Rethinking Low-Carbon Edge Computing System Design with Renewable Energy Sharing
Pages 950 - 960
Abstract
The geographically distributed edge servers can naturally draw power from nearby renewable energy (RE) generators. Complemented by the dynamic scheduling of energy storage batteries, edge service providers (ESPs) can thus build low- or even zero-carbon edge computing systems. Nevertheless, the distributed and heterogeneous nature of edge computing systems, as well as the limited information sharing among ESPs, leads to a more complex battery planning problem than that in cloud computing. The unpredictability of RE resources further complicates the problem, making conventional model-based approaches ineffective. To this end, we propose a multi-agent deep reinforcement learning (MADRL) approach for the independent decision making of individual ESPs. Particularly, MADRL takes privacy into account by ensuring that no sensitive information is disclosed among ESPs. For better model training, we further customize the invalid action masking and develop action transformation techniques based on segmented linear optimization. Extensive experiments demonstrate that, with our proposed approach, the overall carbon emission of edge computing systems can be significantly reduced (by over 60%) while maintaining acceptable operation costs in battery scheduling.
References
[1]
Baris Aksanli, Tajana Rosing, and Eddie Pettis. 2013. Distributed battery control for peak power shaving in datacenters. In Proc. the 2013 IEEE International Green Computing Conference. IEEE, 1–8.
[2]
Xiaofeng Cao, Guoming Tang, Deke Guo, Yan Li, and Weiming Zhang. 2020. Edge federation: Towards an integrated service provisioning model. IEEE/ACM Transactions on Networking 28, 3 (2020), 1116–1129.
[3]
Yujie Cao, Ming Cheng, Sufang Zhang, Hongju Mao, Peng Wang, Chao Li, Yihui Feng, and Zhaohao Ding. 2022. Data-driven flexibility assessment for internet data center towards periodic batch workloads. Applied Energy 324 (2022), 119665.
[4]
Chi-Kin Chau, Guanglin Zhang, and Minghua Chen. 2016. Cost minimizing online algorithms for energy storage management with worst-case guarantee. IEEE Transactions on Smart Grid 7, 6 (2016), 2691–2702.
[5]
Yinghao Chu, Bryan Urquhart, Seyyed MI Gohari, Hugo TC Pedro, Jan Kleissl, and Carlos FM Coimbra. 2015. Short-term reforecasting of power output from a 48 MWe solar PV plant. Solar Energy 112 (2015), 68–77.
[6]
Microsoft corp.2019. Making Data Centers Part of Europe’s Sustainable Energy Transformation. https://blogs.microsoft.com/eupolicy/2019/06/18/data-centers-sustainable-energy-transformation.
[7]
Mehiar Dabbagh, Bechir Hamdaoui, Ammar Rayes, and Mohsen Guizani. 2017. Shaving data center power demand peaks through energy storage and workload shifting control. IEEE Transactions on Cloud Computing 7, 4 (2017), 1095–1108.
[8]
Miyuru Dayarathna, Yonggang Wen, and Rui Fan. 2015. Data center energy consumption modeling: A survey. IEEE Communications surveys & tutorials 18, 1 (2015), 732–794.
[9]
Peter Xiang Gao, Andrew R Curtis, Bernard Wong, and Srinivasan Keshav. 2012. It’s not easy being green. Proc. of the ACM SIGCOMM 42, 4 (2012), 211–222.
[10]
Íñigo Goiri, William Katsak, Kien Le, Thu D Nguyen, and Ricardo Bianchini. 2013. Parasol and greenswitch: Managing datacenters powered by renewable energy. ACM SIGPLAN Notices 48, 4 (2013), 51–64.
[11]
Faranak Golestaneh, Pierre Pinson, and Hoay Beng Gooi. 2016. Very short-term nonparametric probabilistic forecasting of renewable energy generation—With application to solar energy. IEEE Transactions on Power Systems 31, 5 (2016), 3850–3863.
[12]
Chonglin Gu, Hejiao Huang, and Xiaohua Jia. 2016. Green scheduling for cloud data centers using ESDs to store renewable energy. In Proc. of the 2016 IEEE ICC. IEEE, 1–7.
[13]
Lin Gu, Weiying Zhang, Zhongkui Wang, Deze Zeng, and Hai Jin. 2022. Service management and energy scheduling toward low-carbon edge computing. IEEE Transactions on Sustainable Computing 8, 1 (2022), 109–119.
[14]
Fengxian Guo, Liangde Ma, Heli Zhang, Hong Ji, and Xi Li. 2018. Joint load management and resource allocation in the energy harvesting powered small cell networks with mobile edge computing. In Proc. of the IEEE INFOCOM. IEEE, 299–304.
[15]
Yuanxiong Guo and Yuguang Fang. 2012. Electricity cost saving strategy in data centers by using energy storage. IEEE Transactions on Parallel and Distributed Systems 24, 6 (2012), 1149–1160.
[16]
Huaiwen He and Hong Shen. 2021. Minimizing the operation cost of distributed green data centers with energy storage under carbon capping. J. Comput. System Sci. 118 (2021), 28–52.
[17]
Amazon inc.2022. Sustainable Business of Amazon Cloud. https://sustainability.aboutamazon.com/products-services/the-cloud?energyType=true.
[18]
CAISO inc.2023. California ISO.https://www.caiso.com/.
[19]
Google inc.2023. Announcing ‘Round-the-clock Clean Energy for Cloud. https://cloud.google.com/blog/topics/inside-google-cloud/announcing-round-the-clock-clean-energy-for-cloud.
[20]
Nordunet Inc.2024. NORDUNet. https://stats.nordu.net/.
[21]
Unwired Labs. 2024. OpenCelliD.https://opencellid.org/.
[22]
Fang Liu, Guoming Tang, Youhuizi Li, Zhiping Cai, Xingzhou Zhang, and Tongqing Zhou. 2019. A survey on edge computing systems and tools. Proc. IEEE 107, 8 (2019), 1537–1562.
[23]
Longjun Liu, Hongbin Sun, Chao Li, Tao Li, Jingmin Xin, and Nanning Zheng. 2017. Managing battery aging for high energy availability in green datacenters. IEEE Transactions on Parallel and Distributed Systems 28, 12 (2017), 3521–3536.
[24]
Huirong Ma, Peng Huang, Zhi Zhou, Xiaoxi Zhang, and Xu Chen. 2022. GreenEdge: Joint green energy scheduling and dynamic task offloading in multi-tier edge computing systems. IEEE Transactions on Vehicular Technology 71, 4 (2022), 4322–4335.
[25]
Kendall Mongird, Vilayanur V Viswanathan, Patrick J Balducci, Md Jan E Alam, Vanshika Fotedar, V S Koritarov, and Boualem Hadjerioua. 2019. Energy storage technology and cost characterization report. Technical Report. Pacific Northwest National Lab, Richland, WA, US.
[26]
Darshan S Palasamudram, Ramesh K Sitaraman, Bhuvan Urgaonkar, and Rahul Urgaonkar. 2012. Using batteries to reduce the power costs of internet-scale distributed networks. In Proc. of the Third ACM SoCC. 1–14.
[27]
PSCSC. 2024. Rate 23 - industrial power service.https://etariff.psc.sc.gov/Organization/TariffDetail/150?OrgId= 411.
[28]
Shuomiao Su, Zhi Zhou, Tao Ouyang, Ruiting Zhou, and Xu Chen. 2023. Learning to be green: Carbon-aware online control for edge intelligence with colocated learning and inference. In Proc. of the IEEE 43rd ICDCS. IEEE, 567–578.
[29]
Peter Sunehag, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, Nicolas Sonnerat, Joel Z Leibo, Karl Tuyls, 2017. Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017).
[30]
Cheng-Yen Tang, Chien-Hung Liu, Woei-Kae Chen, and Shingchern D You. 2020. Implementing action mask in proximal policy optimization (PPO) algorithm. ICT Express 6, 3 (2020), 200–203.
[31]
Guoming Tang, Deke Guo, and Kui Wu. 2022. Software-Defined Power Supply to Geo-Distributed Edge DCs. In GreenEdge: New Perspectives to Energy Management and Supply in Mobile Edge Computing. Springer, 91–101.
[32]
Guoming Tang, Yi Wang, and Hongyu Lu. 2020. Shiftguard: Towards reliable 5g network by optimal backup power allocation. In Prof. of the IEEE SmartGridComm. IEEE, 1–6.
[33]
Guoming Tang, Hao Yuan, Deke Guo, Kui Wu, and Yi Wang. 2021. Reusing backup batteries as bess for power demand reshaping in 5g and beyond. In Proc. of the IEEE INFOCOM. IEEE, 1–10.
[34]
Rahul Urgaonkar, Bhuvan Urgaonkar, Michael J Neely, and Anand Sivasubramaniam. 2011. Optimal power cost management using stored energy in data centers. In Proc. of the ACM SIGMETRICS. 221–232.
[35]
Haoyu Wang, Haiying Shen, Jiechao Gao, Kevin Zheng, and Xiaoying Li. 2021. Multi-agent reinforcement learning based distributed renewable energy matching for datacenters. In Proc. of the 50th ICPP. 1–10.
[36]
Philipp Wiesner, Ramin Khalili, Dennis Grinwald, Pratik Agrawal, Lauritz Thamsen, and Odej Kao. 2024. Fedzero: Leveraging renewable excess energy in federated learning. In Proc. of the 15th ACM International Conference on Future and Sustainable Energy Systems. 373–385.
[37]
Minxian Xu and Rajkumar Buyya. 2020. Managing renewable energy and carbon footprint in multi-cloud computing environments. J. Parallel and Distrib. Comput. 135 (2020), 191–202.
[38]
Minxian Xu, Adel N. Toosi, Behrooz Bahrani, Reza Razzaghi, and Martin Singh. 2019. Optimized renewable energy use in green cloud data centers. In Proc. of the 17th ICSOC. Springer, 314–330.
[39]
Yan Yin, Junmin Wu, Xu Zhou, Lieven Eeckhout, Amer Qouneh, Tao Li, and Zhibin Yu. 2019. Copa: Highly cost-effective power back-up for green datacenters. IEEE Transactions on Parallel and Distributed Systems 31, 4 (2019), 967–980.
[40]
Hao Yuan, Guoming Tang, Deke Guo, Kui Wu, Xun Shao, Keping Yu, and Wei Wei. 2021. Bess aided renewable energy supply using deep reinforcement learning for 5G and beyond. IEEE Transactions on Green Communications and Networking 6, 2 (2021), 669–684.
[41]
Kuo Zhang, Peijian Wang, Ning Gu, and Thu D Nguyen. 2022. GreenDRL: managing green datacenters using deep reinforcement learning. In Proc. of the 13th SoCC. 445–460.
[42]
Daming Zhao and Jiantao Zhou. 2022. An energy and carbon-aware algorithm for renewable energy usage maximization in distributed cloud data centers. J. Parallel and Distrib. Comput. 165 (2022), 156–166.
[43]
Dongyu Zheng, Lei Liu, Guoming Tang, Yi Wang, and Weichao Li. 2023. Power Demand Reshaping Using Energy Storage for Distributed Edge Clouds. IEEE Transactions on Parallel and Distributed Systems (2023).
[44]
Hankz Hankui Zhuo, Wenfeng Feng, Yufeng Lin, Qian Xu, and Qiang Yang. 2019. Federated deep reinforcement learning. arXiv preprint arXiv:1901.08277 (2019).
Index Terms
- Rethinking Low-Carbon Edge Computing System Design with Renewable Energy Sharing
Recommendations
Managing renewable energy and carbon footprint in multi-cloud computing environments
AbstractCloud computing offers attractive features for both service providers and customers. Users benefit from the pay-as-you-go model by saving expenditures and service providers are deploying their services to cloud data centers to reduce ...
Highlights- Model considering power consumption, renewable energy and carbon footprint.
- ...
Development of Renewable Energy System for Enhancing Reliability of Power
AbstractMeeting global energy demands has been a major challenge due to the shortage of primary energy resources. Adding renewable energy resources to the grid has become increasingly popular. During peak hours of energy demand, the sun's irradiance is ...
Modeling the Impact of Renewable Energy Technologies on Atmospheric Carbon Dioxide Mitigation
AbstractEnergy-related carbon dioxide () emissions have significantly contributed to the increase in atmospheric concentrations. Curbing the carbon dioxide emissions associated with energy generation is crucial for reducing the radiative forcing of ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
August 2024
1279 pages
ISBN:9798400717932
DOI:10.1145/3673038
Copyright © 2024 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 12 August 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- National Natural Science Foundation of China under Grant
- Peng Cheng Laboratory The Major Key Project of PCL
- Guangdong High-Level Talents Special Support Program
- National Key Research and Development Program of China
Conference
ICPP '24
ICPP '24: the 53rd International Conference on Parallel Processing
August 12 - 15, 2024
Gotland, Sweden
Acceptance Rates
Overall Acceptance Rate 91 of 313 submissions, 29%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 249Total Downloads
- Downloads (Last 12 months)249
- Downloads (Last 6 weeks)74
Reflects downloads up to 25 Dec 2024
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in