<p>The growing use of mobile nodes in Wireless Sensor Networks (WSN) improves the system’s Quality of Services (QoS). However, due to the mobility of nodes, the network may suffer various challenges, such as dynamic topology changes, instability in the routing protocol, high energy consumption, and increased control overhead. To deal with these challenges, the Software-Defined Networks (SDN) paradigm has received a lot of attention as it allows networks with limited resources to add new capabilities in order to reduce the overhead brought on by processing and computing in sensor nodes and transfer these energy-intensive tasks to the controller. This paper proposes a Software-defined Distributed Mobility Management (SD-MoMa) framework that employs an Artificial Intelligence (AI) assisted mobility prediction for a Mobile WSN-powered distributed SDN controller. In particular, the SDN controller aims to gather network information from the Mobile Sensor Nodes (MSNs) and predict their successive locations through the MSNs’ current location, direction, and speed using a cutting-edge Artificial Neural Network (ANN) paradigm. Moreover, this mobility prediction enables the controllers to estimate the probability of successful transmission and average latency during the handover of each MSN in the network with frequent topology changes. The ablation and comparative study demonstrate that SD-MoMa exhibits superiority in predicting the future location of Mobile Nodes (MNs). The findings demonstrate that the SD-MoMa framework significantly enhances network performance compared to existing solutions, reducing handover latency by 23%, improving packet delivery ratio by 16%, minimizing control message overhead by 12%, and reduce energy consumption by 27%. These results show that SD-MoMa excels in maintaining network stability and efficiency in dynamic environments with mobile nodes, outperforming state-of-the-art methods across key performance metrics.</p>