Large-scale scientific experiments involve a large number of computers. Thesecomputers generally employ grid computing to perform non-interactive, data-intensivetasks. Recent scientific studies have required multiple computers to handle massive datasets. An efficient method of supporting various research is to provide computing resourcesthrough a unified data center. This has complicated the management of computingresources in the data center. The deployment and the status of computing resources changefrequently according to the requirements of each research, renewal of research supportcontracts, and adjustment of computing resources. This study presents a cyber physicalsystem based on convergence operation of data-intensive computing resources to supportvarious research groups. The proposed operation takes into account the modification ofcomputing resources, other changes resulting from such modification, and informationreflecting modification of the physical world. We first present the workload of operationsand related information. Based on these relationships, we derive an optimized work processand the required physical information. For computing resources including existingequipment, we use a mobile device and a wireless network to facilitate conversion betweenthe physical world and cyber world. The mobile device of administrator captures sequenceof remote controlled management indicator lights to detect physical modification.
Keyword
Operation automation; Data center operation; Resource managemnt