We define congestion in a packet network to be the state where performance degrades due to the saturation of a network resource . Resources required by packet networks en compass the communication links between packet switches and the switches' computational resources—processor cycles and buffe r memory . The degradation arises when the network expends resources in doing work i t can't complete . Congestion arises for a number of reasons . The network may simply be underconfigure d for the offered load . Underconfiguration can result from temporary failures elsewhere i n the network, or it may be a busy-hour occurrence, hence not worthy of reconfiguration . In a network whose resources have differen t capacities, when all the capacity of a high speed link is directed over a lower-speed link , that link cannot carry the offered load . Such over-demand can also arise due to the funnel ing together or flows from several incomin g links to an outgoing link . Packet switches should be able to cope gracefully with these situations. They may simply discard the excess packets, relying o n
[1]
Lixia Zhang,et al.
A new architecture for packet switching network protocols
,
1989
.
[2]
S. Lam,et al.
Congestion Control of Store-and-Forward Networks by Input Buffer Limits - An Analysis
,
1979,
IEEE Transactions on Communications.
[3]
Eric C. Rosen,et al.
The New Routing Algorithm for the ARPANET
,
1980,
IEEE Trans. Commun..
[4]
Van Jacobson,et al.
Congestion avoidance and control
,
1988,
SIGCOMM '88.
[5]
Scott Shenker,et al.
Analysis and simulation of a fair queueing algorithm
,
1989,
SIGCOMM '89.