{"title":"基于能量的异常检测:预测软件故障的新视角","authors":"C. Monni, M. Pezzè","doi":"10.1109/ICSE-NIER.2019.00026","DOIUrl":null,"url":null,"abstract":"The ability of predicting failures before their occurrence is a fundamental enabler for reducing field failures and improving the reliability of complex software systems. Recent research proposes many techniques to detect anomalous values of system metrics, and demonstrates that collective anomalies are a good symptom of failure-prone states. In this paper (i) we observe the analogy of complex software systems with multi-particle and network systems, (ii) propose to use energy-based models commonly exploited in physics and statistical mechanics to precisely reveal failure-prone behaviors without training with seeded errors, and (iii) present some preliminary experimental results that show the feasibility of our approach.","PeriodicalId":180082,"journal":{"name":"2019 IEEE/ACM 41st International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Energy-Based Anomaly Detection A New Perspective for Predicting Software Failures\",\"authors\":\"C. Monni, M. Pezzè\",\"doi\":\"10.1109/ICSE-NIER.2019.00026\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The ability of predicting failures before their occurrence is a fundamental enabler for reducing field failures and improving the reliability of complex software systems. Recent research proposes many techniques to detect anomalous values of system metrics, and demonstrates that collective anomalies are a good symptom of failure-prone states. In this paper (i) we observe the analogy of complex software systems with multi-particle and network systems, (ii) propose to use energy-based models commonly exploited in physics and statistical mechanics to precisely reveal failure-prone behaviors without training with seeded errors, and (iii) present some preliminary experimental results that show the feasibility of our approach.\",\"PeriodicalId\":180082,\"journal\":{\"name\":\"2019 IEEE/ACM 41st International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE/ACM 41st International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSE-NIER.2019.00026\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE/ACM 41st International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSE-NIER.2019.00026","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Energy-Based Anomaly Detection A New Perspective for Predicting Software Failures
The ability of predicting failures before their occurrence is a fundamental enabler for reducing field failures and improving the reliability of complex software systems. Recent research proposes many techniques to detect anomalous values of system metrics, and demonstrates that collective anomalies are a good symptom of failure-prone states. In this paper (i) we observe the analogy of complex software systems with multi-particle and network systems, (ii) propose to use energy-based models commonly exploited in physics and statistical mechanics to precisely reveal failure-prone behaviors without training with seeded errors, and (iii) present some preliminary experimental results that show the feasibility of our approach.