 |
What is transmission latency?
A common concern in the procurement of telecommunication systems is a simple question:
Will my data arrive fast enough?
This question in fact contains many subtle parts, based on the interplay of several factors. The perceived 'fastness' (speed being a scientific quantity related to propagation and latency) is highly dependent on user requirements and the measurement technique.
A common misunderstanding is that having greater throughput means a “faster” connection. However, throughput, latency, the type of information transmitted, and the way that information is applied all affect the "perceived speed" of a connection.
Packet loss reflects upon latency in that the percentage of all measurement packets that do not result in a response from the destination; those are considered lost. For example, four responses to five packets indicates 20% packet loss (one packet in five is lost). These numbers are summarized by a method similar to that for latency. ISPs are constantly modifying their networks, so destinations sometimes become inaccessible. This causes packet loss values to be slightly inflated. To minimize this effect, periodically the ISPs as well as communication infrastructures reset IP ports constantly, as the world spins, by removing such dead destinations.
This can also be remedied with various techniques, such as increasing the TCP congestion window size, or more drastic solutions, such as packet coalescing, TCP acceleration, and forward error correction, all of which are used for high reachability site requirements.
Learn more >>
|
|
|
|
