In　most　data　centers　(DCs),　hot　spots　reduce　the　reliability,　durability,　and　efficiency　of　server　cooling.　The　hot　spots　are　mainly　attributed　to　the　uneven　airflow　distribution　and　the　resulting　mixing　of　cold　and　hot　air.　To　evenly　distribute　the　airflow,　the　relay　jet　fan,　an　active　local　adjustment　technology,　is　introduced　into　the　under-floor　air　distribution　in　DCs.　The　jet　fans　are　set　in　front　of　the　closed　cold　aisle　where　the　hot　spots　most　often　appear.　The　nozzle　height,　nozzle　angle,　horizontal　position　and　attachment　distance　greatly　influence　the　performance　of　the　new　system.　To　comprehensively　evaluate　the　multiple　levels　of　these　affecting　parameters,　a　large　number　of　cases　that　need　testing　make　it　impossible　to　conduct　research.　An　approach　based　on　the　Taguchi　method　with　grey　relational　analysis　optimizes　the　system　and　the　L16　(44)　orthogonal　array　is　employed　to　design　the　experiments.　The　Taguchi　method　combined　with　computational　fluid　dynamics　determines　the　optimal　combinations　of　the　Supply　Heat　Index　(SHI),　Return　Temperature　Index　(RTI),　β,　and　Index　of　Mixing　(IOM).　The　significance　of　the　affecting　parameters　is　revealed　and　ranked,　and　through　the　main　effect　analysis　and　the　analysis　of　variance,　the　nozzle　angle　is　chosen　as　the　most　important　among　the　four　affecting　parameters.　After　that,　the　Taguchi-based　grey　relational　analysis　transforms　the　multi-objective　into　a　single-objective　to　determine　the　optimal　combination　of　design　variables.　Finally,　a　confirmatory　test　was　conducted,　and　the　optimal　combination　reduces　the　server　temperature　by　up　to　7.2　°C.　©　2021　Elsevier　Ltd