With the rapid expansion of large-bandwidth grid services in recent years, efficient resource allocation has become a critical challenge. This paper explores an optimized resource allocation strategy that integrates satellite communication technology to ensure efficient and stable grid communication services in high-bandwidth scenarios. The main contributions of this study are as follows: we propose a two-stage prediction–allocation closed-loop framework for high-throughput-satellite (HTS)–enabled smart-grid communications. The framework comprises an attention-based traffic-prediction module and a dynamic bandwidth-allocation module, which respectively provide accurate forecasts of future node traffic and priority-aware multibeam bandwidth optimization, thereby offering end-to-end decision support for satellite resource scheduling. Experimental results show that the proposed scheme enhances the grid’s adaptability to future traffic variations at communication nodes, addresses bandwidth provisioning under uncertain high-bandwidth conditions, improves priority-aligned bandwidth utilization and priority efficiency, and ensures both the stability of large-bandwidth grid communications and the performance of critical services.

Low-Earth orbit (LEO) satellite networks can achieve global network coverage without geographical restrictions and are essential to the future communication network. In this article, we study the computing offloading problem in a satellite-terrestrial integrated network for the Internet of Remote Things (IoRT), which aims to reduce the total cost (weighted sum of energy consumption and delay), and jointly offload node selection, offloading ratio, and computational resource allocation to achieve the dynamic management of network resources. First, we propose a hybrid cloud and satellite multilayer multiaccess edge computing (MEC) network architecture that can provide heterogeneous computing resources to terrestrial users. Subsequently, since the problem under consideration is a mixed-integer nonlinear programming problem, we propose a computing offloading algorithm for multiagent reinforcement learning, which is an integration of double deep Q learning (DDQN) and deep deterministic policy gradient (DDPG). The algorithm can learn the optimal policy for actions containing a mixture of discrete and continuous variables. Finally, an optimal computational resource allocation scheme is proposed to improve the task computation efficiency. Simulation results show that the proposed task offloading and resource allocation scheme can achieve reasonable scheduling of computational tasks and optimal allocation of computational resources, reducing the cost of task computation.

A robotic locker system is needed where automated storage and retrieval of items are required without the need for staff presence. For example, a robot can provide 7/24 available services of medical items pick-up and return, during the COVID-19 pandemic (or under other emergencies). A robotic locker system is usually equipped with a user-friendly intuitive interface (e.g., a touchscreen); meanwhile, the robot desires a multitask agent that can observe, understand, and operate the locker’s interface to complete many tasks of storing/accessing/shipping items. In this article, we study building a multitask agent for interacting with robotic locker systems, called AgentMario. Without human intervention for a specific task, AgentMario decomposes solving a task into learning basic skills (states or user interfaces) and planning over the skills (finding the next state/interface). When the agent is solving a task, our search algorithm walks on the finite state machine graph and generates the proper plans (operation sequence) for the agent. In experiments, our method accomplishes four diverse tasks of picking-up/storing/dropping-off/shipping items. By employing image recognition and mechanical automation technologies, we implement AgentMario with a robot arm to enable contactless operation over the locker’s interface. Experimental results show that our method outperforms baselines in most tasks by a large margin.

The healthcare landscape is increasingly challenged by the need for efficient management of medical resources amidst advancing medical technology and aging populations. Traditional medical resource management systems often suffer from limitations in data collection and system stability, hindering decision-making and impacting service quality. However, the advent of IoT (Internet of Things) and cloud computing technologies has revolutionized medical resource management by enabling seamless data integration and storage across multiple layers. This paper introduces, MedSync, a multi-layered medical resource management system with Cloud-Edge Synergy by simultaneously leveraging IoT and cloud computing technologies. By efficiently coordinating data service and storage across four layers, a.k.a., the smart terminal layer, the hospital center layer, the SPD (Supply Processing and Distribution) edge layer, and the SPD cloud layer, the system provides hospitals with a comprehensive, intelligent solution for resource management. Through collaborative operation, hospitals can better understand patients’ needs, adjust medical plans, and enhance service effectiveness and satisfaction. Moreover, the system enhances management and decision support, thus improving operational efficiency and service quality. Through detailed system design, implementation, and efficacy evaluation, this paper offers novel insights and approaches for medical resource management, aiming to elevate service standards and patient experiences.

This article considers a two-hop wireless-powered relay network consisting of multiple sources, multiple destinations, and one relay. The relay can receive energy from the sources and forward data to the destinations. We focus on the source selection problem during the energy transfer process and the resource allocation problem during the data transmission process. First, the relay can choose among all sources based on the transferred energy from the sources. A credit mechanism is introduced for the relay to achieve optimal selection. Second, a Stackelberg differential game-based model is adopted for the resource allocation problem in the data transmission process, using the differential equation to describe the dynamic variation of energy, and the Stackelberg game to describe the relationships between the sources and the relay. In the proposed approach, both sources and relays consider energy consumption and energy revenue. To find the optimal solutions, an adaptive dynamic programming-based algorithm is utilized. The Lyapunov-based stability analysis shows that the system has uniform ultimate boundedness and convergence. Finally, the trained neural networks can achieve optimal resource allocation strategies. Through extensive simulation experiments, the effectiveness of the proposed algorithm is verified.

Unmanned aerial vehicle (UAV) communications have become a prominent technology for emergency communications to enhance network services. This article investigates computing offloading and resource allocation in nonorthogonal multiple access (NOMA)-based UAV emergency communication scenarios. To minimize the computational overhead of the terminal device, a joint task offloading and resource allocation problem is investigated, where the computation overhead of the marine Internet of Things (IoT) device is measured as a weighting of the task completion time and the energy consumption of the device. The optimization of the transmission of IoT devices, the allocation of computing resources to UAVs, task offloading, and carrier allocation are formulated in the considered problem, which is an NP-hard mixed integer nonlinear programming problem. To reduce the complexity, we decompose it into two parts from the property of the problem: 1) the resource optimization problem and 2) the task offloading problem. To solve the resource allocation problem, we first decouple the problem and then use the proposed quasi-convex and convex optimization methods. Meanwhile, a low-complexity task offloading algorithm is designed to achieve a Nash-stable solution by introducing a coalition game approach based on this. Numerical results verify the algorithm’s effectiveness and are compared with other schemes in the literature.

In this paper, we propose a multi-leader multi-follower Stackelberg game model for the resource allocation problem between edge nodes and terminal users in the multi-access edge computing system. In the proposed model, the edge nodes can set the price of edge computing resources according to the strategies of other nodes and predict users’ behaviors. Subsequently, the terminal users can choose their optimal strategies based on the price strategies of edge nodes. A game theory based algorithm is proposed to find the optimal pricing strategies and optimal resource allocation solutions by solving the Nash equilibriums, so that the benefits of both edge nodes and terminal users are optimally satisfied. Simulation results show that the proposed approach yields a high utility at the equilibrium.