Edge computing (EC) has recently emerged as a promising paradigm that supports resource-hungry Internet of Things (IoT) applications with low latency services at the network edge. However, the limited capacity of computing resources at the edge server poses great challenges for scheduling application tasks. In this paper, a task scheduling problem is studied in the EC scenario, and multiple tasks are scheduled to virtual machines (VMs) configured at the edge server by maximizing the long-term task satisfaction degree (LTSD). The problem is formulated as a Markov decision process (MDP) for which the state, action, state transition, and reward are designed. We leverage deep reinforcement learning (DRL) to solve both time scheduling (i.e., the task execution order) and resource allocation (i.e., which VM the task is assigned to), considering the diversity of the tasks and the heterogeneity of available resources. A policy-based REINFORCE algorithm is proposed for the task scheduling problem, and a fully-connected neural network (FCN) is utilized to extract the features. Simulation results show that the proposed DRL-based task scheduling algorithm outperforms the existing methods in the literature in terms of the average task satisfaction degree and success ratio.

We propose a futures-based resource trading scheme via a forward contract to tackle the risk of trading failure and unfairness associated with the on-site negotiation process in facilitating resource sharing in wireless networks. More specifically, the resource requester and the resource owner negotiate a mutually beneficial forward contract in advance, where the agreement between the two parties are based on the historical statistics related to the resource supply and demand. The risk of trading failure is utilized to determine the contract price and resource amount. Spectrum trading between two different service providers is studied as an example and simulation results show that the proposed futures-based resource trading scheme achieves better performance in terms of success rate and fairness compared with the traditional on-site mechanism.

Sensing begins to rise as a fundamental functionality in integrated sensing and communication (ISAC), especially for sensing-aided communication enhancement (SACE), where base stations (BSs) are promising to perform ubiquitous sensing for communication enhancement. Resource allocation between sensing and communication is a crucial issue in SACE. Therefore, this paper investigates a RIS-assisted SACE (R-SACE) mechanism that jointly designs the time resource allocation between sensing and communication at the BS and the reflecting precoding at the RIS. The performance-guaranteed sensing result obtained at the BS serves as the basis for the proposed R-SACE mechanism, which aims to maximize the average achievable capacity of the RIS-assisted communication link and suppress caused interference. The closed-form expressions of sensing performance metrics are derived. Alternating algorithm (AO) is used to iteratively solve a proved convex optimization subproblem and a transformed quadratic constraint quadratic programming (QCQP) subproblem. Simulation results show priorities of the proposed R-SACE mechanism in enhancing communication capacity while suppressing interference with assists of sensing and RIS.

In the direction of arrival (DOA) estimation problem, when a low-bit analog to digital converter (ADC) is used, the estimation performance severely deteriorates. In this paper, the DOA estimation problem is considered in a low-cost direction finding system with low-bit ADC. To eliminate quantization noise, we propose a novel network ADCnet, which is a composition of fully connected layers and exponential linear unit (ELU) layers, and the input signals are the received signals using low-bit ADC. After the ADCnet, an AtomicNet is also proposed to estimate the DOA from the denoised signals, where atomic vectors are corresponding to the steer vectors. A loss function considering both the reconstruction performance and the sparsity is proposed in the AtomicNet. Different from the exiting atomic norm-based methods, the proposed method can avoid an optimization problem and estimate the DOA with lower computational complexity. Simulation results show that the proposed method outperforms the existing methods in the DOA estimation performance using low-bit ADC.

Technology advancements on sensing, communications, and computing directly accelerate the recent development of Internet of Things (IoT), leading to rich and diverse applications in industry and business processes. For enabling IoT applications, smart devices and networks rely on the capabilities for information collection, processing and tight collaboration with their neighbors. However, the rapid proliferation of IoT devices and real-time IoT applications result in dramatically increased demand for communication and computing resources, posing a significant challenge for the underlying resource constrained wireless networks. Due to their resource constraint, it is extremely difficult for such devices and networks to meet stringent requirements of many real-time IoT applications. To overcome these challenges, resource sharing among IoT devices and networks has been studied as an effective solution by exploiting unused resources.