Parallel machine scheduling with a common server

Conference · Sat Dec 31 04:00:00 EST 1994

OSTI ID:36106

Hall, N; Sriskandarajah, C; Potts, C

This paper considers the nonpreemptive scheduling of a given set of jobs on several identical, parallel machines. Each job must be processed on one of the machines. Prior to processing, a job must be loaded (setup) by a single server onto the relevant machine. The server may be a human operator, a robot, or a piece of specialized equipment. We study a number of classical scheduling objectives in this environment, including makespan, maximum lateness, the sum of completion times, the number of late jobs, and total tardiness, as well as weighted versions of some of these. The number of machines may be constant or arbitrary. Setup times may be unit, equal, or arbitrary. Processing times may be unit or arbitrary. For each problem considered, we attempt to provide either an efficient algorithm, or a proof that such an algorithm is unlikely to exist. Our results provide a mapping of the computational complexity of these problems. Included in these results are generalizations of the classical algorithms of Moore, Lawler and Moore and Lawler. In addition, we describe two heuristics for makespan scheduling in this environment, and provide an exact analysis of their worst-case performance.

• OSTI ID: 36106
• Report Number(s): CONF-9408161--
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
COMPUTER ARCHITECTURE
DESIGN
OPTIMIZATION
PARALLEL PROCESSING
TASK SCHEDULING