Abstract We investigate a quality of experience (QoE) based computation offloading scheduling problem for Edge Computing, in which data processing and decision making are placed at the edge of the Internet and close to smart mobile devices and end users. Considering that smart device owners value both response time and battery life, it is reasonable to properly address the latency and energy tradeoff. This paper captures a user-centric view to tackle the offloading scheduling problem via jointly allocating communication and computation resources with consideration of the QoE of users. We formulate our design as a mix-integer non-linear programming (MINLP) problem and solve it in an efficient way by RLT-based branch-and-bound method. Numerical results demonstrate that the proposed offloading scheme achieves an improved performance on latency time and energy consumption, when compared to benchmark schemes.