EUVIMEDEUVIMED entdecken
Crossref

IceEdge: Thermal-Aware Machine Learning Inference Serving for Emerging Edge Applications

Omais Shafi, Mohammad Khalid Pandit, Arpan Gujarati, Aastha Mehta, Rijurekha Sen

ACM Transactions on Sensor Networks · 30.07.2026 · 22 (4) · 1-26

DOI: 10.1145/3801093 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Sensor Networks, online erschienen am 25.04.2026. Verfasst von Omais Shafi und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Smart city applications require machine learning (ML) capabilities at the edge, for which they require edge devices equipped with specialized processors (e.g., GPUs). However, deploying such high-end edge devices in large numbers is challenging, particularly in regions that face infrastructure and budget constraints (e.g., cities lacking ubiquitous broadband) or extreme weather conditions (e.g., hot temperatures over sustained periods of time). Hence, custom ML frameworks are necessary that can support efficient and safe consolidation of multiple applications with diverse workloads on fewer edge servers. We present IceEdge, an inference serving framework for CPU-GPU based edge computing servers, which isolates colocated applications using existing container mechanisms and provides a deadline- and thermal-aware scheduler for the ML workloads. We implement IceEdge for a Dockerized environment on NVIDIA Jetson Xavier AGX platform. IceEdge outperforms state-of-the-art real-time inference serving frameworks Triton and DeepRT, improving the frame drop rate by up to 15% and reducing the temperature rise by around 12°C compared to Triton inference serving framework.

Zitieren

APA

Shafi, O., Pandit, M. K., Gujarati, A., Mehta, A., & Sen, R. (2026). IceEdge: Thermal-Aware Machine Learning Inference Serving for Emerging Edge Applications. ACM Transactions on Sensor Networks, 22(4), 1-26. https://doi.org/10.1145/3801093

Vancouver

Shafi O, Pandit MK, Gujarati A, Mehta A, Sen R. IceEdge: Thermal-Aware Machine Learning Inference Serving for Emerging Edge Applications. ACM Transactions on Sensor Networks. 2026;22(4):1-26. doi:10.1145/3801093

BibTeX
@article{Shafi2026,
  author = {Shafi, Omais and Pandit, Mohammad Khalid and Gujarati, Arpan and Mehta, Aastha and Sen, Rijurekha},
  title = {IceEdge: Thermal-Aware Machine Learning Inference Serving for Emerging Edge Applications},
  journal = {ACM Transactions on Sensor Networks},
  year = {2026},
  volume = {22},
  number = {4},
  pages = {1--26},
  doi = {10.1145/3801093}
}
Kostenlos starten →