The laser communication system is about *40% faster* than fiber due to the
speed of light in vacuum
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
The number of laser transponders in a second-generation Starlink satellite
is not mentioned in the information I found. However, it is worth noting
that the second-generation Starlink satellites are expected to be
significantly more capable than their predecessors
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
They will be larger and much faster, with a capacity of up to *80 Gbps per
satellite*, compared to *18 Gbps* in the current version
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
The proposed Starlink Gen2 constellation, consisting of approximately
30,000 satellites, would have a total instantaneous bandwidth of at least
*500 terabits per second (Tbps) over land*, which is around 1800 Tbps
including ocean coverage
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
Please note that the information I provided is based on available sources
and may not cover all the details about the second-generation Starlink
satellites. For more specific information, it is recommended to refer to
official sources or SpaceX’s announcements.
Is there anything else I can help you with? 😊
Learn more:
1. nextbigfuture.com
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
2. arstechnica.com
<https://arstechnica.com/information-technology/2021/01/spacex-adds-laser-links-to-starlink-satellites-to-serve-earths-polar-areas/>
3. spaceflightnow.com
<https://spaceflightnow.com/2021/09/14/spacex-launches-first-full-batch-of-laser-equipped-starlink-satellites/>— see
less
" *(End of BING Response)*
Hesham
On Sat, Sep 23, 2023, 2:55 PM Larry Press via Starlink
<[email protected]> wrote:
In his first Starlink simulation, Mark Hadley assumed five
transponders per satellite -- Two in-plane, two adjacent, and one
crossing:
https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3
<https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3>
In his next Starlink simulation, Mark Hadley assumed four:
https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2
<https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2>
I guess he assumed the relative velocities were too high for the
crossing connection.
I asked Bard "How many laser transponders are in a
second-generation Starlink satellite?" and it said "four."
I asked ChatGPT "How many laser transponders are in a
second-generation Starlink satellite?" and it said it did not know.
I asked Bard again and the second time it said it did not know.
When I pointed out that it had told me "four" the first time I
asked, Bard apologized for its previous answer.
I remain an "AI" skeptic:
https://circleid.com/posts/20230721-google-bard-fails-to-answer-satellite-internet-questions
*From:* Starlink <[email protected]> on
behalf of David Lang via Starlink <[email protected]>
*Sent:* Friday, September 22, 2023 1:41 AM
*To:* Alexandre Petrescu <[email protected]>
*Cc:* [email protected] <[email protected]>
*Subject:* Re: [Starlink] APNIC56 last week
I believe that I read that STarlink has 5 lasers per sat. but
whatever the
number, it's a tiny number compared to the number of satellites
that they have
up there.
As you are looking at 'trains', check their altitude. They aren't
going to
shuffle sats around much, it's expensive in terms of fuel and they
are only
allowed to provide service when they are in their proper orbits.
We know the lasers are in operation as they are providing service
to places more
than one sat hop away from ground stations. We also know they have
a lot of
ground stations around to share the load.
We have almost no details on the specific modules they are using,
and none on
what routing they are using.
David Lang
On Fri, 22 Sep 2023,
Alexandre Petrescu via Starlink wrote:
> Date: Fri, 22 Sep 2023 10:26:26 +0200
> From: Alexandre Petrescu via Starlink
<[email protected]>
> Reply-To: Alexandre Petrescu <[email protected]>
> To: [email protected]
> Subject: Re: [Starlink] APNIC56 last week
>
>
> Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
>> Not going to go into details but lasers have been identified in
photos
>> of the sats and one of the component suppliers is known. (The
scale is
>> novel, not the tech, demisabiliy is new though)
>
> 4 or 2 lasers on each sat (N-S, E-W) is potentially a very
different
> matter from an IP routing standpoint. It still is a reduced set of
> variables, for a routing protocol (it is not like there being an
> arbitrary number of IP interfaces, it's just 2 or 4).
>
> For component manufacturers: yes, I heard about a few
manufacturers of
> such equipment for laser comms for LEO sats, experimented.
There is
> public information about a few of them. I dont know which is
considered
> by starlink, but there is not my worry. There is also a difference
> between laser links between sats on different orbit altitudes (e.g.
> laser for ISL for GEO to MEO) and lasers between sats on a same
orbit
> altitude, or on a same orbit. It's three different things, with
> different sets of requirements: focusing, power levels, distance
ranges.
>
> At the lowest limit (cheapest, less powerful, less range
distance), I
> suppose it is possible to use simply LiFi optical links (a sort
of WiFi
> but with light). If so, then it is very easy to have IP on it.
>
> There is also an 'optical' spec that was circulated here on this
list
>
(https://urldefense.com/v3/__https://www.sda.mil/wp-content/uploads/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$
),
> although it seemed to me to figure on kepler's website, not on
> starlink's. In that spec, it is said Ethernet, among other
things. On
> Ethernet, IP can run easily.
>
>>
>> Starlink can't deliver to Antarctica or Northern parts of Alaska,
>> Ascension Island, Diego Garcia, Easter Island, Vanuatu, Iran
without
>> ISL's etc
>
> I'll have to look where these places are.
>
> When looking at starlink satellites I often see trains forming and
> lasting for a while. Someone said these sats are like that
(trains)
> prior to be put on a more evenly distanced, in-orbit; but some time
> passed, and they continue this kind of behaviour: form denser
trains,
> then distance more evenly, and back again. So I am not sure these
> 'trains' are ephemeral. They seem to be in such 'train'
structure while
> above some particular continents or areas, but not sure. It
takes a lot
> of time to make a meaning of it.
>
> Also, now here are at least two kinds of starlink subscription
plans:
> 40EUR/month and 287EUR/month, for fixed vs mobile.
>
>>
>> North South links seem to work but not East West (if they exist)
>
> Yes, good question. It makes a lot of difference whether there
are 2 or
> 4 laser links on each sat. It also makes a lot of difference if
trying
> to make IP routing work there (assuming there could be 2 or 4 IP
> interfaces for lasers).
>
> This (number of ISL links on a starlink sat) can have an impact
on how
> people show LEO satellite topologies in Internet Drafts at IETF.
>
> Alex
>
>>
>> On Thu, Sep 21, 2023, 2:20 PM Alexandre Petrescu via Starlink
>> <[email protected]> wrote:
>>
>>
>> Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
>> > FWIW, I gave a talk about Starlink - insights from a year
in -
>> at last
>> > week's APNIC56 conference in Kyoto:
>> >
>> >
https://urldefense.com/v3/__https://conference.apnic.net/56/program/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$
>>
>>
>> Thanks for the presentation.
>>
>> I would like to ask what do you mean by "Method #2: "space
>> lasers""and
>> "Not all Starlink satellites have
>> lasers" on slide 5?
>>
>> It seems to be saying there is inter-satellite
communications. The
>> need
>> of that seems to stem from the lack of ground 'teleport'
that is
>> necessary for DISHY-SAT-Internet communications, so a
SAT-to-SAT
>> communication is apparently used with lasers. I can agree with
>> the need.
>>
>> What standard is used for these lasers?
>>
>> Is this ISL communicaiton within the starlink constellation a
>> supposition or a sure thing?
>>
>> Other presentations of starlink mentioned on this list dont
talk
>> about
>> this lasers between sats (dont show lasers on the sats),
but kepler
>> talks about optical links, and also there is talk about
ISOC LEO
>> Internet about such 'lasers from space'.
>>
>> (I must say that I thought previously that there were only
2 or 3
>> ground
>> teleports overall in EU and USA, but I see now there is a
teleport
>> in NZ
>> too).
>>
>> (for price comparison: it is said 100USD monthly, but in
France right
>> now the monthly subscription is at around 40 Euros; this
competes
>> very
>> advantageously to other satcoms ISPs for rural areas
non-covered
>> by 5G;
>> the cellular monthly subscriptions are still much more
advantageous,
>> where there is 5G, of course).
>>
>> Alex
>>
>> >
>> > Also well worth looking at is Geoff Huston's excellent
piece on the
>> > foreseeable demise of TCP in favour of QUIC in the same
session.
>> One
>> > of Geoff's main arguments is that the Internet is
becoming local,
>> > i.e., most traffic goes between a CDN server and you, and
most
>> data is
>> > becoming proprietary to the application owner, meaning it
suits the
>> > Googles and Facebooks of this world very well not to be using
>> TCP for
>> > its transport, but rather pull the transport specifics
into the
>> > application layer where the have full control.
>> >
>> > Food for thought, especially since LEO networks are a
>> particularly bad
>> > place to put local content caches, since the concept of
what's
>> "local"
>> > in a LEO network changes constantly, at around 20,000
miles an
>> hour or
>> > so. Spoke to a Rwandan colleague who installs Starlink
there and
>> sees
>> > all traffic to anywhere go via the US with RTTs of nearly 2
>> seconds,
>> > even if the Rwandan user is trying to access a Rwandan
service.
>> >
>> > About to hop onto a plane (ZK-NZJ) tonight with free WiFi
(Ka band
>> > GEO) enroute to Auckland in the hope of getting a better
experience
>> > than last time when the system seemed to run out of IP
addresses on
>> > its DHCP.
>> >
>> _______________________________________________
>> Starlink mailing list
>> [email protected]
>>
https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>>
>>
>> _______________________________________________
>> Starlink mailing list
>> [email protected]
>>
https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> _______________________________________________
> Starlink mailing list
> [email protected]
>
https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>
_______________________________________________
Starlink mailing list
[email protected]
https://lists.bufferbloat.net/listinfo/starlink
