研究GitHub上AIOps项目的特征
Studying the Characteristics of AIOps Projects on GitHub
AI总结：
本研究首次系统分析GitHub上的开源AIOps项目，通过仓库指标、定性分析和质量评估，揭示其快速增长但质量较差的问题，并提出改进方向。
摘要：
人工智能用于IT运维（AIOps）利用人工智能方法来处理软件系统运维过程中产生的大量数据。先前的工作已经提出了各种AIOps解决方案，以支持系统运维和维护中的不同任务，例如异常检测。在本研究中，我们对开源AIOps项目进行了深入分析，以了解AIOps在实践中的特征。我们首先从GitHub上仔细识别了一组AIOps项目，并分析了它们的仓库指标（例如，使用的编程语言）。然后，我们定性检查这些项目，以了解它们的输入数据、分析技术和目标。最后，我们使用不同的质量指标（例如，bug数量）来评估这些项目的质量。为了提供背景，我们还从GitHub上采样了两组基线项目：一组是机器学习项目的随机样本，另一组是通用项目的随机样本。通过比较我们识别的AIOps项目与这些基线之间的不同指标，我们得出了有意义的见解。我们的结果揭示了近期对AIOps解决方案日益增长的兴趣。然而，质量指标表明，AIOps项目比我们的基线项目存在更多问题。我们还指出了AIOps方法中最常见的问题，并讨论了解决这些挑战的潜在方案。我们的发现为研究人员和实践者提供了宝贵的指导，使他们能够理解AIOps实践的当前状态，并揭示改进AIOps薄弱方面的不同途径。据我们所知，这项工作标志着首次尝试对开源AIOps项目进行特征化描述。
英文摘要：
Artificial Intelligence for IT Operations (AIOps) leverages AI approaches to handle the massive amount of data generated during the operations of software systems. Prior works have proposed various AIOps solutions to support different tasks in system operations and maintenance, such as anomaly detection. In this study, we conduct an in-depth analysis of open-source AIOps projects to understand the characteristics of AIOps in practice. We first carefully identify a set of AIOps projects from GitHub and analyze their repository metrics (e.g., the used programming languages). Then, we qualitatively examine the projects to understand their input data, analysis techniques, and goals. Finally, we assess the quality of these projects using different quality metrics, such as the number of bugs. To provide context, we also sample two sets of baseline projects from GitHub: a random sample of machine learning projects and a random sample of general-purposed projects. By comparing different metrics between our identified AIOps projects and these baselines, we derive meaningful insights. Our results reveal a recent and growing interest in AIOps solutions. However, the quality metrics indicate that AIOps projects suffer from more issues than our baseline projects. We also pinpoint the most common issues in AIOps approaches and discuss potential solutions to address these challenges. Our findings offer valuable guidance to researchers and practitioners, enabling them to comprehend the current state of AIOps practices and shed light on different ways of improving AIOps' weaker aspects. To the best of our knowledge, this work marks the first attempt to characterize open-source AIOps projects.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
