Satellite-ground integrated layered handover method and device for high-speed train communication and medium

Abstract

This application relates to the field of wireless communication and intelligent decision-making technology, and discloses a satellite-ground integrated hierarchical handover method, device, and medium for high-speed train communication. The method includes constructing a satellite-ground integrated wireless communication system; dividing the operating time of the satellite-ground integrated wireless communication system into discrete time slots, in which each base station broadcasts status information to high-speed trains within its coverage area; constructing a channel model and corresponding communication performance evaluation indicators; using the communication performance evaluation indicators and the base station resource occupancy status information of candidate base stations to evaluate the link service capability of candidate base stations and obtain evaluation results; constructing a link handover decision model, inputting the evaluation results into the link handover decision model, and obtaining a link handover decision; the high-speed train establishes a communication link with the target base station according to the link handover decision, realizing the dynamic handover of the high-speed train to the serving base station in the satellite-ground integrated wireless communication system, improving the achievable link rate, and reducing frequent handovers caused by link fluctuations.

Description

Technical Field

[0001] This application relates to the fields of wireless communication and intelligent decision-making technology, specifically to a satellite-ground integrated hierarchical handover method, equipment, and medium for high-speed train communication. Background Technology

[0002] With the rapid growth in demand for mobile communication services, traditional terrestrial wireless communication networks are increasingly unable to meet the communication needs of high-speed mobile scenarios in terms of coverage and service continuity. This is especially true in high-speed train communication scenarios, where high train speeds and drastic changes in the link environment lead to frequent communication link switching, resulting in communication interruptions, increased latency, and data loss. Low Earth Orbit (LEO) satellites, with their advantages of wide coverage and flexible deployment, can collaborate with terrestrial trackside base stations to build a space-ground integrated communication system. This effectively improves communication coverage and service continuity, and has become an important development direction for high-speed mobile communications.

[0003] To address the frequent handover issues in space-ground converged communications, existing research primarily employs threshold-triggered methods based on signal strength, distance, or elevation angle, as well as path selection methods based on optimization or graph theory. While these methods can reduce handover failure rates or improve link quality to some extent, they struggle to balance multiple performance metrics such as communication rate, latency, and load balancing, and their adaptability in dynamic environments is limited. Furthermore, some studies have introduced reinforcement learning methods to learn strategies through interaction with the environment and optimize handover decisions. However, existing methods are mostly focused on single-user or single-network scenarios, and for the complex collaborative decision-making problems involving multiple trains and multiple links operating in parallel within a space-ground converged environment, an effective unified modeling and optimization mechanism is still lacking.

[0004] Extensive research has addressed the frequent handover issues in low-Earth orbit (LEO) satellite communication networks. Typical methods include handover triggering mechanisms based on indicators such as signal strength, distance, or elevation angle, as well as comprehensive decision-making methods incorporating multi-dimensional link parameters. While these methods can reduce handover failure rates and improve link stability to some extent, the decision-making process typically relies on fixed rules or thresholds, making it difficult to adapt to dynamically changing communication environments. Furthermore, to address the high handover complexity in LEO satellite networks, some studies model the handover process as an optimization or path selection problem, using graph theory methods or heuristic algorithms to find the optimal handover path. Although these methods can comprehensively consider link quality and resource status, improving system performance, their reliance on global network information results in high computational complexity, making them unsuitable for large-scale networks and real-time decision-making requirements. With the development of artificial intelligence technology, reinforcement learning methods have been gradually introduced into satellite communication handover problems. In addition, some studies have proposed a hybrid network architecture that combines low-orbit satellites and ground base stations, and achieved coordinated optimization of base station selection and sub-channel allocation through cross-layer design or joint optimization methods. However, most of these studies focus on single-user or single-agent decision-making, or emphasize a single network structure. For satellite-ground integrated communication systems with multiple trains and multiple links existing in parallel, there is a lack of a unified modeling and optimization framework. Furthermore, the interaction effects of various decision-making entities in multi-agent scenarios have not been fully considered, making it difficult to achieve optimal overall system performance.

[0005] This shows that there are still many shortcomings in the existing satellite-to-ground converged communication handover optimization process: (1) Existing methods mostly adopt single agent or independent decision-making mechanism. In multi-user concurrent scenarios, each user makes access selection independently based on its own local observation, lacking effective collaborative decision-making ability. This can easily lead to multiple users accessing the same base station at the same time, thus causing resource competition and load imbalance, affecting the overall system performance. (2) Existing methods usually rely on centralized control or global state information for policy optimization. When the network scale expands or the number of nodes increases, the system needs to collect and process global information frequently, which leads to a significant increase in communication overhead and computational complexity, making it difficult to adapt to the high-speed dynamic change of the communication environment. (3) The link states in the space-ground integrated network have significant time-varying characteristics. Existing reinforcement learning methods are mostly based on static or weak dynamic modeling, which makes it difficult to accurately depict the dynamic changes between multiple links, which can easily lead to policy update delays and reduce the real-time performance and effectiveness of handover decisions. (4) Existing methods usually handle access selection and resource allocation separately during the handover decision-making process. They lack a unified joint optimization mechanism and it is difficult to achieve an effective trade-off between multi-dimensional performance indicators such as communication rate, service continuity and handover overhead, which limits the further improvement of system performance.

[0006] Therefore, there is an urgent need to develop a new type of satellite-ground converged hierarchical handover method, equipment, and medium for high-speed train communication to solve or partially solve the shortcomings in the existing satellite-ground converged communication handover optimization process. Summary of the Invention

[0007] To address the technical problems existing in current satellite-ground converged communication handover optimization processes, such as insufficient multi-user collaborative decision-making capabilities, high dependence on global information, difficulty in adapting to dynamic link changes, and lack of a unified joint optimization mechanism for access selection and resource allocation, this invention proposes a satellite-ground converged hierarchical handover method, device, and medium for high-speed train communication. The proposed method aims to construct a satellite-ground converged wireless communication system based on low-Earth orbit satellite base stations and ground-based trackside base stations. It models train handover as a multi-agent decision-making process, achieving distributed hierarchical handover optimization, jointly optimizing access selection and resource allocation, and balancing communication benefits, connection stability, and handover costs.

[0008] To achieve the above objectives, a first aspect of the present invention provides a satellite-to-ground integrated hierarchical handover method for high-speed train communication, comprising the following steps: A space-ground integrated wireless communication system is constructed, which consists of interconnected low-Earth orbit satellite base stations, ground trackside base stations, and multiple high-speed trains. Any of the multiple high-speed trains can select either the low-Earth orbit satellite base station or the ground trackside base station as the current serving base station during operation and establish a communication link with the current serving base station. The low-Earth orbit satellite base station is used to provide wide-area coverage communication services, and the ground trackside base stations are distributed along the railway tracks and are used to provide low-latency access services. The operating time of the satellite-ground integrated wireless communication system is divided into several discrete time slots. Within a time slot, the low-orbit satellite base station and the ground trackside base station broadcast status information to the high-speed trains within their coverage areas. The length of the time slot satisfies the following: within a single time slot, the spatial positions between the low-orbit satellite base station, the ground trackside base station, and the high-speed train do not change. The status information includes at least base station resource occupancy status information. A first channel model and a corresponding first communication performance evaluation index are constructed based on the first communication link established between the high-speed train and the low-orbit satellite base station; a second channel model and a corresponding second communication performance evaluation index are constructed based on the second communication link established between the high-speed train and the ground trackside base station. Using the first communication performance evaluation index and the base station resource occupancy status information of the candidate low-Earth orbit satellite base stations, the first candidate link service capability of the candidate low-Earth orbit satellite base stations is evaluated to obtain a first evaluation result, and / or The second communication performance evaluation index and the base station resource occupancy status information of the candidate ground trackside base station are used to evaluate the second candidate link service capability of the candidate ground trackside base station, and the second evaluation result is obtained. A link handover decision model for the high-speed train in the satellite-ground integrated wireless communication system is constructed, and the first evaluation result and / or the second evaluation result are input into the link handover decision model to obtain a link handover decision, wherein the link handover decision includes at least the target base station; The high-speed train establishes a communication link with the target base station, enabling the high-speed train to dynamically switch to the serving base station in the space-ground integrated wireless communication system.

[0009] In some embodiments of the present invention, the data structure of the status information includes, in sequence, a MAC header, frame information, broadcast information and a verification field, wherein the broadcast information includes one or more of the following: base station identifier, base station location, number of access trains, number of available resources, train identifier and remaining service time.

[0010] In some embodiments of the present invention, the communication performance evaluation index of the first communication link includes at least one or more of the following: a first signal-to-interference-plus-noise ratio, a first achievable rate, and a first remaining service time.

[0011] Furthermore, the formula for calculating the first signal-to-interference-plus-noise ratio is: The formula for calculating the first signal-to-interference-plus-noise ratio is: in, The first signal-to-interference-plus-noise ratio; For ground-orbiting satellite base stations With high-speed trains The L2T communication link between them occupies Sub-channel, when When the time indicates that the subchannel is occupied, otherwise it is not. There are a total of Strip channel; For low-orbit satellite base stations The transmission power; For low-orbit satellite base stations The gain of the transmitting antenna; For feeder losses at the low-orbit satellite launch terminal; For the antenna gain of the high-speed train receiver; This represents large-scale path loss. This represents the small-scale fading coefficient on the sub-channel. Boltzmann's constant; The equivalent noise temperature at the high-speed train receiver; This refers to the sub-channel bandwidth of the L2T communication link between low-orbit satellite base stations and high-speed trains. The first achievable rate is calculated using the Shannon formula, and the formula for calculating the first achievable rate is as follows: in, The first achievable rate; This refers to the sub-channel bandwidth of the L2T communication link; The first remaining service time is calculated from the minimum elevation angle constraint between the low-orbit satellite base station and the high-speed train.

[0012] In some embodiments of the present invention, the communication performance evaluation indicators of the second communication link include at least one or more of the following: a second signal-to-interference-plus-noise ratio, a second achievable rate, and a second remaining service time.

[0013] Furthermore, the formula for calculating the second signal-to-interference-plus-noise ratio is as follows: The formula for calculating the second signal-to-interference-plus-noise ratio is: in, This is the second signal-to-interference-plus-noise ratio; ground-based railside base station With high-speed trains The G2T communication link between them occupies Sub-channel, when When the time indicates that the sub-channel is occupied, otherwise There are a total of Strip channel; ground-based railside base station The transmission power; Ground-based railside base station With high-speed trains In sub-channel Time slot The equivalent complex channel gain of G2T on the surface; The noise power spectral density per unit bandwidth; This refers to the sub-channel bandwidth of the G2T communication link between the ground-based trackside base station and the high-speed train; The formula for calculating the second achievable rate is as follows: in, This is the second achievable rate; This refers to the sub-channel bandwidth of the G2T communication link; The second remaining service time is calculated using the constraint relationship between the train motion model and the three-dimensional coverage radius of the ground trackside base station.

[0014] In some embodiments of the present invention, constructing a link switching decision model for the high-speed train in the space-ground integrated wireless communication system specifically includes: At the start of a time slot, each high-speed train receives status information broadcast by its current serving base station, candidate low-orbit satellite base stations, and candidate ground trackside base stations, and obtains the communication performance evaluation indicators corresponding to each base station. The environmental status of the high-speed train in the current time slot is constructed based on the status information of each base station and the corresponding communication performance evaluation indicators. Each high-speed train is treated as an independent intelligent agent, and the link switching decision model is constructed using a multi-intelligent decision-making method. Within discrete time slots, link switching decisions are made using the aforementioned link switching decision model based on the environmental conditions, specifically including: If the target access base station is the same as the current serving base station, the connection will be maintained. If the target access base station is different from the current serving base station, the high-speed train initiates a handover request, and the target access base station completes the access handover or refuses the handover based on its base station resource occupancy status information.

[0015] In some embodiments of the present invention, the satellite-to-ground integrated hierarchical handover method for high-speed train communication further includes: A time-slot-level reward function is constructed to evaluate the link switching decisions of the high-speed train in a dynamic environment. The calculation formula for the time slot-level reward function is as follows: in, For slot-level reward functions; weighting coefficients It is a non-negative parameter used to adjust the trade-off between communication benefits, connection stability, and handover costs; The achievable speed of the communication link between high-speed train n and satellite base station k within time slot t; Let T be the achievable rate of the communication link between high-speed train n and roadside base station m within time slot t; T represents the remaining service time that the target base station can continuously provide services. This is a handover indication function. It takes a value of 1 when a train undergoes a handover of a serving base station between adjacent time slots, and a value of 0 otherwise, to characterize the handover cost.

[0016] A second aspect of this invention provides a satellite-to-ground converged hierarchical handover device for high-speed train communication, comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to implement the satellite-ground fusion hierarchical handover method for high-speed train communication as described in any of the preceding claims.

[0017] A third aspect of the present invention also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to implement the satellite-ground fusion hierarchical handover method for high-speed train communication as described in any of the preceding embodiments.

[0018] The method proposed in this application can bring the following beneficial effects: The method proposed in this application achieves an effective trade-off between communication performance and handover overhead by constructing a multi-dimensional state representation that integrates link communication performance, remaining service time, and base station load status, and by designing a reward function in conjunction with handover cost constraints. Compared with existing handover methods based on signal strength or threshold triggering, this invention, based on a multi-agent collaborative decision-making mechanism, enables each train to adaptively select the optimal access base station in a dynamically changing network environment, thereby improving the achievable link rate and reducing frequent handovers caused by link fluctuations. Simultaneously, by introducing remaining service time constraints, the continuity of the connection is improved, mitigating handover instability caused by changes in satellite visibility. Furthermore, this invention employs a distributed decision-making mechanism, where each train independently completes handover decisions based on its own local observations, without relying on a central control node, thus reducing system implementation complexity and improving the system's scalability and robustness in multi-train concurrent scenarios. Under multi-train access conditions, by introducing base station load status, dynamic and balanced allocation of communication resources is achieved, effectively alleviating local congestion problems. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart illustrating the satellite-ground integrated hierarchical handover method for high-speed train communication in this application embodiment; Figure 2 This is a schematic diagram of the structure of a satellite-ground integrated hierarchical switching device for high-speed train communication in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of the space-ground integrated wireless communication system constructed in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the state information in the embodiments of this application; Figure 5This is a flowchart illustrating the link switching process in the satellite-ground integrated hierarchical handover method for high-speed train communication in this embodiment of the application. Figure 6 This is the reward convergence curve during the training process of the link switching decision model proposed in this application embodiment; Figure 7 The reward variation curves for the satellite-ground fusion hierarchical handover method for high-speed train communication proposed in this application are shown under different numbers of high-speed trains. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0022] Figure 1 This is a flowchart illustrating a satellite-to-ground integrated hierarchical handover method for high-speed train communication provided in one or more embodiments of this specification. Figure 1 As shown, one embodiment of this application provides a satellite-to-ground integrated hierarchical handover method for high-speed train communication, which includes the following steps: A space-ground integrated wireless communication system is constructed, which consists of interconnected low-Earth orbit satellite base stations, ground trackside base stations, and multiple high-speed trains. Any of the multiple high-speed trains can select either the low-Earth orbit satellite base station or the ground trackside base station as the current serving base station during operation and establish a communication link with the current serving base station. The low-Earth orbit satellite base station is used to provide wide-area coverage communication services, and the ground trackside base stations are distributed along the railway tracks and are used to provide low-latency access services. The operating time of the satellite-ground integrated wireless communication system is divided into several discrete time slots. Within a time slot, the low-orbit satellite base station and the ground trackside base station broadcast status information to the high-speed trains within their coverage areas. The length of the time slot satisfies the following: within a single time slot, the spatial positions between the low-orbit satellite base station, the ground trackside base station, and the high-speed train do not change. The status information includes at least base station resource occupancy status information. A first channel model and a corresponding first communication performance evaluation index are constructed based on the first communication link established between the high-speed train and the low-orbit satellite base station; a second channel model and a corresponding second communication performance evaluation index are constructed based on the second communication link established between the high-speed train and the ground trackside base station. Using the first communication performance evaluation index and the base station resource occupancy status information of the candidate low-Earth orbit satellite base stations, the first candidate link service capability of the candidate low-Earth orbit satellite base stations is evaluated to obtain a first evaluation result, and / or The second communication performance evaluation index and the base station resource occupancy status information of the candidate ground trackside base station are used to evaluate the second candidate link service capability of the candidate ground trackside base station, and the second evaluation result is obtained. A link handover decision model for the high-speed train in the satellite-ground integrated wireless communication system is constructed, and the first evaluation result and / or the second evaluation result are input into the link handover decision model to obtain a link handover decision, wherein the link handover decision includes at least the target base station; The high-speed train establishes a communication link with the target base station, enabling the high-speed train to dynamically switch to the serving base station in the space-ground integrated wireless communication system.

[0023] In this embodiment, the data structure of the status information includes, in sequence, a MAC header, frame information, broadcast information, and a verification field. The broadcast information includes one or more of the following: base station identifier, base station location, number of access trains, number of available resources, train identifier, and remaining service time.

[0024] In this embodiment, the communication performance evaluation index of the first communication link includes at least one or more of the following: first signal-to-interference-plus-noise ratio, first achievable rate, and first remaining service time.

[0025] Furthermore, the formula for calculating the first signal-to-interference-plus-noise ratio is: The formula for calculating the first signal-to-interference-plus-noise ratio is: in, The first signal-to-interference-plus-noise ratio; For ground-orbiting satellite base stations With high-speed trains The L2T communication link between them occupies Sub-channel, when When the time indicates that the subchannel is occupied, otherwise it is not. There are a total of Strip channel; For low-orbit satellite base stations The transmission power; For low-orbit satellite base stations The gain of the transmitting antenna; For feeder losses at the low-orbit satellite launch terminal; For the antenna gain of the high-speed train receiver; This represents large-scale path loss. This represents the small-scale fading coefficient on the sub-channel. Boltzmann's constant; The equivalent noise temperature at the high-speed train receiver; This refers to the sub-channel bandwidth of the L2T communication link between low-orbit satellite base stations and high-speed trains. The first achievable rate is calculated using the Shannon formula, and the formula for calculating the first achievable rate is as follows: in, The first achievable rate; This refers to the sub-channel bandwidth of the L2T communication link; The first remaining service time is calculated from the minimum elevation angle constraint between the low-orbit satellite base station and the high-speed train.

[0026] In this embodiment, the communication performance evaluation indicators of the second communication link include at least one or more of the following: second signal-to-interference-plus-noise ratio, second achievable rate, and second remaining service time.

[0027] Furthermore, the formula for calculating the second signal-to-interference-plus-noise ratio is as follows: The formula for calculating the second signal-to-interference-plus-noise ratio is: in, This is the second signal-to-interference-plus-noise ratio; ground-based railside base station With high-speed trains The G2T communication link between them occupies Sub-channel, when When the time indicates that the sub-channel is occupied, otherwise There are a total of Strip channel; ground-based railside base station The transmission power; Ground-based railside base station With high-speed trains In sub-channel Time slot The equivalent complex channel gain of G2T on the surface; The noise power spectral density per unit bandwidth; This refers to the sub-channel bandwidth of the G2T communication link between the ground-based trackside base station and the high-speed train; The formula for calculating the second achievable rate is as follows: in, This is the second achievable rate; This refers to the sub-channel bandwidth of the G2T communication link; The second remaining service time is calculated using the constraint relationship between the train motion model and the three-dimensional coverage radius of the ground trackside base station.

[0028] In this embodiment, the link switching decision model for the high-speed train in the space-ground integrated wireless communication system is constructed, specifically including: At the start of a time slot, each high-speed train receives status information broadcast by its current serving base station, candidate low-orbit satellite base stations, and candidate ground trackside base stations, and obtains the communication performance evaluation indicators corresponding to each base station. The environmental status of the high-speed train in the current time slot is constructed based on the status information of each base station and the corresponding communication performance evaluation indicators. Each high-speed train is treated as an independent intelligent agent, and the link switching decision model is constructed using a multi-intelligent decision-making method. Within discrete time slots, link switching decisions are made using the aforementioned link switching decision model based on the environmental conditions, specifically including: If the target access base station is the same as the current serving base station, the connection will be maintained. If the target access base station is different from the current serving base station, the high-speed train initiates a handover request, and the target access base station completes the access handover or refuses the handover based on its base station resource occupancy status information.

[0029] In this embodiment, the satellite-ground integrated hierarchical handover method for high-speed train communication further includes: A time-slot-level reward function is constructed to evaluate the link switching decisions of the high-speed train in a dynamic environment. The calculation formula for the time slot-level reward function is as follows: in, For slot-level reward functions; weighting coefficients It is a non-negative parameter used to adjust the trade-off between communication benefits, connection stability, and handover costs; The achievable speed of the communication link between high-speed train n and satellite base station k within time slot t; Let T be the achievable rate of the communication link between high-speed train n and roadside base station m within time slot t; T represents the remaining service time that the target base station can continuously provide services. This is a handover indication function. It takes a value of 1 when a train undergoes a handover of a serving base station between adjacent time slots, and a value of 0 otherwise, to characterize the handover cost.

[0030] This embodiment proposes a satellite-ground fusion hierarchical handover method for high-speed train communication. By constructing a multi-dimensional state representation of fused link communication performance, remaining service time, and base station load status, and combining this with a reward function designed to address handover cost constraints, an effective trade-off between communication performance and handover overhead is achieved. Compared to existing handover methods based on signal strength or threshold triggering, this invention utilizes a multi-agent collaborative decision-making mechanism, enabling each train to adaptively select the optimal access base station in a dynamically changing network environment. This improves the achievable link rate and reduces frequent handovers caused by link fluctuations. Simultaneously, by introducing remaining service time constraints, connection persistence is enhanced, mitigating handover instability caused by changes in satellite visibility. Furthermore, this invention employs a distributed decision-making mechanism, where each train independently completes handover decisions based on its own local observations, eliminating reliance on a central control node. This reduces system implementation complexity and enhances the system's scalability and robustness in multi-train concurrent scenarios. Under multi-train access conditions, the introduction of base station load status enables dynamic and balanced allocation of communication resources, effectively alleviating local congestion problems.

[0031] To better understand the satellite-ground integrated hierarchical handover method for high-speed train communication described in the above embodiments, further detailed explanations are provided below for those skilled in the art.

[0032] To address the shortcomings of existing technologies in the optimization of satellite-ground converged communication handover, such as insufficient multi-user collaborative decision-making capabilities, high dependence on global information, difficulty in adapting to dynamic link changes, and lack of a unified joint optimization mechanism, this embodiment proposes a satellite-ground converged hierarchical handover method for high-speed train communication. This method aims to improve collaborative decision-making capabilities in multi-user scenarios, reduce the system's dependence on global information, enhance adaptability to dynamic link environments, and achieve collaborative optimization of access selection and resource allocation, thereby improving the overall communication performance and service quality of the system.

[0033] First, a space-ground integrated wireless communication system is constructed, consisting of low-Earth orbit satellite base stations, ground-based trackside base stations, and high-speed trains. Its structure is as follows: Figure 3 As shown. In a space-ground integrated wireless communication system, low-Earth orbit (LEO) satellite base stations provide wide-area coverage communication services, while ground-based trackside base stations are distributed along railway tracks to provide low-latency access services. High-speed trains, as mobile users, access the network via either LEO satellite base stations or ground-based trackside base stations during operation. The set of trains in the system is defined as follows: ,in This indicates the total number of high-speed trains in the system. Indicates the first High-speed trains. The set of low-orbit satellite base stations is defined as... ,in This indicates the total number of low-orbit satellite base stations. Indicates the first A set of low-Earth orbit satellite base stations. The set of ground-based orbital base stations is defined as follows: ,in This indicates the total number of ground-based railside base stations. Indicates the first There are 10 ground-based rail-side base stations. The total number of base stations is 10. , .

[0034] The operating time of the satellite-ground integrated wireless communication system is divided into several discrete time slots. The length of each time slot must satisfy the requirement that the relative positions of all nodes (i.e., low-Earth orbit satellite base stations, ground-based trackside base stations, and high-speed trains) remain unchanged within each time slot. At the beginning of each time slot, each base station broadcasts status information to trains within its coverage area. The data structure of the status information includes, in sequence, a MAC header, frame information, broadcast information, and a checksum field. The broadcast information includes one or more of the following: base station identifier, base station location, number of connected trains, number of available resources, train identifier, and remaining service time. Figure 4 As shown, the high-speed train constructs the communication environment state of the current time slot based on the received broadcast information and link measurement results, which is used as the state input in the subsequent handover decision-making process.

[0035] Channel models were constructed based on the communication links established between low-orbit satellite base stations, ground trackside base stations and high-speed trains, and communication performance evaluation indicators corresponding to the communication links were constructed accordingly.

[0036] For low-Earth orbit (LEO) satellite links, the space-ground integrated wireless communication system employs narrow-beam directional transmission and spectrum reuse mechanisms to ensure good spatial isolation between different links, thus negligible co-channel interference. Based on this, the first signal-to-interference-plus-noise ratio (SINR) is used to characterize the downlink communication quality between the LEO satellite base station and the high-speed train in time slots.

[0037] The formula for calculating the first signal-to-interference-plus-noise ratio is: The formula for calculating the first signal-to-interference-plus-noise ratio is: in, The first signal-to-interference-plus-noise ratio; For ground-orbiting satellite base stations With high-speed trains The L2T communication link between them occupies Sub-channel, when When the time indicates that the subchannel is occupied, otherwise it is not. There are a total of Strip channel; For low-orbit satellite base stations The transmission power; For low-orbit satellite base stations The gain of the transmitting antenna; For feeder losses at the low-orbit satellite launch terminal; For the antenna gain of the high-speed train receiver; This represents large-scale path loss. This represents the small-scale fading coefficient on the sub-channel. Boltzmann's constant; The equivalent noise temperature at the high-speed train receiver; This refers to the sub-channel bandwidth of the L2T communication link between low-orbit satellite base stations and high-speed trains. The first achievable rate is calculated using the Shannon formula, and the formula for calculating the first achievable rate is as follows: in, The first achievable rate; This refers to the sub-channel bandwidth of the L2T communication link; The availability of the low-Earth orbit (LEO) satellite link, i.e., the first communication link, is constrained by visibility. The communication link between the LEO satellite and the high-speed train is only available when the link meets the minimum elevation angle condition. Let's assume a LEO satellite base station... With high-speed trains In the time slot The spatial locations are respectively and , Then, in the case of satisfying The instantaneous elevation angle between the two is expressed as: If the duration for which the first communication link continuously satisfies the visibility constraint is defined as the first remaining serviceable time of the link, then the low-Earth orbit satellite base station With the train In the time slot The remaining service time is expressed as follows: That is, the first remaining service time is calculated from the minimum elevation angle constraint between the low-orbit satellite base station and the high-speed train.

[0038] For ground-based trackside base station links, communication quality is affected by path loss, small-scale fading, and co-channel interference. Therefore, the communication quality of the downlink between ground-based trackside base stations and high-speed trains in time slots is also characterized by a second signal-to-interference-plus-noise ratio (SINR). The formula for calculating the second SINR is: in, This is the second signal-to-interference-plus-noise ratio; ground-based railside base station With high-speed trains The G2T communication link between them occupies Sub-channel, when When the time indicates that the sub-channel is occupied, otherwise There are a total of Strip channel; ground-based railside base station The transmission power; Ground-based railside base station With high-speed trains In sub-channel Time slot The equivalent complex channel gain of G2T on the surface; The noise power spectral density per unit bandwidth; This refers to the sub-channel bandwidth of the G2T communication link between the ground-based trackside base station and the high-speed train; The formula for calculating the second achievable rate is as follows: in, This is the second achievable rate; This refers to the sub-channel bandwidth of the G2T communication link; To characterize the continuous service capability of ground-based trackside base stations for high-speed trains, assume the train travels along the track at a speed of... Motion, the direction of which is determined by a unit vector This indicates that the train will be in the future. The spatial location at a given time is represented as: Let the three-dimensional equivalent coverage radius of the ground-based railside base station be... When the train is located at the coverage boundary of a base station, the following conditions should be met: Substituting the high-speed train motion model into the above constraints, we can obtain information about... The functional relationship is then transformed into a quadratic equation in one variable: Assuming the high-speed train is within the coverage area, the non-negative real root of the above equation is taken as the second remaining service time for the high-speed train from the ground trackside base station. The formula for calculating the second remaining service time is as follows: The second remaining service time was calculated using the constraint relationship between the train motion model and the three-dimensional coverage radius of the ground trackside base station.

[0039] Based on the aforementioned communication model between low-Earth orbit satellite links and ground-based trackside base station links, communication performance evaluation indicators such as signal-to-interference-plus-noise ratio (SIR), achievable data rate, and remaining service time between high-speed trains and candidate base stations can be obtained. Combining these communication performance evaluation indicators with base station resource occupancy status allows for the assessment of the service capabilities of candidate links, yielding evaluation results. These results can then serve as state inputs for the subsequent link handover decision model and strategy optimization.

[0040] Based on the communication performance evaluation indicators of each candidate base station, a link handover decision model for high-speed trains in a space-ground integrated communication system is constructed. For example... Figure 5 As shown, the link handover process is executed cyclically within discrete time slots, including state acquisition, handover decision, handover execution, and data transmission. At the beginning of each time slot, the high-speed train receives the state information broadcast by the current serving base station and all reachable candidate base stations, and combines it with the link measurement results to obtain the communication performance evaluation indicators corresponding to each candidate base station. The indicators include the link signal-to-interference-plus-noise ratio, achievable rate, remaining service time, and base station load status, and construct the environmental state of the current time slot accordingly.

[0041] Each high-speed train is treated as an independent intelligent agent. A multi-intelligence decision-making method is used to construct a link handover decision model. The high-speed train comprehensively evaluates all reachable candidate base stations and determines the target access base station as the handover decision result. When the target access base station is the same as the current serving base station, the current connection is maintained; when they are different, the high-speed train initiates a handover request to the target access base station and enters the handover execution process. The target access base station allocates resources based on resource availability: when available resources exist, it allocates communication resources to the high-speed train and establishes a new connection; when resources are insufficient, it rejects the handover request, and the high-speed train maintains its current connection. After the link is established or maintained, the high-speed train transmits data through the current serving base station until the current time slot ends. Subsequently, the space-ground integrated wireless communication system enters the next time slot and repeats the above process, thereby realizing continuous dynamic handover of the train in the space-ground integrated communication environment.

[0042] Based on the aforementioned link switching mechanism, the train switching problem is modeled as a multi-agent decision-making problem, in which each high-speed train acts as an independent agent and makes access decisions based on the environmental state within discrete time slots, providing a unified modeling foundation for subsequent switching strategy optimization and multi-agent reinforcement learning algorithm design.

[0043] Based on the aforementioned link switching decision-making process, to characterize the communication environment of high-speed trains in the current time slot, the train switching problem is modeled as a multi-agent decision-making process, where each high-speed train is treated as an independent agent. The state of the high-speed train in the time slot is defined as follows: in, Indicates time slot Inner Mongolia high-speed train With base station The links between them can achieve a normalized rate value; This indicates that, under the condition that no geometric mismatch or visibility failure occurs, the base station It can still be used for high-speed trains The normalized value of the remaining serviceable time; Indicates base station In the time slot The normalized value of the number of high-speed trains currently in service is used to characterize the current load status of the base station; Indicates time slot Inner and high-speed trains The current serving base station that establishes the connection; Indicates high-speed train Service type identifier in time slot.

[0044] Within each time slot, the high-speed train, acting as an intelligent agent, needs to select a target access base station from the candidate base station set as the access node. (Define the high-speed train...) In the time slot action The action space of the selected target access base station index is defined as follows: in, This represents the set of all base stations in the system. Due to limitations in visibility from low-Earth orbit satellites and coverage of ground-based orbital base stations, in time slots... Inside, high-speed train The actual number of accessible base stations is a subset of its reachable base stations. Therefore, in the specific decision-making process, the train only selects the target base station from the set of reachable base stations, and does not participate in the selection for actions corresponding to unreachable base stations.

[0045] Furthermore, set Indicates train In the time slot The current serving base station, then when When the train maintains its current connection in the next time slot, it does not trigger a handover operation; when When resources are successfully allocated, the train performs a handover operation from the current serving base station to the target base station.

[0046] To comprehensively evaluate the impact of different handover decisions on system performance and achieve an effective trade-off between communication performance, connection stability, and handover overhead, a time-slot-level reward function is constructed to guide high-speed trains' access and handover decisions in dynamic environments. Specifically, the time-slot-level reward function consists of a communication benefit term, a connection stability term, and a handover cost term. The communication benefit term is characterized by the achievable link rate obtained by the high-speed train at the current serving base station, representing the system's data transmission capacity. The connection stability term is characterized by the remaining service time of the link, representing connection persistence and suppressing frequent handovers. The handover cost term is represented by a handover indicator variable, incurring a penalty when the train experiences a change of serving base station between adjacent time slots.

[0047] Based on the above factors, the formula for calculating the time slot-level reward function of high-speed trains is as follows: in, For slot-level reward functions; weighting coefficients It is a non-negative parameter used to adjust the trade-off between communication benefits, connection stability, and handover costs; The achievable speed of the communication link between high-speed train n and satellite base station k within time slot t; Let T be the achievable rate of the communication link between high-speed train n and roadside base station m within time slot t; T represents the remaining service time that the target base station can continuously provide services. This is a handover indication function. It takes a value of 1 when a train undergoes a handover of a serving base station between adjacent time slots, and a value of 0 otherwise, to characterize the handover cost.

[0048] Based on the time-slot-level reward function, the optimization objective of the satellite-ground integrated wireless communication system is defined as maximizing the long-term cumulative expected return, and its expression is: To solve the aforementioned optimization problem, a Multi-Agent Proximal Policy Optimization (MAPPO) method is employed to train and optimize the train handover strategy. In this embodiment, each high-speed train acts as an independent agent, selecting a target access base station from candidate base stations as its decision action within discrete time slots based on its own observed local state information and the constraints of the reachable base station set, thus achieving distributed handover decision-making. Each agent shares a unified policy network structure to enable policy parameter updates and experience reuse. During policy training, joint state information is constructed based on the interaction trajectories of multiple trains, and the policy is evaluated and optimized using a value network to characterize the resource competition relationship and environmental coupling effects among multiple trains, thereby improving the stability and convergence performance of the multi-agent parallel learning process. During policy execution, each agent independently outputs a handover decision based solely on its own local observed state and available action constraints, without relying on a central control node. By introducing a proximal policy constraint mechanism, the policy update magnitude is limited to improve the stability of the training process. Through the above strategy optimization, the train can adaptively select the optimal access base station in a dynamically changing space-ground converged communication environment, thereby improving the communication rate while reducing the handover frequency and the probability of handover failure, thus optimizing the long-term performance of the system.

[0049] In this embodiment, the satellite-ground integrated wireless communication system exhibits a gradual increase and stabilization of system rewards during training rounds. Figure 6 As shown, the link switching decision model proposed in this embodiment can effectively converge and achieve stable decision performance. Figure 7 As shown, under different train numbers, the satellite-ground fusion hierarchical handover method for high-speed train communication proposed in this embodiment can achieve a high and stable reward level, indicating that the method proposed in this application has good adaptability and scalability in scenarios with varying user scales.

[0050] like Figure 2 As shown in the figure, this application embodiment also provides a satellite-ground fusion hierarchical handover device for high-speed train communication, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the satellite-ground fusion hierarchical handover method for high-speed train communication in any of the above embodiments.

[0051] This application also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to implement the satellite-ground fusion hierarchical handover method for high-speed train communication in any of the above embodiments.

[0052] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so they are described more simply; relevant parts can be referred to the descriptions of the method embodiments.

[0053] The devices and media provided in this application correspond one-to-one with the system. Therefore, the devices and media also have similar beneficial technical effects as their corresponding systems. Since the beneficial technical effects of the system have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0054] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0056] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0058] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0059] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0060] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0061] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0062] The above description is merely an embodiment of this application and is not intended to limit the scope of 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 spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for satellite-ground integration layered handover for high-speed train communication, characterized in that, Includes the following steps: A space-ground integrated wireless communication system is constructed, which consists of interconnected low-Earth orbit satellite base stations, ground trackside base stations, and multiple high-speed trains. Any of the multiple high-speed trains can select either the low-Earth orbit satellite base station or the ground trackside base station as the current serving base station during operation and establish a communication link with the current serving base station. The low-Earth orbit satellite base station is used to provide wide-area coverage communication services, and the ground trackside base stations are distributed along the railway tracks and are used to provide low-latency access services. The operating time of the satellite-ground integrated wireless communication system is divided into several discrete time slots. Within a time slot, the low-orbit satellite base station and the ground trackside base station broadcast status information to the high-speed trains within their coverage areas. The length of the time slot satisfies the following: within a single time slot, the spatial positions between the low-orbit satellite base station, the ground trackside base station, and the high-speed train do not change. The status information includes at least base station resource occupancy status information. A first channel model and a corresponding first communication performance evaluation index are constructed based on the first communication link established between the high-speed train and the low-orbit satellite base station; a second channel model and a corresponding second communication performance evaluation index are constructed based on the second communication link established between the high-speed train and the ground trackside base station. The service capability of the first candidate link of the candidate low-Earth orbit satellite base station is evaluated using the first communication performance evaluation index and the base station resource occupancy status information of the candidate low-Earth orbit satellite base station, to obtain the first evaluation result, and / or The second communication performance evaluation index and the base station resource occupancy status information of the candidate ground trackside base station are used to evaluate the second candidate link service capability of the candidate ground trackside base station, and the second evaluation result is obtained. A link handover decision model for the high-speed train in the satellite-ground integrated wireless communication system is constructed, and the first evaluation result and / or the second evaluation result are input into the link handover decision model to obtain a link handover decision, wherein the link handover decision includes at least a target base station; The high-speed train establishes a communication link with the target base station, enabling the high-speed train to dynamically switch to the serving base station in the space-ground integrated wireless communication system.

2. The satellite-ground integrated hierarchical handover method for high-speed train communication according to claim 1, characterized in that: The data structure of the status information includes, in sequence, a MAC header, frame information, broadcast information, and a verification field. The broadcast information includes one or more of the following: base station identifier, base station location, number of access trains, number of available resources, train identifier, and remaining service time.

3. The satellite-to-ground integrated hierarchical handover method for high-speed train communication according to claim 1, characterized in that: The communication performance evaluation indicators of the first communication link include at least one or more of the following: first signal-to-interference-plus-noise ratio, first achievable rate, and first remaining service time.

4. The satellite-to-ground integrated hierarchical handover method for high-speed train communication according to claim 3, characterized in that: The formula for calculating the first signal-to-interference-plus-noise ratio is: in The first signal-to-interference-plus-noise ratio; For ground-orbiting satellite base stations With high-speed trains The L2T communication link between them occupies Sub-channel, when When the time indicates that the subchannel is occupied, otherwise it is not. There are a total of Strip channel; For low-orbit satellite base stations The transmission power; For low-orbit satellite base stations The gain of the transmitting antenna; Low-Earth orbit satellite launcher feeder loss; For the antenna gain of the high-speed train receiver; This represents large-scale path loss. This represents the small-scale fading coefficient on the sub-channel. Boltzmann's constant; The equivalent noise temperature at the high-speed train receiver; This refers to the sub-channel bandwidth of the L2T communication link between low-orbit satellite base stations and high-speed trains. The first achievable rate is calculated using the Shannon formula, and the formula for calculating the first achievable rate is as follows: The first achievable rate; This refers to the sub-channel bandwidth of the L2T communication link; The first remaining service time is calculated from the minimum elevation angle constraint between the low-orbit satellite base station and the high-speed train.

5. The satellite-to-ground integrated hierarchical handover method for high-speed train communication according to claim 1, characterized in that: The communication performance evaluation metrics for the second communication link include at least one or more of the following: second signal-to-interference-plus-noise ratio, second achievable rate, and second remaining service time.

6. The satellite-to-ground integrated hierarchical handover method for high-speed train communication according to claim 5, characterized in that: The formula for calculating the second signal-to-interference-plus-noise ratio is: in, This is the second signal-to-interference-plus-noise ratio; Ground-based railside base station With high-speed trains The G2T communication link between them occupies Sub-channel, when When the time indicates that the sub-channel is occupied, otherwise Total Strip channel; Ground-based railside base station The transmission power; Ground-based railside base station With high-speed trains In sub-channel Time slot The equivalent complex channel gain of G2T on the surface; The noise power spectral density per unit bandwidth; This refers to the sub-channel bandwidth of the G2T communication link between the ground-based trackside base station and the high-speed train; The formula for calculating the second achievable rate is as follows: in, This is the second achievable rate; This refers to the sub-channel bandwidth of the G2T communication link; The second remaining service time is calculated using the constraint relationship between the train motion model and the three-dimensional coverage radius of the ground trackside base station.

7. The satellite-ground integrated hierarchical handover method for high-speed train communication according to claim 1, characterized in that, Constructing the link switching decision model for the high-speed train in the satellite-ground integrated wireless communication system specifically includes: At the start of a time slot, each high-speed train receives status information broadcast by its current serving base station, candidate low-orbit satellite base stations, and candidate ground trackside base stations, and obtains the communication performance evaluation indicators corresponding to each base station. The environmental status of the high-speed train in the current time slot is constructed based on the status information of each base station and the corresponding communication performance evaluation indicators. Each high-speed train is treated as an independent intelligent agent, and the link switching decision model is constructed using a multi-intelligent decision-making method. Within discrete time slots, link switching decisions are made using the aforementioned link switching decision model based on the environmental conditions, specifically including: If the target access base station is the same as the current serving base station, the connection will be maintained. If the target access base station is different from the current serving base station, the high-speed train initiates a handover request, and the target access base station completes the access handover or refuses the handover based on its base station resource occupancy status information.

8. The satellite-ground integrated hierarchical handover method for high-speed train communication according to claim 1, characterized in that, The method further includes: A time-slot-level reward function is constructed to evaluate the link switching decisions of the high-speed train in a dynamic environment. The calculation formula for the time slot-level reward function is as follows: in, For slot-level reward functions; weighting coefficients It is a non-negative parameter used to adjust the trade-off between communication benefits, connection stability, and handover costs; The achievable speed of the communication link between high-speed train n and satellite base station k within time slot t; Let T be the achievable rate of the communication link between high-speed train n and roadside base station m within time slot t; T represents the remaining service time that the target base station can continuously provide services. This is a handover indication function. It takes a value of 1 when a train undergoes a handover of a serving base station between adjacent time slots, and a value of 0 otherwise, to characterize the handover cost.

9. A satellite-ground integrated hierarchical handover device for high-speed train communication, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to implement the satellite-ground fusion hierarchical handover method for high-speed train communication as described in any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are configured to implement the satellite-ground integrated hierarchical handover method for high-speed train communication as described in any one of claims 1 to 8.

Images