{"title":"如何配置对软件日志进行屏蔽事件异常检测?","authors":"Jesse Nyyssölä, M. Mäntylä, M. Varela","doi":"10.1109/ICSME55016.2022.00050","DOIUrl":null,"url":null,"abstract":"Software Log anomaly event detection with masked event prediction has various technical approaches with countless configurations and parameters. Our objective is to provide a baseline of settings for similar studies in the future. The models we use are the N-Gram model, which is a classic approach in the field of natural language processing (NLP), and two deep learning (DL) models long short-term memory (LSTM) and convolutional neural network (CNN). For datasets we used four datasets Profilence, BlueGene/L (BGL), Hadoop Distributed File System (HDFS) and Hadoop. Other settings are the size of the sliding window which determines how many surrounding events we are using to predict a given event, mask position (the position within the window we are predicting), the usage of only unique sequences, and the portion of data that is used for training. The results show clear indications of settings that can be generalized across datasets. The performance of the DL models does not deteriorate as the window size increases while the N-Gram model shows worse performance with large window sizes on the BGL and Profilence datasets. Despite the popularity of Next Event Prediction, the results show that in this context it is better not to predict events at the edges of the subsequence, i.e., first or last event, with the best result coming from predicting the fourth event when the window size is five. Regarding the amount of data used for training, the results show differences across datasets and models. For example, the N-Gram model appears to be more sensitive toward the lack of data than the DL models. Overall, for similar experimental setups we suggest the following general baseline: Window size 10, mask position second to last, do not filter out non-unique sequences, and use a half of the total data for training.","PeriodicalId":300084,"journal":{"name":"2022 IEEE International Conference on Software Maintenance and Evolution (ICSME)","volume":"227 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"How to Configure Masked Event Anomaly Detection on Software Logs?\",\"authors\":\"Jesse Nyyssölä, M. Mäntylä, M. Varela\",\"doi\":\"10.1109/ICSME55016.2022.00050\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Software Log anomaly event detection with masked event prediction has various technical approaches with countless configurations and parameters. Our objective is to provide a baseline of settings for similar studies in the future. The models we use are the N-Gram model, which is a classic approach in the field of natural language processing (NLP), and two deep learning (DL) models long short-term memory (LSTM) and convolutional neural network (CNN). For datasets we used four datasets Profilence, BlueGene/L (BGL), Hadoop Distributed File System (HDFS) and Hadoop. Other settings are the size of the sliding window which determines how many surrounding events we are using to predict a given event, mask position (the position within the window we are predicting), the usage of only unique sequences, and the portion of data that is used for training. The results show clear indications of settings that can be generalized across datasets. The performance of the DL models does not deteriorate as the window size increases while the N-Gram model shows worse performance with large window sizes on the BGL and Profilence datasets. Despite the popularity of Next Event Prediction, the results show that in this context it is better not to predict events at the edges of the subsequence, i.e., first or last event, with the best result coming from predicting the fourth event when the window size is five. Regarding the amount of data used for training, the results show differences across datasets and models. For example, the N-Gram model appears to be more sensitive toward the lack of data than the DL models. Overall, for similar experimental setups we suggest the following general baseline: Window size 10, mask position second to last, do not filter out non-unique sequences, and use a half of the total data for training.\",\"PeriodicalId\":300084,\"journal\":{\"name\":\"2022 IEEE International Conference on Software Maintenance and Evolution (ICSME)\",\"volume\":\"227 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-08-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE International Conference on Software Maintenance and Evolution (ICSME)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSME55016.2022.00050\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Software Maintenance and Evolution (ICSME)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSME55016.2022.00050","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
摘要
基于屏蔽事件预测的软件日志异常事件检测技术手段多种多样,配置和参数无数。我们的目标是为将来类似的研究提供一个基线。我们使用的模型是N-Gram模型,这是自然语言处理(NLP)领域的经典方法,以及两个深度学习(DL)模型长短期记忆(LSTM)和卷积神经网络(CNN)。对于数据集,我们使用了四个数据集Profilence, BlueGene/L (BGL), Hadoop Distributed File System (HDFS)和Hadoop。其他设置包括滑动窗口的大小,它决定了我们使用多少周围事件来预测给定事件,掩码位置(我们预测的窗口内的位置),仅使用唯一序列,以及用于训练的数据部分。结果显示了可以跨数据集推广的设置的明确指示。DL模型的性能不会随着窗口大小的增加而下降,而N-Gram模型在BGL和Profilence数据集上随着窗口大小的增加而表现出更差的性能。尽管下一个事件预测很受欢迎,但结果表明,在这种情况下,最好不要预测子序列边缘的事件,即第一个或最后一个事件,当窗口大小为5时,最好的结果来自预测第四个事件。关于用于训练的数据量,结果显示了数据集和模型之间的差异。例如,N-Gram模型似乎比DL模型对缺乏数据更敏感。总的来说,对于类似的实验设置,我们建议以下一般基线:窗口大小为10,掩码位置倒数第二,不过滤掉非唯一序列,并使用总数据的一半进行训练。
How to Configure Masked Event Anomaly Detection on Software Logs?
Software Log anomaly event detection with masked event prediction has various technical approaches with countless configurations and parameters. Our objective is to provide a baseline of settings for similar studies in the future. The models we use are the N-Gram model, which is a classic approach in the field of natural language processing (NLP), and two deep learning (DL) models long short-term memory (LSTM) and convolutional neural network (CNN). For datasets we used four datasets Profilence, BlueGene/L (BGL), Hadoop Distributed File System (HDFS) and Hadoop. Other settings are the size of the sliding window which determines how many surrounding events we are using to predict a given event, mask position (the position within the window we are predicting), the usage of only unique sequences, and the portion of data that is used for training. The results show clear indications of settings that can be generalized across datasets. The performance of the DL models does not deteriorate as the window size increases while the N-Gram model shows worse performance with large window sizes on the BGL and Profilence datasets. Despite the popularity of Next Event Prediction, the results show that in this context it is better not to predict events at the edges of the subsequence, i.e., first or last event, with the best result coming from predicting the fourth event when the window size is five. Regarding the amount of data used for training, the results show differences across datasets and models. For example, the N-Gram model appears to be more sensitive toward the lack of data than the DL models. Overall, for similar experimental setups we suggest the following general baseline: Window size 10, mask position second to last, do not filter out non-unique sequences, and use a half of the total data for training.