Competition

PAKDD2021 2nd Alibaba Cloud AIOps Competition

Introduction

In the large-scale data centers, memory failures account for the largest proportion of sever failures. The frequent occurrence of memory failures will affect the stability and reliability of the server and even the entire IT infrastructure, which have a negative impact on business SLAs (Service-Level Agreement). Thus, prediction of memory failures has become an important topic for IT or big data company.

However, the topic has several challenges, such as high data noise, extremely imbalanced classification, and time-varying features. And contestants should spend more time on solving these problems. Meanwhile, since stability overwhelms everything, the effectiveness and stability of prediction model will also be considered. If contestants can discover reasonable approaches to predict memory failures in such a large-scale system, all IT and big data companies might be able to adopt such approaches to boost prosperity of the cloud computing.

This contest is consists of two parts: the competition and the call for paper. Each part has an independent evaluation processes and awards.

More details and registration of the competition can be found at:
https://tianchi.aliyun.com/competition/entrance/531874/introduction?lang=en-us

Program Details

 Chair: Dr Mengling Feng, ephfm@nus.edu.sg
 Co-Chair, Dr Yi Liu, mars.ly@alibaba-inc.com
 May 13, 10:15AM– 12:30 PM IST time
 15 min presentation + 5 min Q&A

ID Time Title
1 10:15 AM – 10:35 AM IST A Large-Scale Production Dataset for DRAM Failure Prediction
Zhinan Cheng
2 10:35 AM – 10:55 AM IST Predicting Memory Failures with a Two-Stage Machine Learning Method
Zhuo Yin.
3 10:55 AM – 11:15 AM IST DRAM Failure Prediction in AIOps: Empirical Evaluation, Challenges and Opportunities
Hongzuo Xu.
4 11:15 AM – 11:35 AM IST Large-Scale Memory Failure Prediction Based on Machine Learning
Yifan Li.
5 11:35 AM – 11:55 AM IST FDSt: Memory Error Prediction Based on Feature Derivation and Stacking
Ruyi Zhang.
6 11:55 AM -12:15: PM IST Highly Efficient Memory Failure Prediction using Mcelog-based Data Ming and Machine Learning
Chengdong Yao.
7 12:15 AM -12:35: PM IST The Application of LightGBM on Memory Failure Prediction in Second Alibaba Cloud AIOps Competition
Zhikai Chang.

Important Dates

Start of Competition Feb 3, 2021
End of Qualification Round Mar 22, 2021
End of Semi-Final Apr 22, 2021
Finals Apr 29, 2021
Paper Submission Deadline Apr 24, 2021

*All deadlines are 23:59 Pacific Standard Time (PST)

Host Institutions


Platinum Sponsor


Publication