Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels
This work addresses energy efficiency and privacy for edge computing applications, but it is incremental as it builds on existing model compression and splitting methods.
The paper tackles the problem of high energy consumption and data privacy risks in remote DNN inference by proposing a technique that uses model compression and time-varying model splitting between edge and remote nodes, resulting in minimal energy consumption and CO2 emissions while maintaining high accuracy in image classification tasks.
Today's intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a remote node that performs the inference task. However, this may incur high transmission energy costs and puts data privacy at risk. In this paper, we propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. The time-varying representation accounts for time-varying channels and can significantly reduce the total energy at the edge device while maintaining high accuracy (low loss). We implement our approach in an image classification task using the MNIST dataset, and the system environment is simulated as a trajectory navigation scenario to emulate different channel conditions. Numerical simulations show that our proposed solution results in minimal energy consumption and $CO_2$ emission compared to the considered baselines while exhibiting robust performance across different channel conditions and bandwidth regime choices.