Towards data center self-diagnosis using a mobile robot
Proceedings of the 8th ACM international conference on Autonomic computing
| Hi-index | 0.00 |
Management and monitoring of data centers is a growing field of interest, with much current research, and the emergence of a variety of commercial products aiming to improve performance, resource utilization and energy efficiency of the computing infrastructure. Despite the large body of work on optimizing data center operations, few studies actually focus on discovering and tracking the physical layout of assets in these centers. Such asset tracking is a prerequisite to faithfully performing administration and any form of optimization that relies on physical layout characteristics. In this work, we describe an approach to completely automated asset tracking in data centers, employing a vision-based mobile robot in conjunction with an ability to manipulate the indicator LEDs in blade centers and storage arrays. Unlike previous large-scale asset-tracking methods, our approach does not require the tagging of assets (e.g., with RFID tags or barcodes), thus saving considerable expense and human labor. The approach is validated through a series of experiments in a production industrial data center.