Say for an example, X connection arriving per Y sec (maintaining Poisson distribution). Avg connection holding time: Z sec. Max connection BW= P Gbps, and arriving connection request BW = (fully random) or (any of n-predefined BW, and connections are distributed in particular ratio say a:b:c:d).
From the beginning IP networks were not designed for providing Multimedia Services.
These networks were intended for data transfer without predefined paths so that in case of breakdown of one of the routers, other path could be chosen.
Path of packet can change and so can change transfer parameters.
The IP Networks were designed so that a node failure allowed another route to be selected so that payload could be delivered.
For Data traffic, it is necessary to estimate network performance under load and link overflow.
This problem is handled by theory of queuing systems. Therefore,
Erlang B and Erlang C can be used. Erlang B formula deals with data loss in relation with network load.
Erlang C formula defines probability of inserting data into waiting queues and so resembles to an IP network behaviour where data queuing occurs before sending further.
Summary: For your case a combination of Erlang B and C should be used for your Data Case.