WO2023231193A1 - 一种基于6g空中基站信号增强及智能按需覆盖优化方法 - Google Patents

一种基于6g空中基站信号增强及智能按需覆盖优化方法 Download PDF

Info

Publication number
WO2023231193A1
WO2023231193A1 PCT/CN2022/114155 CN2022114155W WO2023231193A1 WO 2023231193 A1 WO2023231193 A1 WO 2023231193A1 CN 2022114155 W CN2022114155 W CN 2022114155W WO 2023231193 A1 WO2023231193 A1 WO 2023231193A1
Authority
WO
WIPO (PCT)
Prior art keywords
satellite
base station
intelligent
user
constellation
Prior art date
Application number
PCT/CN2022/114155
Other languages
English (en)
French (fr)
Inventor
王玉梁
Original Assignee
中电信数智科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中电信数智科技有限公司 filed Critical 中电信数智科技有限公司
Publication of WO2023231193A1 publication Critical patent/WO2023231193A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/18—Network planning tools
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/22—Traffic simulation tools or models
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/04—Large scale networks; Deep hierarchical networks
    • H04W84/06—Airborne or Satellite Networks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the invention belongs to the technical field of satellite base stations, and specifically relates to a method based on 6G air base station signal enhancement and intelligent on-demand coverage optimization.
  • Non-terrestrial network nodes such as UAV, HAPS, and VLEO satellites will become part of the 6G network infrastructure. Although they can provide similar functions to terrestrial base stations, the design of non-terrestrial nodes still needs to be improved to meet strict link budget requirements. Combined with the expected progress in payload radio frequency modules and processing capabilities, there is a lot of room for breakthroughs in 6G air interface design.
  • wireless networks have primarily consisted of static ground access points. However, given the likely ubiquity of UAV, HAPS and VLEO satellites in the future, as well as the desire to integrate satellite communications into cellular networks (NR), future systems will no longer be horizontal and two-dimensional. Emerging 3D vertical networks include many mobile high-altitude access points (excluding geostationary satellites) such as UAV HAPS and VLEO satellites. At the same time, it also highlights the status of AI/ML in the field of 6G wireless communications.
  • 6G wireless networks will be much more functionally complex than 5G, under the principle of lowest cost, new applications, new requirements, and new indicators will bring huge challenges to air interface design. Therefore, the 6G air interface is in urgent need of innovation.
  • the air interface framework of 6G must be smarter and more energy-saving to meet the needs of 6G in terms of deployment efficiency, cost, power consumption, complexity, etc.
  • the 6G air interface framework must take into account relevant air interface enabling technologies from the beginning of the design, including artificial intelligence, new frequencies, non-terrestrial communication systems, and cognitive communications.
  • the technical problem to be solved by the present invention is to provide a method based on 6G air base station signal enhancement and intelligent on-demand coverage optimization in view of the above-mentioned shortcomings of the existing technology. It is oriented to the 6G network communication environment and can support the emerging 6G wireless access technology, 6G Empty design.
  • a method based on 6G air base station signal enhancement and intelligent on-demand coverage optimization including:
  • Step 1 Set up a 6G satellite base station, use Markov chain algorithm to build a transmission efficiency prediction model, and test the same user's uplink signal through distributed MIMO to enhance non-terrestrial communications;
  • Step 2 When the movement of non-GEO satellites brings frequent beam switching, the Transformer algorithm is used to build a satellite scheduling model to achieve intelligent on-demand coverage, and the preset switching program is used to optimize and adjust faults according to the type of faults that occur.
  • multiple satellites in the 6G satellite base station simultaneously receive the current user's uplink signal, input the uplink signal data into the transmission efficiency prediction model, and predict the probability that each satellite node will receive the strongest uplink signal in the next time period, thereby enhancing non-terrestrial communications. .
  • the non-ground communication infrastructure in the 6G aerial scenario includes UAV, HAPS, and VLEO; and the non-ground infrastructure and ground user terminals are connected through wireless signals, and their wireless communication related log data is stored in on air infrastructure.
  • Step 2 above includes:
  • Step 21 Perform interpolation analysis on the log historical data stored on each satellite node of the constellation, and obtain the edge coverage of the constellation when the satellite node fails to receive the user's uplink signal, the satellite node reaches the upper limit of the load capacity, and the relative position of the user is moved due to satellite movement. Analysis data of poor signal;
  • Step 22 Input the analyzed data into the satellite scheduling model, and predict the probability of occurrence of a failure of the satellite node in the constellation receiving the user's uplink signal, the satellite node reaching the upper limit of the load capacity, or the relative position movement of the user caused by satellite movement, resulting in poor edge coverage signal reaching the constellation;
  • Step 23 Based on the predicted probability in step 22, perform fault optimization and adjustment according to the type of fault that occurs through the preset switching program.
  • x is the time series value
  • y is the interpolation business data
  • i is the time series number
  • the model formula of the satellite scheduling model described in step 23 above is:
  • positional encoding is used for timing encoding, and attention is used to explore feature correlations in the timing dimension;
  • N is the adjustable length
  • the attention calculation formula is as follows:
  • dk represents the dimension of K
  • V is the input data
  • Q is the query feature map
  • K is the feature map to be matched
  • WO is the feature fusion matrix
  • Concat is the feature cascade fusion
  • MultiHead is the multi-head feature fusion
  • headi is the temporal attention, which is the result of attention calculation, which is fused in the spatial dimension through MultiHead;
  • Qi is the i-th group query feature map
  • Ki is the i-th set of feature maps to be matched
  • Vi is the i-th group of monitoring data mapping, that is, the i-th group of input data.
  • step 23 if the satellite node in the predicted satellite node constellation fails to receive the user's uplink signal, the satellite node reaches the upper limit of the load capacity, and the satellite movement causes the relative position of the user to move, resulting in a poor edge coverage signal reaching the constellation, the probability of occurrence is greater than 50%. , then the switching program is automatically triggered to handle and optimize three types of faults: the satellite node in the constellation fails to receive the user's uplink signal, the satellite node reaches the upper limit of the load capacity, and the relative position of the user is moved due to satellite movement, resulting in poor edge coverage signal reaching the constellation.
  • the above step 23 specifically includes:
  • the above-mentioned intra-satellite switching procedure is: immediately transmit the current user UE stored in the configuration file on the faulty satellite node to the configuration file of other nearest satellite nodes through wireless transmission through program control to complete satellite node fault scheduling;
  • the satellite and cellular switching procedure is: the satellite signal passes through the 5G wireless access network, and the RAN uses both NR and LTE (eNB) base stations to complete signal docking with the terrestrial network base station, and the terrestrial network assists the non-terrestrial network;
  • eNB LTE
  • the inter-satellite switching procedure is: two satellites establish inter-satellite links through the conditions preset in the switching procedure for inter-satellite switching, and their positions must meet the following conditions:
  • h is the height of the satellite
  • Hp is the clearance, that is, the distance between the inter-satellite link and the earth's surface
  • Re is the radius of the earth
  • alpha is the geocentric angle between the satellites
  • the minimum clearance corresponds to the maximum inter-satellite geocentric angle alpha (max).
  • alpha ⁇ alpha (max) an inter-satellite link can be established between the two satellites, and vice versa.
  • This invention focuses on two major principles of 6G air interface design: 1. Overcoming the challenges brought by non-terrestrial communications; 2. Using the unique attributes of non-terrestrial nodes, the design is based on 6G air base station signal enhancement and intelligent on-demand coverage optimization methods, highlighting AI /ML's position in the field of wireless communications, combined with artificial intelligence, makes constellation-based networks more intelligent, and makes satellite networks more efficient and mobile through intra-satellite switching, inter-satellite switching, satellite and cellular switching, etc., thus reducing the number of Reduce overhead, shorten interrupt time, and reduce power consumption.
  • Figure 1 is a schematic flow chart of the method of the present invention.
  • a method of the present invention based on 6G air base station signal enhancement and intelligent on-demand coverage optimization includes:
  • Step 1 Set up a 6G satellite base station, use Markov chain algorithm to build a transmission efficiency prediction model, and test the same user's uplink signal through distributed MIMO to enhance non-terrestrial communications;
  • non-ground communication infrastructure mainly consists of common facilities such as UAV, HAPS, and VLEO.
  • Non-ground infrastructure and ground user terminals are connected through wireless signals, and their wireless communication related log data is stored on the air infrastructure:
  • UAV unmanned aerial vehicle
  • HAPS High Altitude Platform Station communication system places wireless base stations on aircraft that stay at high altitudes for a long time to provide telecommunications services. It is considered to be a broadband wireless access method with good potential application value after 2010. . If its height is 20km, a communication area with a ground coverage radius of about 500km can be achieved
  • MIMO Multiple input multiple output wireless transmission technology has opened a new era in the development and utilization of space resources in mobile communication systems.
  • P represents the one-step transition probability matrix
  • Each 3dB increase or decrease means doubling or halving the power.
  • Step 2 Aiming at the problem of frequent beam switching caused by the movement of non-GEO satellites, the Transformer algorithm is used to build a satellite scheduling model to achieve intelligent on-demand coverage. And through the preset switching program, fault optimization adjustments such as intra-satellite switching, inter-satellite switching, satellite and cellular switching, etc. are carried out according to the type of faults that occur. At the same time, constellation-based network intelligence and efficient mobility are achieved to reduce signaling overhead, shorten interruption time, and reduce power consumption.
  • fault optimization adjustments such as intra-satellite switching, inter-satellite switching, satellite and cellular switching, etc.
  • a satellite constellation is a collection of satellites that are launched into orbit and can work normally. It is usually a satellite network composed of a number of satellite rings configured in a certain way.
  • Step 21 Perform interpolation analysis on the log history data stored on each satellite node of the constellation to obtain a more accurate picture of whether a satellite node fails to receive the user's uplink signal, the satellite node reaches the upper limit of the load capacity, or the movement of the satellite causes the relative position of the user to move Analytical data resulting in poor signal coverage at the edges of the constellation.
  • the quadratic difference method is used to interpolate every 3 adjacent points to obtain the quadratic interpolation. That is, data optimized by artificial intelligence algorithms.
  • y Y-axis of interpolated service data (uplink signal failure data)
  • Time series serial number i (the serial number of the data time, there may be several data intervals from serial number i to serial number i+1)
  • Step 22 Input the interpolation analysis data into the satellite scheduling model, and predict that a certain satellite node in the constellation fails to receive the user's uplink signal, the satellite node reaches the upper limit of the load capacity, or the relative position of the user is moved due to satellite movement, resulting in poor edge coverage signals arriving at the constellation. Probability of occurrence.
  • positional encoding is used for timing encoding, and attention is used to explore feature correlations in the timing dimension.
  • N is the adjustable length size
  • the Attention calculation formula is as follows:
  • Q is the query feature map
  • K is the feature map to be matched
  • V is the monitoring data map
  • V is the input data: (the uplink signal fails, the satellite node reaches the upper limit of the load capacity, the relative position of the user moves due to satellite movement, resulting in poor edge coverage signal reaching the constellation) are all input data.
  • Q is query feature mapping: there is no specific business attribute, it is a parameter in the network, which is equivalent to learned
  • K is the feature map to be matched: there is no specific business attribute, it is a parameter in the network, which is equivalent to learned
  • N is the adjustable length
  • Q is the query feature map
  • K is the feature map to be matched
  • V is the monitoring data map
  • headi is the result of temporal attention, which is integrated with multiple spatial dimensions through MultiHead.
  • Qi is the i-th group query feature map
  • Ki is the i-th set of feature maps to be matched
  • Vi is the monitoring data mapping of the i-th group
  • WO is the feature fusion matrix
  • PositionEncoding is the position sequence encoding
  • Attention_output is (see the aforementioned formula).
  • MultiHead is multi-head feature fusion.
  • Step 23 If the predicted probability of occurrence of the three types of faults on the satellite node is greater than 50%, the switching program is automatically triggered to handle and optimize the three types of faults.
  • the intra-satellite handover procedure will be triggered.
  • Intra-satellite switching program Immediately through program control, the current user UE stored in the configuration file on the faulty satellite node is wirelessly transmitted to the configuration file of other nearest satellite nodes to complete satellite node fault scheduling.
  • the constellation receives the user's uplink signal and the predicted probability of reaching the upper limit of the load capacity is large (greater than 50%). Then, the satellite and cellular switching procedure is triggered.
  • Satellite and cellular handover procedure that is, the [satellite scheduling model] is introduced to predict the situation where the probability of the constellation receiving user UE load capacity exceeding the upper limit is high (greater than 50%). Satellite signals are generated through the 5G Radio Access Network (RAN), which can use both NR (gNB) and LTE (eNB) base stations. This completes the process of signal docking with the terrestrial network base station and the terrestrial network assisting the non-terrestrial network.
  • RAN Radio Access Network
  • gNB NR
  • eNB LTE
  • Inter-satellite switching procedure that is, two satellites establish an inter-satellite link through the conditions preset in the switching procedure, and their positions must meet the following conditions:
  • h is the height of the satellite
  • Hp is the clearance (the distance between the inter-satellite link and the earth's surface)
  • Re is the radius of the earth.
  • the minimum clearance corresponds to the maximum inter-star geocentric angle alpha(max). When alpha ⁇ alpha (max), an inter-satellite link can be established between the two satellites, and vice versa.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Astronomy & Astrophysics (AREA)
  • General Physics & Mathematics (AREA)
  • Radio Relay Systems (AREA)

Abstract

本发明公开了一种基于6G空中基站信号增强及智能按需覆盖优化方法，包括步骤1、组建6G卫星基站，采用马尔可夫链算法构建传输效率预测模型，并通过分布式MIMO测试同一用户上行信号，进而增强非地面通讯；步骤2、当非GEO卫星移动带来频繁波束切换时，采用Transformer算法构建卫星调度模型，实现智能按需覆盖，并通过预置切换程序根据发生的故障类型进行故障优化调整。本发明突出了AI/ML在无线通讯领域中的地位，结合人工智能使得基于星座的网络更加智能化，并通过星内切换、星间切换、卫星和蜂窝切换等，使得卫星网络更具高效移动性，从而减少信令开销、缩短中断时间，降低功耗。

Description

一种基于6G空中基站信号增强及智能按需覆盖优化方法 技术领域
本发明属于卫星基站技术领域，具体涉及一种基于6G空中基站信号增强及智能按需覆盖优化方法。
背景技术
UAV、HAPS、VLEO卫星等非地面网络节点将成为6G网络基础设施的一部分，虽然它们能提供和地面基站类似的功能，但非地面节点的设计仍需改进，以满足严格的链路预算要求。结合载荷射频模块和处理能力的预期进展，6G空口设计有很大的突破空间。
在过去的几十年里，无线网络主要由静态地面接人点组成。然而，考虑到未来可能普遍存在的UAV、HAPS和VLEO卫星，以及人们将卫星通信融人蜂窝网络(NR)的愿望，未来的系统将不再是横向的、二维的。新兴的3D垂直网络包括许多移动的高空接人点(不包括对地静止卫星)、例如UAV HAPS和VLEO卫星。同时也突出了AI/ML在6G无线通讯领域的地位。
由于6G无线网络在功能上将比5G复杂得多，在成本最低原则下，新应用、新要求、新指标都给空口设计带来了巨大挑战。因此，6G空口亟须革新。
相比NR，6G的空口框架要更智能、更节能，才能满足6G在部署效率、成本、功耗、复杂度等方面的需求。为了实现这些目标，6G空口框架在设计之初就必须要考虑到相关空口使能技术，包括人工智能、新频诸、非地面通信系统和感知通信等。
发明内容
本发明所要解决的技术问题是针对上述现有技术的不足，提供一种基于6G空中基站信号增强及智能按需覆盖优化方法，面向6G网络通信环境，可支撑新兴的6G无线接人技术、6G空口设计。
为实现上述技术目的，本发明采取的技术方案为：
一种基于6G空中基站信号增强及智能按需覆盖优化方法，包括：
步骤1、组建6G卫星基站，采用马尔可夫链算法构建传输效率预测模型，并通过分布式MIMO测试同一用户上行信号，进而增强非地面通讯；
步骤2、当非GEO卫星移动带来频繁波束切换时，采用Transformer算法构建卫星调度模型，实现智能按需覆盖，并通过预置切换程序根据发生的故障类型进行故障优化调整。
为优化上述技术方案，采取的具体措施还包括：
上述的步骤1中，6G卫星基站中多卫星同时接收当前用户上行信号，将上行信号数据输入传输效率预测模型，预测出下时间段各卫星节点接收上行信号最强的概率，从而增强非地面通讯。
上述的步骤1中，所述6G的空中场景中非地面通讯基础设施包括UAV、HAPS、VLEO；且非地面基础设施与地面用户终端之间通过无线信号进行连接，其无线通讯相关日志数据存储在空中基础设施上。
上述的步骤2包括：
步骤21、对存储在星座的各卫星节点上的日志历史数据进行插值分析，得到卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的分析数据；
步骤22、将分析数据输入卫星调度模型，预测得到星座中卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的发生概率；
步骤23、基于步骤22的预测概率，通过预置切换程序根据发生的故障类型进行故障优化调整。
上述的步骤21所述插值分析公式如下：
Figure PCTCN2022114155-appb-000001
其中，x为时间序列数值，y为插值业务数据，i为时间序列序号。
上述的步骤23所述卫星调度模型的模型公式为：
针对时间维度，利用positional encoding进行时序编码，利用attention发掘时序维度的特征关联；
positionl encoding＝cos2(pos/N)
N为可调长度大小；
attention计算公式如下：
Figure PCTCN2022114155-appb-000002
其中，dk代表K的维度；V为输入数据；Q为查询特征映射；K为待匹配特征映射；
针对空间维度，利用multi head attention提取不同多空间维度特征，公式如下：
MultiHead(Q，K，V)＝Concat(head1，...，headh)*WO
headi＝Attention(Qi，Ki，Vi)
其中，WO为特征融合矩阵；Concat为特征级联融合；MultiHead为多头特征融合；
headi为时间注意力，即attention计算得到的结果，其在空间维度通过MultiHead融合；
Qi为第i组查询特征映射；
Ki为第i组待匹配特征映射；
Vi为第i组监测数据映射，即第i组输入数据。
上述的步骤23中，如果预测的卫星节点星座中卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的发生概率大于50％，则自动触发切换程序实现星座中卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差三种类型故障的处理及优化。
上述的步骤23具体包括：
1)如果卫星节点接收用户上行信号发生故障的概率大于50％，则触发星内切换程序；
2)如果卫星节点达到荷载能力上限的概率大于50％，则触发卫星与蜂窝切换程序；
3)如果卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的概率大于50％，则触发星间切换程序。
上述的星内切换程序为：立即通过程序控制将故障卫星节点上配置文件中存储的当前用户UE通过无线传输到最近的其他卫星节点配置文件中完成卫星节点故障调度；
卫星与蜂窝切换程序为：卫星信号通过5G无线接入网，RAN同时使用NR和LTE(eNB)基站，从而完成与地面网络基站进行信号对接，地面网络辅助非地面网络；
星间切换程序为：通过切换程序预置的条件两颗卫星建立星间链路进行星间切换，其位置必须满足如下条件：
(Re+h)cos(alpha/2)＞＝Re+Hp
其中，h为卫星高度；Hp为余隙，即星间链路与地球表面的距离；Re为地球半径；alpha为星间地心角；
且最小余隙对应最大星间地心角alpha(max)，当alpha＜alpha(max)时，两卫星之间能够建立星间链路，反之则不能建立链路。
本发明具有以下有益效果：
本发明针对6G空口设计的两大原则：1、克服非地面通信带来的挑战；2、利用非地面节点特有的属性，设计基于6G空中基站信号增强及智能按需覆盖优化方法，突出了AI/ML在无线通讯领域中的地位，结合人工智能使得基于星座的网络更加智能化，并通过星内切换、星间切换、卫星和蜂窝切换等，使得卫星网络更具高效移动性，从而减少信令开销、缩短中断时间，降低功耗。
附图说明
图1为本发明方法流程原理图。
具体实施方式
以下结合附图对本发明的实施例作进一步详细描述。
参见图1，本发明一种基于6G空中基站信号增强及智能按需覆盖优化方法，包括：
步骤1、组建6G卫星基站，采用马尔可夫链算法构建传输效率预测模型，并通过分布式MIMO测试同一用户上行信号，进而增强非地面通讯；
即，多卫星同时接收当前用户上行信号，收集数据放入【传输效率预测模型】预测下时间段(毫秒、秒、分)各卫星节点接收上行信号最强的概率。从而增强非地面通讯。
1)、在6G空中场景中非地面通讯基础设施主要由UAV、HAPS、VLEO等常用设施组成。
非地面基础设施与地面用户终端之间通过无线信号进行连接，其无线通讯相关日志数据存储在空中基础设施上：
具体描述：
UAV：无人驾驶飞机
HAPS：高空平台(HAPS：High Altitude Platform Station)通信系统将无线基站安放在长时间停留在高空的飞行器上来提供电信业务，被认为是一种2010年以后有良好潜在应用价值的宽带无线接入手段。若其高度在20km，则可以实现地面覆盖半径约500km的通信区
VLEO：星座
分布式MIMO：多输入多输出(mulTIple input mulTIple output，MIMO)无线传输技术开启了移动通信系统空间资源开发利用的新纪元。
2)、传输效率预测模型
马尔可夫转移概率矩阵模型公式：X(k+1)＝X(k)×P
式中：
X(k)表示趋势分析与预测对象在t＝k时刻的状态向量，P表示一步转移概率矩阵，X(k+1)表示趋势分析与预测对象在t＝k+1时刻的状态向量。
通过访问存储在空中基础设施上的与地面通讯的历史日志数据生成矩形集合。包括：用户终端UE、卫星节点名称、信号增益数值(db，可通过该数值比较上一次增益程度本次增益db-上次增益db＝本次信号增益情况，结合传播时延间接得出本次信号强弱情况)、传播时延(ms)。
通过以下矩形数据分析计算得出：
上时段信号增益(db)概率【0.3、0.7】
当前时段信号变强增益转移(db)概率【0.6、0.4】
当前时段信号变弱增益转移(db)概率【0.3、0.7】
通过模型计算得出：X(k+1)＝X(k)×P
下时段信号变强增益转移概率：
0.3x0.6+0.3x0.7＝0.39
下时段信号变弱增益转移概率：
0.3x0.4+7x0.7＝0.61
最后，下时段信号增益转移概率【0.39 0.61】，通过【传输效率预测模型】预测运算结果结合当前增益(db)，依据行业通用的3dB法则：
每增加或降低3dB意味着增加一倍或降低一半的功率。
预测未来信号
1、-3dB＝1/2功率；
2、-6dB＝1/4功率；
3、+3dB＝2*功率；
4、+6dB＝4*功率。
步骤2、针对非GEO卫星移动所带来的频繁波束切换的问题，采用Transformer算法构建卫星调度模型，实现智能按需覆盖。并通过预置切换程序根据发生的故障类型进行星内切换、星间切换、卫星和蜂窝切换等故障优化调整。同时完成基于星座的网络智能化，高效移动性，来减少信令开销、缩短中断时间，降低功耗。
卫星星座是发射入轨能正常工作的卫星的集合，通常是由一些卫星环按一定的方式配置组成的一个卫星网。
具体描述：
步骤21、对存储在星座的各卫星节点上的日志历史数据进行插值分析，从而得到更加精确的某个卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的分析数据。
首先、为适应模型处理，对不同节点采样不均匀的数据做差值处理。
采用二次差值方法，以每3个相邻点做插值，得到二次插值。即，人工智能算法提优后的数据。
此方法优点：
1、间隔均匀，和transformer时序处理更加匹配。
2、较真实还原星座的各卫星节点(上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差)场景缺失数据。
公式如下：
Figure PCTCN2022114155-appb-000003
x：时间序列数值X轴(上行信号发生故障数据的数值)
y：插值业务数据Y轴(上行信号发生故障数据)
i：时间序列序号i(数据时间的序号，序号i到序号i+1间隔可能有几个数据)
步骤22、将插值分析数据输入卫星调度模型，预测得到星座中某个卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的发生概率。
模型公式：
针对时间维度，利用positional encoding进行时序编码，利用attention发掘时序维度的特征关联。
PositionEncoding＝cos2(pos/N)
参数说明：N为可调长度大小
Attention_output＝Attention(Q，K，V)
Attention计算公式如下：
Figure PCTCN2022114155-appb-000004
其中dk代表K的维度
参数说明：其中Q为查询特征映射，K为待匹配特征映射，V为监测数据映射。
V为输入数据：(上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差)都是输入数据。
Q为查询特征映射：没有具体业务属性，是网络里的参数，相当于学习出来的
K为待匹配特征映射：没有具体业务属性，是网络里的参数，相当于学习出来的
针对空间维度，利用multi head attention提取不同多空间维度特征，公式如下：
Headi＝Attention(Qi，Ki，Vi)
MultiHead(Q，K，V)＝Concat(head1，...，headh)*WO
其中，N为可调长度大小；Q为查询特征映射；K为待匹配特征映射；V为监测数据映射；
headi为时间注意力得到的结果，通过MultiHead融合多空间维度
Qi为第i组查询特征映射；
Ki为第i组待匹配特征映射；
Vi为第i组监测数据映射；
WO为特征融合矩阵；Attention为(见前述公式)；
Concat(特征级联融合)；pos为数据序列号；
PositionEncoding为位置序列编码；
Attention_output为(见前述公式)；
MultiHead为多头特征融合。
步骤23、如果预测的卫星节点三种类型故障发生概率大于50％，自动触发切换程序实现三种类型故障的处理及优化。
1、如果星座接收用户上行信号发生故障概率较大(大于50％)则，触发星内切换程序。
星内切换程序：立即通过程序控制将故障卫星节点上配置文件中存储的当前用户UE通过无线传输到最近的其他卫星节点配置文件中完成卫星节点故障调度。
2、如果星座接收用户上行信号发生达到荷载能力上限预测概率较大(大于50％)的情况。则，触发卫星与蜂窝切换程序。
卫星与蜂窝切换程序：即，引入【卫星调度模型】，预测星座接收用户UE荷载能力突破上限概率较大(大于50％)的情况。卫星信号发生信号给通过5G无线接入网(RAN)，RAN能同时使用NR(gNB)和LTE(eNB)基站。从而完成与地面网络基站进行信号对接，地面网络辅助非地面网络的流程。
3、引入【卫星调度模型】，预测卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的概率较大(大于50％)的情况。触发星间切换程序。
星间切换程序：即，通过切换程序预置的条件两颗卫星建立星间链路，其位置必须满足如下条件：
(Re+h)cos(alpha/2)＞＝Re+Hp(1)
其中h为卫星高度，Hp为余隙(星间链路与地球表面的距离)，Re为地球半径。最小余隙对应着最大星间地心角alpha(max)。当alpha＜alpha(max)时，两卫星之间能够建立星间链路，反之则不能建立链路。
以上仅是本发明的优选实施方式，本发明的保护范围并不仅局限于上述实施例，凡属于本发明思路下的技术方案均属于本发明的保护范围。应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理前提下的若干改进和润饰，应视为本发明的保护范围。

Claims (9)

  1. 一种基于6G空中基站信号增强及智能按需覆盖优化方法，其特征在于，包括：
    步骤1、组建6G卫星基站，采用马尔可夫链算法构建传输效率预测模型，并通过分布式MIMO测试同一用户上行信号，进而增强非地面通讯；
    步骤2、当非GEO卫星移动带来频繁波束切换时，采用Transformer算法构建卫星调度模型，实现智能按需覆盖，并通过预置切换程序根据发生的故障类型进行故障优化调整。
  2. 根据权利要求1所述的一种基于6G空中基站信号增强及智能按需覆盖优化方法，其特征在于，所述步骤1中，6G卫星基站中多卫星同时接收当前用户上行信号，将上行信号数据输入传输效率预测模型，预测出下时间段各卫星节点接收上行信号最强的概率，从而增强非地面通讯。
  3. 根据权利要求1所述的一种基于6G空中基站信号增强及智能按需覆盖优化方法，其特征在于，所述步骤1中，所述6G的空中场景中非地面通讯基础设施包括UAV、HAPS、VLEO；且非地面基础设施与地面用户终端之间通过无线信号进行连接，其无线通讯相关日志数据存储在空中基础设施上。
  4. 根据权利要求1所述的一种基于6G空中基站信号增强及智能按需覆盖优化方法，其特征在于，所述步骤2包括：
    步骤21、对存储在星座的各卫星节点上的日志历史数据进行插值分析，得到卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的分析数据；
    步骤22、将分析数据输入卫星调度模型，预测得到星座中卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的发生概率；
    步骤23、基于步骤22的预测概率，通过预置切换程序根据发生的故障类型进行故障优化调整。
  5. 根据权利要求4所述的一种基于6G空中基站信号增强及智能按需覆盖优化方法，其特征在于，步骤21所述插值分析公式如下：
    Figure PCTCN2022114155-appb-100001
    其中，x为时间序列数值，y为插值业务数据，i为时间序列序号。
  6. 根据权利要求4所述的一种基于6G空中基站信号增强及智能按需覆盖优化方法，其 特征在于，步骤23所述卫星调度模型的模型公式为：
    针对时间维度，利用positional encoding进行时序编码，利用attention发掘时序维度的特征关联；
    positionl encoding＝cos2(pos/N)
    N为可调长度大小；
    attention计算公式如下：
    Figure PCTCN2022114155-appb-100002
    其中，dk代表K的维度；V为输入数据；Q为查询特征映射；K为待匹配特征映射；
    针对空间维度，利用multi head attention提取不同多空间维度特征，公式如下：
    MultiHead(Q，K，V)＝Concat(head1，...，headh)*WO
    headi＝Attention(Qi，Ki，Vi)
    其中，WO为特征融合矩阵；Concat为特征级联融合；MultiHead为多头特征融合；
    headi为时间注意力，即attention计算得到的结果，其在空间维度通过MultiHead融合；
    Qi为第i组查询特征映射；
    Ki为第i组待匹配特征映射；
    Vi为第i组监测数据映射，即第i组输入数据。
  7. 根据权利要求4所述的一种基于6G空中基站信号增强及智能按需覆盖优化方法，其特征在于，所述步骤23中，如果预测的卫星节点星座中卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的发生概率大于50％，则自动触发切换程序实现星座中卫星节点接收用户上行信号发生故障、卫星节点达到荷载能力上限、卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差三种类型故障的处理及优化。
  8. 根据权利要求7所述的一种基于6G空中基站信号增强及智能按需覆盖优化方法，其特征在于，所述步骤23具体包括：
    1)如果卫星节点接收用户上行信号发生故障的概率大于50％，则触发星内切换程序；
    2)如果卫星节点达到荷载能力上限的概率大于50％，则触发卫星与蜂窝切换程序；
    3)如果卫星移动导致用户相对位置移动造成到达星座的边缘覆盖信号差的概率大于50％，则触发星间切换程序。
  9. 根据权利要求8所述的一种基于6G空中基站信号增强及智能按需覆盖优化方法，其特征在于，所述星内切换程序为：立即通过程序控制将故障卫星节点上配置文件中存储的当前用户UE通过无线传输到最近的其他卫星节点配置文件中完成卫星节点故障调度；
    卫星与蜂窝切换程序为：卫星信号通过5G无线接入网，RAN同时使用NR和LTE(eNB)基站，从而完成与地面网络基站进行信号对接，地面网络辅助非地面网络；
    星间切换程序为：通过切换程序预置的条件两颗卫星建立星间链路进行星间切换，其位置必须满足如下条件：
    (Re+h)cos(alpha/2)＞＝Re+Hp
    其中，h为卫星高度；Hp为余隙，即星间链路与地球表面的距离；Re为地球半径；alpha为星间地心角；
    且最小余隙对应最大星间地心角alpha(max)，当alpha＜alpha(max)时，两卫星之间能够建立星间链路，反之则不能建立链路。
PCT/CN2022/114155 2022-05-31 2022-08-23 一种基于6g空中基站信号增强及智能按需覆盖优化方法 WO2023231193A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210604405.0A CN115002790B (zh) 2022-05-31 2022-05-31 一种基于6g空中基站信号增强及智能按需覆盖优化方法
CN202210604405.0 2022-05-31

Publications (1)

Publication Number Publication Date
WO2023231193A1 true WO2023231193A1 (zh) 2023-12-07

Family

ID=83030497

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/114155 WO2023231193A1 (zh) 2022-05-31 2022-08-23 一种基于6g空中基站信号增强及智能按需覆盖优化方法

Country Status (2)

Country Link
CN (1) CN115002790B (zh)
WO (1) WO2023231193A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115963520B (zh) * 2022-09-06 2024-04-16 中电信数智科技有限公司 一种基于6g空中基站结合北斗卫星定位的优化方法
CN115460633B (zh) * 2022-09-29 2023-10-27 中电信数智科技有限公司 6g网络ai信号优化的方法、系统、设备和存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106470901A (zh) * 2014-02-26 2017-03-01 克拉克·艾默生·科恩 改进性能和成本的全球导航卫星系统架构
CN110518961A (zh) * 2019-08-29 2019-11-29 东南大学 大规模mimo卫星移动通信方法及系统
US20220052756A1 (en) * 2018-09-10 2022-02-17 Telesat Technology Corporation Resource deployment optimizer for non-geostationary and/or geostationary communications satellites

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101299713A (zh) * 2008-03-21 2008-11-05 哈尔滨工业大学深圳研究生院 一种多层卫星网络系统路由设定方法
CN104125594B (zh) * 2014-07-31 2017-12-01 广州杰赛科技股份有限公司 基于用户感知的无线网络优化方法及系统
US9775191B2 (en) * 2015-09-18 2017-09-26 Global Eagle Entertainment Inc. Physical layer hand-off and diversity combining in non-geostationary satellite constellation
CN110059385B (zh) * 2019-04-09 2022-10-18 集美大学 一种耦合异速生长的网格动力学情景模拟方法及终端设备
CN110809292B (zh) * 2019-11-12 2021-03-09 北京理工大学 一种低轨卫星通信中基于负载均衡的联合切换方法
CN112911664B (zh) * 2021-02-03 2023-09-19 凯睿星通信息科技(南京)股份有限公司 一种基于概率排序的低轨卫星切换方法
CN113189623B (zh) * 2021-04-21 2022-08-12 中国电子科技集团公司第五十四研究所 一种卫星导航系统信号质量等级评估方法
CN113487061A (zh) * 2021-05-28 2021-10-08 山西云时代智慧城市技术发展有限公司 一种基于图卷积-Informer模型的长时序交通流量预测方法
CN113472421B (zh) * 2021-06-29 2022-06-14 中国人民解放军军事科学院国防科技创新研究院 基于拉格朗日插值的低轨网联卫星星间波束指向方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106470901A (zh) * 2014-02-26 2017-03-01 克拉克·艾默生·科恩 改进性能和成本的全球导航卫星系统架构
US20220052756A1 (en) * 2018-09-10 2022-02-17 Telesat Technology Corporation Resource deployment optimizer for non-geostationary and/or geostationary communications satellites
CN110518961A (zh) * 2019-08-29 2019-11-29 东南大学 大规模mimo卫星移动通信方法及系统

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
"3rd Generation Partnership Project; Technical Specification Group Radio Access Network; Solutions for NR to support non-terrestrial networks (NTN) (Release 16)", 3GPP TR 38.821, no. V16.1.0, 30 June 2021 (2021-06-30), pages 1 - 140, XP052029957 *
BAI WEIGANG; SHENG MIN; DU PANPAN: "Mobility Management of the 6G Satellite IoT: Challenges and Key Techniques", CHINESE JOURNAL ON INTERNET OF THINGS, vol. 4, no. 1, 23 March 2020 (2020-03-23), pages 104 - 110, XP009551104, ISSN: 2096-3750 *
CHEN SHANZHI; LIANG YING-CHANG; SUN SHAOHUI; KANG SHAOLI; CHENG WENCHI; PENG MUGEN: "Vision, Requirements, and Technology Trend of 6G: How to Tackle the Challenges of System Coverage, Capacity, User Data-Rate and Movement Speed", IEEE WIRELESS COMMUNICATIONS, COORDINATED SCIENCE LABORATORY; DEPT. ELECTRICAL AND COMPUTER ENGINEERING; UNIVERSITY OF ILLINOIS AT URBANA-CHAMPAIGN, US, vol. 27, no. 2, 1 April 2020 (2020-04-01), US , pages 218 - 228, XP011786139, ISSN: 1536-1284, DOI: 10.1109/MWC.001.1900333 *
XU HUI; MIAO DESHAN; KANG SHAOLI; SUN SHAOHUI: "Network Architecture and Key Technologies for the Integrated Satellite and Terrestrial Mobile Communication System", SPACE-INTEGRATED-GROUND INFORMATION NETWORKS, vol. 1, no. 2, 20 December 2020 (2020-12-20), pages 2 - 10, XP009551550, ISSN: 2096-8930, DOI: 10.11959/j.issn.2096-8930.20200201 *

Also Published As

Publication number Publication date
CN115002790A (zh) 2022-09-02
CN115002790B (zh) 2023-11-17

Similar Documents

Publication Publication Date Title
WO2023231193A1 (zh) 一种基于6g空中基站信号增强及智能按需覆盖优化方法
Shayea et al. Key challenges, drivers and solutions for mobility management in 5G networks: A survey
Pan et al. User-centric C-RAN architecture for ultra-dense 5G networks: Challenges and methodologies
Casoni et al. Integration of satellite and LTE for disaster recovery
CN111262616B (zh) 一种低轨卫星信关站的用户数据切换装置及切换方法
Wang et al. Hybrid satellite-aerial-terrestrial networks in emergency scenarios: A survey
CN104735738B (zh) 一种gmr‑1卫星移动通信系统中的切换方法
Yang et al. 5G mobile communication convergence protocol architecture and key technologies in satellite internet of things system
CN103313259B (zh) 低空气球荷载的中继应急无线数据通信架构
EP4123921A1 (en) Satellite communication method and apparatus
CN112702772B (zh) 一种面向星地融合网络的终端切换方法
Ji et al. Flexible and distributed mobility management for integrated terrestrial-satellite networks: Challenges, architectures, and approaches
CN112383927B (zh) 无线网络的交互方法、装置、设备及存储介质
Niu et al. 3D location and resource allocation optimization for UAV-enabled emergency networks under statistical QoS constraint
Wang et al. Exploiting dual connectivity for handover management in heterogeneous aeronautical network
Ganjalizadeh et al. Impact of correlated failures in 5G dual connectivity architectures for URLLC applications
Wu et al. Modeling control delays for edge-enabled UAVs in cellular networks
Liu et al. Operation and Key Technologies in Space-Air-Ground Integrated Network
WO2023071716A1 (zh) 卫星通信方法和卫星通信装置
Qi et al. A multi-layer architecture for space-air-ground network and IoT services
Zhang et al. Architecture design of electric power emergency communication based on 4G LTE network
EP4178265A1 (en) Terminal device access control method and apparatus
Zhang et al. Autonomous navigation and configuration of integrated access backhauling for UAV base station using reinforcement learning
WO2021058393A1 (en) Computing device comprising a pool of terminal devices and a controller
Zhu et al. Research on hybrid network communication scheme of high and low orbit satellites for power application

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22944504

Country of ref document: EP

Kind code of ref document: A1