This is the authors' abstract. We don't add key points for this paper.
This paper proposes a distributed cloud model predictive control (DCMPC) approach with delay compensation tailored for heterogeneous vehicle platoons. Leveraging the cloud's extensive computational power and scalability, this method aims to enhance control over complex vehicle platoon systems. Despite the benefits, network delays inherent in cloud-based systems can severely impact control performance. To address this challenge, our method incorporates a tube-based model predictive control (MPC) framework. This innovative approach effectively compensates for the delays associated with cloud control processes. In our solution, the DCMPC algorithm, which is computationally demanding, is executed in the cloud. Simultaneously, a feedback compensator is implemented at the vehicle edge to improve the robustness of the system and ensure coordinated platoon control. We validate the proposed algorithm through simulation experiments involving heterogeneous vehicle platoons. The results demonstrate the algorithm's effectiveness across various scenarios with different delay upper bounds, confirming its capability to manage delays and maintain good control performance.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: