I spent 10 years working with radio access networks (RAN), first in WCDMA (3G) then LTE (4G), then 5G. Our systems were also software defined radio (SDR), but, and this is crucial (and the paper points to this), the SDR as "malleable" as it is, is still highly dependent on the underlying hardware to achieve good performance.
Also, we spent huge amount of time making sure uplink performance is top-notch, as is the general stability and determinism, i.e. jitter and tail latency. In the paper they show that OAI is quite unstable, and they only achieve 5-49% of theoretical uplink capacity.
Also note this is a tiny setup, single server, four simultaneous UEs (phones). The systems I worked with handled 20 000 phones per second, with quality guarantees, in environments like central Tokyo and midtown Manhattan.
So great for independent research, but unfortunately, still very much bound to small end research.
OAI and the other projects I’m excited to see what happens with GPUs after the upcoming crash. Also AI to help with development and integration.
And with Intel having screwed everyone before by not exposing the FPGA frontend on their chips, I’m hopeful one of the newer companies will have something better or maybe with new leadership they’ll make better decisions.
But I think we need to settle on use cases for what we want openRan to actually be able to do in what release.
Also, having that project led by legacy vendors was a large part of the problem, but something the telcos were pushing hard.
I think, and correct me if I am wrong. Nvidia's OpenRAN on CUDA and its CPU platform along with Nokia's OpenRAN solution working with SoftBank in Japan has proved to be an actual competitive and viable solution to other commercial offering.
Do we expect to see more of these or are there caveats that they are not saying.
I spent 10 years working with radio access networks (RAN), first in WCDMA (3G) then LTE (4G), then 5G. Our systems were also software defined radio (SDR), but, and this is crucial (and the paper points to this), the SDR as "malleable" as it is, is still highly dependent on the underlying hardware to achieve good performance.
Also, we spent huge amount of time making sure uplink performance is top-notch, as is the general stability and determinism, i.e. jitter and tail latency. In the paper they show that OAI is quite unstable, and they only achieve 5-49% of theoretical uplink capacity.
Also note this is a tiny setup, single server, four simultaneous UEs (phones). The systems I worked with handled 20 000 phones per second, with quality guarantees, in environments like central Tokyo and midtown Manhattan.
So great for independent research, but unfortunately, still very much bound to small end research.
OAI and the other projects I’m excited to see what happens with GPUs after the upcoming crash. Also AI to help with development and integration.
And with Intel having screwed everyone before by not exposing the FPGA frontend on their chips, I’m hopeful one of the newer companies will have something better or maybe with new leadership they’ll make better decisions.
But I think we need to settle on use cases for what we want openRan to actually be able to do in what release.
Also, having that project led by legacy vendors was a large part of the problem, but something the telcos were pushing hard.
I think, and correct me if I am wrong. Nvidia's OpenRAN on CUDA and its CPU platform along with Nokia's OpenRAN solution working with SoftBank in Japan has proved to be an actual competitive and viable solution to other commercial offering.
Do we expect to see more of these or are there caveats that they are not saying.
Is this research any value to the industry?
Note that this is about RAN (Radio Access Network) platforms, not the past tense of the verb "to run".