ABSTRACT

Performing a detailed diagnosis for a system issue mainly includes problem identification (i.e., identifying and detecting the problems), determination (i.e., fault diagnosis and root cause analysis), and resolution (i.e., providing resolutions). System diagnosis requires a deep understanding about the target system. In real-world IT infrastructures, many system issues are repeated and the associated resolutions can be found in the relevant events and tickets resolved in the past. In this chapter, we present several data-driven applications for system diagnosis.