Multi-objective computation offloading based on Invasive Tumor Growth Optimization for collaborative edge-cloud computing

The rapid development of 5G network-connected Internet of Things (IoT) has attracted great attention of academia and industry with a huge demand for IoT application task processing, which is usually delay-sensitive with the constraints of resource limitation and cost budget. Facing the challenges of massive computing tasks, various users' requirements and resource limitations, this paper formulates a multi-objective optimization problem for computation offloading in a collaborative edge-cloud computing paradigm for handling various types of IoT tasks, aiming to provide efficient computing service to multiple IoT users. With the aim of minimizing task processing delay, mobile device energy consumption and economic cost, a discrete multi-objective Invasive Tumor Growth Optimization algorithm based on Invasive Tumor Growth Optimization is proposed to obtain diverse Pareto-optimal solutions, employing four types of cells with different search strategies to improve the search efficiency, convergence and diversity. Simulation results under complex scenarios show that the proposed algorithm can effectively solve the modeled computation offloading optimization problem of various task types and task scales and can also be well applied to a variety of different computing platforms. Compared with state-of-the-art algorithms, our proposed algorithm achieves better convergence and diversity in three objectives, which implies superior performance, scalability and applicability.