KlZOnmyway

> > How long did you simulate? > > To achieve 2% load, on average the number of incast per second is: 320 (hosts) * 100Gbps * 0.02 * /...

> > > > How long did you simulate? > > > > To achieve 2% load, on average the number of incast per second is: 320 (hosts) * 100Gbps...

> My reproduced results are somewhat different from those in the paper. For example, for the small size flow, the FCT slowdown of DCQCN and TIMELY is much smaller than...

Hi, I also met this problem and I ran with command: _python3 test_tcp.py_. All other params are set to default. I found in other issues that reduce steptime may make...

I use the default one. Did you train on a pretrained encoder?