CoolEdge: hotspot-relievable warm water cooling for energy-efficient edge datacenters
Qiangyu Pei, Shutong Chen, Qixia Zhang, Xinhui Zhu, Fangming Liu, Ziyang Jia, Yishuo Wang, Yongjie Yuan
Abstract
As the computing frontier drifts to the edge, edge datacenters play a crucial role in supporting various real-time applications. Different from cloud datacenters, the requirements of proximity to end-users, high density, and heterogeneity, present new challenges to cool the edge datacenters efficiently. Although warm water cooling has become a promising cooling technique for this infrastructure, the one-size-fits-all cooling control would lower the cooling efficiency considerably because of the severe thermal imbalance across servers, hardware, and even inside one hardware component in an edge datacenter. In this work, we propose CoolEdge, a hotspot-relievable warm water cooling system for improving the cooling efficiency and saving costs of edge datacenters. Specifically, through the elaborate design of water circulations, CoolEdge can dynamically adjust the water temperature and flow rate for each heterogeneous hardware component to eliminate the hardware-level hotspots. By redesigning cold plates, CoolEdge can quickly disperse the chip-level hotspots without manual intervention. We further quantify the power saving achieved by the warm water cooling theoretically, and propose a custom-designed cooling solution to decide an appropriate water temperature and flow rate periodically. Based on a hardware prototype and real-world traces from SURFsara, the evaluation results show that CoolEdge reduces the cooling energy by 81.81% and 71.92%, respectively, compared with conventional and state-of-the-art water cooling systems.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext df732ca9-df30-4243-ae59-78f50f9cebfeCited by top-tier papers2
- TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud PlatformsJovan Stojkovic, Chaojie Zhang, Íñigo Goiri, Esha Choukse et al.ASPLOS 2025 · 30 citations
- More is Different: Prototyping and Analyzing a New Form of Edge Server with Massive Mobile SoCsLi Zhang, Zhe Fu, Boqing Shi, Xiang Li et al.USENIX ATC 2024
Builds on5
- Cost-Efficient Overclocking in Immersion-Cooled DatacentersMajid Jalili, Ioannis Manousakis, Iñigo Goiri, Pulkit A. Misra et al.ISCA 2021 · 54 citations
- Flex: High-Availability Datacenters With Zero Reserved PowerChaojie Zhang, Alok Gautam Kumbhare, Ioannis Manousakis, Deli Zhang et al.ISCA 2021 · 43 citations
- Gemini: Learning to Manage CPU Power for Latency-Critical Search EnginesLiang Zhou, Laxmi N. Bhuyan, K. K. RamakrishnanMICRO 2020 · 27 citations
- Heat to Power: Thermal Energy Harvesting and Recycling for Warm Water-Cooled DatacentersXinhui Zhu, Weixiang Jiang, Fangming Liu, Qixia Zhang et al.ISCA 2020 · 18 citations
- GreenDIMM: OS-assisted DRAM Power Management for DRAM with a Sub-array Granularity Power-Down StateSeunghak Lee, Ki-Dong Kang, Hwanjun Lee, Hyungwon Park et al.MICRO 2021 · 14 citations
Related papers
- TempSched: A Temperature-Aware Storage Scheduler for Time Series Across Cloud-Edge-DeviceShuangshuang Cui, Hongzhi Wang, Xianglong Liu, Xiaoou DingICDE 2025 · 6 citations
- Online Container Scheduling for Data-intensive Applications in Serverless Edge ComputingXiaojun Shang, Yingling Mao, Yu Liu, Yaodong Huang et al.INFOCOM 2023 · 39 citations
- CooLSM: Distributed and Cooperative Indexing Across Edge and Cloud MachinesNatasha Mittal, Faisal NawabICDE 2021 · 4 citations
- INVAR: Inversion Aware Resource Provisioning and Workload Scheduling for Edge ComputingBin Wang, David Irwin, Prashant J. Shenoy, Don TowsleyINFOCOM 2024 · 11 citations
- RDC: Energy-Efficient Data Center Network Congestion Relief with Topological Reconfigurability at the EdgeWeitao Wang, Dingming Wu, Sushovan Das, Afsaneh Rahbar et al.NSDI 2022 · 14 citations
