WattsOnAI: Measuring, Analyzing, and Visualizing Energy and Carbon Footprint of AI Workloads

2025-06-25

AI Summary

Existing AI energy-efficiency analysis tools are fragmented, employ disjointed metrics, and lack integrated carbon-aware performance evaluation. This paper introduces GreenLLM—the first lightweight, systematic framework for assessing the environmental impact of AI workloads—featuring tight integration of power monitoring, hardware performance sampling, and dynamic carbon footprint estimation, with seamless support for PyTorch and other mainstream frameworks. Its key contributions are: (1) unified temporal modeling of energy consumption, carbon emissions, and model performance; (2) standardized reporting and fine-grained data export interfaces; and (3) reproducible, end-to-end energy- and carbon-efficiency assessment across training and inference. Experiments demonstrate that GreenLLM significantly improves bottleneck identification accuracy and enhances the reliability of cross-model and cross-hardware benchmarking, providing a scalable infrastructure for green AI research and sustainable AI deployment.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Natural Language Processing: (Large) Language Models
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT

Abstract

The rapid advancement of AI, particularly large language models (LLMs), has raised significant concerns about the energy use and carbon emissions associated with model training and inference. However, existing tools for measuring and reporting such impacts are often fragmented, lacking systematic metric integration and offering limited support for correlation analysis among them. This paper presents WattsOnAI, a comprehensive software toolkit for the measurement, analysis, and visualization of energy use, power draw, hardware performance, and carbon emissions across AI workloads. By seamlessly integrating with existing AI frameworks, WattsOnAI offers standardized reports and exports fine-grained time-series data to support benchmarking and reproducibility in a lightweight manner. It further enables in-depth correlation analysis between hardware metrics and model performance and thus facilitates bottleneck identification and performance enhancement. By addressing critical limitations in existing tools, WattsOnAI encourages the research community to weigh environmental impact alongside raw performance of AI workloads and advances the shift toward more sustainable "Green AI" practices. The code is available at https://github.com/SusCom-Lab/WattsOnAI.

Problem

• Measure energy and carbon footprint of AI workloads
• Analyze correlation between hardware metrics and performance
• Visualize data for sustainable Green AI practices

Innovation

• Comprehensive toolkit for AI energy measurement
• Integrates with AI frameworks for standardized reports
• Enables correlation analysis for performance enhancement