Artificial Intelligence for IT Operations (AIOps) has emerged as a new model for automating and streamlining operating operational workflow in large-scale IT infrastructures using AI-supported methods and tools on different levels. AIOps platforms can collect and aggregate the increasing volumes of data generated by multiple IT infrastructure components, provide real-time monitoring and analysis of cloud and edge resources, detect significant events and patterns related to application performance and availability before they become critical, and even in some cases automatically resolve these issues without human intervention. Based on these concepts, our presentation will introduce a new experimental AIOps framework developed in OpenNebula and its Prometheus integration for the evaluation of AI techniques in order to provide intelligent workload forecasting and infrastructure orchestration capabilities to automate and optimize the provisioning and deployment of geographically distributed edge/cloud infrastructures and applications. We will also present the results of the evaluation of AI-based time series forecasting techniques to predict the CPU usage of VMs, and optimization techniques for the placement of VMs on top of the physical infrastructure, based on CPU usage predictions.