Cloud-fog computing frameworks are emerging paradigms developed to add benefits to the current Internet of Things (IoT) architectures. In such frameworks, task scheduling plays a key role, and the optimized schedule of IoT task requests can improve system performance and productivity. In this paper, we developed an alternative task scheduling technique for IoT requests in a cloud-fog environment based on a modified artificial ecosystem-based optimization (AEO), called AEOSSA. This modification is developed using the operators of the Salp Swarm Algorithm (SSA) in an attempt to enhance the exploitation ability of AEO during the process of finding the optimal solution for the problem under consideration. The performance of the designed AEOSSA approach to tackling the task scheduling problem is evaluated using different synthetic and real-world datasets of different sizes. In addition, a comparison is conducted between AEOSSA and other well-known metaheuristic methods for performance investigation. The experimental results demonstrate the high ability of AEOSSA to tackle the task scheduling problem and perform better than other methods according to the performance metrics such as makespan time and throughput.