Enabling Low-latency-capable Satellite-Ground Topology for Emerging LEO Satellite Networks

Abstract

The network topology design is critical for achieving low latency and high capacity in future integrated satellite and terrestrial networks (ISTN). However, existing studies mainly focus on the design of inter-satellite topology of ISTN, and very little is known about the design of satellite-ground topology, as well as its impact on the attainable network performance.

In this paper, we conduct a quantitative study on the impact of various satellite-ground designs on the network performance of ISTN. We identify that the high-density and high-dynamicity characteristics of emerging mega-constellations have jointly imposed big challenges, such as significant routing instability, low network reachability, high latency and jitter on the ISTN paths. To alleviate the above challenges, we formulate the Low-latency Satellite-Ground Interconnecting (LSGI) problem, targeting at the integration of space and ground segment in the ISTN, while minimizing the maximum transmission latency and keeping routing stable. We further design algorithms to solve the LSGI problem through wisely coordinating the establishment of ground-to-satellite links among distributed ground stations. Comprehensive experiment results demonstrate that our solution can outperform existing related schemes by about 19% reduction of the latency and 70% reduction of the jitter on average, while sustaining the highest network reachability.

网络拓扑设计对于在未来的天地一体化网络（ISTN）中实现低时延和高容量至关重要。然而，现有研究主要集中在天地一体化网络的星间拓扑设计上，而对于星地拓扑的设计及其对可达网络性能的影响则知之甚少。

本文中，我们对各种星地设计对天地一体化网络性能的影响进行了定量研究。我们发现，新兴巨型星座的高密度和高动态特性共同给天地一体化网络带来了巨大挑战，例如显著的路由不稳定性、低网络可达性、高时延和高抖动。为了缓解上述挑战，我们构建了低时延星地互连（LSGI）问题，旨在整合天地一体化网络中的空间段和地面段，同时最小化最大传输时延并保持路由稳定。我们进一步设计了算法，通过巧妙地协调分布式地面站之间地对星链路的建立来解决LSGI问题。全面的实验结果表明，与现有的相关方案相比，我们的解决方案能够将时延平均降低约19%，将抖动平均降低约70%，同时保持最高的网络可达性。

Introduction

The idea of using mega-constellations with thousands of Low Earth Orbit (LEO) satellites to provide global Internet services has attracted much attention in recent years. Commercial enterprises, such as SpaceX, Amazon, Oneweb, etc., have joined this fierce “NewSpace” race. Through integration with existing terrestrial networks (TNs), such LEO satellite networks (SNs) have great potential to provide low-latency, high-bandwidth Internet coverage for global users [28].

近年来，利用包含数千颗低地球轨道（LEO）卫星的巨型星座来提供全球互联网服务的构想备受关注。诸如SpaceX、亚马逊、Oneweb等商业公司已纷纷加入这场激烈的“新太空”（NewSpace）竞赛。通过与现有地面网络（TNs）相融合，此类低轨卫星网络（SNs）在为全球用户提供低时延、高带宽的互联网覆盖方面展现出巨大潜力[28]。

Figure 1 plots quintessential scenarios and use cases of future Integrated Satellite and Terrestrial Networks (ISTN). First, it can offload global traffic for TNs. Traffic from data centers or users on the ground can be directed to the ground station (GS), then to satellite through ground-satellite links (GSLs) and inter-satellite links (ISLs), and finally to TNs or users [24], [50]. For example, Kuiper’s GS sites will be selected to support Amazon network infrastructure [1]. Second, a large amount of data is generated from space every day [35], e.g., earth imagery, weather observations, etc. For example, a Sentinel1A earth observation satellite delivers high-resolution global data every 12 days at a rate of 2.5TB per day [43], which needs to be transmitted to TNs through GSes.

图1描绘了未来天地一体化网络（ISTN）的典型场景与用例。首先，它能为地面网络分流全球业务。来自数据中心或地面用户的流量可被导向地面站（GS），然后通过地星链路（GSLs）和星间链路（ISLs）传输至卫星，最终抵达地面网络或用户[24], [50]。例如，Kuiper的地面站选址就将支持亚马逊的网络基础设施[1]。其次，太空每天都会产生海量数据[35]，如地球影像、气象观测数据等。例如，一颗Sentinel-1A地球观测卫星每12天便能提供一次全球高分辨率数据，速率高达每天2.5TB [43]，这些数据需要通过地面站传输至地面网络。

These quintessential use cases all require stable and performant data transmission over LEO SNs, where the network topology plays a vital role. Existing works mainly focus on the design of the inter-satellite topology of ISTN [13], and very little is known about the design of the satellite-ground topology. This is because the small scale of LEO SNs in the early stage makes the solution intuitive and straightforward. However, the constellation density has significantly scaled up in recent years. Through quantitative experiments, we find that for the emerging LEO mega-constellations (e.g., Starlink [2], Kuiper [1]), existing satellite-ground interconnection schemes can involve significant challenges, such as high satelliteground fluctuation, low network reachability, high end-to-end latency and jitter on the ISTN paths. For instance, the one-way latency between two GSes may change from less than 40 milliseconds to more than 100 milliseconds (250% increase), which is common when using existing schemes.

这些典型用例均要求数据在低轨卫星网络上进行稳定且高性能的传输，其中网络拓扑扮演着至关重要的角色。现有工作主要聚焦于天地一体化网络的星间拓扑设计[13]，而关于星地拓扑的设计则鲜有研究。这是因为早期低轨卫星网络规模较小，使得解决方案显得直观且直接。然而，近年来星座密度已显著提升。通过定量实验我们发现，对于新兴的低轨巨型星座（如Starlink [2], Kuiper [1]），现有的星地互联方案会引发严峻挑战，例如剧烈的星地波动、低网络可达性、以及天地一体化网络路径上的高点到点时延与抖动。举例而言，在使用现有方案时，两个地面站间的单向时延从低于40毫秒变为超过100毫秒（增长250%）的情况十分普遍。

To address the above challenges, first we formulate the Lowlatency Satellite-Ground Interconnecting (LSGI) problem, targeting at the integration of space and ground segment in the ISTN, while minimizing the maximum transmission latency on the basis of stable routing and high network reachability. Second, to solve the problem, we decompose it into topology design at a single time point and topology transition on time set. We then propose the Coordinated Satellite-Ground Interconnecting (CSGI) algorithm in distributed ground stations. Different from existing works [14], [32], [40], [41], [49], CSGI wisely coordinates the establishment of GSLs among GSes and utilizes the similar characteristics of visible satellites distribution over different GSes, so that lower latency and jitter transmission is achieved while keeping stable routing and high network reachability.

为应对上述挑战，我们首先构建了低时延星地互连（LSGI）问题，旨在整合天地一体化网络中的空间段与地面段，并在保障路由稳定与高网络可达性的基础上， 最小化最大传输时延 。其次，为求解该问题，我们将其分解为单一时间点的拓扑设计和时间集上的拓扑演进两个子问题。接着，我们提出了一种 在分布式地面站中运行的协同式星地互连（CSGI）算法 。与现有工作[14], [32], [40], [41], [49]不同，CSGI巧妙地协调了各分地面站间地星链路的建立，并利用了不同地面站上空可见卫星分布的相似性特征，从而在保持路由稳定和高网络可达性的同时，实现了更低的时延与抖动传输。

We conduct evaluations under two real GS datasets in various constellations to verify the effectiveness of CSGI. Comprehensive experiments demonstrate that CSGI can significantly improve the overall network performance, compared with the related algorithms. CSGI reduces topology change times and maintains the highest packet delivery ratio, and also outperforms other algorithms with about 35% reduction of the average maximum hops, 19% reduction of the average end-toend latency and 70% reduction of the average jitter.

我们在两种真实地面站数据集和多种星座下进行了评估，以验证CSGI的有效性。全面的实验证明，与相关算法相比，CSGI能显著提升整体网络性能。CSGI减少了拓扑变更次数，维持了最高的分组投递率，并且在其他指标上也表现更优，平均最大跳数减少约35%，平均端到端时延降低约19%，平均抖动减小约70%。

In conclusion, the contributions of this paper can be summarized as follows.

• We conduct a quantitative study on the impact of various satellite-ground designs on the network performance of ISTN, revealing that the existing designs have inherent shortcomings in realizing stable routing, high network reachability and low-latency communication.

• We formulate the Low-latency Satellite-Ground Interconnecting (LSGI) problem for minimizing the maximum endto-end transmission latency while keeping stable routing and high network reachability.

• We propose a Coordinated Satellite-Ground Interconnecting algorithm in distributed ground stations, called CSGI, to approximately solve the LSGI problem.

• To evaluate the algorithm, we conduct experiments under two real GS datasets in different constellations. Comprehensive experiment results demonstrate that our CSGI can outperform existing related schemes in terms of network performance and stability.

综上所述，本文的贡献可总结如下：

• 我们对各种星地设计对天地一体化网络性能的影响进行了定量研究，揭示了现有设计在实现路由稳定、高网络可达性和低时延通信方面存在固有缺陷。

• 我们构建了低时延星地互连（LSGI）问题，旨在最小化最大端到端传输时延，同时保持路由稳定和高网络可达性。

• 我们提出了一种在分布式地面站中运行的协同式星地互连算法（CSGI），以近似求解LSGI问题。

• 为评估该算法，我们在两种真实的地面站数据集和不同星座下进行了实验。全面的实验结果表明，我们的CSGI在网络性能和稳定性方面均能超越现有的相关方案。