Gallant Ant Colony Optimized Machine Learning Framework (GACO-MLF) for Quality of Service Enhancement in Internet of Things-Based Public Cloud Networking

Load management is a crucial aspect of allocating resources inside a data center for use by the Internet of Things-based public cloud networking (IoT-PCN). It’s a significant pain in the IoT-PCN when queries become bogged down due to the complexity of Internet computing. All virtual machines (VM) must have evenly distributed workloads for load balancing to be effective. Scheduling tasks is a huge step toward improving cloud computing’s overall efficiency. Both are crucial to minimize resource consumption and increase service providers’ output by speeding up the processing time. This research proposes a gallant ant colony optimized machine learning framework (GACO-MLF) balance the load in IoT-PCN that arises rapidly. A machine learning strategy is applied to precisely identify the imbalanced load across IoT-PCN. Ant colony optimization is enhanced to optimize and schedule the imbalanced loads across all data centers. GACO-MLF is evaluated using Cloudsim simulator with standard performance metrics, and the results indicate that GACO-MLF has superior performance than the current strategies.