Abstract
The growing electricity demand of cloud and edge computing increases operational costs and will soon have a considerable impact on the environment. A possible countermeasure is equipping IT infrastructure directly with on-site renewable energy sources. Yet, particularly smaller data centers may not be able to use all generated power directly at all times, while feeding it into the public grid or energy storage is often not an option. To maximize the usage of renewable excess energy, we propose Cucumber, an admission control policy that accepts delay-tolerant workloads only if they can be computed within their deadlines without the use of grid energy. Using probabilistic forecasting of computational load, energy consumption, and energy production, Cucumber can be configured towards more optimistic or conservative admission. We evaluate our approach on two scenarios using real solar production forecasts for Berlin, Mexico City, and Cape Town in a simulation environment. For scenarios where excess energy was actually available, our results show that Cucumber’s default configuration achieves acceptance rates close to the optimal case and causes 97.0% of accepted workloads to be powered using excess energy, while more conservative admission results in 18.5% reduced acceptance at almost zero grid power usage.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
DeepAR parameters: GRU, 3 Layers, 64 nodes, 0.1 Dropout; 20–30 min training time on commodity hardware.
- 6.
References
Acun, B., et al.: A holistic approach for designing carbon aware datacenters. arXiv:2201.10036 [cs.DC] (2022)
Aksanli, B., Venkatesh, J., Zhang, L., Rosing, T.: Utilizing green energy prediction to schedule mixed batch and service jobs in data centers. In: HotPower 2011 (2011). https://doi.org/10.1145/2039252.2039257
Alencar, D.B., de Mattos Affonso, C., Oliveira, R.C.L., Rodríguez, J.L.M., Leite, J.C., Filho, J.C.R.: Different models for forecasting wind power generation: case study. Energies 10 (2017). https://doi.org/10.3390/en10121976
Bank, W.: State and trends of carbon pricing 2020. Technical report. World Bank, Washington, DC (2020)
Barroso, L.A., Hölzle, U.: The case for energy-proportional computing. Computer 40(12) (2007). https://doi.org/10.1109/MC.2007.443
Bright, J.M., Killinger, S., Lingfors, D., Engerer, N.A.: Improved satellite-derived PV power nowcasting using real-time power data from reference PV systems. Solar Energy 168 (2018). https://doi.org/10.1016/j.solener.2017.10.091
Chen, X., Mohapatra, P., Chen, H.: An admission control scheme for predictable server response time for web accesses. In: WWW. ACM (2001). https://doi.org/10.1145/371920.372156
Chien, A.A., Zhang, C., Nguyen, H.D.: Zero-carbon cloud: research challenges for datacenters as supply-following loads. Technical report CS-TR-2019-08. University of Chicago (2019)
Freitag, C., Berners-Lee, M., Widdicks, K., Knowles, B., Blair, G., Friday, A.: The climate impact of ICT: a review of estimates, trends and regulations. arXiv:2102.02622 [physics.soc-ph] (2021)
Goiri, I., et al.: Matching renewable energy supply and demand in green datacenters. Ad Hoc Netw. 25 (2015). https://doi.org/10.1016/j.adhoc.2014.11.012
Gontarska, K., Geldenhuys, M., Scheinert, D., Wiesner, P., Polze, A., Thamsen, L.: Evaluation of load prediction techniques for distributed stream processing. In: International Conference on Cloud Engineering (IC2E). IEEE (2021). https://doi.org/10.1109/IC2E52221.2021.00023
Google: 24/7 by 2030: Realizing a carbon-free future. Technical report, Google (2020)
Hazemi, F.A.: A hybrid green policy for admission control in web-based applications. In: SoftCOM. IEEE (2013). https://doi.org/10.1109/SoftCOM.2013.6671846
Hirsch, A., Parag, Y., Guerrero, J.: Microgrids: a review of technologies, key drivers, and outstanding issues. Renew. Sustain. Energy Rev. 90 (2018). https://doi.org/10.1016/j.rser.2018.03.040
Kallio-Myers, V., Riihelä, A., Lahtinen, P., Lindfors, A.: Global horizontal irradiance forecast for Finland based on geostationary weather satellite data. Solar Energy 198 (2020). https://doi.org/10.1016/j.solener.2020.01.008
Khalyasmaa, A.I., et al.: Prediction of solar power generation based on random forest regressor model. In: SIBIRCON (2019). https://doi.org/10.1109/SIBIRCON48586.2019.8958063
Koller, R., Verma, A., Neogi, A.: Wattapp: an application aware power meter for shared data centers (2010). https://doi.org/10.1145/1809049.1809055
Kordkheili, R.A., Hinkle, T., Gandhi, M., der Pas, N.V., Davari, P.: On-site power generation for data centers. Technical report, Sust. Digital Infrastructure Alliance (2021)
Li, Q., et al.: Prediction of power generation of two 30 kw horizontal axis wind turbines with gaussian model. Energy 231 (2021). https://doi.org/10.1016/j.energy.2021.121075
Li, W., et al.: On enabling sustainable edge computing with renewable energy resources. IEEE Commun. Mag. 56(5) (2018). https://doi.org/10.1109/MCOM.2018.1700888
Liu, L., Sun, H., Li, C., Li, T., Xin, J., Zheng, N.: Managing battery aging for high energy availability in green datacenters. IEEE Trans. Parallel Distrib. Syst. 28(12) (2017). https://doi.org/10.1109/TPDS.2017.2712778
Luo, J., Rao, L., Liu, X.: Temporal load balancing with service delay guarantees for data center energy cost optimization. IEEE Trans. Parallel Distrib. Syst. 25(3) (2014). https://doi.org/10.1109/TPDS.2013.69
Masanet, E., Shehabi, A., Lei, N., Smith, S., Koomey, J.: Recalibrating global data center energy-use estimates. Science 367 (2020). https://doi.org/10.1126/science.aba3758
Radovanovic, A., Chen, B., Talukdar, S., Roy, B., Duarte, A., Shahbazi, M.: Power modeling for effective datacenter planning and compute management. IEEE Trans. Smart Grid (2021). https://doi.org/10.1109/TSG.2021.3125275
Radovanovic, A., et al.: Carbon-aware computing for datacenters. IEEE Trans. Power Syst. (2022). https://doi.org/10.1109/TPWRS.2022.3173250
Salinas, D., Flunkert, V., Gasthaus, J., Januschowski, T.: Deepar: probabilistic forecasting with autoregressive recurrent networks. Int. J. Forecast. 36(3) (2020). https://doi.org/10.1016/j.ijforecast.2019.07.001
Toosi, A.N., Qu, C., de Assunção, M.D., Buyya, R.: Renewable-aware geographical load balancing of web applications for sustainable data centers. J. Netw. Comput. Appl. 83 (2017). https://doi.org/10.1016/j.jnca.2017.01.036
Verbois, H., Rusydi, A., Thiery, A.: Probabilistic forecasting of day-ahead solar irradiance using quantile gradient boosting. Solar Energy 173 (2018). https://doi.org/10.1016/j.solener.2018.07.071
Weng, Q., et al.: MLaaS in the wild: workload analysis and scheduling in large-scale heterogeneous GPU clusters. In: NSDI, vol. 22 (2022)
Wiesner, P.: Artifact and instructions to generate experimental results for the Euro-Par 2022 paper: “cucumber: renewable-aware admission control for delay-tolerant cloud and edge workloads”. Figshare: https://doi.org/10.6084/m9.figshare.19984556
Wiesner, P., Behnke, I., Scheinert, D., Gontarska, K., Thamsen, L.: Let’s wait awhile: how temporal workload shifting can reduce carbon emissions in the cloud. In: Middleware2021. ACM (2021). https://doi.org/10.1145/3464298.3493399
Wiesner, P., Thamsen, L.: LEAF: simulating large energy-aware fog computing environments. In: 5th International Conference on Fog and Edge Computing (ICFEC). IEEE (2021). https://doi.org/10.1109/ICFEC51620.2021.00012
Yuan, H., Bi, J., Tan, W., Li, B.H.: CAWSAC: cost-aware workload scheduling and admission control for distributed cloud data centers. IEEE Trans. Autom. Sci. Eng. 13(2) (2016). https://doi.org/10.1109/TASE.2015.2427234
Zhang, H., Liu, Y., Yan, J., Han, S., Li, L., Long, Q.: Improved deep mixture density network for regional wind power probabilistic forecasting. IEEE Trans. Power Syst. 35(4) (2020). https://doi.org/10.1109/TPWRS.2020.2971607
Acknowledgments and Data Availability Statement
The datasets and code generated and analyzed in this paper are available in the Figshare repository: https://doi.org/10.6084/m9.figshare.19984556 [30].
We sincerely thank Solcast for the uncomplicated and free access to their solar forecast APIs. This research was supported by the German Academic Exchange Service (DAAD) as ide3a and the German Ministry for Education and Research (BMBF) as BIFOLD (grant 01IS18025A) and Software Campus (01IS17050).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Wiesner, P., Scheinert, D., Wittkopp, T., Thamsen, L., Kao, O. (2022). Cucumber: Renewable-Aware Admission Control for Delay-Tolerant Cloud and Edge Workloads. In: Cano, J., Trinder, P. (eds) Euro-Par 2022: Parallel Processing. Euro-Par 2022. Lecture Notes in Computer Science, vol 13440. Springer, Cham. https://doi.org/10.1007/978-3-031-12597-3_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-12597-3_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12596-6
Online ISBN: 978-3-031-12597-3
eBook Packages: Computer ScienceComputer Science (R0)