Predictive Failure Analysis
Soft failures are abnormal yet allowable behaviors that can slowly lead to the degradation of the operating system. To help eliminate soft failures, use Predictive Failure Analysis (PFA). PFA is intended to detect abnormal behavior early enough to allow you to correct the problem before it affects your business. PFA uses remote checks from IBM® Health Checker for z/OS® to collect data about your installation, and then uses machine learning to analyze this historical data to identify abnormal behavior. It warns you by issuing an exception message when a system trend might cause a problem. To help you correct the problem, it identifies a list of potential issues. PFA can invoke Runtime Diagnostics to analyze and report insufficient metric activity for specific checks and provide the next action that you can take to avoid a problem.