Improving the Efficiency of a Deep Reinforcement Learning-Based Power Management System for HPC Clusters Using Curriculum Learning
On the map: Deep reinforcement learning methods → RL for energy, networks and operations
Abstract (arXiv)
High energy consumption remains a key challenge in high-performance computing (HPC) systems, which often feature hundreds or thousands of nodes drawing substantial power even in idle or standby modes. Although powering down unused nodes can improve energy efficiency, choosing the wrong time to do so can degrade quality of service by delaying job execution. Machine learning, in particular reinforcement learning (RL), has shown promise in determining optimal times to switch nodes on or off. In this study, we enhance the performance of a deep reinforcement learning (DRL) agent for HPC power management by integrating curriculum learning (CL), a training approach that introduces tasks with gradually increasing difficulty. Using the Batsim-py simulation framework, we compare the proposed CL-based agent to both a baseline DRL method (without CL) and the conventional fixed-time timeout strategy. Experimental results confirm that an easy-to-hard curriculum outperforms other training orders in terms of reducing wasted energy usage. The best agent achieves a 3.73% energy reduction over the baseline DRL method and a 4.66% improvement compared to the best timeout configuration (shutdown every 15 minutes of idle time). In addition, it reduces average job waiting time by 9.24% and maintains a higher job-filling rate, indicating more effective resource utilization. Sensitivity tests across various switch-on durations, power levels, and cluster sizes further reveal the agent's adaptability to changing system parameters without retraining. These findings demonstrate that curriculum learning can significantly improve DRL-based power management in HPC, balancing energy savings, quality of service, and robustness to diverse configurations.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 9 of its 47 references that are in the map. First posted on arXiv 27 Feb 2025.
Builds on
9 of 47 references.
References · 9
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
- 2018An Introduction to Deep Reinforcement Learningcited by 206
- 2018Learning Scheduling Algorithms for Data Processing Clusterscited by 134
- 2018Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networkscited by 114
- 2023ControlPULP: A RISC-V On-Chip Parallel Power Controller for Many-Core HPC Processors with FPGA-Based Hardware-In-The-Loop Power and Thermal Emulationcited by 1
- 2023Design of an energy aware petaflops class high performance cluster based on power architecturecited by 1
- 2023Exploring Energy Saving Opportunities in Fault Tolerant HPC Systemscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Green Energy Management for Sustainable Data Centers Using Deep Reinforcement Learning
- 2026Offline Reinforcement-Learning-Based Power Control for Application-Agnostic Energy Efficiency
- 2026Cutting AI Datacenter Energy with Reinforcement Learning: Measured Power Control of LLM Training from One GPU to the Fleet
- 2026Scalable machine learning-based approaches for energy saving in densely deployed Open RAN ↗
- 2024SustainDC: Benchmarking for Sustainable Data Center Control
- 2025Data Center Cooling System Optimization Using Offline Reinforcement Learning
- 2026Toward an Energy-Optimized Operation of Data Centers Located in Wind Farms Using Reinforcement Learning
- 2024CAFEEN: A Cooperative Approach for Energy Efficient NoCs with Multi-Agent Reinforcement Learning