Hats Network | LogoHats Network
BackbonePoP Latency

Latency Coordinates & Fiber Model Inputs

How AS203314 resolves public city-centre coordinates with GeoNames and selects fiber, attenuation, amplifier, and route-stretch model inputs.

Open Data

The latency model starts with public city-centre coordinates, then applies the physical constants and engineering assumptions listed below. The formula verification works through the equations and a fixed numerical example.

A city reference, not a facility address

Published coordinates identify the GeoNames city centre. They deliberately do not reveal a router, carrier hotel, cable landing station, or other private infrastructure location. The resulting value is a city-to-city physical reference, not a reconstruction of the production fiber route.

1. Resolving the theoretical physical location

Coordinate lookup uses the PoP's public city name and ISO 3166-1 alpha-2 country code. The GeoNames Search Webservice receives these constraints:

ParameterValuePurpose
name_equalsPublic PoP city namePrefer an exact toponym or alternate-name match
countryISO country codePrevent collisions such as Paris, France vs. Paris, Texas
featureClassPRestrict results to populated places
styleFULLReturn identity and location fields needed for validation
maxRows20Permit local disambiguation when names are shared

When the exact query returns no result, the resolver retries with a required-name search. It normalizes diacritics, checks the country and populated-place class, then selects the highest-population exact or alternate-name match. This resolves names such as São Paulo, Frankfurt am Main and New York City without a facility address.

The checked snapshot records the GeoNames ID, canonical name, feature code, coordinates, source, date and attribution. Refresh it with pnpm --filter @hatsnet/docs geonames:refresh and GEONAMES_USERNAME. Normal builds read the snapshot rather than querying GeoNames.

PoPGeoNames placeCountryCity-centre coordinates
AMSAmsterdamNL52.37403, 4.88969
BERBerlinDE52.52437, 13.41053
FRAFrankfurt am MainDE50.11552, 8.68417
LONLondonGB51.50853, -0.12574
MRSMarseilleFR43.29695, 5.38107
MOWMoscowRU55.75204, 37.61781
PARParisFR48.85341, 2.34880
IADAshburnUS39.04372, -77.48749
LAXLos AngelesUS34.05223, -118.24368
MIAMiamiUS25.77427, -80.19366
NYCNew York CityUS40.71427, -74.00597
SEASeattleUS47.60621, -122.33207
GRUSão PauloBR-23.54750, -46.63611
HKGHong KongHK22.27832, 114.17469
MELMelbourneAU-37.81400, 144.96332
SINSingaporeSG1.28967, 103.85007
SYDSydneyAU-33.86785, 151.20732
TPETaipeiTW25.05306, 121.52639
TYOTokyoJP35.68950, 139.69171
JNBJohannesburgZA-26.20227, 28.04363

The coordinate snapshot uses GeoNames data under CC BY 4.0. It is separate from operational topology records.

2. Model inputs and engineering evidence

Constants, material properties and engineering assumptions have different evidential roles:

InputModel valueRole and evidence
Earth modelWGS-84 ellipsoidThe inverse geodesic uses Charles F. F. Karney's robust Algorithms for geodesics
Vacuum light speed299,792.458km/sExact physical constant used for the absolute propagation floor
Standard fiber group index1.4679Conventional single-mode reference from Corning's fiber latency white paper
Low-latency group index1.4620Optimistic SMF-28 ULL material comparison from the same Corning paper
Optical path allowance1.05×Transparent engineering reference for slack and small route deviations
Attenuation reference0.20dB/kmConservative long-haul single-mode planning value
Optical span80kmLower edge of the 80–120km range in Cisco's long-haul design guide
Amplifier transit delay0.05µs per passRounded from the roughly 10m equivalent fiber length described by the GÉANT transport report
Mapped-fiber reference1.33×Median conduit-to-geodesic comparison reported in Dissecting Latency in the Internet's Fiber Infrastructure

ITU-T G.652 defines the relevant characteristics of standard single-mode fiber. The broader distinction between the speed-of-light baseline and routed-network path inflation is also discussed in cISP: A Speed-of-Light Internet Service Provider.

Formula derivation and numerical verification

See Theoretical Fiber Latency Formula Verification for the rendered equations, unit conversions, boundary checks, and the complete Tokyo (TYO) to Sydney (SYD) worked example.

3. Separation of model layers

  • The geographic layer resolves city-centre coordinates and the shortest WGS-84 surface distance.
  • The physical layer compares vacuum, conventional silica, and low-latency silica propagation.
  • The engineering layer adds a 5% path allowance and idealized inline-amplifier transit time.
  • The research layer provides a 1.33× mapped-fiber comparison without treating it as a universal route prediction.
  • The comparison layer relates the published RTT to the standard-fiber physical floor.

Attenuation affects optical power, span count and amplifier count, not the speed of propagation. This lower-bound model excludes vendor-specific transponder, FEC, OTN switching, router, serialization and queueing delays.

4. Estimated stability indicators

City-pair pages report statistics from their published probe round. The separate 24-hour, 7-day and 30-day trend graphic is an estimated comparison, not a history of collected rounds. City-table jitter and loss fields are also estimated indicators.

Do not use estimated indicators as an outage record or an SLA measurement.

5. Interpretation checklist

  • Use vacuum RTT only as an absolute law-of-physics reference.
  • Use fiber RTT as the shortest possible RTT through standard silica along the WGS-84 geodesic.
  • Use engineering floor as a transparent low-latency optical design reference with small cable and amplifier allowances.
  • Use 1.33× mapped-fiber RTT as a research comparison, not as a universal route prediction.
  • Compare efficiency across routes only after considering city-centre coordinates, submarine cable geography, routing policy, and normal measurement variation.
  • Do not interpret any value on these pages as an SLA or as disclosure of a production facility or cable path.

The formula verification shows the calculation. Published observations are in the latency matrix and the city-pair directory.

On this page