Open-access publishing in science, technology & health ID | EN  ·  Log in Sign up
FJI FJI Press
Open Access Publisher

Home / Article

Open Access DOI: 10.5555/fji-demo-001 How to use a DOI?

Adaptive Cooling Control for Small-Scale Data Centers Using Reinforcement Learning

Nadia Rahmadani* iD1, Budi Santoso iD2

*Corresponding author: Nadia Rahmadani

1Universitas Cakrawala
2Institute of Technology Nusantara

Research Article · Pages 1–14 · Journal of Sustainable Computing, Volume 3 (2026) · Published 2026-06-15 · 253 views · 104 downloads

Article history: Received 2026-04-10 · Accepted 2026-05-22 · Available online 2026-06-15

Abstract

Small data centers in tropical climates face disproportionate cooling costs. We propose a reinforcement-learning controller that adjusts cooling setpoints in response to workload and ambient temperature. In a six-month simulation of a 40-rack facility, the controller reduced cooling energy by 23% compared to a fixed-setpoint baseline while keeping all racks within thermal limits.

Keywords: green computing; reinforcement learning; data center cooling

⇩ Download PDF
Cite this article

Nadia Rahmadani, Budi Santoso (2026). Adaptive Cooling Control for Small-Scale Data Centers Using Reinforcement Learning. Journal of Sustainable Computing, 3(1), 1–14. https://doi.org/10.5555/fji-demo-001

Download the citation in your preferred format:

BibTeX RIS

© 2026 The Authors. Published by FJI Press.

This is an open access article distributed under the CC BY-NC 4.0 license. CC BY-NC 4.0

DOI
10.5555/fji-demo-001
Article type
Research Article
Pages
1–14
Published
2026-06-15
Metrics
253 views · 104 downloads