The sixth-generation mobile communication systems are faced with the challenge of supporting massive user access while satisfying massive ultra-reliable and low latency communications (mURLLC). Although the cell-free massive multiple input multiple output (CF mMIMO) has significant advantages, seamless coverage is still challenging. Moreover, mURLLC is limited by the mutual constraints of latency, reliability and connection density for a scalable CF mMIMO system. In this paper, we first develop an analytical model of mURLLC based on a scalable CF mMIMO architecture. By introducing the access point planning matrix and combining it with the maximum-ratio combining method, we derive the user’s post-processing signal-to-noise ratio. Second, we employ the finite blocklength theoretical analysis tools to derive the latency and error probability, which can quantify system reliability, and use the connection density metric to portray scalability. Furthermore, we analyze the interplay mechanism between latency, reliability and connection density. Through simulation experiments, we verify the constraints among latency, reliability and connection density, and find that the scalable CF mMIMO can effectively meet mURLLC requirements for massive user access with appropriate parameters.

Amid the rise of Sixth Generation (6G) wireless net-works, expected to support vast connectivity and highly reliable transmissions, devising methods for efficient spectrum reuse is vital. This paper delves into the coexistence challenges facing enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low Latency Communications (URLLC) services in cellular networks, proposing a superposition framework for transmitting multiple URLLC packets alongside a single eMBB user's signal. We've developed a mathematical model and formulated the URLLC allocation as a mixed-integer non-linear program (MINLP) to optimize URLLC admission rates and eMBB rate loss. We utilize one-to-many bipartite matching for eMBB-URLLC pairings and adopt the Non-Orthogonal Multiple Access (NOMA) for superim-posed transmissions, with a power allocation model. For unpaired users, a puncturing approach is used. The subsequent simulation showcases substantial performance gains from our approach.

To meet the extremely low latency requirements of 6G Internet of Things (IoT) services, 6G network should be able to intelligently allocate the network resources. Based on Mobile edge computing (MEC) and network function virtualization (NFV), the 6G NFV/MEC-enabled IoT architecture will be a viable architecture to enable flexible and efficient resource allocation. The architecture will enable the deployment of service function chains (SFCs) in NFV-enabled network edge nodes. However, due to the heterogeneous and dynamic nature of 6G IoT, it is a challenge to deploy SFCs rationally. Therefore, this paper proposes a knowledge-assisted deep reinforcement learning (KADRL) based SFC deployment scheme. The scheme achieves flexible and efficient resource allocation by deploying SFCs at appropriate edge nodes for the requirements of 6G IoT services. Simulation results demonstrate that KADRL can achieve better convergence performance and can meet the requirements of delay-sensitive IoT services.

For the Belief Propagation (BP) algorithm of low-density parity-check (LDPC) codes, existing deep learning methods have a limited performance improvement and it is difficult to train deep-level networks. In this paper, a model-driven quasi-residual network (Quasi-ResNet) BP decoding architecture is proposed for LDPC codes to further improve the performance of standard BP decoding. This method feeds the reliable messages calculated in current iteration into the next iteration based on the shortcut connection, and adjusts the weight of shortcut connection based on the error Back Propagation algorithm of neural network to determine the optimal genetic proportion of reliable messages. The decoding architecture is composed of a model-driven deep neural network (DNN) and shortcut connection. Simulation results show that the decoder can not only unfold more layers quickly compared with the DNN-based BP decoder, but also further improve the decoding performance.

In order to meet the strict quality of service requirements of delay-sensitive networks, this paper studies resource-autonomous decision-making algorithms for 6G MEC networks to improve key performance indicators (KPIs) such as delay, computing rate, and system stability. This paper considers task offloading and resource allocation decisions in multi-user MEC networks with time-varying channels, where user task data arrive randomly. We designed an autonomous decision-making algorithm for Lyapunov Assisted Deep Reinforcement learning (Ly-DRL) that satisfies the data queue stability and average power constraints and maximizes the network computing rate. We construct a dynamic queue of user task data through queue theory and apply Lyapunov optimization theory to decouple the MINLP problem into subproblems for each time slot. Combining DRL and traditional numerical optimization, the subproblems of each slot are solved with low computational complexity. Simulations show that the algorithm performs best while stabilizing the data Queue.

In response to the explosive growth of data computation in vehicular terminals, computation offloading has emerged as a viable solution to mitigate the limitations of resources. Efficient offloading decisions not only meet the demanding requirements of complex vehicular tasks in terms of time, energy consumption, and computational performance but also minimize competition and resource consumption in the network. However, existing work on task offloading in vehicular networks often exhibits certain limitations, such as incomplete consideration of relevant factors or suboptimal utilization of available resources. This research presents the construction of a three-layer vehicular network environment, which is based on cloud and edge computing paradigms. The design entails the formulation of real-time vehicle location tracking and task priority metrics, while also considering the challenges posed by time-varying channels and signal blockage prevalent in vehicular network environments. In this paper, a novel variant of the Deep Deterministic Policy Gradient (DDPG) algorithm NLDDPG is proposed to iteratively train the model, aiming to optimize a weighted objective function. Simulation results show that this algorithm can improve the efficiency and optimize the task average utility.

The coexistence of enhanced mobile broadband (eMBB) and ultra-reliable low-latency communication (URLLC) is common in 5G networks. 5G services require eMBB users to achieve higher data rate, and URLLC users to meet high reliability and low latency requirements. How to utilize limited resources to maximize the throughput of eMBB users in the system while meeting URLLC latency requirements is a very meaningful issue. In this paper, we delve into the latency composition of URLLC packets and subsequently derive an expression to determine the number of mini-slots that URLLC packets can be queued. We propose a greedy scheduling algorithm based on queuing theory, which solves the complex scheduling problem of URLLC packets with different latency requirements. At each mini-slot, we dynamically schedule the URLLC packets that arrive using the proposed algorithm. We demonstrate the significant advantages of our algorithm compared to other algorithms through extensive simulations. Specifically, our algorithm significantly reduces the throughput loss of eMBB users, and also meets the high reliability requirements of URLLC in the case of high URLLC load.

Knowing the network states in time has become an indispensable part of network management. However, as users put forward higher requirements for service experience, only focusing on key performance indicators (KPIs) cannot guarantee the quality of user experience. Key quality indicators (KQIs) can reflect the service performance experienced by users and are considered to be an essential factor in optimizing the network. However, it is an urgent problem to represent the network states with different network indicators. In this paper, we propose a novel intelligent representation scheme by exploring the indepth correlation among multi-layer network indicators. Experiments are carried out using the real dataset of the 5G network, and the simulation results demonstrate the feasibility and accuracy of the proposed scheme.

This paper proposes a multi-critic deep Reinforcement learning framework (MCDRL) and a knowledge-embedded multi-critic deep reinforcement learning(KEMCDRL) Decision-making method, the method can ensure users’ real-time QoS delay requirements. Compared with implementing the deep reinforcement learning algorithm directly in the communication system, this method can accelerate the convergence and guarantee the initial QoS performance of the system. Simulation results show that the design method can significantly reduce the convergence time compared with traditional deep reinforcement learning, and has nearly optimal decision delay compared with existing decision-making methods, which can actualize real-time decision-making in a time-varying channel environment.

The network selection in heterogeneous wireless networks is considered as a crucial technology to take advantage of network resource in the coming fifth‐generation (5G) mobile networks. Considering the emergence of 5G novel services and the guarantee of quality of service requirements, in the study, the authors propose a network selection algorithm based on evolutionary game named NS‐EG, by using analytic hierarchy process to jointly analyse user preferences and service requirements. The utility is structured as a joint function of network decision attributes and available capacity. In addition, the dynamic behaviour of users accessing different networks with replicator dynamics are explicitly provided. In order to verify the superiority of the algorithm proposed, the authors evaluate the evolutionary equilibria as well as the iteration of the algorithm by comparing with the simple additive weighting algorithm, multiplicative exponent weighting algorithm and Q‐learning based algorithm. Simulation results confirm that the proposed algorithm outperforms the contrast algorithms and achieve network load balancing.

Pattern division multiple access (PDMA) is a multi- carrier non-orthogonal multiple access (NOMA), which can meet the requirements of massive user connections and super-high data rate in the fifth generation (5G) wireless networks. In this paper, we work on the optimization of power allocation to improve the performance in the down-link PDMA system with imperfect channel state information (CSI) at transmitter. The outage throughput of the system is maximized by optimizing the power allocation under the constraints of maximum transmits power, minimum user data rate, and outage probability. Since this optimization problem is a probabilistic mixing problem, we first turn it into a non-probability problem. Then, assuming the pattern matrix is known, we propose an iterative power allocation scheme. The closed-form expression of power allocation is derived based on Karush-Kuhn-Tucker (KKT) conditions. The simulation results demonstrate that the proposed iterative power allocation scheme yields better performance over the existing schemes.

With the coming of the fifth-generation (5G) mobile communications, in mobile edge computing (MEC), the growth of user services and the personalization of QoS requirements have posed great challenges for heterogeneous wireless networks (HWNs) access selection. Based on the multiattribute decision theory and the fuzzy logic theory, we propose a novel network selection scheme for multiservice QoS requirements in MEC. The main procedures of the scheme include dynamic adaptive process, fuzzy process, hierarchical analysis, and integrated attributes assessment. The scheme proposed contributes to efficiently reduce the ping-pong effect and effectively select accurate network in a dynamic environment. Simulation results show that our scheme can select network access according to the type of user services and whether to switch networks. In addition, compared with commonly used simple additive weighting (SAW), random access selection (RAS), and price-based and QoS-based network selection scheme, our scheme has better performance in improving average user satisfaction and reducing access failures.

Pattern division multiple access (PDMA) is a multi- carrier non-orthogonal multiple access (NOMA), which can meet the requirements of massive user connections and super-high data rate in the fifth generation (5G) wireless networks. In this paper, we work on the optimization of power allocation to improve the performance of the downlink PDMA system significantly. Considering the perfect channel state information (CSI) is acquired at the transmitter, we propose an iterative power allocation (IPA) scheme based on the integration of the iterative subgradient method and the Mann iterative method. Moreover, Lagrange multipliers and the allocated power are updated until converged in each iteration. It is demonstrated in simulation results that the achievable sum throughput superiority of our proposed scheme over other schemes.

High reliability and low latency, increasingly demanded by mission critical IoT applications, are the two key requirements for modern wireless communication systems. In this paper, we consider a battery-limited wireless machine type communication network where non-orthogonal multiple access (NOMA) is embedded to support massive connectivity. Hence, energy efficient NOMA transmission under statistical delay constraints is required to prolong the battery lifetime of the devices. We firstly derive the probabilistic upper bounds of the queueing delays of NOMA devices via the (min,×) stochastic network calculus. Then, we propose a transmit power optimization algorithm based the probabilistic delay bounds. Simulation results verify the tightness of the derived upper bound of the delay violation probability and thus the effectiveness of the proposed power control algorithm.

Pattern Division Multiple Access (PDMA) is a novel non-orthogonal multiple access scheme proposed to meet the demand of massive connection in the future 5G communications. PDMA is based on the joint design of transmitter and receiver. The multiuser signals are superposed on the multiple signal domains based on different characteristic patterns at the transmitter side, and the successive interference cancellation (SIC) is used to separate the multiuser signals at the receiver side. In this paper, we proposed the enhanced technology of PDMA, named as interleaver-based PDMA (IPDMA). IPDMA scheme could distinguish different user based on different bit-level interleavers, different characteristic patterns, and different combinations of bit-level interleaver and characteristic pattern. Then the iterative decoding and detection was used at the receiver to separate multi-users. Simulation results showed that the proposed IPDMA could improve the block error rate (BLER) performance, compared to the PDMA. And analysis indicated that the complexity of the IPDMA scheme is closed to the PDMA scheme.

Pattern Division Multiple Access (PDMA) is a novel non-orthogonal multiple access scheme proposed to meet the diverse demands on high capacity and large number of connections in the fifth generation (5G) wireless networks. PDMA uses the characteristic pattern to define the sparse mapping from data to a group of resources, and the sparsity of the pattern gives impacts on the capacity performance and detection complexity. In this paper, we considered the pattern assignment and power allocation in downlink PDMA system. The Joint Pattern assignment and Power Allocation (JPPA) scheme based on the optimum Iterative Water-Filling (IWF) algorithm was proposed to optimize the total throughput of all users. The simulation results demonstrated that the proposed JPPA scheme can improve the sum throughput significantly, compared to the Random Pattern assignment and IWF Power Allocation (RPPA) scheme.