Optimized Task Group Aggregation-Based Overflow Handling on Fog Computing Environment Using Neural Computing

It is a non-deterministic challenge on fog computing network to schedule resources or jobs in manner that increases device efficacy and throughput, diminishes reply period, maintains the system well-adjusted. Using Machine Learning as component of neural computing, we developed an improved Task Group Aggregation (TGA) overflow handling for environments. As result TGA usage conjunction with Artificial Neural Network (ANN), may assess model’s QoS characteristics detect overloaded server then move data virtual machines (VMs). Overloaded underloaded will be balanced according parameters, such CPU, memory, bandwidth control concerns help ANN machine learning concept. Additionally, Bee Colony (ABC) algorithm, which system, employed optimization technique separate services users depending their individual qualities. The response time success rate were both enhanced using newly proposed optimized ANN-based algorithm. Compared present work’s minimal reaction time, total improvement average about 3.6189 percent, Resource Scheduling Efficiency has by 3.9832 percent. In terms efficiency resource scheduling, rate, task completion are improved. TGA-based domain enhances compared current approaches. Fog example, demonstrates how artificial intelligence-based systems can made more efficient.