Performance Evaluation of Device LED Extraction for Data Center Infrastructure Monitoring
Misheel Enkhbaatar, Tatsuya Yamazaki · 2022 IEEE 11th Global Conference on Consumer Electronics (GCCE) · 2022
Availability is the core metric of a data center operation. To be available at any time, data centers must use a real-time and precise failure detection method. However, current methods are not enough to bring data centers to their goal. One of the practical device failure detection methods is visual monitoring. Human inspectors detect failures by checking LEDs of infrastructure devices. This manual method requires a lot of effort as well as it is not suitable for real-time monitoring for big scale data centers. The goal of this study is to achieve real-time and high accuracy failure monitoring for the data center. This paper presents performance evaluation of an automatic LED extraction system which is a part of work to achieve an automatic data center monitoring. The system performed the LED detection with an accuracy of 83.7%.