Improving the Efficiency of a Deep Reinforcement Learning-Based Power Management System for HPC Clusters Using Curriculum Learning
Open Access
- 10 March 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Abstract
No abstract availableAll Related Versions
Funding Information
- Grant-in-Aid for Challenging Research (Exploratory) (22K19764)
- Grant-in-Aid for Scientific Research (B) (24K02945)
This publication has 27 references indexed in Scilit:
- ControlPULP: A RISC-V On-Chip Parallel Power Controller for Many-Core HPC Processors with FPGA-Based Hardware-In-The-Loop Power and Thermal EmulationInternational Journal of Parallel Programming, 2024
- Exploring energy saving opportunities in fault tolerant HPC systemsJournal of Parallel and Distributed Computing, 2023
- An Advantage Actor-Critic Deep Reinforcement Learning Method for Power Management in HPC Systems2023
- Toward Building a Digital Twin of Job Scheduling and Power Management on an HPC System2023
- Multi-agent reinforcement learning for autonomous vehicles: a surveyAutonomous Intelligent Systems, 2022
- Data Centers Job Scheduling with Deep Reinforcement LearningLecture Notes in Computer Science, 2020
- Batsim: A Realistic Language-Independent Resources and Jobs Management Systems Simulator2017
- Lessons learned from development and operation of the K computerParallel Computing, 2017
- Human-level control through deep reinforcement learningNature, 2015
- Experience with using the Parallel Workloads ArchiveJournal of Parallel and Distributed Computing, 2014