Research map / Reinforcement learning / Visual and representation RL
EA: Managing Green Data Centers Using Deep Reinforcement Learning Without Discounting
Peijian Wang, Thu Nguyen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| apply the EA framework (finite-horizon approximation, stationary policy) instead of GreenDRL | PPO green DC agent · Green DC simulator (old simulator) | reward: -103.7 -> −82.7 | Improved |
| use EA instead of PEB | PPO green DC agent · Green DC simulator (new simulator) | reward: −97.9 -> −84.6 | Improved |
| use EA instead of APO (average-reward) | PPO green DC agent · Green DC simulator (new simulator) | reward: −117.4 -> −84.6 | Improved |
| lengthen episode from 0.5-1 day to at least 1.5 days (ablation) | EA · Green DC simulator | reward: −7506.3 -> −89.0 (1.5 days); −84.6 at 3 days | Improved |
| keep repeating pattern in short episodes (vs. long episode without repeating pattern) (ablation) | EA · Synthetic traces | reward: (−3.4 ± 2.3) × 105 -> −103.3 (2h deadline) | Improved |
| lengthen deferrable deadline from 2 to 4 hours (ablation) | EA with repeating pattern · Synthetic traces | reward: −103.3 -> −85.7 | Improved |
| use total episode reward instead of reward-to-go as advantage (no baseline) (ablation) | EA · Green DC simulator | reward: −117.2 -> −86.1 | Improved |
| add input-dependent baseline to reward-to-go (ablation) | EA · Green DC simulator | reward: −117.2 -> −85.9 | Improved |
| add input-dependent baseline to total episode reward (ablation) | EA · Green DC simulator | reward: −86.1 -> −84.6 | Improved |
| add state-value baseline to total episode reward (ablation) | EA · Green DC simulator | reward: −86.1 -> −87.2 | No clear effect |
| use GreenDRL inputs and actions with EA framework (Mixed) vs full EA (ablation) | EA · Green DC simulator (old simulator) | reward: −84.9 -> −82.7 | No clear effect |
Closest papers by meaning
- Carbon Footprint Reduction for Sustainable Data Centers in Real-Time (AAAI 2024 · similarity 0.91)
- SustainDC: Benchmarking for Sustainable Data Center Control (NeurIPS 2024 · similarity 0.91)
- Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters (AAAI 2025 · similarity 0.91)
- Sustainability of Data Center Digital Twins with Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Data Center Cooling System Optimization Using Offline Reinforcement Learning (ICLR 2025 · similarity 0.90)
- LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
