Many software services today are hosted on cloud computing platforms, such as Amazon EC2, due to many benefits like reduced operational costs. However, node failures in these platforms can impact the availability of their hosted services and potentially lead to large financial losses. Predicting node failures before they actually occur is crucial, as it enables DevOps engineers to minimize their impact by performing preventative actions. However, such predictions are hard due to many challenges like the enormous size of the monitoring data and the complexity of the failure symptoms. AIOps ( A rtificial I ntelligence for IT Op eration s ), a recently introduced approach in DevOps, leverages data analytics and machine learning to improve the quality of computing platforms in a cost-effective manner. However, the successful adoption of such AIOps solutions requires much more than a top-performing machine learning model. Instead, AIOps solutions must be trustable, interpretable, maintainable, scalable, and evaluated in context. To cope with these challenges, in this article we report our process of building an AIOps solution for predicting node failures for an ultra-large-scale cloud computing platform at Alibaba. We expect our experiences to be of value to researchers and practitioners, who are interested in building and maintaining AIOps solutions for large-scale cloud computing platforms.

Background and Objectives Existing generic preference-based measures were all developed in Western countries. Evidence shows that the Chinese population may have different perceptions about health and health-related quality of life. This study aimed at developing a descriptive system of a new generic preference-based measure under the initiative of China Health Related Outcomes Measures (CHROME). Methods Qualitative data were collected through semi-structured interviews conducted in-person or online. Respondents were recruited from both the general public and populations with chronic diseases. Open-ended questions about the respondent’s perception of general health and important aspects of health-related quality of life were asked. Probing questions based on a systematic review of existing generic preference-based measures were also used. The framework analysis was used to synthesize the qualitative data. Candidate items for the descriptive system were selected following the ISPOR and COSMIN guidelines. Expert panel review and cognitive debriefings were conducted for further revisions. Results Qualitative interviews were conducted among 68 respondents, with 48.5% male and a mean age of 47.8 years (range 18–81 years). In total, 1558 codes were identified and then aggregated to 31 sub-themes and corresponding six themes to inform the development of the initial version of the descriptive system. Feedback from the expert panel survey and meeting ( n = 15) and the cognitive debriefing interviews ( n = 30) was incorporated into the revised version of the measure. Finally, the generic version of CHROME (CHROME-G) included 12 items across six domains, namely, pain, fatigue, appetite, mobility, vision, hearing, sleeping, daily activities, depression, worry, memory, and social interactions. The descriptive system used a mix of four-level and five-level response options and a 7-day recall period. Conclusions The CHROME-G is the first generic preference-based measure to be developed based on the inputs from the Chinese populations. Supplementary Information The online version contains supplementary material available at 10.1007/s40273-022-01151-9.

No abstract