This paper proposes a superimposed transmission strategy for cooperative cellular and cell-free massive MIMO systems. By classifying users into near and far, the base station transmits an additional data symbol for each near user, superimposed on the signals from distributed access points. Successive interference cancellation is employed at near-user receivers to decode both symbols. The proposed strategy achieves the highest peak spectral efficiency while maintaining fairness at the cell edge, thereby outperforming all the existing network configurations in system capacity.

In this paper, we investigate a marine Internet of Things (M-IoT) network with high altitude platform (HAP) secure computation offloading at risk of eavesdropping. To ensure the security of HAP’s information transmission, we utilize a group of unmanned surface vehicles (USVs) with an HAP to form a non-orthogonal multiple access (NOMA) transmission group to provide co-channel interference. Our goal is to minimize the total energy consumption by jointly optimizing HAP’s computation offloading workload, HAP’s transmission power, data transmission time, and USV’s transmission power while meeting the security and delay requirements. Although this problem is strictly non-convex optimization, we use problem transformation and vertical decomposition methods to decompose the problem into an underlying problem and a top-level problem. The underlying problem is to determine the HAP’s transmission power and HAP’s computation offloading workload, and the top-level problem is to determine the data transmission time, which is solved by using proximal policy optimization (PPO). The two subproblems are solved iteratively over each other to obtain the minimum total energy consumption. Simulation results show that the proposed algorithm converges faster and reduces the energy consumption of 30.34% compared to asynchronous advantage actor-critic (A3C).

This paper seeks to determine the most efficient uplink technique for cell-free massive MIMO systems. Despite offering great advances, existing works suffer from fragmented methodologies and inconsistent assumptions (e.g., single- vs. multi-antenna access points, ideal vs. spatially correlated channels). To address these limitations, we: (1) establish a unified analytical framework compatible with centralized/distributed processing and diverse combining schemes; (2) develop a universal optimization strategy for max-min power control; and (3) conduct a holistic study among four critical metrics: worst-case user spectral efficiency (fairness), system capacity, fronthaul signaling, and computational complexity. Through analyses and evaluation, this work ultimately identifies the optimal uplink technique for practical cell-free deployments.

Whittle index is a heuristic tool that leads to good performance for the restless bandits problem. In this paper, we extend Whittle index to a new multi-agent reinforcement learning (MARL) setting with multiple discrete actions and a possibly changing constraint on the state space, resulting in WIMS (Whittle Index with Multiple actions and State constraint). This setting is common for inventory management where each agent chooses a replenishing quantity level for the corresponding stock-keeping-unit (SKU) such that the total profit is maximized while the total inventory does not exceed a certain limit. Accordingly, we propose a deep MARL algorithm based on WIMS for inventory management. Empirically, our algorithm is evaluated on real large-scale inventory management problems with up to 2307 SKUs and outperforms operation-research-based methods and baseline MARL algorithms.

Cell-free massive multi-input multi-output (MIMO) has recently gained much attention for its potential in shaping the landscape of sixth-generation (6G) wireless systems. This paper proposes a hierarchical network architecture tailored for cell-free massive MIMO, seamlessly integrating co-located and distributed antennas. A central base station (CBS), equipped with an antenna array, positions itself near the center of the coverage area, complemented by distributed access points spanning the periphery. The proposed architecture remarkably outperforms conventional cell-free networks, demonstrating superior sum throughput while maintaining a comparable worst-case per-user spectral efficiency. Meanwhile, the implementation cost associated with the fronthaul network is substantially diminished.

Recently, resource trading has been regarded as a promising solution to deal with the resource scarcity of Internet-of-Things devices (IoTDs) to meet the performance requirements of sixth-generation (6G) networks. As 6G networks evolve to support diverse applications across multiple domains, trading of resources becomes essential to ensure efficient allocation and utilization of resources. However, ensuring transaction security and trust among traders and determining the best trading strategy for mobile virtual network operators (MVNOs) and IoTDs are challenging tasks. In this article, we first explore the resource trading literature and the types of resources IoTDs want to trade. Second, we investigate the trading strategies and pricing models for resource trading in 6G. Third, we present an artificial intelligence (AI)-native blockchain for multidomain resource trading (ABMRT) framework combining blockchain, AI approaches, and trading models that involve multiple MVNOs and IoTDs with varying service demands. The proposed framework is designed to support the diversified resource requirements of the IoTDs in a multidomain trading scenario. Finally, we discuss some challenges and future directions of resource trading in 6G networks.

Multi-agent reinforcement learning (MARL) is employed to develop autonomous agents that can learn to adopt cooperative or competitive strategies within complex environments. However, the linear increase in the number of agents leads to a combinatorial explosion of the action space, which may result in algorithmic instability, difficulty in convergence, or entrapment in local optima. While researchers have designed a variety of effective algorithms to compress the action space, these methods also introduce new challenges, such as the need for manually designed prior knowledge or reliance on the structure of the problem, which diminishes the applicability of these techniques. In this paper, we introduce Evolutionary action SPAce Reduction with Knowledge (eSpark), an exploration function generation framework driven by large language models (LLMs) to boost exploration and prune unnecessary actions in MARL. Using just a basic prompt that outlines the overall task and setting, eSpark is capable of generating exploration functions in a zero-shot manner, identifying and pruning redundant or irrelevant state-action pairs, and then achieving autonomous improvement from policy feedback. In reinforcement learning tasks involving inventory management and traffic light control encompassing a total of 15 scenarios, eSpark consistently outperforms the combined MARL algorithm in all scenarios, achieving an average performance gain of 34.4 two types of tasks respectively. Additionally, eSpark has proven to be capable of managing situations with a large number of agents, securing a 29.7 improvement in scalability challenges that featured over 500 agents. The code can be found in https://github.com/LiuZhihao2022/eSpark.git.

Low Earth Orbit (LEO) satellite networks provide global connectivity but are vulnerable to security threats such as link flooding attacks. To defend against such attacks, stateof-the-art approaches employ SDN to acquire a global view of the network, enabling the detection and mitigation of malicious traffic. However, in LEO constellation networks, the distributed nature of satellites across a large spatial scale introduces significant latency in both satellite-to-ground and inter-satellite links, with latency reaching up to tens of milliseconds, while attack traffic dynamically adapts within sub-milliseconds. As a result, existing defense systems face challenges in countering these attacks effectively due to the increased reaction time caused by link latency. In this paper, we leverage programmable switches to build a real-time defense system against link flooding attacks (LFA) in LEO constellation networks. To achieve this, we analyze the practical constraints encountered in the deployment of LFA attacks against state-of-the-art LEO satellite systems. We observe that despite the ability of bots to initiate attack traffic from any location worldwide, an anomalous distribution of flow rate on the affected links can still be detected. We propose SatShield, an in-network defense system that filters out suspicious traffic (heavy flows) in the network and mitigates these threats by leveraging programmable packet scheduling. By using SatShield, we are able to achieve real-time identification and rate-limiting of attacks at line rate on a per-packet basis. We implement SatShield with P4 in a commercial programmable switch and evaluate it with real-world traffic traces. Our evaluation shows that SatShield autonomously identifies LFA attack flows and rapidly mitigates LFA attacks.

Recently, intelligent reflecting surface (IRS)-aided millimeter-wave (mmWave) and terahertz (THz) communications are considered in the wireless community. This paper aims to design a beam-based multiple-access strategy for this new paradigm. Its key idea is to make use of multiple sub-arrays over a hybrid digital-analog array to form independent beams, each of which is steered towards the desired direction to mitigate inter-user interference and suppress unwanted signal reflection. The proposed scheme combines the advantages of both orthogonal multiple access (i.e., no inter-user interference) and non-orthogonal multiple access (i.e., full time-frequency resource use). Consequently, it can substantially boost the system capacity, as verified by Monte-Carlo simulations.

The development of engineering technology, the logistics system composed of wheeled mobile robots (WMR) and automated guided vehicles (AGV) have been widely used in industrial scenes. However, traditional manufacturing scenes with dense layout, such as weaving workshops, have higher requirements for automatic transportation of materials. How to realize the intelligent transportation and management of materials in the manufacturing workshop and balance the efficiency and safety of material processing and transportation is still a great challenge. To address this problem, we designed a logistics system based on cloth-roll handling robot (CHR) and its path tracking hybrid deep reinforcement learning (DRL) considering spatiotemporal efficiency and safety in weaving workshop. This research first focuses on the design of a dynamic observation Markov decision-making process that integrates scene features. Further, a deep reinforcement learning considering the heterogeneity of observation data is proposed to obtain the optimal action solution. Then, a distributed scenarios training is implemented to improve the interaction ability between agents and the environment in complex scenes. In addition, the balance between dynamic observation and on-site calculation is considered in the path tracking for actual weaving workshop.

Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment. This paradigm is applicable to various industrial scenarios such as autonomous driving, quantitative trading, and inventory management. However, applying MARL to these real-world scenarios is impeded by many challenges such as scaling up, complex agent interactions, and non-stationary dynamics. To incentivize the research of MARL on these challenges, we develop MABIM (Multi-Agent Benchmark for Inventory Management) which is a multi-echelon, multi-commodity inventory management simulator that can generate versatile tasks with these different challenging properties. Based on MABIM, we evaluate the performance of classic operations research (OR) methods and popular MARL algorithms on these challenging tasks to highlight their weaknesses and potential.

The current focus of academia and the telecommunications industry has been shifted to the development of the six-generation (6G) cellular technology, also formally referred to as IMT-2030. Unprecedented applications that 6G aims to accommodate demand extreme communications performance and, in addition, disruptive capabilities such as network sensing. Recently, there has been a surge of interest in terahertz (THz) frequencies as it offers not only massive spectral resources for communication but also distinct advantages in sensing, positioning, and imaging. The aim of this paper is to provide a brief outlook on opportunities opened by this under-exploited band and challenges that must be addressed to materialize the potential of THz-based communications and sensing in 6G systems.

针对现有的带式输送机煤量检测方法会受到井下昏暗环境的影响,识别精度不高的问题,提出一种适用于井下环境的带式输送机煤量检测方法.基于深度图像的获取不受井下昏暗环境影响的特点,以深度相机获取的不同煤量深度图像为研究对象,对其进行滤波处理以滤除干扰信息并增强特征信息,提出一种DID-CNN识别网络对滤波后的煤量深度图像进行特征提取,并最终将煤量分为3 个不同类别作为检测结果,该结果可用于胶带机带速的分级调控.结果表明:所提出的煤量检测模型的准确率达到99.3%,模型的F1 分数为0.991,平均检测每张图片的时间为0.024 3 s.基于深度图像的带式输送机煤量检测方法可以有效消除井下昏暗环境对煤量检测造成的干扰,具有较高的检测精度和较快的处理速度.该方法可为提高带式输送机运输效率、实现节能降耗以及延长设备使用寿命等方面提供支持.

An approach for photonic generation of multilevel frequency-hopping (FH) microwave signal based on a Sagnac loop is proposed and investigated. In the Sagnac loop, several Mach-Zehnder Interferometers (MZI), driven by the coding signals, are connected in series to act as a tunable photonic filter. By carefully adjusting the coding signals, the photonic filter can select the specific frequency component from the input optical frequency comb (OFC), so as to generate multilevel FH microwave signal. Theoretical analysis and simulation works are per-formed to demonstrate a 7-level FH microwave signal generator, and the discussion about the impact of non-ideal factors is given. The approach features high FH speed, wideband and amenable to photonic integration. In addition, the Sagnac loop ensures the equal optical path for clockwise and counterclockwise lights, which can enhance signal performance due to the better phase stability.

This paper presents a new nonsingular fast terminal sliding mode back-stepping control (BSC) for uncertain nonlinear systems subjected to unknown mismatched disturbance based on an adaptive super-twisting sliding mode nonlinear disturbance observer (ASTSM-NDO). The proposed algorithms utilize BSC technique to manage high-order uncertainty systems by compounding the dynamic surface control (DSC) architecture to get rid of ‘complexity explosion’. To cope with the unknown upper-bound mismatched disturbance, an adaption law is devised by finite time stability ASTSM-NDO designation. Besides, in the last step, the actual control scheme is designed by an integral nonsingular fast terminal sliding mode control algorithms combined with disturbance estimation and uncertainty adaption law to eliminate the influence of modeling error and mismatched interference on systems. Lya-punov stability theory is applied to prove that the tracking deviation of the whole system is uniformly and ultimately bounded. Finally, two examples are simulated by comparing the derived outcomes with existing method to verify the effectiveness and feasibility of the devised methodology.

This paper investigates memory nonfragile mixed-objective output feedback robust model predictive control (OFRMPC) for a class of uncertain systems subjected to physical constraint, bounded disturbance, unmeasurable delayed state and possible controller fragility. By employing a delay-independent Lyapunov-Krasovskii function and linear matrix inequality (LMI) framework, novel sufficient conditions for the proposed memory non-fragile OFRMPC are derived to asymptomatically stabilize the closed-loop system with guaranteed H∞/H2 performance for all admissible polytopic uncertainties, external disturbance, state delay, and additive or multiplicative gain perturbation. A key technique for this controller is the online optimization of an infinite-horizon objective function followed by a memory output feedback control law based on the pre-specified offline state estimator using modified quadratic bounded conditions. Moreover, the input constraint and the recursive feasibility have been further guaranteed via additional LMI-based conditions. Finally, a numerical example is given to illustrate the effectiveness of the proposed OFRMPC approach.

Drug-target interactions (DTIs) prediction plays an important role in the process of drug discovery. Most computational methods treat it as a binary prediction problem, determining whether there are connections between drugs and targets while ignoring relational types information. Considering the positive or negative effects of DTIs will facilitate the study on comprehensive mechanisms of multiple drugs on a common target, in this work, we model DTIs on signed heterogeneous networks, through categorizing interaction patterns of DTIs and additionally extracting interactions within drug pairs and target protein pairs. We propose signed heterogeneous graph neural networks (SHGNNs), further put forward an end-to-end framework for signed DTIs prediction, called SHGNN-DTI, which not only adapts to signed bipartite networks, but also could naturally incorporate auxiliary information from drug-drug interactions (DDIs) and protein-protein interactions (PPIs). For the framework, we solve the message passing and aggregation problem on signed DTI networks, and consider different training modes on the whole networks consisting of DTIs, DDIs and PPIs. Experiments are conducted on two datasets extracted from DrugBank and related databases, under different settings of initial inputs, embedding dimensions and training modes. The prediction results show excellent performance in terms of metric indicators, and the feasibility is further verified by the case study with two drugs on breast cancer.

Most object detection methods based on deep learning require large amounts of labeled data and can detect only the categories in the training set. Such issues significantly limit applications in remote sensing scenarios where it usually needs to recognize novel, unseen objects given very few training examples. To address these limitations, a novel meta-learning-based object detection method using Faster R-CNN framework is proposed for optical remote sensing image. Specifically, a diversity measurement module is proposed to measure diversity information between support images and query images on base classes so as to acquire more meta-knowledge. Experiments on DIOR dataset demonstrate our method has achieved superior performance than state-of-the-art meta-learning detection models in the field of remote sensing.