Data Mining for Thermal Analysis of Big Dataset of HPC-Data Center

Greening of Data Centers could be achieved through energy savings in two major areas namely: compute systems and cooling systems. A reliable cooling system is necessary to produce a persistent flow of cold air to cool the servers due to increasingly demanding computational load. Servers’ dissipated heat effects a strain on the cooling systems. Consequently, it is imperative to individual servers that frequently occur in the hotspot zones. This is facilitated through the application of data mining techniques to an available big data set with thermal characteristics of HPC-ENEA-Data Center, namely Cresco 6. This work involves the implementation of an advanced algorithm on the workload management platform produces hotspots maps with the goal to reduce data centre wide thermal-gradient, and cooling effectiveness