In today's digital age, Distributed Denial of Service (DDoS) attacks have emerged as a formidable threat to the availability of online services. The ability to predict these attacks in advance is a crucial element in ensuring uninterrupted access to these services. This is where our proposed methodology comes into play. We propose the use of Federated Learning in the prediction of DDoS attacks on Software Defined Networks (SDN). Federated Learning is a cutting-edge approach that allows multiple agents, such as network devices, to collaborate and learn a shared model without the need to share their raw data. Our proposed system leverages the collective intelligence of SDN-enabled network devices to construct a prediction model that can detect DDoS attacks in real time. The experimental results of our study demonstrate the efficacy of our approach in detecting DDoS attacks with a high degree of accuracy and minimal instances of false alarms. We believe that our proposed methodology can prove to be an invaluable tool for service providers in their efforts to prevent DDoS attacks and preserve the availability of online services.