Abstract
We consider an Erlang loss system (modem bank) with two streams of arriving customers, where arrival rates vary by time-of-day. We can observe one of the traffic streams (our customers), but we do not know how many servers the system has, or the characteristics of the other stream. Using detailed sample-path data, we construct a maximum likelihood estimator that makes good use of the data, but is slow to evaluate. As an alternative, we present an estimation system based on traffic data summarized by hour. This estimation system is much faster, and tends to produce good lower bounds on the size of the system and competing traffic.
Similar content being viewed by others
References
J. Abate and W. Whitt, Calculating transient characteristics of the Erlang loss model by numerical transform inversion, Commun. Statistics Stochastic Models 14(3) (1998) 663–680.
R.B. Cooper, Introduction to Queueing Theory, 3rd ed. (CEE Press, 1990).
D.J. Daley and L.D. Servi, Exploiting Markov chains to infer queue length from transactional data, J. Appl. Probab. 29(3) (1992) 713–732.
J.L. Davis, W.A. Massey and W. Whitt, Sensitivity to the service-time distribution in the nonstationary Erlang loss model, Managm. Sci. 41(6) (1995) 1107–1116.
R.F. Farmer and I. Kaufman, On the numerical evaluation of some basic traffic formulae, Networks 8 (1978) 153–186.
W.K. Grassmann, Transient solutions in Markovian queueing systems, Comput. Oper. Res. 4(1) (1977) 47–56, and correction in 5(2).
L.V. Green and P.J. Kolesar, The pointwise stationary approximation for queues with nonstationary arrivals, Managm. Sci. 37(1) (1991) 84–97.
L.V. Green, P.J. Kolesar and J. Soares, Improving the SIPP approach for staffing service systems that have cyclic demands, Oper. Res. 49(4) (2001) 549–564.
L.V. Green, P.J. Kolesar and A. Svoronos, Some effects of nonstationarity on multiserver Markovian queueing systems, Oper. Res. 39(3) (1991) 502–511.
N. Grier, W.A. Massey, T. McKoy and W. Whitt, The time-dependent Erlang loss model with retrials, Telecommunication Systems 7(1–3) (1997) 253–265.
D.L. Jagerman, Some properties of the Erlang loss function, Bell System Tech. J. 53(3) (1974) 525–551.
D.L. Jagerman, Nonstationary blocking in telephone traffic, Bell System Tech. J. 54(3) (1975) 625–661.
M.A. Johnson, S. Lee and J.R. Wilson, NPPMLE and NPPSIM – software for estimating and simulating nonhomogeneous Poisson processes having cyclic behavior, Software Review, Oper. Res. Lett. 15(5) (1994) 273–282.
R.C. Larson, The queue inference engine – deducing queue statistics from transactional data, Managm. Sci. 36(5) (1990) 586–601.
W.A. Massey and W. Whitt, An analysis of the modified offered-load approximation for the nonstationary Erlang loss model, Ann. Appl. Probab. 4(4) (1994) 1145–1160.
W.A. Massey and W. Whitt, Stationary-process approximations for the nonstationary Erlang loss model, Oper. Res. 44(6) (1996) 976–983.
C. Moler and C. van Loan, Nineteen dubious ways to compute the exponential of a matrix, SIAM Rev. 20(4) (1978) 801–836.
I. Najfeld and T.F. Havel, Derivatives of the matrix exponential and their computation, Adv. in Appl. Math. 16(3) (1995) 321–375.
S. Nelakuditi, Z.-L. Zhang and R.P. Tsang, Adaptive proportional routing: A localized QoS routing approach, in: Proc. of IEEE INFOCOM 2000, 19th Annual Joint Conf. of the IEEE Computer and Communications Societies, Vol. 3 (2000) pp. 1566–1575.
S.M. Ross, Introduction to Probability Models, 5th ed. (Academic Press, New York, 1993).
L. Schruben and R. Kulkarni, Some consequences of estimating parameters for the M/M/1 queue, Oper. Res. Lett. 1(2) (1982) 75–78.
R.B. Sidje, Expokit: A software package for computing matrix exponentials, ACM Trans. Math. Software 24(1) (1998) 130–156.
W. Whitt, The pointwise stationary approximation for Mt/Mt/s queues is asymptotically correct as the rates increase, Managm. Sci. 37(3) (1991) 307–314.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ross, A.M., Shanthikumar, J.G. Estimating Effective Capacity in Erlang Loss Systems under Competition. Queueing Syst 49, 23–47 (2005). https://doi.org/10.1007/s11134-004-5554-8
Issue Date:
DOI: https://doi.org/10.1007/s11134-004-5554-8