ABSTRACT
With the rapid development of data center, it is urgent to reduce energy consumption from the perspective of central cooling plant. At the same time, with the deepening application of clustering methods in data analysis, this study combines the K-means clustering method in machine learning with the energy consumption simulation software, DeST and applies it to actual case. The weather data of whole year are clustered into 29 typical daily patterns in Changzhou to study the load characteristic. It is found that there are 9 operation modes in the data center. The impact of hourly weather data changes on the external load of the data center is analyzed. The positive and negative impact of the temperature on the load of the following day are 4.96 % and -5.73 % in the heating season, 3.72 % and -2.63 % in the cooling season, which can be ignored. The cooling load of IT equipment accounts for a large proportion while the external load of hot and cold only accounts for 5.02 % and -5.73 % in the data center. Due to its 24-hour operation, the annual load change is relatively stable. The accuracy of load prediction is 56.60 %.
- L. N. Yang, P. Zhao, P. Z. Wang, “Research on predicting model of energy consumption in data center based on GRU neural network,” Electric Power ICT., vol.19, no.3, pp.10-18,2021, doi: 10.16543/j.2095-641x.electric.power.ict.2021.03.002.Google ScholarCross Ref
- H. D. Cheng, H. X. Chen, S. G. Shao, , “Comprehensive COP evaluation system for energy efficiency of data center cooling system,” Journal of Refrigeration, vol.41, no.6, pp.77-84.,2020, doi:10. 3969 /j. issn.0253-4339.2020.06.077.Google Scholar
- Q. J. Wang, “Energy saving control optimization analysis of HVAC water cooling system in data center,” Energy Conservation and Environmental Protection, no.9, pp.41-43,2022.Google Scholar
- R. H. Ding, C. G. Cui, Y. H. Wang, , “Air conditioning system optimization in data center based on deep reinforcement learning,” Cryogenics/Refrigeration, vol.50, no.9, pp.79-85+100,2022, doi:10.16711 /j.1001-7100. 2022.09.013.Google Scholar
- Y. J. Cho, B. R. Park, J. Y. Hyun , “Development of an adaptive artificial neural network model and optimal control algorithm for a data center cyber-physical system,” Building and Environment (Feb.), vol.210,2022, doi: 10.1016/j.buildenv.2021.108704.Google ScholarCross Ref
- Z. X. Huang, “Data center air conditioning system design and energy-saving technical measures,” Building Energy Conservation, vol.6, no.3, pp.7-10, 2022.Google Scholar
- H. X. Shao, Z. Su, J. Bian, “Energy saving research on the envelope of data center rooms in different climate zones,” HV&AC, vol.52, no.3, pp.57-61,2022, doi:10.19991/jhvac1971.2022.03.08.Google ScholarCross Ref
- X. J. Cheng, B. Liu, “Application of energy saving technology on air conditioning system in data center,” Building Energy & Environment, vol.40, no.7, pp.52-55,2021.Google Scholar
- C. C. Zhou, F. Zhang, Z. Yuan, , “Study on load forecasting to data centers of high-power density based on power usage effectiveness,” IOP Conference Series Earth and Environmental Science, vol.40,2016, doi:10.1088/1755-1315/40/1/012053.Google ScholarCross Ref
- S. Taheri, M. Goudarzi, O. Yoshie, “Learning-based power prediction for geo-distributed Data Centers: weather parameter analysis,” Journal of Big Data, vol.7, no.1, pp.1-16, 2020, doi:10.1186/s40537-020-0284-2.Google ScholarCross Ref
- J. S. Wu, S. F. Zhang, X. M. Xu, , “Short-term power load forecasting method of data centers considering PUE,” Journal of Harbin University of Science and Technology, vol.26, no.6, pp.1-9, 2021, doi:10. 15938 /j. jhust.2021.06.001.Google Scholar
- X. Wu, Z. Tian, C. Z. Tian, , “Generation method of hourly outdoor design parameters for heating and air-conditioning loads calculation,” Building Science, vol.38, no.6, pp.16-23, 2022, doi:10.13614 /j. cnki.11-1962 /tu.2022.06.03.Google Scholar
- H. Y. Yang, Q. R. Liu, Y. Q. Ruan, “Selection of typical daily cooling and heating load of CCHP system based on k-means clustering algorithm,” Thermal Power Generation, vol.50, no.3, pp.84-90,2021, doi: 10.19666/j.rlfd.202005135.Google ScholarCross Ref
- J. Shi, K. H. Nan, Q. Zhou, , “Research on grouped load forecasting based on K-means clustering algorithm in big data environment,” Power Systems and Big Data, vol.23, no.6, pp.9-16,2020, doi: 10.19317/j.cnki.1008-083x.2020.06.002.Google ScholarCross Ref
- D. N. Liu, Y. Zhang, X. F. Peng, , “Clustering prediction of electric vehicle charging load considering similar days and meteorological factors,” Electric Power Construction, vol.42, no.2, pp.43-49,2021, doi: 10. 12204 /j.issn. 1000-7229. 2021. 02. 006.Google Scholar
Index Terms
- Data Center Cooling Load Prediction and Analysis based on Weather Data Clustering
Recommendations
Software for estimating reference evapotranspiration using limited weather data
The FAO-56 Penman-Monteith combination equation (FAO-56 PM) has been recommended as the standard equation for estimating reference evapotranspiration (ET"0). The FAO-56 PM equation requires the numerous weather data that are not available in the most of ...
An incremental clustering pattern sequence-based short-term load prediction for cloud computing
Short-term load prediction is a significant cost-optimal resource allocation and energy saving approach for a cloud computing environment. Traditional linear or nonlinear prediction models that forecast future load directly from historical information ...
Energy Efficient Free Cooling System for Data Centers
CLOUDCOM '11: Proceedings of the 2011 IEEE Third International Conference on Cloud Computing Technology and ScienceA data center is a facility used to keep computer related equipments. It is estimated that heat production rate of the data center is doubled in every two years and hence the inevitability of the cooling system gets increased. In due course power ...
Comments