Refrigeration equipment model construction based in data center cooling station

ABSTRACTABSTRACTThe energy consumption of data centers (DCs) is rising year by year, and cooling station accounts for more than 40% of the total DCs’ energy consumption, which has a huge energy-saving potential. Building models for whole DCs’ cooling station can help predict total power to improve the energy efficiency of the system, before this, establishing a single model for each component is a basic work. This paper mainly studies the chiller and cooling tower models and compares the predictive performance of the empirical model, hybrid model, and neural network model of chillers and cooling towers. Giving the model selection scheme of the chiller and cooling tower for the establishment of the whole system of the refrigeration station. For the chiller model, the Yoshida function model in empirical models has the highest accuracy with a mean square error of 0.0592, followed by the neural network model with a mean square error of 0.2, and the hybrid model has a lower accuracy than the former two models. For the cooling tower model, the empirical models and the neural network model have similar accuracy, and both are higher than the hybrid model.KEYWORDS: Data centercooling towerchillerempirical modelnerual networkhybrid model AcknowledgementsThis work has been supported by the National Natural Science Foundation of China (Grant numbers: 51876161), Key R&D projects in Shaanxi Province (S2021-YF-GXZD-0024), and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China (No.51721004). Thanks to Kunfeng Zhao for his valuable comments in the process of drafting and revising the paper.Disclosure statementNo potential conflict of interest was reported by the author(s).NomenclatureCOPCoefficientofPerformanceTwiEvaporatorinletwatertemperature,∘CTciCondenserinletwatertemperature,∘CQrefChillercapacityatfullloadratedreferencevalue,WTwoEvaporatoroutletwatertemperature,∘CPrefChillerinputpoweratfullloadcondition,WPChillerinputpower,WTci_edRatedcondenserinletwatertemperature,∘CTwo_edRatedevaporatoroutletwatertemperature,∘CmcwCondenserwatermassflowrate,kg/smewEvaporatorwatermassflowrate,kg/smcw_edRatedcondenserwatermassflowrate,kg/smew_edRatedevaporatorwatermassflowrate,kg/sAPPTowerapporachtemperature,∘CTrWatertemperaturedecrease,∘CratioWatermassflowtoairmassflowm_airAirmassflowrate,kg/sm,nRegressionparametersai−jiRegressionparametersQCoolingcapacity,WmwaterWatermassflowrate,kg/smairedRatedairmassflowrate,kg/smwateredRatedwatermassflowrate,kg/shEnthalpy,J/kgzElevation,mkwMasstransfercoefficient,kg/(m2s)aAreaperunitvolume,m−1VTotalvolumeoftower,m3m˙aAirmassflowrate,kg/shsSaturatedairenthalpy,J/kgTwTemperature,∘Cm˙wMassflowrateofwater,kg/sCpwSpecificheatofwaterunderconstantpressure,J/(kgK)NMerkelnumbert1Towerinletwatertemperature,∘Ct2Toweroutletwatertemperature,∘CLWatermassflowrate,kg/sGAirmassflowrate,kg/sAdditional informationFundingThe work was supported by the National Natural Science Foundation of China [51876161].