Intelligent Offloading in Vehicular Edge Computing: A Comprehensive Review of Deep Reinforcement Learning Approaches and Architectures
arXiv:2502.06963v3 Announce Type: replace Abstract: The increasing complexity of Intelligent Transportation Systems (ITS) has led to significant interest in computational offloading to external infrastructures such as edge servers, vehicular nodes, and UAVs. These dynamic and heterogeneous environments pose challenges for traditional offloading strategies, prompting the exploration of Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) as adaptive decision-making frameworks. This survey presents a comprehensive review of recent advances in DRL-based offloading for vehicular edge
The increasing complexity and dynamism of Intelligent Transportation Systems (ITS) are driving the need for more sophisticated and adaptive computational offloading solutions in vehicular edge computing.
This review consolidates advancements in Deep Reinforcement Learning (DRL) for vehicular edge computing offloading, highlighting critical research directions and practical applications that will shape the future of autonomous vehicles and smart cities.
The focus on DRL signifies a shift towards highly adaptive, intelligent decision-making systems for managing computational resources in dynamic, real-world vehicular networks, improving efficiency and reliability.
- · Autonomous vehicle manufacturers
- · Smart city infrastructure developers
- · AI/ML research institutions
- · Edge computing hardware providers
- · Traditional fixed-logic offloading algorithm developers
- · Cloud-only computing service providers in mobility
- · Legacy ITS solutions
Improved efficiency and responsiveness of vehicular edge computing systems through DRL-optimized offloading.
Accelerated development and deployment of fully autonomous transportation systems and advanced driver-assistance features enabled by robust edge intelligence.
Enhanced urban mobility and safety, potentially leading to new business models in logistics, ride-sharing, and smart city services.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG