当前位置: X-MOL 学术Sci. Tech. Built Environ. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
The ASHRAE Great Energy Predictor III competition: Overview and results
Science and Technology for the Built Environment ( IF 1.9 ) Pub Date : 2020-08-24 , DOI: 10.1080/23744731.2020.1795514
Clayton Miller 1 , Pandarasamy Arjunan 2 , Anjukan Kathirgamanathan 3 , Chun Fu 1 , Jonathan Roth 1, 4 , June Young Park 5 , Chris Balbach 6 , Krishnan Gowri 7 , Zoltan Nagy 5 , Anthony D. Fontanini 8 , Jeff Haberl 9
Affiliation  

In late 2019, ASHRAE hosted the Great Energy Predictor III (GEPIII) machine learning competition on the Kaggle platform. This launch marked the third energy prediction competition from ASHRAE and the first since the mid-1990s. In this updated version, the competitors were provided with over 20 million points of training data from 2,380 energy meters collected for 1,448 buildings from 16 sources. This competition’s overall objective was to find the most accurate modeling solutions for the prediction of over 41 million private and public test data points. The competition had 4,370 participants, split across 3,614 teams from 94 countries who submitted 39,403 predictions. In addition to the top five winning workflows, the competitors publicly shared 415 reproducible online machine learning workflow examples (notebooks), including over 40 additional, full solutions. This paper gives a high-level overview of the competition preparation and dataset, competitors and their discussions, machine learning workflows and models generated, winners and their submissions, discussion of lessons learned, and competition outputs and next steps. The most popular and accurate machine learning workflows used large ensembles of mostly gradient boosting tree models, such as LightGBM. Similar to the first predictor competition, preprocessing of the data sets emerged as a key differentiator.



中文翻译:

ASHRAE大能源预测器III竞赛:概述和结果

在2019年末,ASHRAE在Kaggle平台上举办了Great Energy Predictor III(GEPIII)机器学习竞赛。这次发射标志着ASHRAE的第三次能源预测竞赛,也是自1990年代中期以来的第一次。在此更新版本中,为竞争对手提供了来自2380个电表的2000万个培训数据,这些电表收集了来自16个来源的1448座建筑物的电能。这项竞赛的总体目标是找到最准确的建模解决方案,以预测超过4100万个私有和公共测试数据点。比赛共有4,370名参赛者,来自94个国家的3,614支球队参加了比赛,共提交了39,403个预测。除了前五名获奖的工作流程之外,竞争对手还公开分享了415个可重现的在线机器学习工作流程示例(笔记本),其中包括40多个额外的,完整的解决方案。本文概述了比赛的准备和数据集,选手及其讨论,机器学习工作流程和生成的模型,获胜者及其提交的内容,经验教训的讨论以及比赛的结果和下一步。最流行,最准确的机器学习工作流程使用了大型的,主要是梯度增强树模型的集成,例如LightGBM。与第一个预测变量竞赛类似,对数据集的预处理成为关键的区分因素。最流行,最准确的机器学习工作流程使用了大型的,主要是梯度增强树模型的集成,例如LightGBM。与第一个预测变量竞赛类似,对数据集的预处理成为关键的区分因素。最流行,最准确的机器学习工作流程使用了大型的,主要是梯度增强树模型的集成,例如LightGBM。与第一个预测变量竞赛类似,对数据集的预处理成为关键的区分因素。

更新日期:2020-10-06
down
wechat
bug