Optimized Energy Management with Fuzzy Clustering for Heterogeneous Fog-Mist-IoT Networks

The rapid expansion of the Internet of Things (IoT) has led to an era dominated by diverse networks, with Mist and Fog computing becoming crucial for closer-to-device data processing. Despite the advantages, the surge of data from numerous devices raises challenges in optimizing system longevity, throughput, and latency. Most past research in Mist-IoT did not fully account for factors like residual energy, device location, workload capacity, butter size, and communication frequency, leading to high energy consumption during data exchanges between IoT and Fog systems. This study aims to address these factors for improved energy efficiency, especially with increasing data volume. It introduces a new approach using a Takagi-Sugeno-Kang (TSK) Type 2 Fuzzy Inference within a Fog-Mist-IoT architecture for smarter resource management during communication and task offloading in IoT ecosystem. Simulation results confirm its effectiveness.