Opportunistic Scheduling for Optimal Spot Instance Savings in the Cloud

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bhuyan, Neelkamal, Bhatia, Randeep, Kodialam, Murali, Lakshman, TV
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911383762763776
author Bhuyan, Neelkamal
Bhatia, Randeep
Kodialam, Murali
Lakshman, TV
author_facet Bhuyan, Neelkamal
Bhatia, Randeep
Kodialam, Murali
Lakshman, TV
contents We study the problem of scheduling delay-sensitive jobs over spot and on-demand cloud instances to minimize average cost while meeting an average delay constraint. Jobs arrive as a general stochastic process, and incur different costs based on the instance type. This work provides the first analytical treatment of this problem using tools from queuing theory, stochastic processes, and optimization. We derive cost expressions for general policies, prove queue length one is optimal for low target delays, and characterize the optimal wait-time distribution. For high target delays, we identify a knapsack structure and design a scheduling policy that exploits it. An adaptive algorithm is proposed to fully utilize the allowed delay, and empirical results confirm its near-optimality.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12266
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Opportunistic Scheduling for Optimal Spot Instance Savings in the Cloud
Bhuyan, Neelkamal
Bhatia, Randeep
Kodialam, Murali
Lakshman, TV
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
Performance
Optimization and Control
C.4; C.2.4
We study the problem of scheduling delay-sensitive jobs over spot and on-demand cloud instances to minimize average cost while meeting an average delay constraint. Jobs arrive as a general stochastic process, and incur different costs based on the instance type. This work provides the first analytical treatment of this problem using tools from queuing theory, stochastic processes, and optimization. We derive cost expressions for general policies, prove queue length one is optimal for low target delays, and characterize the optimal wait-time distribution. For high target delays, we identify a knapsack structure and design a scheduling policy that exploits it. An adaptive algorithm is proposed to fully utilize the allowed delay, and empirical results confirm its near-optimality.
title Opportunistic Scheduling for Optimal Spot Instance Savings in the Cloud
topic Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
Performance
Optimization and Control
C.4; C.2.4
url https://arxiv.org/abs/2601.12266