AI RESEARCH
CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing
arXiv CS.AI
•
ArXi:2603.27420v1 Announce Type: cross Deep learning applications at the network edge lead to a significant growth in AI-related carbon emissions, presenting a critical sustainability challenge. The existing edge computing frameworks optimize for latency and throughput, but they largely ignore the environmental impact of inference workloads. This paper