The upcoming development of 5G network is envisioned to offer various types of services like virtual reality/augmented reality and autonomous vehicles applications with low latency requirements in Internet of Things (IoT) networks. Mobile edge computing (MEC) has become a promising solution for enhancing the computation capacity of mobile devices at the edge of network in 5G wireless network. Additionally, multiple radio access technologies (multi-RATs) have been verified with the potential in lowering the transmission latency and energy consumption, while improving the quality of services (QoS). Benefiting from the cooperation of multi-RATs, large latency-sensitive computing service tasks (L2SC) can be offloaded by different RATs simultaneously, which has great practical significance for data partitioned oriented applications with large task sizes. In this paper, to enhance the L2SC offloading services for satisfying low latency requirements with low energy consumption, we investigate the energy-latency tradeoff problem for partial task offloading in the MEC-enhanced multi-RAT network, considering the limitation of energy and computing in capability-constrained end devices in IoT networks. Specifically, we formulated the L2SC task computation offloading problem to minimize the weighted sum of the latency cost and the energy consumption by jointly optimizing the local computing frequency, task splitting and transmit power, while guaranteeing the stringent latency requirement and the residual energy constraint. Due to the non-smoothness and non-convexity of the formulated problem with high complexity, we convert the tradeoff problem into a smooth biconvex problem, and propose an alternate convex search based algorithm, which can greatly reduce the computational complexity. Numerical simulation results show the effectiveness of the proposed algorithm with various performance parameters.

In mobile edge computing (MEC), the computation offloading of massive users could cause the task uploading congestion to deteriorate the users’ offloading delay. The non-orthogonal multiple access (NOMA) enabled MEC is envisioned to address this issue by allowing multiple users to simultaneously upload their tasks on one subchannel. However, the differentiated uploading delay of users may make task uploading completion inconsistent with NOMA decoding order, which complicates the co-channel interference and restricts NOMA to reducing the uploading delay. In this paper, we characterize the interaction between the differentiated uploading delay and co-channel interference for a pair of NOMA users. Furthermore, we propose a computation offloading scheme to reduce the users’ average offloading delay by jointly optimizing offloading decision and resource allocation. Specifically, the proposed scheme first obtains the optimal power allocation based on the characterized interaction and the closed-form solution of computation resource allocation by convex programming. Then, the NOMA user pairing and offloading decision are iteratively determined by semidefinite relaxation and convex-concave procedure. Simulation results show that the proposed scheme effectively mitigates co-channel interference under differentiated uploading delay of users and outperforms in reducing the users’ average offloading delay and increasing the number of users to offload tasks.

The application of deep learning improves the processing speed and the accuracy of automatic modulation recognition (AMR). As a result, it realizes intelligent spectrum management and electronic reconnaissance. However, deep learning-aided AMR usually requires a large number of labeled samples to obtain a reliable neural network model. In practical applications, due to economic costs and privacy constraints, there is a small number of labeled samples but a large number of unlabeled samples. This paper proposes a Transformer-based contrastive semi-supervised learning framework for AMR. First, self-supervised contrastive pre-training of the Transformer-based encoder is completed using unlabeled samples, and data augmentation is realized through time warping. Then, the pre-trained encoder and a randomly initialized classifier are fine-tuned using labeled samples, and hierarchical learning rates are employed to ensure classification accuracy. Considering the problems of applying Transformer to AMR, a convolutional transformer deep neural network is proposed, which involves convolutional embedding, attention bias, and attention pooling. In experiments, the feasibility of the framework is analyzed through linear evaluation of the framework components on the RML2016.10a dataset. Also, the proposed framework is compared with existing semi-supervised methods on RML2016.10a and RML2016.10b datasets to verify its superiority and stability.

The 5G cellular network employs non-orthogonal multiple access (NOMA) to enhance network connectivity and capacity, and device-to-device (D2D) communications to improve spectrum efficiency. However, the underlay D2D communications may destroy the execution condition for the successive interference cancellation (SIC) decoding of NOMA cellular networks by introducing the extra interference, which degrades the cellular transmission reliability. Thus, we develop the interlay mode as a special D2D mode for NOMA system, which enables the power domain multiplexing of the D2D pair and cellular users to eliminate the strong interference between them by the SIC decoding. When D2D pair conducts the selection between the interlay mode and underlay mode, the SIC decoding constraint should be satisfied at both D2D receiver and NOMA base station. In order to maximize the system sum rate while meeting the SIC decoding constraint, we propose a joint D2D mode selection and resource allocation scheme with interlay mode, which can be formulated as a combinatorial optimization problem. To tackle the combinatorial nature of mode selection and spectrum assignment, we first prove that the original problem can be reformulated as a maximum weight clique problem, and then propose a graph-based algorithm by applying branch-and-bound method to obtain its optimal solution. Finally, simulation results are provided to demonstrate that the interlay mode along with the proposed algorithms can coordinate D2D communications and NOMA cellular network to significantly improve the system sum rate and the D2D access rate.

Adaptive bitrate (ABR) streaming has recently been deployed in vehicular networks (VNs) to deal with the time-varying channels due to reasons such as high user mobility. Caching at the wireless edge (e.g., base station) to support ABR streaming is a challenging problem. In the paper, we propose a two time-scale dynamic caching scheme for ABR streaming in VNs, in which the video quality adaptation at the application layer and cache placement at the BS are performed at a larger time-scale while the video data transmission at the physical layer is performed at a smaller time-scale. Lyapunov optimization technique is employed to maximize the time-averaged network reward, which is the weighted sum of video quality and backhual saving. Without the prior knowledge of channel statistics, we develop a dynamic cache algorithm (DCA) to obtain the video quality adaptation, cache placement, and radio bandwidth allocation decisions. For the arbitrary sample path of channel states, we compare the network reward achieved by DCA with that achieved by an optimal T-slot lookahead algorithm, i.e., the knowledge of the future channel path over an interval of length T time slots. Simulation results demonstrate the advantages of DCA for ABR streaming in time-varying VNs over the static cache approach.

6G wireless networks have raised increasing attention with computation-sensitive services such as AI Internet of things (AIoT) and mobile augmented reality/virtual reality (AR/VR) applications. Mobile edge computing (MEC) provides rich computation resources for user equipments (UE) at the edge of networks. Aided by MEC servers, computation-intensive applications that are commonly modeled as Directed Acyclic Graphs (DAG) can be performed locally and offloaded to MEC servers to enhance execution efficiency. However, it is a key issue to efficiently provide low latency with limited energy. In this paper, we investigate a multiobjective task scheduling problem in MEC-aided 6G network. Then, an improved multiobjective cuckoo search (IMOCS) algorithm is proposed to deal with a DAG-based task scheduling problem, which aims to reduce the execution latency and energy consumption of UE. Particularly, the proposed IMOCS algorithm is based on the single-objective cuckoo search algorithm and Pareto dominance. An external archive is used to record nondominated solutions, whose update strategy improves the quality of solutions by the aid of fast nondominated sorting and crowding distance sorting. Simulation results demonstrate that IMOCS algorithm outperforms other four benchmark algorithms, which can provide optimal task scheduling policy for MEC severs in 6G networks.