Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base Stations
Passively cooled base stations (PCBSs) have emerged to deliver better cost and energy efficiency. However, passive cooling necessitates intelligent thermal control via traffic management, i.e., the instantaneous data traffic or throughput of a PCBS directly impacts its thermal performance. This is p...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Machine Learning in Communications and Networking |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10802970/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850227171744808960 |
|---|---|
| author | Zhanwei Yu Yi Zhao Xiaoli Chu Di Yuan |
| author_facet | Zhanwei Yu Yi Zhao Xiaoli Chu Di Yuan |
| author_sort | Zhanwei Yu |
| collection | DOAJ |
| description | Passively cooled base stations (PCBSs) have emerged to deliver better cost and energy efficiency. However, passive cooling necessitates intelligent thermal control via traffic management, i.e., the instantaneous data traffic or throughput of a PCBS directly impacts its thermal performance. This is particularly challenging for outdoor deployment of PCBSs because the heat dissipation efficiency is uncertain and fluctuates over time. What is more, the PCBSs are interference-coupled in multi-cell scenarios. Thus, a higher-throughput PCBS leads to higher interference to the other PCBSs, which, in turn, would require more resource consumption to meet their respective throughput targets. In this paper, we address online decision-making for maximizing the total downlink throughput for a multi-PCBS system subject to constraints related on operating temperature. We demonstrate that a reinforcement learning (RL) approach, specifically soft actor-critic (SAC), can successfully perform throughput maximization while keeping the PCBSs cool, by adapting the throughput to time-varying heat dissipation conditions. Furthermore, we design a denial and reward mechanism that effectively mitigates the risk of overheating during the exploration phase of RL. Simulation results show that our approach achieves up to 88.6% of the global optimum. This is very promising, as our approach operates without prior knowledge of future heat dissipation efficiency, which is required by the global optimum. |
| format | Article |
| id | doaj-art-fb7404c64d134b4787b4768a4964a397 |
| institution | OA Journals |
| issn | 2831-316X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Machine Learning in Communications and Networking |
| spelling | doaj-art-fb7404c64d134b4787b4768a4964a3972025-08-20T02:04:54ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2025-01-013647910.1109/TMLCN.2024.351761910802970Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base StationsZhanwei Yu0https://orcid.org/0000-0001-7306-8354Yi Zhao1https://orcid.org/0000-0002-6025-3515Xiaoli Chu2https://orcid.org/0000-0003-1863-6149Di Yuan3https://orcid.org/0000-0001-8119-5206Department of Information Technology, Uppsala University, Uppsala, SwedenDepartment of Information Technology, Uppsala University, Uppsala, SwedenDepartment of Electronic and Electrical Engineering, University of Sheffield, Sheffield, U.K.Department of Information Technology, Uppsala University, Uppsala, SwedenPassively cooled base stations (PCBSs) have emerged to deliver better cost and energy efficiency. However, passive cooling necessitates intelligent thermal control via traffic management, i.e., the instantaneous data traffic or throughput of a PCBS directly impacts its thermal performance. This is particularly challenging for outdoor deployment of PCBSs because the heat dissipation efficiency is uncertain and fluctuates over time. What is more, the PCBSs are interference-coupled in multi-cell scenarios. Thus, a higher-throughput PCBS leads to higher interference to the other PCBSs, which, in turn, would require more resource consumption to meet their respective throughput targets. In this paper, we address online decision-making for maximizing the total downlink throughput for a multi-PCBS system subject to constraints related on operating temperature. We demonstrate that a reinforcement learning (RL) approach, specifically soft actor-critic (SAC), can successfully perform throughput maximization while keeping the PCBSs cool, by adapting the throughput to time-varying heat dissipation conditions. Furthermore, we design a denial and reward mechanism that effectively mitigates the risk of overheating during the exploration phase of RL. Simulation results show that our approach achieves up to 88.6% of the global optimum. This is very promising, as our approach operates without prior knowledge of future heat dissipation efficiency, which is required by the global optimum.https://ieeexplore.ieee.org/document/10802970/Reinforcement learninginterferencepassive coolingthroughput maximizationthermal management |
| spellingShingle | Zhanwei Yu Yi Zhao Xiaoli Chu Di Yuan Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base Stations IEEE Transactions on Machine Learning in Communications and Networking Reinforcement learning interference passive cooling throughput maximization thermal management |
| title | Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base Stations |
| title_full | Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base Stations |
| title_fullStr | Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base Stations |
| title_full_unstemmed | Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base Stations |
| title_short | Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base Stations |
| title_sort | online learning for intelligent thermal management of interference coupled and passively cooled base stations |
| topic | Reinforcement learning interference passive cooling throughput maximization thermal management |
| url | https://ieeexplore.ieee.org/document/10802970/ |
| work_keys_str_mv | AT zhanweiyu onlinelearningforintelligentthermalmanagementofinterferencecoupledandpassivelycooledbasestations AT yizhao onlinelearningforintelligentthermalmanagementofinterferencecoupledandpassivelycooledbasestations AT xiaolichu onlinelearningforintelligentthermalmanagementofinterferencecoupledandpassivelycooledbasestations AT diyuan onlinelearningforintelligentthermalmanagementofinterferencecoupledandpassivelycooledbasestations |