Feedback Learning in Software-Defined Mobile Network for Resource Aware Load Balancing Under Fault Tolerance Conditions

Abstract

Fault-tolerant-based load balance resource allocation can help in the explosive data flow in the mobile network. System parameter function, system load factors, network-level configuration, network characteristics, and routing parameters are all affected by volatile data. In today's era of Big Data, one of the most important areas of study in mobile communications is how to adapt to traffic flow. The accessibility of load balancing sensors helps eliminate delays, which in turn helps reduce energy consumption and shorten execution time. In this research, we present a load balancing method for software-defined mobile networks (SDMNs) that is known to maximize the utility of the sensors by considering both the processing power of the sensors and the requirements of their sources. A proactive action technique that takes advantage of the wireless facility is proposed, and a wireless load balancing design solution using the learning method is then utilized in the designed framework. To achieve high resource utilization, we use a method based on convergence. Intelligent resource utilization by multiple sensor devices can help to cope with high bandwidth applications such as multimedia in mobile networks. Compared to conventional methods, the model has the potential to achieve better results.