Optimization flow control—I: basic algorithm and convergence
IEEE/ACM Transactions on Networking (TON)
The Mathematics of Internet Congestion Control (Systems and Control: Foundations and Applications)
The Mathematics of Internet Congestion Control (Systems and Control: Foundations and Applications)
Achieving near-optimal traffic engineering solutions for current OSPF/IS-IS networks
IEEE/ACM Transactions on Networking (TON)
Cross-layer optimization in TCP/IP networks
IEEE/ACM Transactions on Networking (TON)
IEEE/ACM Transactions on Networking (TON)
Stability of multi-path dual congestion control algorithms
IEEE/ACM Transactions on Networking (TON)
Computer Networks ISE: A Systems Approach
Computer Networks ISE: A Systems Approach
TCP Vegas: end to end congestion avoidance on a global Internet
IEEE Journal on Selected Areas in Communications
User-centric network fairness through connection-level control
INFOCOM'10 Proceedings of the 29th conference on Information communications
Cost of not splitting in routing: characterization and estimation
IEEE/ACM Transactions on Networking (TON)
| Hi-index | 0.00 |
The paper considers a TCP/IP-style network with flow control at end-systems based on congestion feedback and routing decisions at network nodes on a per-destination basis. The main generalization with respect to standard IP is to allow routers to split their traffic in a controlled way between the outgoing links. We formulate global optimization criteria, combining those used in the congestion control and traffic engineering, and propose decentralized controllers at sources and routers to reach these optimal points, based on congestion price feedback. We first consider adapting the traffic splits at routers to follow the negative price gradient; we prove this is globally stabilizing when combined with primal congestion control, but can exhibit oscillations in the case of dual congestion control. We then propose an alternative anticipatory control of routing, proving its stability for the case of dual congestion control. We present a concrete implementation of such algorithms, based on queueing delay as congestion price. We use TCP-FAST for congestion control and develop a multipath variant of the distance vector routing protocol RIP. We demonstrate through ns2-simulations the collective behavior of the system, in particular that it reaches the desired equilibrium points.