Mobile edge computation (MEC) is a potential technology to reduce the energy consumption and task execution delay for tackling computation-intensive tasks on mobile device (MD). The resource allocation of MEC is an optimization problem, however, the existing large amount of computation may hinder its practical application. In this work, we propose a multiuser MEC framework based on unsupervised deep learning to reduce energy consumption and computation by offloading tasks to edge servers. The binary offloading decision and resource allocation are jointly optimized to minimize energy consumption of MDs under latency constraint and transmit power constraint. This joint optimization problem is a mixed integer nonconvex problem which result in the gradient vanishing problem in backpropagation. To address this, we propose a novel binary computation offloading scheme (BCOS), in which a deep neural network (DNN) with an auxiliary network is designed. By using the auxiliary network as a teacher network, the student network can obtain the lossless gradient information in joint training phase. As a result, the sub-optimal solution of the optimization problem can be acquired by the learning-based BCOS. Simulation results demonstrate that the BCOS is effective to solve the binary offloading problem by the trained network with low complexity.

Traditional wireless data aggregation (WDA) technology based on the principle of separated communication and computation is difficult to achieve large-scale access under the limited spectrum resources, especially in scenarios with strict constraints on time latency (e.g. autonomous driving). To solve this problem, Over-the-Air Computation (AirComp) has emerged as a new fast WDA solution. AirComp can perform ultra-high-speed wireless data aggregation in the scenario of limited communication capacity. In this paper, to overcome the disadvantage of wireless channel propagation, we use reconfigurable intelligent surface (RIS) to assist AirComp. As far as we know, most of the research on AirComp is focused on optimizing aggregation errors. Most edge devices of the Internet of Things (IoT) are battery-powered. Therefore, optimizing the transmit power of devices could prolong the life cycle of nodes and save the system power consumption. In this paper, we aim for minimizing the system transmit power subject to maximum tolerable aggregation error constraint, while ensuring that each device rate meets the minimum rate constraint. Unfortunately, the problem presented is a very tricky non-convex problem. To solve the proposed thorny problem, we propose a two-step optimization method. Specifically, we introduce matrix lifting technology to transform the original problems into semidefinite programming problems (SDP) in the first step and then propose an alternate difference-of-convex (DC) framework to solve SDP subproblems. The numerical results show that RIS-assisted communication can greatly save system power and reduce aggregation error. And the proposed alternate DC method is superior to the alternate SDR method.