Affiliations: Department of Computer Sciences, Purdue University, 1398 Computer Science Building, West Lafayette, IN 47907‐1398, USA E‐mail: [email protected] | Department of CIS, The Ohio State University, Columbus, OH 43210, USA E‐mail: [email protected]‐state.edu | Department of ECSE, Rensellaer Polytechnic Institute, Troy, NY 12180‐3590, USA E‐mail: [email protected] | Axiowave Networks, 200 Nickerson Road, Marlborough, MA 01752, USA E‐mail: [email protected] | Nokia, Mountain View, CA 94043, USA E‐mail: [email protected]
Abstract: In a multi‐service network such as ATM, adaptive data services (such as ABR) share the bandwidth left unused by higher priority services. The network indicates to the ABR sources the fair and efficient rates at which they should transmit to minimize their cell loss. Switches must constantly measure the demand and available capacity, and divide the capacity fairly among the contending connections. In this paper, we propose a new method for determining the “effective” number of active connections, and the fair bandwidth share for each connection. We prove the efficiency and fairness of the proposed method analytically, and use several simulations to illustrate its fairness dynamics and transient response properties.
