Abstract
We study the stochastic machine replenishment problem, which is a canonical special case of closed multiclass queuing systems in Markov decision theory. The problem models the scheduling of processor repairs in a multiprocessor system in which one repair can be made at a time and the goal is to maximize system utilization. We analyze the performance of a natural greedy index policy for this problem. We first show that this policy is a 2 approximation by exploring linear queuing structure in the index policy. We then try to exploit more complex queuing structures, but this necessitates solving an infinite-size, non-linear, non-convex, and non-separable function-maximization program. We develop a general technique to solve such programs to arbitrary degree of accuracy, which involves solving a discretized program on the computer and rigorously bounding the error. This proves that the index policy is in fact a 1.51 approximation.
The main non-trivial ingredients of the proof are two folds: finding a way to analyze the complex queuing structure of the index policy, and bounding the error in discretization when numerically solving the non-linear function-maximization. We believe that this framework is general enough to be useful in the analysis of index policies in related problems. As far as we are aware, this is one of the first non-trivial approximation analysis of an index policy a multi-class queuing problem, as well as one of the first non-trivial example of an approximation ratio that is rigorously proven by numerical optimization via a computer.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bar-Noy, A., Bhatia, R., Naor, J., Schieber, B.: Minimizing service and operation costs of periodic scheduling. In: Proc. ACM-SIAM Symp. on Discrete Algorithms, pp. 11–20 (1998)
Bertsekas, D.: Dynamic Programming and Optimal Control. 2nd edn. Athena Scientific (2001)
Bertsimas, D., Gamarnik, D., Tsitsiklis, J.: Performance of multiclass markovian queueing networks via piecewise linear Lyapunov functions. Annals of Applied Probability 11(4), 1384–1428 (2002)
Bertsimas, D., Niño-Mora, J.: Restless bandits, linear programming relaxations, and a primal-dual index heuristic. Oper. Res. 48(1), 80–90 (2000)
Dean, B., Goemans, M., Vondrák, J.: Approximating the stochastic knapsack problem: The benefit of adaptivity. In: Proc. of the 2004 Annual Symp. on Foundations of Computer Science (2004)
Dean, B., Goemans, M., Vondrák, J.: Adaptivity and approximation for stochastic packing problems. In: Proc. of the 2005 Annual ACM-SIAM Symp. on Discrete Algorithms (2005)
Durrett, R.: Probability: Theory and Examples, 3rd edn. Duxbury Press (2004)
Gittins, J.C., Jones, D.M.: A dynamic allocation index for the sequential design of experiments. Progress in statistics (European Meeting of Statisticians) (1972)
Goemans, M.X., Kleinberg, J.M.: An improved approximation ratio for the minimum latency problem. In: SODA, pp. 152–158 (1996)
Goseva-Popstojanova, K., Trivedi, K.S.: Stochastic modeling formalisms for dependability, performance and performability. In: Performance Evaluation: Origins and Directions, pp. 403–422 (2000)
Harrison, J.M.: Dynamic scheduling of a multiclass queue: Discount optimality. Operations Research 23(2), 370–382 (1975)
Jain, K., Mahdian, M., Saberi, A.: A new greedy approach for facility location problems. In: Proc. of the 2002 Annual ACM Symp. on Theory of Computing (May 2002)
Kenyon, C., Schabanel, N.: The data broadcast problem with non-uniform transmission times. In: Proc. ACM-SIAM Symp. on Discrete Algorithms (1999)
Mehta, A., Saberi, A., Vazirani, U., Vazirani, V.: Adwords and generalized on-line matching. In: FOCS 2005. Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science, pp. 264–273 (2005)
Munagala, K., Babu, S., Motwani, R., Widom, J.: The pipelined set cover problem. In: Proc. Intl. Conf. Database Theory (2005)
Niño Mora, J.: Restless bandits, partial conservation laws and indexability. Adv. in Appl. Probab. 33(1), 76–98 (2001)
Papadimitriou, C.H., Tsitsiklis, J.N.: The complexity of optimal queuing network control. Math. Oper. Res. 24(2), 293–305 (1999)
Tsitsiklis, J.N.: A short proof of the Gittins index theorem. Annals of Applied Probability 4(1), 194–199 (1994)
Whittle, P.: Restless bandits: Activity allocation in a changing world. Appl. Prob. 25(A), 287–298 (1988)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Munagala, K., Shi, P. (2008). The Stochastic Machine Replenishment Problem. In: Lodi, A., Panconesi, A., Rinaldi, G. (eds) Integer Programming and Combinatorial Optimization. IPCO 2008. Lecture Notes in Computer Science, vol 5035. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-68891-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-68891-4_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68886-0
Online ISBN: 978-3-540-68891-4
eBook Packages: Computer ScienceComputer Science (R0)