Deploying Lightweight Mobilenet Models on Edge Devices for Energy Efficient Real Time Ai in Iot Networks
Year: 2025
Type: article
Abstract: This paper proposes a framework for deploying energy-efficient AI models on devices in real-time time applications. This approach minimizes latency, power consumption, and dependence on cloud-based systems by utilizing edge computing's proximity to the IoT devices. The paper evaluates the accuracy, latency, and energy consumption of the MobileNet model, a lightweight convolutional neural network (CNN), for use in IoT environments. We can see models get 92% training and 90% test accuracy. Based on latency comparison, an edge device processes an image in 20ms while compared to 10ms processing on a cloud server. The edge and cloud energy consumption per image was measured to be 0.5mJ and 1.2mJ, respectively. These results illustrate the potential of deploying scalable, energy-efficient AI models on resource-constrained edge devices to achieve real-time IoT applications.
Language: English
Topic: IoT and Edge/Fog Computing
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7117364165
FWCI:
Cites:
Cited by:
Related to: