Crossl.earning: Vertical and Horizontal Learning for Request Scheduling in Edge-Cloud Systems

With the rapid development of Internet of Things (loT) device performance, edge-cloud systems are generating vast volumes of complex data. Meanwhile, the distributed and multi-layer structure of edge-cloud systems pose significant challenges to scheduling decision-making and convergence of the algorithm. In this paper, from a vertical and horizontal perspective of edge-cloud systems, we propose a deep reinforcement learning (DRL) algorithm called CrossLearning. We apply a curiosity-driven multi-agent learning method horizontally to accelerate the convergence speed of the algorithm. We introduce an inter-layer decision refinement mechanism vertically to address the challenge of inaccurate decision-making. We also refine the service types and levels to efficiently match the various application needs of users in the big data era. Finally, we implement a prototype system on a network hardware system and conduct experiments using real datasets. The evaluation shows that, in comparison to baseline methods, CrossLearning demonstrates significant im-provements in terms of time efficiency and load balance, with a notable enhancement in algorithm convergence speed.