Read this paper. It may help: iFogSim: A Toolkit for Modeling and Simulation of Resource Management Techniques in Internet of Things, Edge and Fog Computing Environments
For implementing functionalities of iFogSim architecture, we leveraged basic event simulation functionalities found in CloudSim. Entities in CloudSim, like data centers, communicate between each other by message passing operations (sending events, to be more precise). Hence, the core CloudSim layer is responsible for handling events between Fog computing components in iFogSim.
It simulates the Cloud, Fog, and pure Edge Computing (mist computing) environments. It supports mobility, supports computing on edge devices, supports the devices heterogeneity, different quality of service requirements. and so on... You can evaluate different architectures (combinations of computing paradigms), implement your load balancing /tasks orchestration algorithm, and much more...
Hi, if you take a look at my publications you will notice that I used Omnet++ for most of my PhD's publications. In my case, I considered latency-sensitive applications on edge computing infrastructures.
Also, have a look at LEAF (https://github.com/dos-group/leaf), it's a new simulator for fog computing environments with a special focus on energy consumption and scalability.
Conference Paper LEAF: Simulating Large Energy-Aware Fog Computing Environments