Abstract
With the advantage of being close to the network, edge cloud-enabled computing mode brings flexibility to task scheduling. However, with the heterogeneity of computing resources between cloud and edge cloud, and the complexity of computing and communication processes between multi-edge cloud, challenges have been brought to the deployment and computing of tasks in cloud-edge collaborative environments. In order to solve this challenge, firstly a deep reinforcement learning controller based cloud-edge collaborative computing framework has been proposed. Then a system QoS model has been estab-lished considering both the user benefits and the service provider benefits. By using deep Q-network, a deep reinforcement learning based collaborative task placement algorithm has been proposed for dynamically optimizing the target system utility. Finally, the experimental results show that the proposed method has a good learning ability for the computing cost of cloud and edge cloud as well as the communication cost between multi-edge cloud. In addition, compared with Q-table learning, random computing and cloud computing, a 10% improvement of system utility has been achieved with the proposed method.