Striking Trade-off Between High Performance and Energy Efficiency in an Edge Computing Application for Detecting Floating Plastic Debris

The Edge Computing environments facilitate the creation of pervasive applications distributed across vast geographical regions, addressing particular challenges associated with centralized information processing, such as network bandwidth saturation and the requirement for extensive computing infrastructures. However, the performance of edge nodes is not comparable to that of high-end servers. Consequently, researchers must adopt specific methodologies to account for the influence of the computing environment on application development. The present study introduces an application to detect floating plastic debris using low-power and high-performance edge computing devices. The primary objective is to establish a methodology for achieving an optimal balance between performance and energy consumption. The applications were validated using a Nvidia Jetson Nano sensor board, demonstrating favorable accuracy, effectiveness, and reduced energy consumption.