By delegating the infrastructure management, such as provisioning or scaling to third-party providers, serverless edge computing has recently been widely adopted in several applications, especially Internet of Things (IoT) applications. Task scheduling is a critical issue in serverless edge computing as it significantly impacts the quality of user experience. In contrast to the centralized scheduling in the cloud center, serverless edge task scheduling is more challenging due to the heterogeneous and resource-constrained nature of edge resources. This article aims to study the distributed task scheduling for the IoT in serverless edge computing networks, in which heterogeneous serverless edge computing nodes are rational individuals with interests to optimize their own scheduling utility while the nodes only have access to local observations. The task scheduling competition process is formulated as a partially observable stochastic game (POSG) to enable serverless edge computing nodes to noncooperatively schedule tasks and allocate computing resources depending on their locally observed system state, which takes into account the associated task generation state, data queue state, communication channel state, and previous computing resource allocation state. To solve the proposed POSG and deal with the partial observability, a multiagent task scheduling algorithm based on the dueling double deep recurrent $Q$ -network (D3RQN) method is developed to approximate the optimal task scheduling and resource allocation solution. Finally, extensive simulation experiments are conducted to validate the effectiveness and superiority of the proposed scheme.

In this article, we propose a multilayer Ka/Q-band satellite–terrestrial integrated network for the Internet of Remote Things (IoRT) to achieve a high transmission rate with communication robustness in dynamic network environments. Under this architecture, we investigate how to jointly manage the offloading path selection and resource allocation to offload computation-intensive and delay-sensitive tasks in the IoRT. Considering continuous low earth orbit (LEO) satellite movements and Markovian rainfall changes, the computation offloading problem is described as a Markov decision process (MDP) formulation with the objective of maximizing the number of offloaded tasks with satisfied delay requirements and minimizing the power consumption of the LEO satellites. A deep reinforcement learning (DRL) approach is leveraged to make optimal decisions by taking account of dynamic queues of IoRT devices, channel conditions that vary with rainfall intensities and satellite positions, and computing capabilities of ground stations. Extensive simulations are conducted to validate the effectiveness and superiority of our proposed scheme.

Edge intelligence is emerging as a new interdiscipline to push learning intelligence from remote centers to the edge of the network. However, with its widespread deployment, new challenges arise in terms of training efficiency and service of quality (QoS). Massive repetitive model training is ubiquitous due to the inevitable needs of users for the same types of data and training results. Additionally, a smaller volume of data samples will cause the over-fitting of models. To address these issues, driven by the Internet of intelligence, this paper proposes a distributed edge intelligence sharing scheme, which allows distributed edge nodes to quickly and economically improve learning performance by sharing their learned intelligence. Considering the time-varying edge network states including data collection states, computing and communication states, and node reputation states, the distributed intelligence sharing is formulated as a multi-agent Markov decision process (MDP). Then, a novel collective deep reinforcement learning (CDRL) algorithm is designed to obtain the optimal intelligence sharing policy, which consists of local soft actor-critic (SAC) learning at each edge node and collective learning between different edge nodes. Simulation results indicate our proposal outperforms the benchmark schemes in terms of learning efficiency and intelligence sharing efficiency.

In this letter, we propose an efficient uplink transmission scheme over ultra-dense low earth orbit (LEO) satellite networks with multiband antennas. A two-timescale transmission resource allocation and frequency band switching optimization framework is established with the objective of maximizing the overall data rate while reducing the band switching cost. The small-timescale transmission resource allocation problem is described as a Markov decision process (MDP) considering continuous LEO satellite movements and Markovian rainfall changes, while the large-timescale satellite band switching is formulated as an integer programming problem. A hierarchical algorithm based on the deep reinforcement learning (DRL) approach and the greedy method is proposed to make efficient decisions. Extensive simulations are conducted to validate the effectiveness and advantages of our proposed scheme.

To comply with the trend of ubiquitous intelligence in 6G, native AI wireless networks are proposed to orchestrate and control communication, computing, data, and AI model resources according to network status, and efficiently provide users with quality-guaranteed AI services. In addition to the quality of communication services, the quality of AI services (QoAISs) includes multiple dimensions, such as AI model accuracy, overhead, and data privacy. This paper proposes a QoAIS optimization method for AI training services in 6G native AI wireless networks. To improve the accuracy and reduce the delay of AI services, we formulate an integer programming problem to obtain proper task scheduling and resource allocation decisions. To quickly obtain decisions that meet the requirements of each dimension of QoAIS, we further transform the single-objective optimization problem into a multi-objective format to facilitate the QoAIS configuration of network protocols. Considering the computational complexity, we propose G-TSRA and NSG-TSRA heuristic algorithms to solve the proposed problems. Finally, the feasibility and performance of QoAIS optimization are verified by simulation.

With the rapid advancement of technology, intelligent applications increasingly require higher computing power, driving the evolution of the end-edge-cloud Collaborative Scheduling (CS) paradigm. However, this paradigm primarily focuses on vertical collaboration, neglecting horizontal coordination among ubiquitous heterogeneous computing resources, leading to imbalanced resource utilization. Fortunately, the Computing Power Network (CPN) has been introduced to facilitate ubiquitous resource coordination through pervasive networks. The core issue in CPN is the CS of network-wide computing tasks, yet most existing research has largely concentrated on offloading decisions while critical aspects of network routing remain underexplored. Therefore, this paper studies the optimization of joint routing and scheduling within large-scale CPNs. Initially, we develop a CS framework that accommodates the return of task computing results. We then incorporate computing information into the routing domain and introduce a CS mechanism based on Compute-aware Routing (CaR), which narrows the scope of routing exchanges and collaborative scheduling. Ultimately, we present a Deep Reinforcement Learning (DRL)-based algorithm to optimize the long-term CS problems based on balanced CaR, enhancing the success rate of computing tasks and ensuring balanced utilization of computing and network resources. The effectiveness of our proposed mechanism and algorithm is confirmed through simulation experiments.