] For example, such as Figure 7 As shown, Figure 7 The graph shows the Carrier-to-Interference Ratio Cumulative Distribution Function (C / I CDF) for links using mountain base stations and LSTM-predicted channel quality information, and links without mountain base stations. The C / I for links using mountain base stations and LSTM-predicted channel quality information is represented by a dashed line, while the C / I for links without mountain base stations is represented by a dotted line. Figure 7 It is evident that if mountain base station links can be used in random access, and LSTM is used to predict channel information quality, the link C / I is improved compared to not using mountain base station links.
[0125] This optional example demonstrates how LSTM prediction can improve handover success rates and avoid unnecessary handovers. Intelligent prediction, dynamic resource scheduling, and high-Earth orbit (HEO) / low-Earth orbit (LEO) collaborative optimization enhance terminal access efficiency, optimize handover management, and improve system reliability and stability. Dynamic allocation strategies for spectrum resources among HEO / LLE star links and terrestrial base station links, methods for terminal access path selection based on LSTM-predicted link channel state information, and strategies for seamless handover between HEO / LLE star links and terrestrial base station links improve system spectrum resource utilization. The application of LSTM models in access selection, along with methods for access path optimization based on channel quality prediction and strategies for dynamic access adjustment using historical data, enhances system stability and user experience. Overall, this significantly improves the access efficiency, handover stability, and user experience of the communication system.
[0126] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0127] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0128] According to another aspect of the embodiments of this application, an access cell handover apparatus for a terminal device is also provided. This access cell handover apparatus for a terminal device can be used to implement the access cell handover method for a terminal device provided in the above embodiments, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0129] Figure 8 This is a structural block diagram of an optional access cell handover device for a terminal device according to an embodiment of this application, such as... Figure 8 As shown, the access cell handover device of the terminal equipment includes:
[0130] The prediction unit 802 is used to predict the signal quality of the target cell based on the signal quality of the target cell monitored by the terminal device when the terminal device is about to switch from the current cell to the target cell.
[0131] The first sending unit 804 is used to send a random access request to the target access base station through the terminal device when the handover execution conditions are met based on the predicted signal quality of the target cell. The target access base station is the base station corresponding to the target cell.
[0132] The second sending unit 806 is used to send a resource allocation request to the target access base station through the terminal device when it receives a random access reply returned by the target access base station and the random access reply indicates that the terminal device is allowed to randomly access the target cell. The resource allocation request is used to request the allocation of access resources of the target cell for the terminal device.
[0133] The first execution unit 808 is used to perform a random access operation by the terminal device according to the target access link indicated in the resource allocation reply when receiving the resource allocation reply from the target access base station, so as to perform cell handover. The target access link is an access resource that is in an available state and is allocated to the terminal device by the target access base station in the order of high-orbit star link, low-orbit star link and base station link.
[0134] It should be noted that the prediction unit 802 in this embodiment can be used to execute the above step S202, the first sending unit 804 in this embodiment can be used to execute the above step S204, the second sending unit 806 in this embodiment can be used to execute the above step S206, and the first execution unit 808 in this embodiment can be used to execute the above step S208.
[0135] The embodiments provided in this application, when a terminal device is waiting to switch from the current cell to a target cell, predict the signal quality of the target cell based on the signal quality monitored by the terminal device; if the handover execution conditions are met based on the predicted signal quality of the target cell, a random access request is sent to the target access base station, where the target access base station is the base station corresponding to the target cell; if a random access response is received from the target access base station, and the random access response indicates that the terminal device is allowed to randomly access the target cell, a resource allocation request is sent to the target access base station; if a resource allocation response is received from the target access base station, a random access operation is performed according to the target access link indicated in the resource allocation response to perform cell handover, wherein the target access link is an access resource that is available and allocated to the terminal device by the target access base station in the order of high-orbit satellite link, low-orbit satellite link, and base station link. This solves the technical problem of low spectrum resource utilization in satellite communication methods in related technologies and improves the utilization rate of spectrum resources.
[0136] In one exemplary embodiment, the apparatus further includes: a second execution unit, configured to continuously monitor the signal quality of the current cell through a terminal device, generate a measurement report, and send the generated measurement report to the current access base station, wherein the current access base station is the base station corresponding to the current cell; and a monitoring unit, configured to continuously monitor the signal quality of the target cell through the terminal device upon receiving a handover command returned by the current access base station based on the measurement report.
[0137] In an exemplary embodiment, the prediction unit includes: an input unit, configured to input the current signal quality sequence into a trained first prediction model via a terminal device to obtain the predicted signal quality, wherein the current signal quality sequence includes the signal quality of the target cell monitored in a continuous set of monitoring times, the first prediction model is a time series model, and the predicted signal quality is the predicted signal quality of the target cell at the time following the last monitoring time in the set of monitoring times; wherein the handover execution condition includes: the signal quality of the cell to be handed over is greater than or equal to a signal quality threshold.
[0138] In an exemplary embodiment, the apparatus further includes a second determining unit, configured to, after sending a resource allocation request to a target access base station, perform the following link determining operation through the target access base station in response to the received resource allocation request: if there is an available high-orbit satellite link in a set of high-orbit satellite links of the target cell, determine one available high-orbit satellite link as the target access link; if there is no available high-orbit satellite link in a set of high-orbit satellite links, select the target access link from a set of candidate links based on the link status of candidate links in a set of candidate links, wherein the set of candidate links includes a set of low-orbit satellite links of the target cell and a set of base station links of the target cell.
[0139] In an exemplary embodiment, the second determining unit includes: an input module, configured to input the current link state information of each candidate link in a set of candidate links into a trained second prediction model via a target access base station to obtain a link prediction result, wherein the current link state information of each candidate link is used to indicate the link state of each candidate link at the current time, and the link prediction result is the predicted candidate link selected from the set of candidate links at the current time; and a determining module, configured to determine the candidate link indicated by the link prediction result as the selected target access link via the target access base station.
[0140] In one exemplary embodiment, the second prediction model is a long short-term memory model. The apparatus further includes: an acquisition unit, configured to acquire a training dataset, wherein one training data point in the training dataset corresponds to a specified time point within a specified time period; each training data point in the training dataset includes state feature information of each of the multiple training access links at the specified time point corresponding to each training data point, and a training label corresponding to each training data point; the training label corresponding to each training data point is used to indicate which of the multiple training access links is selected at the specified time point corresponding to each training data point; and a training unit, configured to perform multiple rounds of model training on the second prediction model to be trained using the training dataset to obtain a trained second prediction model.
[0141] In one exemplary embodiment, the apparatus further includes: a reservation unit, configured to reserve access resources allocated to the terminal device in the current cell via the current access base station before performing a random access operation via the target access link indicated in the resource allocation reply, wherein the current access base station is the base station corresponding to the current cell; and an access unit, configured to, after performing a random access operation via the terminal device via the target access link indicated in the resource allocation reply, in the event of a cell handover failure of the terminal device, respond to a backoff request sent by the terminal device and, based on the access resources reserved for the terminal device, re-access the terminal device to the current cell via the current cell.
[0142] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.
[0143] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program executes the steps in any of the above method embodiments when it is run.
[0144] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.
[0145] According to another aspect of the embodiments of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor is configured to perform the steps of any of the method embodiments described above via the computer program. In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0146] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.
[0147] According to another aspect of the embodiments of this application, a computer program product is also provided, comprising a computer program / instructions containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication section 909, and / or installed from a removable medium 911. When the computer program is executed by a central processing unit 901, it performs various functions provided in the embodiments of this application. The sequence numbers of the embodiments of this application above are merely descriptive and do not represent the superiority or inferiority of the embodiments.
[0148] Figure 9 A schematic block diagram of a computer system architecture for implementing embodiments of the present application is shown. Figure 9As shown, the computer system 900 includes a Central Processing Unit (CPU) 901, which performs various appropriate actions and processes based on programs stored in ROM 902 or loaded into RAM 903 from storage section 908. Random Access Memory 903 also stores various programs and data required for system operation. The CPU 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / Output (I / O) interface 905 is also connected to bus 904.
[0149] The following components are connected to I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), and speakers, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card, such as a local area network card or modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to I / O interface 905 as needed. Removable media 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 910 as needed so that computer programs read from them can be installed into storage section 908 as needed.
[0150] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 909, and / or installed from removable medium 911. When the computer program is executed by central processing unit 901, it performs various functions defined in the system of this application.
[0151] It should be noted that, Figure 9 The computer system 900 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0152] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.
[0153] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.
Claims
1. A method for handing over access cells to a terminal device, characterized in that, The method comprises: In the case where the terminal device is to be handed over from a current cell to a target cell, predicting the signal quality of the target cell according to the signal quality of the target cell monitored by the terminal device; In the case where it is determined that the handover execution condition is met based on the predicted signal quality of the target cell, sending a random access request to a target access base station, wherein the target access base station is a base station corresponding to the target cell; In the case where a random access reply of the target access base station is received and the random access reply indicates that the terminal device is allowed to randomly access the target cell, sending a resource allocation request to the target access base station; In the case where a resource allocation reply of the target access base station is received, performing a random access operation according to the target access link indicated by the resource allocation reply to perform cell handover, wherein the target access link is an access resource in an available state allocated by the target access base station for the terminal device in the order of a high-orbit satellite link, a low-orbit satellite link and a base station link; In the case where there is no high-orbit satellite link in an available state in a group of high-orbit satellite links of the target cell, the target access link is an alternative link indicated by a link prediction result, the link prediction result is obtained by inputting current link state information of each alternative link in a group of alternative links into a trained second prediction model, and the group of alternative links includes a group of low-orbit satellite links of the target cell and a group of base station links of the target cell; The second prediction model is a long short-term memory model. The method further comprises: obtaining a training data set, wherein one training data in the training data set corresponds to a specified time of a specified period, each training data in the training data set includes state feature information of each training access link in a plurality of training access links at the specified time corresponding to the each training data, and a training label corresponding to the each training data, the training label corresponding to the each training data is used to indicate a training access link selected from the plurality of training access links at the specified time corresponding to the each training data; performing multiple rounds of model training on the second prediction model to be trained using the training data set to obtain the trained second prediction model.
2. The method of claim 1, wherein, The method further comprises: Continuously monitoring the signal quality of the current cell, generating a measurement report, and sending the generated measurement report to a current access base station, wherein the current access base station is a base station corresponding to the current cell; In the case where a handover command returned by the current access base station based on the measurement report is received, continuously monitoring the signal quality of the target cell.
3. The method of claim 1, wherein, The prediction of the signal quality of the target cell according to the signal quality of the target cell monitored by the terminal device comprises: inputting a current signal quality sequence into a trained first prediction model to obtain a predicted signal quality, wherein the current signal quality sequence comprises signal qualities of the target cell monitored at a continuous group of monitoring time instants, the first prediction model is a time series model, and the predicted signal quality is a predicted signal quality of the target cell at a next time instant of a last monitoring time instant in the group of monitoring time instants; wherein the handover execution condition comprises that a signal quality of a cell to be switched to is greater than or equal to a signal quality threshold.
4. The method of claim 1, wherein, After the resource allocation request is sent to the target access base station, the method further comprises: in response to the received resource allocation request, performing, by the target access base station, a link determination operation as follows: in a case where, in the group of high-orbit satellite links of the target cell, there is a high-orbit satellite link in an available state, determining the high-orbit satellite link in the available state as the target access link; in a case where, in the group of high-orbit satellite links, there is no high-orbit satellite link in an available state, selecting the target access link from a group of candidate links based on link states of candidate links in the group of candidate links.
5. The method of claim 4, wherein, The selecting the target access link from the group of candidate links based on the link states of candidate links in the group of candidate links comprises: inputting current link state information of each candidate link in the group of candidate links into a trained second prediction model to obtain a link prediction result, wherein the current link state information of each candidate link is used to indicate a link state of the each candidate link at a current time instant, and the link prediction result is a predicted candidate link selected from the group of candidate links at the current time instant; determining the candidate link indicated by the link prediction result as the selected target access link.
6. The method of claim 1, wherein, The method further comprises: before performing the random access operation according to the target access link indicated by the resource allocation reply, the method further comprises reserving, by a current access base station, an access resource allocated for the terminal device in the current cell, wherein the current access base station is a base station corresponding to the current cell; after performing the random access operation according to the target access link indicated by the resource allocation reply, in a case where the terminal device fails in the cell handover, in response to a fallback request sent by the terminal device, reaccessing, by the current access base station, the terminal device to the current cell based on the reserved access resource for the terminal device.
7. An access cell switching apparatus of a terminal device, characterized by comprising: comprise: a prediction unit, configured to, in a case where a terminal device is to be handed over from a current cell to a target cell, predict a signal quality of the target cell according to signal qualities of the target cell monitored by the terminal device; a first sending unit, configured to, in a case where it is determined that a handover execution condition is met based on a predicted signal quality of the target cell, send a random access request to a target access base station, wherein the target access base station is a base station corresponding to the target cell. a second sending unit, configured to send a resource allocation request to the target access base station in a case where a random access reply of the target access base station is received and the random access reply indicates that the terminal device is allowed to randomly access the target cell; a first executing unit, configured to perform a random access operation according to a target access link indicated by a resource allocation reply of the target access base station in a case where the resource allocation reply is received, so as to perform cell switching, wherein the target access link is an access resource in an available state allocated by the target access base station to the terminal device in an order of a high-orbit satellite link, a low-orbit satellite link and a base station link; in a case where there is no high-orbit satellite link in an available state in a group of high-orbit satellite links of the target cell, the target access link is an alternative link indicated by a link prediction result, the link prediction result is obtained by inputting current link state information of each alternative link in a group of alternative links into a trained second prediction model, and the group of alternative links includes a group of low-orbit satellite links of the target cell and a group of base station links of the target cell; the second prediction model is a long short-term memory model; the apparatus further includes an obtaining unit configured to obtain a training data set, wherein one training data in the training data set corresponds to a specified time point in a specified time period, each training data in the training data set includes state feature information of each training access link in a plurality of training access links at the specified time point corresponding to the each training data, and a training label corresponding to the each training data, the training label corresponding to the each training data is used to indicate a training access link selected from the plurality of training access links at the specified time point corresponding to the each training data; and a training unit configured to perform multiple rounds of model training on the second prediction model to be trained by using the training data set, to obtain the trained second prediction model.
8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.
Citation Information
Patent Citations
Cellular Core Network and Radio Access Network Infrastructure and Management in Space
US20220052753A1