Approximate modeling of multiple priority congestion control in signalling system no. 7

This talk presents analytical and simulation models that attempt to capture the behavior of a structured common channel Signalling System Number 7 network during congestion conditions. In particular, the objective of these models is to study and evaluate the steady state performance of the congestion control protocol operation of Message Transfer Part - level 3 independent of interac tions in the backbone transport network. Therefore, our performance metric deals with messages in contrast to calls. Our analytical model incorporates multiple priority message sources at the signaling points and studies congestion at a single outgoing link of a signaling transfer point. Rea sonable simplifying assumptions are made in order to develop a Markov model to approximate the performance. Two simulation models are also presented to substantiate the assumptions and verify the analytical model. Through the Markov model and simulations we investigate the normalized throughput and blocking probabilities for each of the two priority messages, as well as other mea sures odel, e.g. offered load, buffer onset threshold ratio, ratio of traffic from different priority classes, and timers are varied. We also compare the multiple priority congestion control scheme with the no-priority case. In addition, by using the second set of simulations, we show that the basic timer of the congestion control mechanism, though a deterministic value in real implementa tion, may be approximated to obey an exponential interarrival distribution without causing major errors. These simulations also show that the mean interarrival time between the expirations of this timer is a function of the offered load, and becomes essentially constant after a critical value of the offered load is exceeded. Since the behavior of this timer is critical to the imbedded Markov chain analysis, where the process is observed after each departure epoch, formulation of the imbedded Ma;rkov chain then becomes possible.