Thu 8 Nov 2018 11:37 - 12:00 at Horizons 5 - Estimation and Prediction Chair(s): Jim Herbsleb

In recent years, many traditional software systems have migrated to cloud computing platforms and are provided as online services. The service quality matters because system failures could seriously affect business and user experience. A cloud service system typically contains a large number of computing nodes. In reality, nodes may fail and affect service availability. In this paper, we propose a failure prediction technique, which can predict the failure-proneness of a node in a cloud service system based on historical data, before node failure actually happens. The ability to predict faulty nodes enables the allocation and migration of virtual machines to the healthy nodes, therefore improving service availability. Predicting node failure in cloud service systems is challenging, because a node failure could be caused by a variety of reasons and reflected by many temporal and spatial signals. Furthermore, the failure data is highly imbalanced. To tackle these challenges, we propose MING, a novel technique that combines: 1) a LSTM model to incorporate the temporal data, 2) a Random Forest model to incorporate spatial data; 3) a ranking model that embeds the intermediate results of the two models as feature inputs and ranks the nodes by their failure-proneness, 4) a cost-sensitive function to identify the optimal threshold for selecting the faulty nodes. We evaluate our approach using real-world data collected from a cloud service system. The results confirm the effectiveness of the proposed approach. We have also successfully applied the proposed approach in real industrial practice.

Thu 8 Nov
Times are displayed in time zone: Guadalajara, Mexico City, Monterrey change

10:30 - 12:00
Estimation and PredictionResearch Papers / Journal-First at Horizons 5
Chair(s): Jim HerbslebCarnegie Mellon University
10:30
22m
Talk
Early prediction of merged code changes to prioritize reviewing tasks
Journal-First
Yuanrui Fan, Xin XiaMonash University, David LoSingapore Management University, Shanping Li
DOI
10:52
22m
Talk
How far we have progressed in the journey? An examination of cross-project defect prediction
Journal-First
Yuming Zhou, Yibiao YangNanjing University, China, Hongmin Lu, Lin ChenNanjing University, Yanhui Li, Yangyang Zhao, Junyan Qian, Baowen Xu
Link to publication DOI
11:15
22m
Talk
A Novel Automated Approach for Software Effort Estimation Based on Data Augmentation
Research Papers
11:37
22m
Talk
Predicting Node Failure in Cloud Service Systems
Research Papers
Qingwei LinMicrosoft, China, Ken Hsieh, Yingnong DangMicrosoft, USA, Hongyu ZhangThe University of Newcastle, Kaixin SuiMicrosoft, China, Yong XuMicrosoft, China, Jian-Guang LouMicrosoft Research, Chenggang LiNortheastern University, China, Youjiang WuMicrosoft, USA, Randolph YaoMicrosoft, USA, Murali ChintalapatiMicrosoft, USA, Dongmei ZhangMicrosoft Research, China