Mobile Edge Computing (MEC) is a promising technique to enhance computation capacity at the edge of mobile networks. The joint problem of partial offloading decision, offloading scheduling and resource allocation for MEC systems is a challenging issue. In this paper, we investigate the joint problem of partial offloading scheduling and resource allocation for MEC systems with multiple independent tasks. A partial offloading scheduling and power allocation problem in single-user MEC systems is formulated. The goal is to minimize the weighted sum of the execution delay and energy consumption while guaranteeing the transmission power constraint of the tasks. The execution delay of tasks running at both MEC and mobile device is considered. The energy consumption of both the task computing and task data transmission is considered as well. The formulated problem is a non-convex mixed-integer optimization problem. In order to solve the formulated problem, we propose a two-level alternation method framework based on Lagrangian dual decomposition. The task offloading decision and offloading scheduling problem, given the allocated transmission power, is solved in the upper level using flow shop scheduling theory or greedy strategy, and the suboptimal power allocation with the partial offloading decision is obtained in the lower level using convex optimization techniques. We propose iterative algorithms for the joint problem of partial offloading scheduling and power allocation. Numerical results demonstrate that the proposed algorithms achieve near-optimal delay performance with a large energy consumption reduction.

Mobile edge computing (MEC) is an emergent architecture, which brings computation and storage resources to the edge of mobile network and provides rich services and applications near the end users. The joint problem of task offloading and resource allocation in the multi-user collaborative mobile edge computing network (C-MEC) based on Orthogonal Frequency-Division Multiple Access (OFDMA) is a challenging issue. In this paper, we investigate the offloading decision, collaboration decision, computing resource allocation and communication resource allocation problem in C-MEC. The delay-sensitive tasks of users can be computed locally, offloaded to collaborative devices or MEC servers. The goal is to minimize the total energy consumption of all mobile users under the delay constraint. The problem is formulated as a mixed-integer nonlinear programming (MINLP), which involves the joint optimization of task offloading decision, collaboration decision, subcarrier and power allocation, and computing resource allocation. A two-level alternation method framework is proposed to solve the formulated MINLP problem. In the upper level, a heuristic algorithm is used to handle the collaboration decision and offloading decisions under the initial setting; and in the lower level, the allocation of power, subcarrier, and computing resources is updated through deep reinforcement learning based on the current offloading decision. Simulation results show that the proposed algorithm achieves excellent performance in energy efficient and task completion rate (CR) for different network parameter settings.

Geographic routing is a research hotspot of the internet of vehicle (IoV) and intelligent traffic system (ITS). In practice, the vehicle movement is not only affected by its characteristics and the relationship between vehicle and position, but also affected by some implicit factors. Pointing to this problem, we combine the vehicle moving position probability matrix, the vehicle position association matrix, and the implicit factors to study the influence of vehicle position potential features, vehicle association potential features, and propose a routing algorithm based on vehicle position analysis (RAVP), which can obtain the more accurate vehicle prediction trajectory. Then, vehicle distance is obtained based on vehicle prediction trajectory. By the normalization of vehicle distance and cache, the vehicle data forwarding capability is obtained and the transmission decision is made. Simulation results show that the proposed algorithm outperforms the other three routing algorithms in terms of packet delivery ratio, average end to end delay and routing overhead ratio.

With the advantages of high mobility and flexible deployment, Unmanned Aerial Vehicle (UAV) combines with Mobile Edge Computing (MEC) is a promising technology. When dynamic Terminal Users (TUs) offload tasks to UAVs, eavesdroppers may eavesdrop on the channel information. The offloading decisions, trajectory plannings of UAVs and resource allocation with the objective of high-capacity secure communication is a challenging problem. In this paper, we design a multi-UAVs MEC system, where the original region is divided into several sub-regions and TUs offload tasks to UAVs which provide computing services for these TUs. Meanwhile, A joint optimization problem of offloading decision, resource allocation and trajectory planning is formulated, where TUs move with the Gauss-Markov random model. In addition, the Base Station (BS) emits jamming signals to evade the eavesdropping of offloading information from eavesdroppers. The goal of the optimization problem is to maximize the TUs’ minimum secure calculation capacity, and a Joint Dynamic Programming and Bidding (JDPB) algorithm is proposed to solve it. The Successive Convex Approximation (SCA) and Block Coordinate Descent (BCD) algorithms are used to handle the resource allocation and trajectory planning problems, and the bidding method is used to address the task offloading decision problem. Simulation results show that JDPB has better performance and better robustness under different parameter settings than other schemes.

Cloud–edge heterogeneous network is an emerging technique built on edge infrastructure, which is based on the core of cloud computing technology and edge computing capabilities. The joint problem of computation offloading, cache decision, and resource allocation for cloud–edge heterogeneous network system is a challenging issue. In this article, we investigate the joint problem of computation offloading, cache decision, transmission power allocation, and CPU frequency allocation for cloud–edge heterogeneous network system with multiple independent tasks. The goal is to minimize the weighted sum cost of the execution delay and energy consumption while guaranteeing the transmission power and CPU frequency constraint of the tasks. The constraint of computing resource and cache capacity of each access point (AP) are considered as well. The formulated problem is a mixed-integer nonlinear optimization problem. In order to solve the formulated problem, we propose a two-level alternation method framework based on reinforcement learning (RL) and sequential quadratic programming (SQP). In the upper level, given the allocated transmission power and CPU frequency, the task offloading decision and cache decision problem is solved using the deep $Q$ -network method. In the lower level, the optimal transmission power and CPU frequency allocation with the offloading decision and cache decision is obtained by using the SQP technique. Simulation results demonstrate that the proposed scheme achieves significant reduction on the sum cost compared to other baselines.