Energy Efficient
Energy-efficient computing focuses on minimizing the energy consumption of computational systems, particularly in resource-constrained environments and large-scale applications like AI. Current research emphasizes developing novel neural network architectures, such as spiking neural networks (SNNs) and optimized convolutional neural networks (CNNs), alongside algorithmic improvements like efficient training methods and hardware-software co-design. These efforts are crucial for mitigating the environmental impact of increasingly energy-intensive AI and for enabling the deployment of intelligent systems in resource-limited settings like edge devices and mobile applications, impacting both sustainability and technological advancement.
Papers
Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization
Daniel Geissler, Bo Zhou, Sungho Suh, Paul Lukowicz
Climate Aware Deep Neural Networks (CADNN) for Wind Power Simulation
Ali Forootani, Danial Esmaeili Aliabadi, Daniela Thraen