• Corpus ID: 239998393

Scheduling Jobs with Stochastic Holding Costs

  title={Scheduling Jobs with Stochastic Holding Costs},
  author={Dabeen Lee and Milan Vojnovic},
This paper proposes a learning and scheduling algorithm to minimize the expected cumulative holding cost incurred by jobs, where statistical parameters defining their individual holding costs are unknown a priori. In each time slot, the server can process a job while receiving the realized random holding costs of the jobs remaining in the system. Our algorithm is a learning-based variant of the cμ rule for scheduling: it starts with a preemption period of fixed length which serves as a learning… 

Figures from this paper


Dynamic Scheduling with Convex Delay Costs: The Generalized CU Rule
We consider a general single-server multiclass queueing system that incurs a delay cost Ck(Tk) for each class k job that resides Tk units of time in the system. This paper derives a scheduling policy
Scheduling Flexible Servers with Convex Delay Costs: Heavy-Traffic Optimality of the Generalized cµ-Rule
A queueing system with multitype customers and flexible (multiskilled) servers that work in parallel is considered and a very simple generalizedcµ-rule is shown to minimizes both instantaneous and cumulative queueing costs, asymptotically, over essentially all scheduling disciplines, preemptive or non-preemptive.
On Learning the cμ Rule in Single and Parallel Server Networks
An almost greedy algorithm that explores only when the number of samples falls below a threshold is proposed and it is shown that this algorithm delivers constant holding-cost regret because a free exploration condition is eventually satisfied.
Scheduling with Testing
This work studies a new class of scheduling problems that capture common settings in service environments, in which one has to serve a collection of jobs that have a priori uncertain attributes and the service provider has to decide how to dynamically allocate resources between testing and processing jobs.
Learning scheduling algorithms for data processing clusters
It is shown that modern machine learning techniques can generate highly-efficient policies automatically and improve average job completion time by at least 21% over hand-tuned scheduling heuristics, achieving up to 2x improvement during periods of high cluster load.
Scheduling: Theory, Algorithms, and Systems
Scheduling will serve as an essential reference for professionals working on scheduling problems in manufacturing and computing environments and Graduate students in operations management, operations research, industrial engineering and computer science will find the book to be an accessible and invaluable resource.
Diagnostic Accuracy Under Congestion
This paper studies an elementary congested system facing an arriving stream of customers and reveals that the optimal search interval shrinks when customer types are more ambiguous a priori, i.e., as the base rate approaches the value at which the agent is indifferent between types.
Borg: the next generation
The findings show that Borg features such as alloc sets are used for resource-heavy workloads; automatic vertical scaling is effective; job-dependencies account for much of the high failure rates reported by prior studies and there is a great deal of variation between different clusters.
Dynamic right-sizing for power-proportional data centers
It is proved that the optimal offline algorithm for dynamic right-sizing has a simple structure when viewed in reverse time, and this structure is exploited to develop a new ‘lazy’ online algorithm, which is proven to be 3-competitive.
Introduction to Multi-Armed Bandits
This book provides a more introductory, textbook-like treatment of multi-armed bandits, providing a self-contained, teachable technical introduction and a brief review of the further developments.