SpaceX has US Federal Communications
Committee (FCC) approval to build a constellation of 4,425 low Earth orbit communication satellites. It will use phased array antennas for up and downlinks and laser communication between
satellites to provide global low-latency high bandwidth coverage.
Mark Handley, University College London built a simulator based on public details from the FCC
filings to understand the latency properties of the network.
They evaluate how to use the laser links to provide a network and look at the problem of routing on this network. They conclude the SpaceX Starlink network can provide lower latency communications than any possible terrestrial optical fiber network for communications over distances greater than about 3000 kilometers.
As network bandwidths have increased, latency has emerged as being the limiting factor for many networked systems, ranging from the extremes of high-frequency trading, to the more mundane effects of latency on VoIP, online gaming, and web performance. Fundamentally, once traffic engineering has mitigated congestion and buffer bloat has been addressed, for wide-area traffic the remaining problem is that the speed of light in glass simply isn’t fast enough.
In Starlink’s initial phase, 1,600 satellites in 1,150 km altitude orbits will provide connectivity to all except far north and south regions of the world. A second phase adds another 2,825 satellites in orbits ranging from 1,100 km altitude to 1325 km, increasing density of coverage at lower latitudes and providing coverage at least as far as 70 degrees North. Finally, in an additional FCC filing SpaceX proposes launching an additional 7,518 satellites in approximately 340 km VLEO orbits. Mark only examined the LEO constellation.
The inverse square law suggests that received power on Starlink could be as much as 2000 times greater than on the EDRS (European Data Relay System). In 2014, the European Data Relay System (EDRS) achieved 1.8 Gb/s from LEO to geostationary earth orbit (GEO), across a distance of 45,000 km. Most Starlink distances will be 1000 km or less.
It seems probable that free-space laser link speeds of 100 Gb/s or higher will be possible.
— Andrew Moore (@awm22) September 25, 2018
A dense LEO constellation like Starlink has two main advantages over terrestrial networks. First, it can connect almost anywhere, however remote. Second, the speed of light in a vacuum os 47% higher than in optical fiber. The ability to connect anywhere is important, but we speculate that providing low-latency wide area communication will be where the money to maintain and operate such a network is made, connecting cities that are already well connected using optical fiber, but with lower latency as a premium service.
Already there are new private microwave relay links between New York and Chicago, London and Frankfurt, and London and Paris. These links have relatively low capacity compared to fiber, but are of high enough value to the finance industry to be worth building new low latency links.
Simulations show dense LEO constellations have very many paths available, and many of them are of similar latency. This allows groundstations to be much more conservative about when they move traffic back to the lowest delay path, using timescales much longer than the latency of the broadcast load reports, so avoiding instability. This is an interesting direction for future routing work on dense LEO constellations.