Abstract: After many years of anticipation, low-earth orbit (LEO) satellite Internet for consumers has finally arrived. For some, anyway. This tutorial talk explains where the challenges lie: How constellation design influences who gets service and who does not, why gateway strategy is important, how we might end up using distributed routing schemes and IPv6 to send packets through multiple satellites in mega-constellations, why the exact design of inter-satellite laser links matters, why the direct-to-site delivery model chosen by current LEO providers makes viral cat videos bad news for users, and what Montana can teach us about Ukraine.

Abstract: We are witnessing the birth of a new kind of high-bandwidth, low-latency connectivity, provided by so-called "mega constellations" of thousands of satellites. SpaceX’s Starlink, Amazon’s Kuiper, OneWeb, and many others are sending thousands of satellites to the Low Earth Orbit (LEO), cutting down latency to tens of milliseconds whilst supporting over 100Mbps bandwidths. However, we believe fundamental changes are needed from a computer networking perspective to make this vision work at scale.
In this talk, we will present a realistic emulation platform that is designed to emulate LEO mega-constellations represented using both virtualised and physical nodes (i.e., compute and radios) offering high degree of realism and wide range of scalable and real-time experimentations. This enables the research community to better understand the complexity of such network, as well as, rethink, design and test new protocols/algorithms across all the protocol stack layers.
We will conclude by discussing the recent measurement study we conducted on Starlink LEO network to study the spatial and temporal characteristics as well as geographic variability of Starlink. We will go through the tools and tests we conducted for the purpose of that study.

Abstract: Upstart space companies are building massive constellations of low-flying satellites to provide Internet service. These developments comprise “one giant leap” in Internet infrastructure, promising global coverage and lower latency. However, fully exploiting the potential of such satellite constellations requires tackling their inherent challenges: thousands of low-Earth orbit (LEO) satellites travel at high velocities relative to each other, and to terrestrial ground stations. The resulting highly dynamic connectivity is at odds with the Internet’s design, which assumes a largely static core infrastructure. Virtually every aspect of Internet design — physical interconnection, routing, congestion control, and application behavior — will need substantial rethinking to integrate this new building block.
In this talk, I will present Hypatia, a framework for simulating and visualizing LEO networks that we built to enable broader research in this area. Using publicly available design details for the upcoming networks to drive our framework, we characterize the expected behavior of these networks, including latency and link utilization fluctuations over time, and the implications of these variations for congestion control and routing.
I will conclude by discussing the benefits of building a globally spanning measurement infrastructure for LEO broadband networks, much like PlanetLab and MeasurementLab for the Internet today. The envisioned testbed will empower the research community to study the various temporal and spatial aspects of these highly dynamic “new space” networks.

Abstract: Satellite network is the first step towards interstellar voyages. It can provide global Internet connectivity everywhere on the earth, where most areas cannot access the Internet by the terrestrial infrastructure due to the geographic accessibility and high deployment cost. The space industry experiences a rise in large low-earth-orbit satellite constellations to achieve universal connectivity. The research community is also urgent to do some leading research to bridge the connectivity divide. Researchers now conduct their work by simulation, which is far from enough. However, experiments on real satellites are hindered by the exceptionally high bar of space technology, such as deployment cost and unknown risks. To solve the above challenges, we are eager to contribute to the universal connectivity and build an open research platform, Tiansuan constellation(www.tiansuan.org.cn), to support experiments on real six satellites. We first introduce the platform architecture, and then discuss the potential research topics that would benefit from the platform. Moreover, we talk about how to use it for research. Finally, we show four case studies (i.e., satellite-borne 5G core network system, native-cloud satellite platform, satellite-ground AI reasoning, DOIP satellite node) that have already been deployed in three satellites.

Abstract: More than 80% of the world’s surface does not have Internet connectivity. While multiple companies are commercially bringing broadband connectivity to “people” in remote locations, these solutions are very expensive for Internet of Things (IoT) devices. Over 75B IoT devices are expected by 2025, and lack of IoT connectivity in 80% of the Earth’s surface is preventing several industries that operate in remote sites, such as Agriculture, Renewables, Fisheries, Supply Chain, etc., from realizing the true potential of data and AI. As a result, a revolution of IoT industry in space has the utmost importance. Several business ventures have already started rolling the wheel. Hundreds of satellites have been launched till date. Although launching satellite has become nondescript now-a-days, “IoT in space” brings about unique needs, opportunities, and challenges. In this talk, we will walk you through how today’s “IoT in space” industry looks like and how we can actively shape up the future.

Abstract: New Earth-observation capabilities enabled by large constellations - e.g., daily global coverage - are limited by continued adherence to bent-pipe satellite operations. Additionally, new challenges - e.g., effectively managing a large constellation by remote control - arise in a more crowded low-Earth orbit (LEO). For example, a proliferated LEO exacerbates the downlink bottleneck: Earth-observation satellites and constellations observe much more data than can be downlinked per orbit revolution.
These challenges are addressed by orbital edge computing (OEC): colocating computing resources with sensors on orbit to process data before transmission. Because evaluating all proposed OEC schemes in orbit is not practical, we have developed the "cote" software library and simulation environment to assess these proposals in simulation. This software tool models satellite orbital mechanics, rotation of the Earth, relative ground station locations, and satellite subsystem characteristics, such as harvested and stored energy, data collection, computation, and communication, and radio bitrates. The open source "cote" software simulation environment supports rapid exploration and evaluation in low-Earth orbit computational space systems.

Abstract:Researchers have proposed to embed compute resources within low-Earth orbit satellite constellations to provide computing services on the LEO Edge. The high cost of such infrastructure, harsh environment of space, rapid mobility of LEO satellites, and the size of the satellite constellations that are currently being proposed and built will all pose significant research challenges to running services on the LEO Edge. On virtual cloud testbeds built using Celestial, researchers can quickly iterate on platforms and software systems for the LEO Edge to test and evaluate their ideas using real code and tooling, even without access to physical satellite infrastructure.
In this tutorial, we will first introduce the opportunities and current research challenges of the LEO Edge and discuss how we have built Celestial to help researchers evaluate LEO Edge software systems in the cloud. In a hands-on live demonstration, we then build and run an example application using a Celestial virtual LEO satellite testbed.