Tasks Scheduling with Load Balancing in Fog Computing: a Bi-level Multi-Objective Optimization Approach

Fog computing is characterized by its proximity to edge devices, allowing it to handle data near the source. This capability alleviates the computational burden on data centers and minimizes latency. Ensuring high throughput and reliability of services in Fog environments depends on the critical roles of load balancing of resources and task scheduling. A significant challenge in task scheduling is allocating tasks to optimal nodes. In this paper, we tackle the challenge posed by the dependency between optimally scheduled tasks and the optimal nodes for task scheduling and propose a novel bi-level multi-objective task scheduling approach. At the upper level, which pertains to task scheduling optimization, the objective functions include the minimization of makespan, cost, and energy. At the lower level, corresponding to load balancing optimization, the objective functions include the minimization of response time and maximization of resource utilization. Our approach is based on an Improved Multi-Objective Ant Colony algorithm (IMOACO). Simulation experiments using iFogSim confirm the performance of our approach and its advantage over existing algorithms, including heuristic and meta-heuristic approaches.