To meet the increasing demand for cloud computing services, the scale and number of data centers keeps increasing worldwide. This growth comes at the cost of increased electricity consumption, which directly correlates to CO2 emissions, the main driver of climate change. As such, researching ways to reduce cloud computing emissions is more relevant than ever. However, although cloud providers are reportedly already working near optimal power efficiency, they fail in providing precise sustainability reporting. This calls for further improvements on the cloud computing consumer's side. To this end, in this paper we propose a user-centric, Kubernetes-based architecture for green cloud computing. We implement a carbon intensity forecaster and we use it to schedule workloads based on the availability of green energy, exploiting both regional and temporal variations to minimize emissions. We evaluate our system using real-world traces of cloud workloads execution comparing the achieved carbon emission savings against a baseline round-robin scheduler. Our findings indicate that our system can achieve up to a 13% reduction in emissions in a strict scenario with heavy limitations on the available resources.