Energy-Aware Deep Learning on Resource-Constrained Hardware
This is an incremental review paper addressing energy efficiency for deep learning on battery-limited or energy-harvesting devices.
The paper provides an overview of energy-aware deep learning approaches for optimizing inference and training on resource-constrained IoT and mobile devices, synthesizing methodologies and limitations to serve as a foundation for future research.
The use of deep learning (DL) on Internet of Things (IoT) and mobile devices offers numerous advantages over cloud-based processing. However, such devices face substantial energy constraints to prolong battery-life, or may even operate intermittently via energy-harvesting. Consequently, \textit{energy-aware} approaches for optimizing DL inference and training on such resource-constrained devices have garnered recent interest. We present an overview of such approaches, outlining their methodologies, implications for energy consumption and system-level efficiency, and their limitations in terms of supported network types, hardware platforms, and application scenarios. We hope our review offers a clear synthesis of the evolving energy-aware DL landscape and serves as a foundation for future research in energy-constrained computing.