VEC-Sim: A Simulation Platform for Evaluating Service Caching and Computation Offloading Policies in Vehicular Edge Networks

TL;DR

Vehicular Edge Computing (VEC) introduces unique challenges for evaluating service caching and computation offloading due to dynamic mobility and heterogeneous resources. This paper presents VEC-Sim, a modular, Python-based time-slice simulator that realistically models VEC networks, including mobility, caching, and offloading, with DRL-driven SDV mobility and synthetic demand generation. It contributes an end-to-end platform with core entities, pluggable policies, and a rich set of experiments—ranging from caching benchmarks to edge placement studies—validating the simulator against ground truths and demonstrating its capacity to reproduce classical policies and inform deployment decisions. The work enables reproducible, scalable evaluation of VEC strategies and provides a foundation for advancing caching-aware and offloading-aware policies in real-world vehicular networks.

Abstract

Computer simulation platforms offer an alternative solution by emulating complex systems in a controlled manner. However, existing Edge Computing (EC) simulators, as well as general-purpose vehicular network simulators, are not tailored for VEC and lack dedicated support for modeling the distinct access pattern, entity mobility trajectory and other unique characteristics of VEC networks. To fill this gap, this paper proposes VEC-Sim, a versatile simulation platform for in-depth evaluation and analysis of various service caching and computation offloading policies in VEC networks. VEC-Sim incorporates realistic mechanisms to replicate real-world access patterns, including service feature vector, vehicle mobility modeling, evolving service popularity, new service upload and user preference shifts, etc. Moreover, its modular architecture and extensive Application Programming Interfaces (APIs) allow seamless integration of customized scheduling policies and user-defined metrics. A comprehensive evaluation of VEC-Sim's capabilities is undertaken in comparison to real-world ground truths. Results prove it to be accurate in reproducing classical scheduling algorithms and extremely effective in conducting case studies.

Figures (11)

• Figure 1: Network model of the VEC environment
• Figure 2: Request sequence diagram illustrating the cases of cache miss and cache hit, where the user has customized an inter-RSU collaboration mechanism. If the selected RSU lacks the required service image in its cache, it retrieves the image from nearby RSUs with cached copies.
• Figure 3: Architecture of VEC-Sim
• Figure 4: Class diagram of VEC-Sim’s $Env$ package, where the gray boxes (e.g., $Conn$, $CDC$, $SDV$, etc.) represent the primary classes that model the core entities and functionalities of the VEC environment. The yellow boxes (e.g., $Cache$, $ConnStatus$) represent auxiliary classes or data structures that are used by or related to the primary classes.
• Figure 5: Supporting modules working alongside with the core $Env$ package.