Software embedded in Cyber-Physical Systems (CPSs) usually has a large life-cycle and continuously evolving. The increasing expansion of IoT and CPSs has highlighted the need for additional mechanisms for remote deployment and updating of this software, to ensure its correct behaviour. Performance problems require special attention, as they may appear in operation due to limitations in lab testing and environmental conditions.

In this context, we propose a microservice-based method to detect performance problems in CPSs. This microservices will be deployed in installation to detect performance problems in run-time when new software versions are deployed. The problem detection is based on Machine Learning algorithms, which predict the performance of a new software release based on knowledge from previous releases. This permits taking corrective actions sot that system reliability is guaranteed.