iteratively obtaining utilization parameter values from first to Nth edge computing environments, training one or more predictive model by machine learning using parameter values of the utilization parameter values obtained by the iteratively obtaining, wherein the training includes training a first computing environment predictive model with use of parameter values of the utilization parameters obtained from the first computing environment by the iteratively obtaining, wherein the first computing environment predictive model is a machine learning model for predicting subsequent performance of the first edge computing environment;

applying query data to the first computing environment predictive model to output a predicted utilization parameter value of the first edge computing environment at a subsequent time;

inputting the predicted utilization parameter value and an updated service level agreement parameter value for the first edge computing environment to a second computing environment predictive model in order to output provisioning data, the second computing environment predictive model being another machine learning model; and

providing an action decision to reprovision the first edge computing environment with use of the provisioning data;

wherein the determining provisioning data for the first edge computing environment includes ascertaining adjusted sensor configuration provisioning data for the first edge computing environment, the ascertaining including querying a sensor resolution predictive model trained with machine learning training data to predict sensor resolution performance of a virtually reprovisioned instance of the first edge computing environment.