Advances, Systems and Applications
Table 8 This table presents the related works of job and task failure prediction using GCT dataset. The algorithm in bold refers to the best model mentioned in the respective article. [Note: SML - Statistical Machine Learning Algorithms, TML - Traditional Machine Learning Algorithms, DL - Deep Learning Algorithms]
From: Cloud failure prediction based on traditional machine learning and deep learning
Article | Prediction scope | Feature studied | SML | TML | DL |
|---|---|---|---|---|---|
Chen et al. [27] | Job and Task Failure | Job Priority, Resource Requested | - | - | RNN |
Soualhia et al. [28] | Task Failure | Waiting Time, Serving Time, Scheduling Class, Priority, Resource Request, Resource Usage | - | Tree, Boost, GLM, CT, RF | NN |
Rosa et al. [29] | Job Failure | Task Priority, Resource Request, Scheduling Class, Job Size | LDA, ELDA, QDA | LR | - |
Tan et al. [30] | Task Failure | Scheduling Class, Priority, Task Duration, Hourly Failure Frequency, Resource Usage | - | K-Means, Clustering | - |
Islam and Manivannan [31] | Job and Task Failure | Resource Usage, Priority, Scheduling Class, Job Duration, Number Of Task Re-Submission, Scheduling Delay | - | - | LSTM |
Liu et al. [32] | Job Failure | Scheduling Time, Scheduling Class, Job Size, Task Priority, Resource Request | - | SVM, OS-SVM | ELM, OS-ELM |
El-Sayed et al. [33] | Job Failure | Job Priority, Sheduling Class Job Size, Resource Request, Resource Usage | - | RF | - |
Jassas and Mahmoud [34] | Job Failure | Resource Request, Scheduling Class, Priority | - | DT, RF | - |
Shetty et al. [35] | Task Failure | Resource Usage, Job Duration | - | XGBoost | - |
Gao et al. [15] | Task Failure | Task Priority, Task Re-Submission, Scheduling Delay, Resource Usage | - | - | Bi-LSTM |
Jassas and Mahmoud [36] | Job Failure | Resource Request, Scheduling Class, Priority | - | DT, RF | ANN |