11 January 2022 in IEEE Transactions on Vehicular Technology
The rapid development of maritime activities has led to the emergence of more and more computation-intensive applications. In order to meet the huge demand for wireless communications in maritime environment, mobile edge computing (MEC) is considered as an effective solution to provide powerful computing capabilities for maritime terminals of resource scarcity or latency sensitive. A basic technology to implement MEC is virtual machine (VM) multiplexing, through which multi-task parallel computing on a server is realized. In this paper, a two-layer unmanned aerial vehicles (UAVs) maritime communication network with a centralized top-UAV (T-UAV) and a group of distributed bottom-UAVs (B-UAVs) is established and MEC is used on T-UAV. We aim to solve the latency minimization problem for both communication and computation in this maritime UAV swarm mobile edge computing network. We reformulate this problem into a Markov decision process (MDP), since it is a non-convex and multiply constrained but has the characteristics of MDP. Based on this MDP model, we take deep reinforcement learning (DRL) as our tool to propose a deep Q-network (DQN) and a deep deterministic policy gradient (DDPG) algorithms to optimize the trajectory of T-UAV and configuration of virtual machines (VMs). Using these two proposed algorithms, we can minimize the system latency. Simulation results show that the given solutions are valid and effective.
16 November 2022 in IEEE Transactions on Communications
With the ubiquitous deployment of a massive number of Internet-of-Things (IoT) devices, the satellite-aerial networks are becoming a promising candidate to provide flexible and seamless service for IoT applications. Concerning about the spectrum scarcity issue, we present a cognitive satellite-aerial network where the multiple unmanned aerial vehicles (UAVs) can share spectrum with the satellite without interfering with satellite communications. To further improve spectral efficiency, non-orthogonal multiple access (NOMA) technique is adopted in this network. Considering the delay-sensitive quality-of-service (QoS) requirement, a joint trajectory and power optimization problem is formulated to minimize the total transmission latency over a long-term task period. In order to reduce the computational complexity and ease the burden of information exchange by using the centralized DRL methods, we propose a multi-agent deep deterministic policy gradient (MADDPG) based algorithm which adopts the framework of centralized training with decentralized execution to solve the sophisticated problem. The simulation results show the proposed algorithm can achieve satisfactory performance through joint trajectory control and power allocation for the UAVs compared with other methods.
27 February 2024 in IEEE Internet of Things Journal
Vehicular edge computing (VEC) is considered to be a key technology to improve the processing efficiency of computing tasks for the Internet of Vehicles (IoV). Using roadside units (RSUs) distributed on both sides of a road as edge servers, computation-intensive and latency-sensitive in-vehicle tasks can be responded to quickly. However, some Quality of Service (QoS) is often difficult to ensure due to clogged dense urban buildings or lack of infrastructure in remote areas. In this article, we propose a software-defined network (SDN)-driven partial offloading model for unmanned aerial vehicle (UAV)-assisted VEC networks, where the RSUs and UAVs jointly provide computing services to the vehicles and collect global information through centralized control using an SDN controller. To guarantee these vehicles obtain computing results in time and rationally utilize computing resources, we develop an optimal offloading mechanism using Age of Information (AoI), together with energy consumption and rental price as a comprehensive weighted cost of our above optimization objective. The total system cost of the performing tasks is minimized by jointly optimizing the UAV trajectory, user association, and offloading decision. Considering the mobility of the vehicles and UAVs and the dynamic network environment, we design a deep reinforcement learning (DRL)-based joint trajectory control and offloading allocation algorithm (DRL-TCOA) to solve the proposed computation offloading problem. Experimental results show that the proposed DRL-TCOA algorithm maintains better information freshness and lower system cost than the other baseline offloading strategies.
4 October 2018 in IEEE Access
On the basis of ${\mathcal{ H_\infty }}$ control approach instead of using the conventional optimization method, we present a distributed power allocation algorithm for a cognitive radio network (CRN), where underlying secondary users (SUs) share same licensed spectrum with primary users (PUs) and the channel gain is time-varying between two time slots. Based on the target signal-to-interference-plus-noise ratio (target-SINR) tracking power control (TPC) algorithm in the conventional network and the dynamic description of the channel gain fluctuation in the CRN as a first-order Markov model, we formulate the power allocation in the CRN into a state-space system model with exogenous input. In this time, the core for us becomes to design a ${\mathcal{ H_\infty }}$ state feedback controller obtained by solving a linear matrix inequality (LMI) for this system to realize power allocation for SUs. The SINR requirement of SUs and the interference temperature (IT) constraint of all PUs can be guaranteed. According to this controller design principle, we also give a ${\mathcal{ H_\infty }}$ delay-independent state feedback controller to treat time-delay for the protection of the communication performance. Simulation results demonstrate the validity, effectiveness, and advantages of this approach compared with the algorithms obtained by the optimization theory for the power allocation in CRNs.
5 July 2021 in IEEE Internet of Things Journal
Green wireless communications have been extensively studied in wireless sensor networks (WSNs), including the use of new energy, renewable energy, and low-power consumption and energy-saving technologies for years. In these networks, due to channel fading, insufficient and random energy arrival, some possible bad deployment of sensors, etc., the communication among sensor nodes in a WSNs will inevitably be affected or even interrupted sometimes, which may result in unacceptable performance in the entire network. In order to solve this problem, we propose a WSN composing of several local subnetworks with amplified forwarding relay and specially designed working time cycle. In this network, we study our resource allocation policies to manage both power and time for throughput maximization. We use deep reinforcement learning (DRL) to develop our resource allocation policies under the model constructed as a Markov decision process for this optimization problem in the subnetwork. We apply an actor–critic strategy to find our optimal solution in continuous state and action space and adaptively achieve maximum throughput of this network based on energy harvesting, causal information of battery state and channel gains. The simulation results demonstrate that the proposed transmission policies can produce higher throughput in the local network and finally improve overall system performance in comparison with greedy policy, random policy, and conservative policy.
14 June 2019 in IEEE Access
Recently, multi-floor indoor positioning has become increasingly interesting for researchers, in which accurate recognition of indoor activities is critical for the detection of floor changes and the improvement of positioning accuracy according to indoor landmarks. However, we have not found a comprehensive study for recognizing indoor activities related to multi-floor indoor positioning based on a robust machine learning algorithm. In this work, we propose a framework for recognizing five indoor activities, i.e., walking, stillness, stair climbing, escalator or elevator taking. In this framework, we investigate the relevant sensors and features to improve the recognition accuracy of these activities, especially some specific features in frequency domain and wavelet domain. We propose to utilize a promising tree-based ensemble learning classifier, XGBoost, to recognize these activities. Based on our dataset created by 40 volunteers, we provide a comprehensive analysis of the proposed framework for indoor activity recognition. Considering both accuracy and computational cost, the XGBoost-based indoor activity recognition algorithm outperforms the other ensemble learning classifiers and single classifiers, and the average recognition F-score of XGBoost reaches 84.41%. Additionally, our introduced specific features in frequency domain and wavelet domain can significantly improve the recognition accuracy. Moreover, we use a publicly available dataset to verify our proposed framework and XGBoost classifier reaches 84.19% that outperforms the other classifiers.