It smells a lot like TCP Vegas, and in fact the
idea of using RTT, bandwidth, and ACK measurments
in some way to moderate the congestion window is
an idea much older than TCP Vegas.
The TCP Vegas paper has good references to these
earlier works, primarily that of Jain and also that of Wang and Crawford.
The relevant papers are:
"TCP Vegas: End to End Congestion Avoidance on a Global Internet." Lawrence S. Brakmo and Larry L. Peterson
"A delay-based approach for congestion avoidance in interconnected heterogeneous computer networks." R. Jain
"A new congestion control scheme: Slow start and search (Tri-S)." Z. Wang and J. Crowcroft
Slashdot Mirror
The TCP Vegas paper has good references to these earlier works, primarily that of Jain and also that of Wang and Crawford.
The relevant papers are:
"TCP Vegas: End to End Congestion Avoidance on a Global Internet." Lawrence S. Brakmo and Larry L. Peterson
"A delay-based approach for congestion avoidance in interconnected heterogeneous computer networks." R. Jain
"A new congestion control scheme: Slow start and search (Tri-S)." Z. Wang and J. Crowcroft