ABSTRACT
Data centers can participate in demand-response schemes by reducing their demand, however, at the expense of the agreed-upon performance of their IT services defined by the SLAs. The successful application of such schemes necessitates a careful analysis so that the amount of degradation of the SLAs with respect to power savings can be quantified helping the data center operators to set up the optimal configuration. In this paper, we study and analyze a system consisting of a data center, its operator, and IT clients under the consideration of relaxed SLAs. For this purpose, we consider a data center system consisting of two heterogeneous pools of servers, where each server is modeled using the single-server system with a power-saving inactive state, non-zero (random) activation/deactivation times, and hot standby state. Making use of the distributional Little’s Law, derive the steady-state performance (in terms of response time distribution) and average power demand and study the power-performance trade-off in an explicit way. Numerical results illustrate the model’s theoretical properties, under different considerations of low, medium, and high workload utilization rates.
- Dlzar Al Kez, Aoife Foley, Faraedoon Ahmed, and John Morrow. 2022. Data Center Potential Flexibilities and Challenges for Demand Response to Facilitate 100% Inverter-Based Resources: A Review. SSRN Electronic Journal (2022), 26 pages. https://doi.org/10.2139/ssrn.4269631Google ScholarCross Ref
- Dlzar Al Kez, Aoife M Foley, Faraedoon W Ahmed, Mark O’Malley, and SM Muyeen. 2021. Potential of data centers for fast frequency response services in synchronously isolated power systems. Renewable and Sustainable Energy Reviews 151 (2021), 111547.Google ScholarCross Ref
- OpenADR Alliance. 2013. OpenADR 2.0 Profile Specification B Profile. Technical Report 20120912-1. OpenADR Alliance.Google Scholar
- Shahab Bahrami, Vincent WS Wong, and Jianwei Huang. 2018. Data center demand response in deregulated electricity markets. IEEE Transactions on Smart Grid 10, 3 (2018), 2820–2832.Google ScholarCross Ref
- Robert Basmadjian. 2019. Flexibility-Based Energy and Demand Management in Data Centers: A Case Study for Cloud Computing. Energies 12, 17, Article 3301 (2019), 22 pages. https://doi.org/10.3390/en12173301Google ScholarCross Ref
- Robert Basmadjian, Juan Felipe Botero, Giovanni Giuliani, Xavier Hesselbach, Sonja Klingert, and Hermann De Meer. 2018. Making Data Centers Fit for Demand Response: Introducing GreenSDA and GreenSLA Contracts. IEEE Transactions on Smart Grid 9, 4 (July 2018), 3453–3464. https://doi.org/10.1109/TSG.2016.2632526Google ScholarCross Ref
- Robert Basmadjian, Pascal Bouvry, Georges Da Costa, László Gyarmati, Dzmitry Kliazovich, Sébastien Lafond, Laurent Lefèvre, Hermann De Meer, Jean-Marc Pierson, Rastin Pries, Jordi Torres, Tuan Anh Trinh, and Samee Ullah Khan. 2015. Green Data Centers. John Wiley & Sons, Ltd, Hoboken, New Jersey, Chapter 6, 159–196. https://doi.org/10.1002/9781118981122.ch6Google Scholar
- Robert Basmadjian and Hermann de Meer. 2018. Modelling and Analysing Conservative Governor of DVFS-Enabled Processors. In Proceedings of the Ninth International Conference on Future Energy Systems (Karlsruhe, Germany) (e-Energy ’18). Association for Computing Machinery, New York, NY, USA, 519–525. https://doi.org/10.1145/3208903.3213778Google ScholarDigital Library
- Robert Basmadjian, Florian Niedermeier, and Hermann de Meer. 2016. Modelling Performance and Power Consumption of Utilisation-Based DVFS Using M/M/1 Queues. In Proceedings of the Seventh International Conference on Future Energy Systems (Waterloo, Ontario, Canada) (e-Energy ’16). Association for Computing Machinery, New York, NY, USA, Article 14, 11 pages. https://doi.org/10.1145/2934328.2934342Google ScholarDigital Library
- Min Chen, Ciwei Gao, Meng Song, Songsong Chen, Dezhi Li, and Qiang Liu. 2020. Internet data centers participating in demand response: A comprehensive review. Renewable and Sustainable Energy Reviews 117 (2020), 109466.Google ScholarCross Ref
- Mark Van der Boor, Sem C. Borst, Johan S. H. Van Leeuwaarden, and Debankur Mukherjee. 2022. Scalable Load Balancing in Networked Systems: A Survey of Recent Advances. SIAM Rev. 64, 3 (2022), 554–622. https://doi.org/10.1137/20M1323746Google ScholarDigital Library
- FERC. 2013. Assessment of Demand Response and Advanced Metering. Technical Report. Federal Energy Regulatory Commission. https://www.ferc.gov/sites/default/files/2020-05/oct-demand-response.pdfGoogle Scholar
- Jean-Michel Fourneau. 2020. Modeling Green Data-Centers and Jobs Balancing with Energy Packet Networks and Interrupted Poisson Energy Arrivals. SN Computer Science 1, 1 (Jan. 2020), 28. https://doi.org/10.1007/s42979-019-0029-5Google ScholarDigital Library
- Anshul Gandhi, Varun Gupta, Mor Harchol-Balter, and Michael A. Kozuch. 2010. Optimality analysis of energy-performance trade-off for server farm management. Performance Evaluation 67, 11 (2010), 1155–1171. https://doi.org/10.1016/j.peva.2010.08.009Google ScholarDigital Library
- Anshul Gandhi, Mor Harchol-Balter, and Ivo Adan. 2010. Server Farms with Setup Costs. Perform. Eval. 67, 11 (Nov. 2010), 1123–1138. https://doi.org/10.1016/j.peva.2010.07.004Google ScholarDigital Library
- Anshul Gandhi, Mor Harchol-Balter, Rajarshi Das, Jeffrey O. Kephart, and Charles Lefurgy. 2009. Power capping via forced idleness. In Proceedings of Workshop on Energy Efficient Design. Computer Science Department, School of Computer Science, Pittsburg, Article 868, 6 pages.Google Scholar
- M. E. Gebrehiwot, S. Aalto, and P. Lassila. 2017. Energy Efficient Load Balancing in Web Server Clusters. In 2017 29th International Teletraffic Congress (ITC 29), Vol. 3. IEEE, Genoa, Italy, 13–18. https://doi.org/10.23919/ITC.2017.8065804Google Scholar
- Clark W. Gellings and John H. Chamberlin. 1988. Demand-side management: concepts and methods. Fairmont Press, Lilburn, Ga.Google Scholar
- Girish Ghatikar, Venkata Ganti, Nance Matson, and Mary Ann Piette. 2012. Demand Response Opportunities and Enabling Technologies for Data Centers: Findings from Field Studies. Technical Report. Lawrence Berkeley National Laboratory.Google Scholar
- Girish Ghatikar, Mary Ann Piette, Sydny Fujita, Aimee McKane, Junqiao Han Dudley, and Anthony Radspieler. 2010. Demand Response and Open Automated Demand Response Opportunities for Data Centers. Technical Report. Lawrence Berkeley National Laboratory.Google Scholar
- Alexander Golovin and Alexander Rumyantsev. 2022. Energy Efficiency of a Single-Server with Inactive State by Matrix-Analytic Method. In Information Technologies and Mathematical Modelling. Queueing Theory and Applications, Alexander Dudin, Anatoly Nazarov, and Alexander Moiseev (Eds.). Springer International Publishing, Cham, 172–184.Google Scholar
- J Keilson and L.D Servi. 1988. A distributional form of Little’s Law. Operations Research Letters 7, 5 (1988), 223–227. https://doi.org/10.1016/0167-6377(88)90035-1Google ScholarDigital Library
- Paul J. Kuehn and Maggie Mashaly. 2019. DVFS-Power Management and Performance Engineering of Data Center Server Clusters. In 2019 15th Annual Conference on Wireless On-demand Network Systems and Services (WONS). IEEE, Wengen, Switzerland, 91–98. https://doi.org/10.23919/WONS.2019.8795470Google Scholar
- Oracle 2020. Oracle’s Power Calculators. Oracle. Retrieved May 5, 2023 from https://www.oracle.com/it-infrastructure/power-calculators/Google Scholar
- Riccardo Pinciroli, Ahsan Ali, Feng Yan, and Evgenia Smirni. 2021. CEDULE+: Resource Management for Burstable Cloud Instances Using Predictive Analytics. IEEE Transactions on Network and Service Management 18, 1 (March 2021), 945–957. https://doi.org/10.1109/TNSM.2020.3039942Google ScholarDigital Library
- Alexander Rumyantsev, Robert Basmadjian, Alexander Golovin, and Sergey Astafiev. 2021. A Three-Level Modelling Approach for Asynchronous Speed Scaling in High-Performance Data Centres. In Proceedings of the Twelfth ACM International Conference on Future Energy Systems(e-Energy ’21). Association for Computing Machinery, New York, NY, USA, 417–423. https://doi.org/10.1145/3447555.3466580Google ScholarDigital Library
- Alexander Rumyantsev, Polina Zueva, Ksenia Kalinina, and Alexander Golovin. 2018. Evaluating a Single-Server Queue with Asynchronous Speed Scaling. In Measurement, Modelling and Evaluation of Computing Systems. Lecture Notes in Computer Science, Vol. 10740. Springer International Publishing, Springer, Cham, 157–172. https://doi.org/10.1007/978-3-319-74947-1_11Google Scholar
- Shengquan Wang, Jian-Jia Chen, Jun Liu, and Xue Liu. 2010. Power Saving Design for Servers under Response Time Constraint. In 2010 22nd Euromicro Conference on Real-Time Systems. IEEE, Brussels, Belgium, 123–132. https://doi.org/10.1109/ECRTS.2010.31Google ScholarDigital Library
- Xi Zheng, Sheng Zhou, Zhiyuan Jiang, and Zhisheng Niu. 2019. Closed-Form Analysis of Non-Linear Age of Information in Status Updates With an Energy Harvesting Transmitter. Ieee Transactions on Wireless Communications 18, 8 (Aug. 2019), 4129–4142. https://doi.org/10.1109/TWC.2019.2921372 Place: Piscataway Publisher: Ieee-Inst Electrical Electronics Engineers Inc WOS:000480661000026.Google ScholarDigital Library
Index Terms
- Little’s Law in a Single-Server System with Inactive State for Demand-Response in Data Centers with Green SLAs
Recommendations
The use of the distributional Little's law in the computational analysis of discrete-time GI/G/1 and GI/D/c queues
In this paper, we first establish a discrete-time version of what is called the distributional Little's law, a relation between the stationary distributions of the number of customers in a system (or queue length) and the number of slots a customer ...
Power Budgeting Techniques for Data Centers
The development of cloud computing and data science result in rapid increases of number and scale of data centers. Because of cost and sustainability concerns, energy efficiency has been a major goal for data center architects. Focusing on reducing the ...
Techniques for energy-efficient power budgeting in data centers
DAC '13: Proceedings of the 50th Annual Design Automation ConferenceWe propose techniques for power budgeting in data centers, where a large power budget is allocated among the servers and the cooling units such that the aggregate performance of the entire center is maximized. Maximizing the performance for a given ...
Comments