Proximity-Driven, Load-Balancing Task Offloading Algorithm for Enhanced Performance in Satellite-Enabled Mist Computing

In an era of rapidly evolving mobile computing, integrating satellite technologies with the Internet of Things (IoT) creates new communication and data management horizons. Our research focuses on the emerging challenge of efficiently managing heavy computing tasks in satellite-based mist computing environments. These tasks, crucial in fields ranging from satellite communication optimization to blockchain-based IoT processes, demand significant computational resources and timely execution. Addressing these challenges, we propose a novel orchestration algorithm, K-Closest Load-balanced Selection (KLS), explicitly designed for satellite-based mist computing. This innovative approach prioritizes the selection of mist satellites based on proximity and load balance, optimizing task deployment and performance. Our experimentation involved varying the percentages of mist layer devices and implementing a round-robin principle for equitable task distribution. The results showed promising outcomes in terms of energy consumption, end-to-end delay, and network usage times, highlighting the algorithm's effectiveness in specific scenarios. However, it also highlighted areas for future improvements, such as CPU utilization and bandwidth consumption, indicating the need for further refinement. Our findings contribute significant insights into optimizing task orchestration in satellite-based mist computing environments, paving the way for more efficient, reliable, and sustainable satellite communication systems.