LEABS: A Latency- and Resource-Aware Bi-Directional Service Scheduling Framework for Relay Chains in the Internet of Vehicles

Abstract

Multiple stakeholders such as automakers, service providers, and regulators tend to maintain their own blockchain systems in the Internet of Vehicles (IoV). This fragmentation leads to data silos and hinders service interoperability across domains. Relay Chains are emerging as a cross-chain service-governance layer, enabling coordination among heterogeneous blockchains. However, scheduling multi-input multi-output (MIMO) transactions introduces new challenges, including complex transaction dependencies, heterogeneous node capabilities, and strict latency constraints. To address these issues, this paper proposes LEABS, a bi-directional service-aware scheduling framework that simultaneously considers user-side service quality and relay-chain-side resource governance. LEABS formulates cross-chain transaction scheduling as a service-delivery optimization problem, modeled by a Mixed-Integer Nonlinear Programming (MINLP) formulation and stabilized through Lyapunov-based queue governance. A Deep Reinforcement Learning (DRL) method is further introduced to learn adaptive policies under dynamic workloads and heterogeneous network conditions. Extensive experiments demonstrate that LEABS achieves a superior balance among confirmation latency and load fairness, highlighting its effectiveness as a Quality-of-Service(QoS)-driven cross-chain service-governance mechanism for future IoV ecosystems.