On-line maintenance of optimal machine schedules

Effective and efficient scheduling in a dynamically changing environment is important for real-time control of manufacturing, computer, and telecommunication systems. This paper illustrates the algorithmic and analytical issues associated with developing efficient and effective methods to update schedules on-line. We consider the problem of dynamically scheduling precedence-constrained jobs on a single processor to minimize the maximum completion time penalty. We first develop an efficient technique to reoptimize a rolling schedule when new jobs arrive. The effectiveness of reoptimizing the current schedule as a long-term on-line strategy is measured by bounding its performance relative to oracles that have perfect information about future job arrivals.