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.

With the development of intelligent connected vehicles (ICVs), there emerge many new services and applications which involve intensive computation. To support the intensive computation in vehicle-to-everything (V2X) communication system, the framework of edge computing networks has been proposed, which exploits the computation ability of edge nodes at the cost of wireless transmission. Hence, it is of vital importance to predict the wireless channel parameters, which can help schedule the system resource management and optimize the system performance in advance. To fulfil this challenge, this paper proposes a novel prediction model based on long short-term memory (LSTM) network, which is powerful in capturing valuable information in the sequence and hence is good at analyzing the spatio-temporal correlation in the channel parameters. To validate the proposed model, we conduct extensive simulations to show that the proposed model is quite effective in the channel prediction. In particular, the proposed model can outperform the conventional ones substantially.

In this paper, we investigate the security of a cacheaided multi-relay communication network in the presence of multiple eavesdroppers, where each relay can pre-store a part of the requested files in order to assist secure data transmission from source to destination. If the relays have cached the requested file, then they can directly send it to the destination; otherwise, traditional dual-hop data transmission is used. For both cases, relay selection is performed to assist the secure data transmission. We analyze the network secrecy performance in both scenarios of non-colluding and colluding eavesdroppers, and obtain a closed-form expression for the average secrecy outage probability (SOP), as well as an asymptotic expression for the high mainto-eavesdropper ratio (MER). Through minimizing the network SOP, we further optimize the cache placement by proposing a stochastic sampling based cache learning (SacLe) strategy, which can be implemented in parallel and thus reduces the implementation latency substantially. Numerical and simulation results are finally presented to verify the proposed analysis, and show that the caching strategy has a significant impact on the network secrecy performance through affecting the caching diversity gain and signal cooperation gain at the relays. The proposed SacLe strategy is shown to be able to achieve the optimal performance obtained by the brute force (BF) algorithm.