The increasing integration of advanced communication technologies in smart grid systems has significantly improved their efficiency and reliability. However, this interconnectedness also exposes the grid to cyber threats, particularly Distributed Denial-of-Service (DDoS) attacks, which can disrupt operations and compromise system security. This study presents the development of a machine learning-based framework for detecting and mitigating DDoS attacks in smart grid environments. The proposed model leverages advanced machine learning algorithms to analyze network traffic, identify abnormal patterns indicative of DDoS attacks, and implement real-time mitigation strategies. A hybrid approach combining supervised and unsupervised learning enhanced detection accuracy and adaptability to evolving attack patterns. The model was tested on simulated and real-world datasets, demonstrating high detection rates, low false-positive rates, and efficient response times. This research contributes to improving the resilience of smart grid systems by providing an intelligent, automated solution for DDoS attack management, ensuring the uninterrupted delivery of essential services.