<![CDATA[Jetson Nano, a Single-Board Computer or SBC developed by NVIDIA, is used to implement a face recognition system that requires large computing resources. This research aims to analyze the resource usage on the Jetson Nano during the running of the face recognition system, including CPU usage, GPU, memory, and power consumption. Monitoring data was obtained using Jtop software to record real-time resource usage and a wattmeter for electrical power consumption. The results showed that the Jetson Nano CPU performed consistently with an average utilization of 77.14%, reflecting an even distribution of workload. The GPU showed an average utilization of 44.05% with higher fluctuations, indicating variations in graphics workload intensity. Memory was used close to the maximum capacity of 4 GB, with an average utilization of 3.75 GB, indicating efficient memory management. Average power consumption was recorded at 8.56 Wh, confirming the energy efficiency of this device. This study concludes that the Jetson Nano is capable of running the facial recognition system stably and efficiently, although there is room for further optimization on GPU load distribution and memory management. With its high power efficiency, the Jetson Nano is an ideal solution for artificial intelligence-based applications with low power requirements.]]>
Copyrights © 2024
