A method for siting a 5G aeroMACS system base station

Abstract

This invention relates to the field of wireless communication technology and proposes a base station site selection method for a 5G AeroMACS system, considering the base station site selection problem from three aspects: base station deployment planning, spectrum planning, and network optimization. In the planning phase, the optimal location of the 5G base station can be scientifically determined, parameters such as inter-site spacing, antenna height, and antenna type can be optimized, and coverage effects can be evaluated. This invention abandons the traditional practice of base station construction based solely on experience, ensuring that the base station can effectively allocate spectrum and control interference. In the high-traffic and complex environment of airports, it can efficiently utilize wireless resources, improving network operating efficiency and user experience.

Description

A method for base station site selection in a 5G AeroMACS system Technical Field

[0001] This invention relates to the field of wireless communication technology, and in particular to a method for selecting a base station location for a 5G AeroMACS system. Background Technology

[0002] 5G technology is a key new technology supporting the high-quality development of the civil aviation industry. In the civil aviation sector, there is an urgent need to combine 5G technology with existing aviation mobile communications, deeply integrate and apply 5G technology to empower smart civil aviation, promote the safe and high-quality development of civil aviation, and create a new era image for the civil aviation industry. Furthermore, AeroMACS, a new broadband communication technology included in the "Roadmap for Next-Generation Aviation Broadband Communication Technology in China's Civil Aviation," is an aviation broadband mobile communication system for airport surface areas. It can provide broadband wireless network connectivity for airport surfaces, communicating with aircraft, emergency vehicles, baggage trucks, weather radar, ground radar, fixed navigation aids, and other sensors. It is primarily used to transmit flight information related to airport operations and requiring safety.

[0003] To ensure the operation of 5G AeroMACS, the site selection of 5G base stations at airports has become a crucial issue that needs to be addressed. As important transportation hubs, airports experience massive passenger flows and have a high demand for communication services. The complex operating environment of airports encompasses multiple stages, including aircraft takeoff and landing, baggage handling, and passenger pick-up and drop-off, all of which place extremely high demands on the immediacy and stability of communications. Due to the relatively high frequency band of 5G AeroMACS, its coverage is relatively limited, thus requiring precise selection of base station locations to effectively utilize the spectrum and reduce interference. Furthermore, base stations deployed at airports need to support multiple services such as airport management, flight scheduling, and security monitoring; therefore, appropriate base station site selection is essential for promoting service integration and improving the overall operational efficiency of the airport. In addition, base station site selection must also consider factors such as the complex electromagnetic environment within the airport area, the required ability to respond to emergencies, and economic cost-effectiveness. Summary of the Invention

[0004] To address the problems in existing technologies, this invention proposes a base station site selection method for 5G AeroMACS systems. This method considers base station site selection from three aspects: base station deployment planning, spectrum planning, and network optimization. In the early stages of 5G AeroMACS construction planning, based on the ITU WRC-07 requirement that the equivalent thermal noise temperature rise of fixed satellite service (FSS) systems should not exceed 2°C, the equivalent isotropic radiated power (EIRP) and elevation angle of the base station and antenna are limited. These limitations must be considered when selecting antennas and tilt directions, determining numerous parameters including base station location, antenna type, antenna parameters, and spectrum allocation, and effectively evaluating the corresponding coverage effect.

[0005] The specific technical solution of the present invention is as follows:

[0006] A method for selecting a base station location for a 5G AeroMACS system includes the following steps:

[0007] Step S1: Establish a digital twin model of the airport environment;

[0008] Step S2: Using the DQN algorithm, with the goal of maximizing signal coverage and minimizing interference, the optimal base station deployment parameters are obtained;

[0009] Step S3: Deploy the network according to the airport's 5G AeroMACS communication requirements and ICAO standards;

[0010] Step S4: Optimize the network through wireless resource management and network topology optimization.

[0011] Preferably, the digital twin model in step S1 includes the following parameters: antenna type and quantity, antenna direction, antenna electrical performance parameters, antenna horizontal beamwidth, operating frequency band, polarization, isolation, VSWR, gain, transmit power, temperature, humidity, antenna downtilt angle, and installation method.

[0012] Preferably, step S2 specifically includes:

[0013] Step S2-1: Define the state space, action space, and reward function;

[0014] Step S2-2: Build a DQN model and train it;

[0015] Step S2-3: Apply the trained DQN model to obtain the optimal base station deployment parameters.

[0016] Preferably, the state space contains a state vector S=[P,θ], where P represents the transmit power and θ represents the antenna direction; the action space contains an action A, including increasing power, decreasing power, and adjusting the antenna direction; the reward function is expressed as: R(S,A)=C(P,θ)-λI(P,θ)-BU(P,θ), where U(P,θ) represents the operating cost, B is the balancing parameter, S represents the state, A represents the action, C(P,θ) represents the coverage area, and I(P,θ) represents interference from other users.

[0017] Preferably, step S2-2 specifically includes:

[0018] Step S2-2-1: Establish a DQN model consisting of an input layer, a hidden layer, and an output layer. The hidden layer is composed of multiple fully connected layers, each containing 128 neurons, and uses an activation function.

[0019] Step S2-2-2: Set up the mechanism for the DQN model learning strategy and train the DQN model.

[0020] Preferably, the mechanism of the DQN model learning strategy in step S2-2-2 includes:

[0021] (1) Environmental Judgment

[0022] State observation: 5G base stations acquire the current state from the airport environment. This includes 5G base station configuration, terminal density, traffic requirements, and interference levels;

[0023] Action selection: Based on the current strategy, the 5G base station selects the action for the current moment. ;

[0024] ε-greedy strategy: Select the current best action and choose a random action with probability ε;

[0025] SoftMax strategy: Probabilistic selection based on action value;

[0026] (2) Strategy evaluation and updating

[0027] Environmental Feedback: After the 5G base station performs its action, the airport environment provides a reward signal for the current moment. And the state in the next moment. ;

[0028] Value function update: A function Q(S,A) for updating action values ​​or a function V(S) for updating state values ​​based on the Bellman equation.

[0029]

[0030] Where η is the learning rate and φ is the discount factor, which measures the impact of future rewards on the current strategy;

[0031] Policy update: In the policy gradient method, the policy parameters are updated directly.

[0032]

[0033] in, This represents the policy parameters at the current moment. This represents the policy parameters for the next time step. Indicates in Choose below The probability of;

[0034] (3) Strategy Improvement

[0035] The SoftMax strategy can be adjusted by adjusting ε or by using a decreasing temperature parameter.

[0036] Preferably, the base station deployment parameters in steps S2-3 include: antenna height h, distance d between the base station and the runway, inter-station spacing L, antenna horizontal lobe width α, and antenna downtilt angle. Determine the distance D of the antenna coverage far point and the elevation angle of the antenna near point. Antenna far point elevation angle The minimum vertical lobe width required for optimal coverage The minimum vertical lobe width required for an antenna The horizontal beamwidth of the antenna beam projected onto the horizontal plane The angle between the projection boundary of the antenna beam onto the horizontal plane and d. The distance of the antenna's coverage blind spot at the airport. and the minimum incident angle of the signal .

[0037] Preferably, step S3 specifically includes:

[0038] Step-size tuning: 5G AeroMACS devices tune their frequencies in steps of 15 kHz or 30 kHz to avoid interference sources;

[0039] Frequency avoidance strategy: Select different frequency step sizes based on the amount of interference signals in the area;

[0040] Multi-channel bandwidth support: Supports channel bandwidths of 5 MHz, 10 MHz, 20 MHz, 30 MHz, 40 MHz and 50 MHz;

[0041] Dynamic bandwidth adjustment: Dynamically adjust the channel bandwidth to optimize network performance based on real-time communication needs and environmental interference.

[0042] Carrier aggregation: Using carrier aggregation technology to improve spectrum efficiency;

[0043] Subcarrier management: A spectrum management method based on subcarrier spacing is adopted to balance network scanning speed and spectrum efficiency;

[0044] Priority management: Prioritize communications involving security and critical tasks to ensure communication remains available even under high load or interference conditions;

[0045] Redundancy design: Design redundant communication links to provide backup communication paths in the event of channel failure or interference.

[0046] Preferably, step S4 specifically includes:

[0047] Step S4-1: Implement radio resource management in three aspects: frequency scheduling, power control, and interference coordination;

[0048] Step S4-2: Optimize network topology using ring networks, star networks, and mesh networks.

[0049] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0050] 1. The 5G AeroMACS system base station site selection method proposed in this invention can determine the optimal location of airport 5G base stations during the planning stage. It covers the optimized configuration of site spacing, antenna installation height, antenna type and parameters, as well as the evaluation of coverage effect, thereby avoiding the practice of base station construction based solely on experience.

[0051] 2. The 5G AeroMACS system base station location method proposed in this invention can ensure that the base station performs effective spectrum allocation and interference control, and can effectively utilize wireless resources even in high-traffic and complex environments, thereby improving network operating efficiency and user experience.

[0052] 3. The 5G AeroMACS system base station site selection method proposed in this invention provides a highly reliable, flexible and easy-to-manage 5G communication network for airports through comprehensive network topology optimization measures, thereby meeting the growing communication needs of airports and ensuring the safety and efficiency of flight operations. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the embodiments will be briefly introduced below. The features and advantages of the present invention can be more clearly understood by referring to the accompanying drawings. The accompanying drawings are schematic and should not be construed as limiting the present invention in any way. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 is a flowchart of the 5G AeroMACS system base station location method of the present invention.

[0055] Figure 2 is a schematic diagram of intelligent dynamic parameter configuration for 5G base stations based on DQN.

[0056] Figure 3 is a 3D model of a 5G network base station at the airport.

[0057] Figure 4 is a schematic diagram of a 5G AeroMACS cell.

[0058] In the diagram, 1-5G base station, 2-runway, 3-projection of the antenna's horizontal 3 dB beamwidth boundary line onto the horizontal plane, 4-antenna's horizontal 3 dB beamwidth boundary line, 5-projection boundary of the antenna beam onto the horizontal plane, and 6-normal line of the antenna's horizontal beamwidth. Detailed Implementation

[0059] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments of the present invention and the features thereof can be combined with each other.

[0060] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0061] The main process of the 5G AeroMACS system base station site selection method proposed in this invention is shown in Figure 1. It mainly considers three aspects: base station deployment planning, spectrum planning, and network optimization, specifically including:

[0062] I. Base station deployment planning;

[0063] 1. To achieve efficient and comprehensive 5G network coverage, the deployment of 5G base stations at airports needs to be rationally planned. This aims to ensure smooth and secure airport communications through precise site selection and antenna deployment. Site selection is a crucial first step in the initial planning of 5G base station deployment. Base station sites are selected based on factors such as airport layout, aircraft routes, and the airport's operational area layout. Based on the requirement of a 500m coverage radius for 5G base stations, terrain, buildings, and other radio interference factors are considered to ensure signal coverage without blind spots. Site selection is precisely planned using a geographic information system (GIS).

[0064] The following is a detailed plan for antenna deployment, set up within a digital twin model of the airport environment:

[0065] Antenna type and quantity: Select the appropriate antenna type and determine the required number of antennas based on the airport area and the actual coverage radius of the 5G base station.

[0066] Antenna orientation: Design the antenna orientation to ensure that the signal can effectively cover the target area.

[0067] Electrical performance parameters: The electrical performance parameters of an antenna have a direct impact on signal quality, including:

[0068] Antenna horizontal beamwidth: 45° / 65°;

[0069] Operating frequency band: 5091–5150 MHz;

[0070] Polarization: ±45°;

[0071] Isolation: ≥ 25;

[0072] Standing wave ratio: ≤ 1.5;

[0073] Gain: 16-19 dB, large linear fading on sidelobes; Transmit power: 30 dBm ~ 40 dBm;

[0074] Temperature: -40°C to +75°C;

[0075] Humidity: 10%RH~95%RH;

[0076] Antenna downtilt angle: 0°~15°;

[0077] Installation method: Pole mounting.

[0078] 2. Based on the DQN algorithm, base station deployment is optimized to obtain the corresponding antenna mounting height h, distance d between the base station and the runway, inter-site spacing L, and antenna horizontal lobe width. and antenna downtilt angle .

[0079] Considering the actual airport environment, it is necessary to optimize the configuration of 5G base stations (such as transmit power P and antenna orientation θ) to maximize signal coverage and minimize interference. The DQN algorithm can be used to dynamically adjust 5G base station parameters (such as transmit power and antenna orientation) to achieve optimal signal coverage and minimal interference. As shown in Figure 2, in the 5G base station deployment optimization problem, the airport environment setting includes state space, action space, reward function, and interaction process with the machine tool environment.

[0080] State space: State vector S=[P,θ], where P represents the transmit power and θ represents the antenna direction.

[0081] Action space: Action A, increase power, decrease power, adjust antenna direction, each action corresponds to a controllable increment to adjust 5G base station parameters.

[0082] Reward Function: The design of the reward function needs to balance coverage effect and interference: R(S,A)=C(P,θ)-λI(P,θ)-BU(P,θ), where U(P,θ) represents operating cost, B is the balancing parameter, S represents state, A represents action, C(P,θ) represents coverage area, and I(P,θ) represents interference from other users.

[0083] The DQN model takes a state vector S=[P,θ] as input. The hidden layers consist of multiple fully connected layers, each containing 128 neurons, and employ activation functions. The output layer represents the action value, calculating the expected cumulative reward for each possible action.

[0084] The following are the specific steps and mechanisms of the learning strategy in the DQN model:

[0085] (1) Environmental Judgment

[0086] State observation: 5G base station (agent) obtains the current state from the airport environment. .

[0087] Action selection: Based on the current policy, the 5G base station (agent) selects the action for the current moment. .

[0088] ε-greedy strategy: Select the current best action and select a random action (exploration) with probability ε to discover new possibilities.

[0089] SoftMax strategy: Make probabilistic choices based on action values, giving higher probability to better actions.

[0090] (2) Strategy evaluation and updating

[0091] Environmental Feedback: After the 5G base station (intelligent agent) performs an action, the airport environment provides a reward signal for the current moment. and the state in the next moment Reward signals are used to evaluate the quality of an action; positive rewards encourage similar behaviors, while negative rewards inhibit them.

[0092] Value function update: A function Q(S,A) for updating action values ​​or a function V(S) for updating state values ​​based on the Bellman equation.

[0093] Where η is the learning rate and φ is the discount factor, which measures the impact of future rewards on the current policy. It is the maximum action value of all possible actions.

[0094] Policy update: In the policy gradient method, the policy parameters are updated directly.

[0095]

[0096] in, This represents the policy parameters at the current moment. This represents the policy parameters for the next time step. Indicates in Choose below The probability; this step is used to optimize the strategy, making it more inclined to choose 5G base station deployment parameter settings that can bring higher cumulative rewards.

[0097] (3) Strategy Improvement

[0098] 5G base stations continuously adjust their strategies to make the selection of deployment parameters more reasonable and effective under different conditions. Strategy improvement can rely on adjusting the weights of deep neural networks. Maintaining a balance between exploration and exploitation during the learning process is crucial, ensuring that the 5G base station can explore the environment to discover better strategies while also utilizing known information to optimize them. Common methods include dynamically adjusting the ε value or using a decreasing temperature parameter to adjust the SoftMax strategy.

[0099] (4) Model training and evaluation

[0100] Extensive training loops in a simulated environment enable 5G base stations to continuously learn and optimize under different scenarios. Techniques such as experience replay and target networks are used to improve the stability and efficiency of training. Specifically, after training, the effectiveness of the strategy is verified by testing in real or simulated environments. Evaluation metrics include coverage, interference level, and user experience. Through reinforcement learning algorithms, 5G base stations can dynamically adjust their deployment parameters to adapt to changing network demands and environmental conditions.

[0101] Dynamic load balancing: When terminal density or traffic demand increases, 5G base stations can adjust transmit power and antenna orientation to optimize coverage and capacity. Interference management: 5G base stations can identify and respond to interference from neighboring base stations, reducing interference by adjusting frequency channels or changing antenna configurations. Energy efficiency optimization: Reducing power consumption under low load while maximizing performance under high load. The DQN model, through continuous learning and policy optimization, enables 5G base stations to provide efficient and reliable network services in complex and dynamic airport environments. This approach not only enhances the intelligent management capabilities of the network but also provides theoretical guidance for practical deployment.

[0102] Currently, the selection of 5G base station sites, antenna operating parameters, and antenna beamwidth at airports largely rely on the experience of designers. From a beamform perspective, existing airport 5G base station antennas mostly employ fixed-beam plate antennas. These modified antennas typically feature a wide horizontal beam (mainly 33° and 65° beamwidth) and a narrow vertical beam (approximately 7°), offering some beamforming capability in the horizontal plane but lacking it in the vertical plane. To improve vertical beam coverage, existing airport 5G base station antennas often use a 2×2 arrangement with two channels in each direction, but this weakens horizontal coverage. From the perspective of coverage holes, due to factors such as airport 5G base station site selection, antenna operating parameters, and antenna beamwidth, airports are prone to coverage holes, i.e., weak coverage areas, manifesting as both horizontal and vertical coverage holes. The direct cause of horizontal and vertical coverage holes is the direct correlation between the energy distribution of the radiated signal from the base station antenna and the antenna pattern. Due to the presence of antenna downtilt and azimuth angles, the projection of the main beam of the 5G base station's radiated signal onto the horizontal plane of the airport surface has a certain angle with the runway, rather than completely coinciding. When the horizontal null point of the antenna pattern is projected exactly onto the runway, it will cause a horizontal coverage hole on the runway. Simultaneously, limited by the horizontal and vertical beamwidths of traditional plate antennas, when the angle between the projection of the main beam of the antenna pattern onto the ground and the runway is large, the projections of multiple lower sidelobes will also fall onto the runway, and the null points between the lobes falling onto the runway will create a vertical coverage hole. Typically, the design of 5G base station sites, antenna operating parameters, and antenna beamwidth at airport surfaces only considers the distance planning between the 5G base station and the runway, as well as the influence of the antenna azimuth and downtilt angles. Furthermore, it should also ensure that the antenna incident angle is greater than or equal to 10°.

[0103] Regarding antenna azimuth and downtilt angles, for newly built 5G base stations at airport sites, the initial azimuth angle planning follows the alignment of the upper half-power angle of the vertical lobe and the outer half-power angle of the horizontal lobe with the farthest coverage point. Within the farthest coverage point, a handover zone of approximately 100-110m is considered; that is, the coverage edge of each airport site 5G network base station is the midpoint of the coverage area of ​​the adjacent 5G network base station offset by half the handover zone position. The initial downtilt angle is determined similarly to the azimuth angle, using the upper half-power angle of the antenna aligned with the coverage edge to determine the antenna downtilt angle.

[0104] This invention establishes a model of a 5G base station on an airport surface, as shown in Figure 3. Here, h represents the antenna height of 5G base station 2, and d represents the distance between the base station and the runway, i.e., the vertical distance between the base station and runway 1. The horizontal lobe width of the 5G base station antenna is α; the near-point elevation angle of the 5G base station antenna is... The elevation angle of the far point of the antenna is The horizontal beamwidth of the antenna beam projected onto the horizontal plane is The angle between the antenna beam's projection boundary 5 and d on the horizontal plane is... As can be seen from Figure 3, from a horizontal coverage perspective, the angle between the antenna beam of the 5G base station projected onto the horizontal plane boundary 5 and d is... This determines the distance between stations, L. When using the intersection of the antenna's horizontal 3 dB beamwidth boundary line 4 projected onto the horizontal plane and the runway as the coverage farthest point, the effective coverage distance of the runway is longer. Simultaneously, when using the intersection of the antenna's horizontal 3 dB beamwidth boundary line 4 projected onto the horizontal plane and the runway as the coverage farthest point, the signal level attenuates rapidly when an aircraft passes the intersection point, which facilitates handover within the cell. This also applies to the antenna's coverage blind spot distance at the airport surface. In addition, the effective coverage range of an antenna for airport surface coverage is also limited by the vertical beamwidth of the main beam. To ensure continuous airport surface coverage and increase the effective coverage range of the antenna, the effective coverage range of the antenna is directly affected by the antenna's vertical beamwidth.

[0105] The proposed 5G AeroMACS system base station site selection method requires that the global deployment of AeroMACS does not violate the ITU WRC-07 requirement of 2°C for satellite temperature rise. It solves for the 5G base station configuration parameters at airports, setting the antenna mounting height h (including the height of the building and its support structure), the distance d between the base station and the runway, the inter-station spacing L, the antenna horizontal lobe width α, and the antenna downtilt angle. Determine the distance D of the antenna coverage far point and the elevation angle of the antenna near point. Antenna far point elevation angle The minimum vertical lobe width required for optimal coverage The minimum vertical lobe width required for an antenna The horizontal beamwidth of the antenna beam projected onto the horizontal plane The angle between the antenna beam's projection boundary 5 and d on the horizontal plane The distance of the antenna's coverage blind spot at the airport. and the minimum incident angle of the signal The details are as follows:

[0106]

[0107]

[0108]

[0109]

[0110]

[0111]

[0112]

[0113]

[0114]

[0115] As shown in Figure 4, this method achieves continuous and efficient wireless network coverage over runways, taxiways, and other key areas by rationally selecting and optimizing the location of multiple 5G base stations (BS1, BS2, BS3, ..., BSN) within the airport area. Base station location is based on the airport's layout characteristics, aircraft routes, building distribution, and potential sources of radio interference, ensuring high-quality communication services without blind spots within the target area. The coverage area of ​​each base station is determined by its antenna beam directivity, transmit power, and antenna parameters (such as horizontal beamwidth, vertical beamwidth, elevation angle, and downtilt angle), and is precisely marked by the projection of the antenna's horizontal 3 dB beamwidth boundary line onto the horizontal plane, reflecting the effective signal coverage area. The coverage areas of each base station overlap, achieving redundant coverage design at runway intersections and near taxiways to improve system reliability and anti-interference capabilities. The antenna's azimuth and downtilt angles are set according to the optimization principles of the farthest coverage point and switching band, ensuring optimal coverage of the antenna's main signal beam within the target area. Simultaneously, by adjusting the step size (e.g., 15 kHz / 30 kHz or 250 kHz) and spectrum management strategies, interference sources are flexibly avoided, optimizing spectrum utilization and network performance. This invention effectively solves the coverage gap problem in 5G communication at airports, providing stable communication guarantees under high traffic or base station failure conditions, and significantly improving the overall performance and security of airport communication networks.

[0116] II. Spectrum Planning;

[0117] Network deployment will be conducted based on the airport surface communication requirements and relevant ICAO standards, with in-depth spectrum allocation and interference management to ensure the stability and reliability of the communication system, including:

[0118] Step-size tuning: 5G AeroMACS devices are frequency tuned in steps of 15 kHz / 30 kHz (5G standard). This allows for flexible avoidance of interference sources such as microwave landing systems (MLS) and airborne mobile telemetry (AMT).

[0119] Frequency avoidance strategy: Select different frequency step sizes based on the amount of interference signals in the area.

[0120] In high-interference areas, larger step sizes (e.g., 250 kHz) should be used to quickly avoid interference. In low-interference areas, smaller step sizes (e.g., 5 kHz to 30 kHz) can be considered to optimize spectrum utilization.

[0121] Multi-channel bandwidth support: Supports channel bandwidths of 5 MHz, 10 MHz, 20 MHz, 30 MHz, 40 MHz and 50 MHz, with 50 MHz used by default to maximize data throughput and network efficiency.

[0122] Dynamic bandwidth adjustment: Channel bandwidth is dynamically adjusted based on real-time communication needs and environmental interference to optimize network performance. For example, greater bandwidth is used during high-traffic periods or in scenarios with high data demand.

[0123] Carrier aggregation: Carrier aggregation (CA) technology is used to improve spectral efficiency, enabling higher data throughput and more stable connections in multi-channel conditions.

[0124] Subcarrier management: A spectrum management method based on subcarrier spacing (SCS) is adopted to balance network scanning speed and spectrum efficiency. The optimal subcarrier spacing is selected according to the specific application scenario and spectrum conditions.

[0125] Priority management: Prioritize communications involving security and mission-critical tasks to ensure reliable communication even under high load or interference conditions.

[0126] Redundancy design: Where possible, design redundant communication links to provide backup communication paths in the event of channel failure or interference.

[0127] III. Network optimization;

[0128] To ensure that the 5G network can efficiently and stably serve the airport environment, network optimization is particularly crucial. This invention addresses network optimization from two aspects: wireless resource management and network topology optimization.

[0129] 1. Wireless Resource Management

[0130] Develop radio resource management (RRM) strategies, including frequency scheduling, power control, and interference coordination. This ensures efficient utilization of radio resources in high-load and complex environments, improving network performance and user experience. The RRM strategy in 5G AeroMACS is crucial for ensuring efficient utilization of radio resources in high-load and complex environments, thereby enhancing network performance and user experience.

[0131] (1) In frequency scheduling

[0132] 5G AeroMACS employs flexible spectrum sharing and dynamic spectrum allocation technologies, adjusting spectrum resource allocation based on real-time demand to optimize spectrum utilization. Through spectrum sensing technology, it monitors the spectrum utilization and network load of each 5G base station, adjusting spectrum allocation in real time. For example, when terminal demand near a terminal increases, unused spectrum resources from neighboring cells can be used to meet the demand. In practice, using software-defined radio technology, 5G base stations can adjust spectrum configurations within milliseconds, ensuring efficient spectrum resource utilization and rapid response.

[0133] Meanwhile, 5G base stations utilize carrier aggregation technology to combine spectrum resources from multiple frequency bands, thereby providing users with higher bandwidth. In operation, 5G base stations support multi-band aggregation modules, enabling simultaneous transmission of multiple frequency bands and reducing data transmission time.

[0134] (2) Power control

[0135] By monitoring the signal strength and channel conditions of terminals in real time, the system dynamically adjusts the transmission power of 5G base stations. When a terminal is close to a 5G base station, the system can reduce transmission power to save energy, while when the terminal is far away, the system will increase power to ensure signal coverage. For example, when an aircraft is taxiing away from the base station, the 5G base station automatically increases transmission power to ensure communication stability, while reducing power when the aircraft is close to the 5G base station to reduce interference.

[0136] (3) Interference coordination

[0137] 5G AeroMACS introduces a variety of interference suppression and management technologies, such as Cooperative Multipoint Transmission (CoMP), Multiple-Input Multiple-Output (MIMO), and beamforming, to enhance signal quality and reduce interference between adjacent cells by coordinating the transmission of multiple base stations or antenna arrays.

[0138] To reduce interference between adjacent 5G base stations, cooperative multi-point transmission technology is used. Multiple 5G base stations coordinate to provide services to terminals located at the edge of the coverage area of ​​multiple 5G base stations by sharing the channel state information of the terminals, thereby enhancing signal quality. Through a low-latency backhaul network, the 5G base stations can quickly share information, ensuring the coordination of signal transmission. For example, when an aircraft is located at the edge of a taxiway, in the boundary area of ​​multiple base stations, multiple 5G base stations transmit data to it simultaneously, ensuring high-quality communication signals even in the boundary area.

[0139] By utilizing beamforming technology, signal energy is concentrated in a specific direction based on the location of the terminal at the airport, thereby improving signal strength and reducing interference. 5G base stations dynamically adjust the signal beam direction by controlling the phase and amplitude of the signal through antenna arrays. For example, when an aircraft moves along the runway, the 5G base station can adjust the beam transmission direction in real time to ensure that the signal strength received by the terminal remains optimal at different locations, thus providing a consistently stable communication experience.

[0140] Furthermore, 5G AeroMACS networks utilize artificial intelligence and machine learning technologies to effectively learn relevant characteristics and changes in the network environment from massive amounts of data. By analyzing historical data and real-time network status, they can predict network load and terminal demands, optimize resource allocation strategies, and improve the network's self-organization and self-optimization capabilities. Through these comprehensive wireless resource management strategies, 5G AeroMACS networks can operate efficiently in high-load and complex environments, providing superior network performance and user experience.

[0141] 2. Network topology optimization

[0142] In the site selection process for 5G base stations at airports, network topology optimization is a crucial step. The core of this process lies in meticulously optimizing the network topology based on the traffic distribution and user needs at the airport. To achieve this goal, this invention employs various network topologies, including ring networks, star networks, and mesh networks. The selection and configuration of these topologies aim to improve network robustness and redundancy, ensuring rapid network recovery and switching in the face of various contingencies, such as equipment failures, link interruptions, or other unexpected events, thereby guaranteeing the continuity and stability of communication services.

[0143] Specifically, ring networks can effectively reduce the impact of single-point failures on the overall performance of airport surface networks because data can be transmitted bidirectionally within the ring structure; even if one segment of the link fails, the data can still reach its destination via another path. Star networks are simple and easy to manage, providing efficient data transmission and centralized control capabilities in key areas of the airport surface, such as terminals and control towers. Mesh networks, with their complexity and multi-path characteristics, offer a more flexible and reliable communication solution for airport surface operations.

[0144] The following principles must be followed during network topology optimization:

[0145] Node redundancy design: Redundant nodes are set up in the critical communication service area of ​​the airport to ensure that when a node fails, other nodes can quickly take over its functions and reduce network downtime.

[0146] Link backup: Provides backup paths for critical links. When the primary link fails, the backup link can immediately take over data transmission and maintain network connectivity.

[0147] Traffic balancing: Network topology design needs to achieve balanced traffic distribution to avoid performance degradation of certain nodes or links due to traffic overload.

[0148] Fault Detection and Response: Deploy an efficient fault detection system that can quickly initiate recovery procedures once a network fault is detected, ensuring the continuity of network services.

[0149] Through the above comprehensive network topology optimization measures, a highly reliable, flexible, and easy-to-manage 5G communication network can be provided for the airport, thereby meeting the airport's growing communication needs and ensuring the safety and efficiency of flight operations. The network topology is optimized based on traffic distribution and user requirements. Ring, star, and mesh topologies are adopted to improve network robustness and redundancy, ensuring rapid recovery and switching in the event of a fault.

[0150] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0151] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0152] In this invention, the terms "first," "second," "third," and "fourth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The term "multiple" refers to two or more unless otherwise expressly defined.

[0153] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for selecting a base station location in a 5G AeroMACS system, characterized in that, The process includes the following steps: Step S1: Establish a digital twin model of the airport environment; Step S2: Use the DQN algorithm to obtain optimal base station deployment parameters with the goal of maximizing signal coverage and minimizing interference; Step S3: Deploy the network according to the airport's 5G AeroMACS communication requirements and ICAO standards; Step S4: Optimize the network through wireless resource management and network topology optimization; Step S2 specifically includes: Step S2-1: Set the state space, action space, and reward function; Step S2-2: Establish a DQN model and train it; Step S2-3: Apply the trained DQN model to obtain optimal base station deployment parameters; The state space contains a state vector S=[P,θ], where P represents the transmit power and θ represents the antenna direction; The action space contains action A, including increasing power, decreasing power, and adjusting antenna direction; the reward function is expressed as: R(S,A)=C(P,θ)-λ1I(P,θ)-BU(P,θ), where U(P,θ) represents operating cost, B is the balancing parameter, S represents state, A represents action, C(P,θ) represents coverage area, and I(P,θ) represents interference from other users; the base station deployment parameters in steps S2-3 include: antenna height h, distance d between base station and runway, inter-station spacing L, antenna horizontal lobe width α, and antenna downtilt angle. Determine the distance D of the antenna coverage far point and the elevation angle of the antenna near point. Antenna far point elevation angle The minimum vertical lobe width required for optimal coverage The minimum vertical lobe width required for an antenna The horizontal beamwidth of the antenna beam projected onto the horizontal plane The angle between the projection boundary of the antenna beam onto the horizontal plane and d. The distance of the antenna's coverage blind spot at the airport. and the minimum incident angle of the signal Step S3 specifically includes: step size tuning: the 5G AeroMACS device performs frequency tuning in steps of 15 kHz or 30 kHz to avoid interference sources; frequency avoidance strategy: different frequency step sizes are selected according to the amount of regional interference signals; multi-channel bandwidth support: supports 5 MHz, 10 MHz, 20 MHz, 30 MHz, 40 MHz and 50 MHz. MHz channel bandwidth; dynamic bandwidth adjustment: dynamically adjust the channel bandwidth according to real-time communication needs and environmental interference to optimize network performance; carrier aggregation: use carrier aggregation technology to improve spectrum efficiency; subcarrier management: adopt a spectrum management method based on subcarrier spacing to balance network scanning speed and spectrum efficiency; priority management: set priority for communication involving security and critical tasks to ensure that communication can still be maintained under high load or interference conditions; redundancy design: design redundant communication links to provide backup communication paths when the channel fails or is interfered with; the specific steps of S2-2 include: step S2-2-1: establish a DQN model, which consists of an input layer, a hidden layer and an output layer, wherein the hidden layer consists of multiple fully connected layers, each fully connected layer contains 128 neurons, and an activation function is used; step S2-2-2: set the mechanism of the DQN model learning strategy and train the DQN model; the mechanism of the DQN model learning strategy in step S2-2-2 includes: (1) environmental decision state observation: the 5G base station obtains the current state from the airport environment. This includes 5G base station configuration, terminal density, traffic demand, and interference levels; Action selection: Based on the current policy, the 5G base station selects the action for the current moment. ; ε-greedy strategy: select the current optimal action and select a random action with probability ε; SoftMax strategy: make a probabilistic selection based on the action value; (2) Strategy evaluation and update environment feedback: after the 5G base station executes the action, the airport environment feeds back the reward signal at the current moment. And the state in the next moment. Value function update: A function Q(S,A) for updating action values ​​or a function V(S) for updating state values ​​based on the Bellman equation. Where η is the learning rate and φ is the discount factor, which measures the impact of future rewards on the current policy. It is the maximum action value among all possible actions; Policy update: In the policy gradient method, the policy parameters are updated directly. in, This represents the policy parameters at the current moment. This represents the policy parameters for the next time step. Indicates in Choose below The probability; (3) Strategy improvement: Adjust the SoftMax strategy by adjusting ε or using decreasing temperature parameters; (4) Model training and evaluation: After training, verify the effectiveness of the strategy by testing in a real or simulated environment. Evaluation indicators include coverage, interference level and user experience; The digital twin model in step S1 includes the following parameters: antenna type and number, antenna direction, antenna electrical performance parameters, antenna horizontal beamwidth, operating frequency band, polarization, isolation, VSWR, gain, transmit power, temperature, humidity, antenna downtilt angle and installation method; Step S4 specifically includes: Step S4-1: Implement wireless resource management in three aspects: frequency scheduling, power control and interference coordination; Step S4-2: Adopt Network topology optimization is achieved using ring, star, and mesh networks. The following principles are followed during the optimization process: Node redundancy design: Redundant nodes are set up in critical communication service areas of the airport to ensure that when one node fails, other nodes can quickly take over its function, reducing network downtime; Link backup: Backup paths are provided for important links so that when the primary link fails, the backup link can immediately take over data transmission, maintaining network connectivity; Traffic balancing: The network topology design must achieve balanced traffic distribution to avoid performance degradation due to traffic overload on certain nodes or links; Fault detection and response: An efficient fault detection system is deployed to quickly initiate recovery procedures once a network fault is detected, ensuring the continuity of network services.

Images