Distributed Renewable Energy Sources (DRES) are considered as instrumental within modern smart grids and more broadly to the various ancillary services contained within the energy trading market. Thus, the adequate power production profiling and forecasting of DRES deployments is of vital importance such as to support various grid optimisation and accounting processes. The variety of DRES in stallation companies in conjunction with the diversity of ownership on DRES machinery, controller firmware and Supervisory Control and Data Acquisition (SCADA) software leads to cases where centralised SCADA measurements are not entirely available or are provided under a subscription-based model. In this work, we consider this pragmatic scenario and introduce a SCADA-agnostic approach that utilises freely available weather measurements for explicitly profiling and forecasting power generation as produced in real wind turbine deployments. For this purpose, we leverage various machine learning (ML) libraries to demonstrate the applicability of our system and further compare it with forecasting outputs obtained when using SCADA measurements. Through this study, we demonstrate a viable and exogenous profiling solution achieving similar accuracy with SCADA-based schemes under much lower computational costs.