CLB-LP: Controller Load Balancing Based on Load Prediction Using Deep Learning for Software-Defined IoT Networks

By integrating Software-Defined Networking (SDN), Software-Defined Internet of Things (SD-IoT) simplifies network configuration while enhancing controllability. The expansion of the IoT scale has led to the emergence of the multiple controller architecture. However, it introduces the challenge of controller load imbalances. Existing schemes primarily focus on dynamic switch migration. Nonetheless, conventional strategies use real-time network information for load measurement and selection of candidate switches, which reduces load balancing performance due to inaccurate load measurement. Moreover, existing approaches struggle to balance load balancing rate and migration cost when selecting the target controllers. Therefore, we propose the controller load balancing based on load prediction (CLB-LP) scheme, which uses historical load data to predict future load, thereby avoiding unnecessary switch migrations. Additionally, we introduce a switch selection algorithm that combines load prediction and migration probability to select candidate switches, effectively improving load balancing performance. Furthermore, we present a target controller selection algorithm based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), which improves the load balancing rate while reducing migration cost. Finally, we evaluate the effectiveness of CLB-LP, and compared to existing schemes, its load balancing rate and response time are 29.4% higher and 28.5% lower, respectively.