Volume 6 Issue 12 2024

The increasing adoption of Internet of Things (IoT) devices has transformed the landscape of cloud computing while simultaneously introducing serious cybersecurity challenges, especially Distributed Denial-of-Service (DDoS) attacks. Traditional Virtual Machine (VM) scheduling algorithms in cloud infrastructures are not designed to handle the dynamic and unpredictable nature of such attacks. This research introduces an IoT-based hybrid Machine Learning (ML) scheduling mechanism combining Random Forest (RF) and Long Short-Term Memory (LSTM) networks to detect, predict, and mitigate DDoS attacks proactively. The model leverages the classification efficiency of RF with the temporal prediction capability of LSTM, enabling adaptive VM resource allocation. Theoretical evaluation demonstrates enhanced detection accuracy, reduced latency, and optimal resource utilization compared to conventional scheduling mechanisms, establishing the framework’s potential for resilient IoT-cloud ecosystems.