EdgeSim++: A Realistic, Versatile, and Easily Customizable Edge Computing Simulator
Qiu Lu, Gaoxing Li, Hengzhou Ye · IEEE Internet of Things Journal · 2024
In the edge computing environment, due to factors such as expensive devices, complex scenarios, and fine control requirements, it is necessary to use simulators to construct heterogeneous devices, simulate task offloading scenarios, and evaluate and optimize decision-making algorithms. However, existing edge computing simulators overly simplify the simulation process, neglecting device interactions and task complexities, making it difficult to finely control the task offloading process and customize complex scenarios. We propose EdgeSim++, a realistic, versatile, and easily customizable edge computing simulator. EdgeSim++ has the capability to generate a batch of heterogeneous devices with various features, supporting the simulation of multi-layer cloud-edge-end scenarios and various MEC architectures. It dynamically sets task and device resource attributes, enables devices to interact and schedule behaviors through the network, and facilitates easy customization of both machine learning and non-machine learning offloading strategies. Additionally, EdgeSim++ supports network topology visualization and result visualization, providing intuitive displays of task transmission processes and offloading results, and real-time monitoring of device resource changes. To test the effectiveness of EdgeSim++, we provided default machine learning and non-machine learning offloading strategies, detailed simulation steps, demonstrated scenario construction, showcased process control, monitored resource changes, and compared algorithm effects. The results illustrated that our simulator could realistically simulate complex edge computing scenarios, flexibly control decision processes, and customize complex offloading algorithms, exhibiting good scalability and reusability.