In this thesis, we present an end-to-end closed system that addresses the aforementioned challenges, taking into account the multi-cloud factor. Our solution leverages a combination of techniques, including Hierarchical Task Networks (HTN) planning, to optimize infrastructure across multiple cloud providers. By analyzing the current state of the infrastructure and utilizing time-series forecasting, we accurately predict future resource usage patterns. These insights are then fed into the HTN Planner (specifically, the GTPyhop Planner), enabling the generation of optimized plans that consider the multicloud environment. By executing the generated plans within the infrastructure, our solution reduces costs, optimizes resource allocation, and minimizes resource wastage across multiple cloud providers. We provide a comprehensive approach to address the challenges associated with cloud-based deployments, taking into account the multicloud factor and the intricacies of managing resources across different cloud providers. This research contributes to advancing cloud computing by providing a holistic solution that enhances resource utilization, mitigates latency issues, optimizes infrastructure, and manages resources effectively in multicloud environments using HTN planning. The proposed system enables organizations to optimize their infrastructure across multiple cloud providers, leading to improved operational efficiency, reduced costs, and enhanced performance in their cloud-based deployments.