Traditional network management is cumbersome, requiring manual configuration for each device. This makes it challenging to maintain secu rity and overall network health. Software-defined networking (SDN) tack les this issue by separating the control plane, which dictates traffic flow, from the data plane, responsible for actual traffic forwarding. This sep aration unlocks several benefits: centralized network management, sim plified automation through programming, and enhanced security through network-wide policy implementation. However, SDN networks are still vulnerable, particularly to distributed denial-of-service (DDoS) attacks that flood the network with traffic, hindering legitimate user access.This paper proposes a solution for SDN environments, where DDoS attacks are prevalent. The method combines statistical analysis to pinpoint abnormal traffic patterns with deep learning for automated attack detection and mitigation. This approach, tested with an SDN controller and network simulator, achieved a 99.75% accuracy rate in identifying DDoS attacks detection rate. Upon attack detection, the system automatically blocks malicious traffic, safeguarding the network.