# Reinforcement Learning Testbed for Power-Consumption Optimization

arXiv: https://arxiv.org/abs/1808.10427 · HTML: https://mlsanity.com/paper/1808.10427/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2018.

## Built on by (most cited first, 18 of 18)

- [Semi-analytical Industrial Cooling System Model for Reinforcement Learning](https://mlsanity.com/paper/2207.13131/) (2022)
- [SustainDC: Benchmarking for Sustainable Data Center Control](https://mlsanity.com/paper/2408.07841/) (2024)
- [PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability](https://mlsanity.com/paper/2310.03906/) (2023)
- [Distributed Multi-Agent Deep Reinforcement Learning Framework for Whole-building HVAC Control](https://mlsanity.com/paper/2110.13450/) (2021)
- [CALE: Continuous Arcade Learning Environment](https://mlsanity.com/paper/2410.23810/) (2024)
- [A Comparison of Classical and Deep Reinforcement Learning Methods for HVAC Control](https://mlsanity.com/paper/2308.05711/) (2023)
- [An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control](https://mlsanity.com/paper/2401.05737/) (2024)
- [Carbon Footprint Reduction for Sustainable Data Centers in Real-Time](https://mlsanity.com/paper/2403.14092/) (2024)
- [Reinforcement Learning for Sustainable Energy: A Survey](https://mlsanity.com/paper/2407.18597/) (2024)
- [BEAR: Physics-Principled Building Environment for Control and Reinforcement Learning](https://mlsanity.com/paper/2211.14744/) (2022)
- [Deep Learning Based Simulators for the Phosphorus Removal Process Control in Wastewater Treatment via Deep Reinforcement Learning Algorithms](https://mlsanity.com/paper/2401.12822/) (2024)
- [A Configurable Pythonic Data Center Model for Sustainable Cooling and ML Integration](https://mlsanity.com/paper/2404.12498/) (2024)
- [DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations](https://mlsanity.com/paper/2602.02137/) (2026)
- [Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning](https://mlsanity.com/paper/2607.16534/) (2026)
- [Robotic Packaging Optimization with Reinforcement Learning](https://mlsanity.com/paper/2303.14693/) (2023)
- [Sustainability of Data Center Digital Twins with Reinforcement Learning](https://mlsanity.com/paper/2404.10786/) (2024)
- [Experimental evaluation of offline reinforcement learning for HVAC control in buildings](https://mlsanity.com/paper/2408.07986/) (2024)
- [MuFlex: A Scalable, Physics-based Platform for Multi-Building Flexibility Analysis and Coordination](https://mlsanity.com/paper/2508.13532/) (2025)

## Abstract (arXiv)

Common approaches to control a data-center cooling system rely on approximated system/environment models that are built upon the knowledge of mechanical cooling and electrical and thermal management. These models are difficult to design and often lead to suboptimal or unstable performance. In this paper, we show how deep reinforcement learning techniques can be used to control the cooling system of a simulated data center. In contrast to common control algorithms, those based on reinforcement learning techniques can optimize a system's performance automatically without the need of explicit model knowledge. Instead, only a reward signal needs to be designed. We evaluated the proposed algorithm on the open source simulation platform EnergyPlus. The experimental results indicate that we can achieve 22% improvement compared to a model-based control algorithm built into the EnergyPlus. To encourage the reproduction of our work as well as future research, we have also publicly released an open-source EnergyPlus wrapper interface directly compatible with existing reinforcement learning frameworks.