Doklady Mathematics ( IF 0.6 ) Pub Date : 2024-03-11 , DOI: 10.1134/s1064562423701223 M. Tiutiulnikov , V. Lazarev , A. Korovin , N. Zakharenko , I. Doroshchenko , S. Budennyy
Abstract
We introduce eco4cast,1 an open-source package aimed to reduce carbon footprint of machine learning models via predictive cloud computing scheduling. The package is integrated with machine learning models and employs an advanced temporal convolution neural network to forecast daily carbon dioxide emissions stemming from electricity generation.The model attains remarkable predictive accuracy by accounting for weather conditions, acknowledged for their robust correlation with carbon energy intensity. The hallmark of eco4cast lies in its capability to identify periods of temporal minimal carbon intensity. This enables the package to manage cloud computing tasks only during these periods, significantly reducing the ecological impact. Our contribution represents a compelling fusion of sustainability and computational efficiency. The code and documentation of the package are hosted on GitHub under the Apache 2.0 license.
中文翻译:
eco4cast:连接预测调度和云计算以减少 ML 模型训练的碳排放
摘要
我们推出了 eco4cast,1一个开源包,旨在通过预测云计算调度来减少机器学习模型的碳足迹。该软件包与机器学习模型集成,并采用先进的时间卷积神经网络来预测发电产生的每日二氧化碳排放量。该模型通过考虑天气条件而获得了显着的预测准确性,该模型因其与碳能源强度的强大相关性而得到认可。eco4cast 的特点在于它能够识别时间上最小碳强度的时期。这使得该包只能在这些时期管理云计算任务,从而显着减少对生态的影响。我们的贡献代表了可持续性和计算效率的引人注目的融合。该包的代码和文档根据 Apache 2.0 许可证托管在 GitHub 上。