Fair end-to-end window-based congestion control
IEEE/ACM Transactions on Networking (TON)
Impact of fairness on Internet performance
Proceedings of the 2001 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
The Mathematics of Internet Congestion Control (Systems and Control: Foundations and Applications)
The Mathematics of Internet Congestion Control (Systems and Control: Foundations and Applications)
IEEE/ACM Transactions on Networking (TON)
Flow rate fairness: dismantling a religion
ACM SIGCOMM Computer Communication Review
Stability of multi-path dual congestion control algorithms
IEEE/ACM Transactions on Networking (TON)
A unified approach to congestion control and node-based multipath routing
IEEE/ACM Transactions on Networking (TON)
| Hi-index | 0.00 |
Methods for network resource allocation have mainly focused on establishing fairness among the rates of individual flows. However, since multiple TCP connections in one or many paths can serve a common user, we advocate in this paper a user-centric notion of fairness, which we formulate in the Network Utility Maximization (NUM) framework. In particular, we develop control laws for the number of connections identified with a certain user, which can include single-path, multipath or more general aggregates of flows, and prove convergence to the optimal resource allocation. This theory applies directly to the case of cooperative users. In the case where connections are generated exogenously by possibly non-cooperative users, we develop admission control policies that ensure both network stability and user-centric fairness.