Setup Times in Multiserver Systems

Abstract: Capacity management, whether it involves servers in a data center, human staff in a call center, or doctors in a hospital, is largely about balancing a resource-delay tradeoff. On the one hand, one would like to turn off servers when not in use (or send home staff that are idle) to save on resources. On the other hand, one wants to avoid the considerable setup time required to turn an off server back on. In this talk, we describe recent work focused on understanding the delay component of this tradeoff. In particular, we discuss new, tight bounds on the average delay in the M/M/k with Deterministic setup times.

Bio: Jalani is currently a 6th year Ph.D. student in the Computer Science Department at Carnegie Mellon University, where he is advised by Prof. Weina Wang. Before coming to CMU, he earned his B. Eng. in Mechanical Engineering at the California Institute of Technology. He is a recipient of the Gates Millennium Scholarship and the GEM Fellowship. Currently, Jalani’s work is focused on investigating how the energy-saving methods being used in today’s datacenters affect the fundamental characteristics of their latency performance. More broadly, Jalani is interested in the areas of applied probability, queueing theory, and decision-making under uncertainty.