International Research Journal of Education and Technology

As the internet of things advances the problem of how to handle the created data of devices which are attached to the net becomes crucial. This is where edge computing comes in as an effective solution by carrying out the data analysis processing closer to the data source hence minimizing on latency, bandwidth usage and Cloud dependence. The current paper studies various data offloading approaches in IoT systems using edge computing such as full offloading, partial offloading, collaborative offloading and dynamic task scheduling. It also looks at how these techniques promote improvement of IoT performance in terms of resource consumption, energy efficiency and real time decision making. Offloading is compared with the efficiency and characteristic of the network through case studies and simulations in different domains including smart cites, healthcare, and autonomous systems. Further, it discusses the issues with realizing large-scale deployments at the edge layers of an IoT system and the possible performance, security, and energy trade-offs that accompany them. The study proves useful for understanding further development of the IoT edge computing problem and provides suggestions to enhance data handling and the network. Further, this research seeks to understand the role of edge computing and data offloading on the performance of IoT systems with an overall goal of expanding knowledge of how the growing, connected devices can effectively and efficiently manage the data that they produce.

Keywords: Edge Computing, Internet of Things (IoT), Data Offloading, Latency Reduction, Collaborative Offloading, Resource Optimization