A Greener Edge: A Framework on Carbon-aware Edge ML System Design
より環境に優しいエッジ：カーボンアウェアなエッジMLシステム設計のフレームワーク (AI 翻訳)
Xuesi Chen, Ilan Mandel, Eren Yıldız, Josiah Hester, Udit Gupta
🤖 gxceed AI 要約
日本語
エッジMLシステムの環境影響を設計段階で最適化するフレームワークMicroGreenを提案。コンポーネントレベルの炭素モデル、ワークロードプロファイリング、環境認識エネルギー分析を組み合わせ、多様な条件下で炭素最適な構成を特定。実際の公園での人物検出デプロイメントにより、均質ベースラインと比較して総排出量を47.72%削減。
English
Presents MicroGreen, a design-time framework for carbon-aware edge ML systems. It combines component-level carbon models, workload profiling, and environment-aware energy analysis to identify carbon-optimal configurations. A real-world deployment in NYC parks shows 47.72% emissions reduction over a homogeneous baseline.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本では工場や都市のIoT機器のScope2排出削減が課題。本フレームワークはエッジデバイスの設計段階でのカーボン最適化を可能にし、SSBJ対応やグリーンICT戦略に示唆を与える。
In the global GX context
As edge computing scales globally, carbon-aware design frameworks like MicroGreen address the overlooked environmental impact of edge ML systems. This work aligns with ISSB's emphasis on value chain emissions and offers a method to reduce Scope 2 and embodied carbon in hardware.
👥 読者別の含意
🔬研究者:A novel framework for carbon-optimized edge ML design that integrates hardware, workload, and environment models.
🏢実務担当者:Use MicroGreen at design time to select carbon-optimal edge hardware configurations.
🏛政策担当者:Encourages policy support for carbon-aware computing standards.
📄 Abstract（原文）
Edge devices are often deployed at scale, yet their environmental impact, shaped by complex interactions between hardware choices, workload demands, power systems, and deployment context, has been overlooked by the mobile computing community. We present MicroGreen, a design-time framework that enables carbon-aware design for edge ML systems. By combining component-level carbon models with workload profiling and environment-aware energy analysis, MicroGreen identifies carbon-optimal configurations across diverse conditions. Our results show that the most energy-efficient processor is not always the most sustainable, and that ambient energy availability, inference rate, and deployment lifetime can shift the carbon-optimal design by over an order of magnitude. Through a real vision-based visitor detection and counting deployment in New York City parks, we demonstrate that heterogeneous, location-aware designs reduce total emissions by 47.72% compared to a homogeneous baseline.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1145/3745756.3809201first seen 2026-06-17 05:47:39 · last seen 2026-06-17 07:14:07
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。