In this paper, we investigate a distributed machine learning approach for a multiuser mobile edge computing (MEC) network in a cognitive eavesdropping environment, where multiple secondary devices (SDs) have some tasks with different priorities to be computed. The SDs can be allowed to use the wireless spectrum as long as the interference to the primary user is tolerated, and an eavesdropper in the network can overhear the confidential message from the SDs, which threatens the data offloading. For the considered system, we firstly present three optimization criteria, whereas criterion I aims to minimize the linear combination of latency and energy consumption, criterion II tries to minimize the latency under a constraint on the energy consumption, and criterion III is to minimize the energy consumption under a constraint on the latency. We then exploit a federated learning framework to solve these optimization problems, by optimizing the offloading ratio, bandwidth and computational capability allocation ratio. Simulation results are finally demonstrated to show that the proposed method can effectively reduce the system cost in terms of latency and energy consumption, and meanwhile ensure more bandwidth and computational capability allocated to the user with a higher taskpriority.

This paper quantifies the impact of correlated fading on secure communication of multiple amplify-and-forward (AF) relaying networks. In such a network, the base station (BS) is equipped with multiple antennas and communicates with the destination through multiple AF relays, while the message from the relays can be overheard by an eavesdropper. We focus on the practical communication scenario, where the main and eavesdropper's channels are correlated. In order to enhance the transmission security, transmit antenna selection is performed at the BS, and the best relay is chosen according to the full- or partial-relay selection criterion, which relies on the dual-hop relay channels or the second-hop relay channels, respectively. For these criteria, we study the impact of correlated fading on the network secrecy performance, by deriving an analytical approximation for the secrecy outage probability and an asymptotic expression for the high main-to-eavesdropper ratio. From these results, it is concluded that the channel correlation is always beneficial to the secrecy performance of full relay selection. However, it deteriorates the secrecy performance if partial-relay selection is used, when the number of antennas at the BS is less than the number of relays.

In this article, we investigate a communication and computation problem for industrial Internet of Things (IoT) networks, where K relays can help accomplish the computation tasks with the assist of M computational access points. In industrial IoT networks, latency and energy consumption are two important metrics of interest to measure the system performance. To enhance the system performance, a three-hierarchical optimization framework is proposed to reduce the latency and energy consumption, which involves bandwidth allocation, off-loading, and relay selection. Specifically, we first optimize the bandwidth allocation by presenting three schemes for the second-hop wireless relaying. We then optimize the computation off-loading based on the discrete particle swarm optimization algorithm. We further present three relay selection criteria by taking into account the tradeoff between the system performance and implementation complexity. Simulation results are finally demonstrated to show the effectiveness of the proposed three-hierarchical optimization framework.

In this paper, we study a multiuser mobile edge computing (MEC) network, where tasks from users can be partially offloaded to multiple computational access points (CAPs). We consider practical cases where task characteristics and computational capability at the CAPs may be time-varying, thus, creating a dynamic offloading problem. To deal with this problem, we first formulate it as a Markov decision process (MDP), and then introduce the state and action spaces. We further design a novel offloading strategy based on the deep Q network (DQN), where the users can dynamically fine-tune the offloading proportion in order to ensure the system performance measured by the latency and energy consumption. Simulation results are finally presented to verify the advantages of the proposed DQN-based offloading strategy over conventional ones.

Although the frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) system can offer high spectral and energy efficiency, it requires to feedback the downlink channel state information (CSI) from users to the base station (BS), in order to fulfill the precoding design at the BS. However, the large dimension of CSI matrices in the massive MIMO system makes the CSI feedback very challenging, and it is urgent to compress the feedback CSI. To this end, this paper proposes a novel dilated convolution based CSI feedback network, namely D ilated C hannel R econstruction Net work (DCRNet). Specifically, the dilated convolutions are used to enhance the receptive field (RecF) of the proposed DCRNet without increasing the convolution size. Moreover, advanced encoder and decoder blocks are designed to improve the reconstruction performance and reduce computational complexity as well. Numerical results are presented to show the superiority of the proposed DCRNet over the conventional networks. In particular, compared to the state-of-the-arts (SOTA) networks, the proposed DCRNet can achieve almost the same performance while reduce floating point operations (FLOPs) by about 30%.

In this paper, we investigate how to deploy computational intelligence and deep learning (DL) in edge-enabled industrial IoT networks. In this system, the IoT devices can collaboratively train a shared model without compromising data privacy. However, due to limited resources in the industrial IoT networks, including computational power, bandwidth, and channel state, it is challenging for many devices to accomplish local training and upload weights to the edge server in time. To address this issue, we propose a novel multi-exit-based federated edge learning (ME-FEEL) framework, where the deep model can be divided into several sub-models with different depths and output prediction from the exit in the corresponding sub-model. In this way, the devices with insufficient computational power can choose the earlier exits and avoid training the complete model, which can help reduce computational latency and enable devices to participate into aggregation as much as possible within a latency threshold. Moreover, we propose a greedy approach-based exit selection and bandwidth allocation algorithm to maximize the total number of exits in each communication round. Simulation experiments are conducted on the classical Fashion-MNIST dataset under a non-independent and identically distributed (non-IID) setting, and it shows that the proposed strategy outperforms the conventional FL. In particular, the proposed ME-FEEL can achieve an accuracy gain up to 32.7% in the industrial IoT networks with the severely limited resources.