Abstract: A computer-implemented method is carried out on an IT framework and a relative apparatus including: an orchestrator module; an optimizer module; a configurator module; a load generator module; and a telemetry module. The method includes: identifying tunable parameters representing a candidate configuration for a System Under Test (SUT), and applying the candidate configuration to the SUT using the configurator module; performance testing the SUT to determine a performance indicator; supplying performance metrics to the optimizer module's machine learning model to generate an optimized candidate configuration. The model provides as output, in correspondence of a candidate set of parameters, an expected value of the performance indicator and a prediction uncertainty thereof, used by the optimizer module to build an Acquisition Function used to derive a candidate configuration and by the load generator module to build the test workload. The test workload is computed through the machine learning model.

Abstract: A tuning system and related computer implemented tuning method carried on an IT system including a System Under Test (SUT) including a stack of software layers, provided with a number of adjustable parameters are disclosed. The method includes the steps of supplying a characterization and prediction module, a tuner module, and a knowledge base (KB). The KB is composed by N tuples, (si, {right arrow over (w)}i, {right arrow over (x)}i, yi) being gathered over iterative tuning sessions where each iteration is started by applying to the SUT si a configuration {right arrow over (xl)} suggested by the tuner module, exposing the system si to an external working condition wi and gathering performance metrics resulting in a performance indicator score yi.

Abstract: Disclosed is a computer implemented method carried on an IT framework and a relative apparatus including: an orchestrator module; an optimizer module; a configurator module; a load generator module; and a telemetry module. The method includes: identifying tunable parameters representing a candidate configuration for the System Under Test (SUT), and applying the candidate configuration to the SUT using the configurator module; performance testing the SUT to determine a performance indicator; supplying performance metrics to the optimizer module's machine learning model to generate an optimized candidate configuration. The model provides as output, in correspondence of a candidate set of parameters, an expected value of the performance indicator and a prediction uncertainty thereof, used by the optimizer module to build an Acquisition Function used to derive a candidate configuration and by the load generator module to build the test workload. The test workload is computed through the machine learning model.