Edge computing, as a new computing paradigm, is designed to share resources of edge devices, such as CPU computing ability, bandwidth, storage capacity and so on, to meet the requirements of the real-time response, privacy and security, computing autonomy. With the development of Internet of things (IoT) and mobile Internet technology, edge computing is of great potential of being widely used. This paper investigates the basic features, concepts and definitions, the latest state of art, and the challenge and trends of edge computing. Based on the key challenge of guarantee of users’ quality of experience (QoE), privacy and security in edge computing, we focus on the requirement of users and consider the quality of experience of users to optimize the edge computing system. We integrate three aspects of trust properties, which are identity trust, behavior trust and ability trust, to evaluate resources and users to ensure the success of resource sharing and collaborative optimization in edge computing. This paper also investigates various computing modes such as cloud computing, P2P computing, CS and grid computing, and constructs a multi-layer, self-adaptive, uniform computing model to dynamically match different application scenarios. This model has four contributions: 1) reveal the mechanism of parameters mapping between quality of service (QoS) and quality of experience; 2) construct identity trust, behavior trust of resources and users evaluation mechanisms; 3) form an integrated trust evaluation architecture and model; 4) design a resource scheduling algorithm for stream processing scenario, considering the computing ability, storage capacity and dynamical channel capacity depends on mobility to improve the quality of experience of users. Through this model and mechanism, resources in the end point, edge network, cloud center three levels are expected to be trusted sharing and optimized using, and the users' QoE needs are well satisfied. At last, simulation results show the validity of the model.