Multi-strategy fusion snake optimizer on task offloading and scheduling for IoT-based fog computing multi-tasks learning

As the 5G era unfolds, the Internet of Things (IoT) has experienced rapid growth. Concurrently, the substantial influx of data traffic and computational demands has placed a strain on the infrastructure of cloud computing. Fog computing framework is regarded as the successor to cloud computing in the next generation, with one of the hurdles in fog computing being the allocation of computational resources to minimize transmission delay and total costs. Addressing the task scheduling issue of Bag-of-Tasks software within cloud-fog environments, a utility function that comprehensively considers node cost, transfer path and transmission delay is selected as the objective function, and a multi-strategy Integrated Snake Optimizer (ISO) is put forward for mathematical modeling. The aim is to alleviate deficiencies in population diversity and speed. This paper utilizes Circle map for initializing the positions of the population, to improve their traversal and non-repetitive characteristics, enhancing the algorithm’s precision and its rate of convergence in the process. The Synergistic Optimization Strategy is adopted in a global search to enhance the diversity of the population. In local search, the elite reverse learning mechanism (ERLM) is introduced to enhance the algorithm’s rate of convergence and the quality of its solutions by strengthening the influence of the optimal individual. Meanwhile, the evolutionary population dynamics introduce the mutation operation into the algorithm, increasing the population’s diversity. Through simulations conducted on 10 different-sized datasets and comparisons with GA, WHO, GWO, WOA, HHO, AOA, and AVOA, the performance of the ISO is validated. The results indicate that the model not only saves total cost but also exhibits good convergence. Compared with existing methods, it also performs better in terms of response speed and transfer path, whilst striking a balance between transmission delay and total cost.