Article
Computer Science, Hardware & Architecture
Zhongyu Ma, Jie Cao, Qun Guo, Xiangwei Li, Hongfeng Ma
Summary: The millimeter-wave mesh backhaul network is a crucial technology for massive traffic backhaul in 5G networks, and a QoS-oriented joint optimization of concurrent scheduling and power control has been proposed to address the challenge of high capacity and green backhaul solutions. By formulating a mixed integer nonlinear programming problem and developing a heuristics and energy-efficient backhaul mechanism, the issue of reducing energy consumption while enhancing the number of successfully transmitted flows has been tackled. Through extensive simulations, the proposed mechanism, HEBM, has been shown to outperform state-of-the-art methods under various traffic modes and system parameters.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Xiaowu Ou, Yin Xu, Hanjiang Hong, Dazhi He, Yiyan Wu, Yihang Huang, Wenjun Zhang
Summary: With the increasing demand for data services, the spectrum has become a valuable resource. The cooperative transmission mechanism, which allows broadcast and unicast to share the same spectrum, can effectively alleviate this issue. A flexible LDM scheme with a variable power injection ratio is proposed to further improve radio resource utilization. Through a DRL-based algorithm, the optimal scheduling scheme is obtained, and the Lyapunov optimization method is applied to convert the problem to a more conducive form for the agent to learn the optimal strategy. Simulation results show significant improvement in system throughput while ensuring the quality of the broadcast service.
IEEE TRANSACTIONS ON BROADCASTING
(2023)
Article
Engineering, Electrical & Electronic
Xiaoting Ma, Junhui Zhao, Yi Gong
Summary: This paper addresses the challenges in massive data training and analysis in vehicular networks by proposing a platoon-based distributed learning framework that utilizes the computation resources of vehicle platooning networks. A joint scheduling and resource allocation scheme is introduced to maximize learning accuracy subject to a given time constraint. Simulation results show that the proposed scheduling policy can efficiently schedule participating vehicles based on the trade-off between learning performance and latency.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Ziyuan Sha, Yang Ming, Chen Sun, Zhaocheng Wang
Summary: In millimeter-wave cellular networks, the use of large-scale antenna arrays generates highly directional beams that significantly reduce inter-cell/intra-cell interferences. To maximize this feature in resource management, near interference-free (NIF) scheduling is introduced as a well-designed user scheduling scheme that avoids strong interferences in mmWave networks. A generalized NIF scheduling methodology is proposed in this paper to jointly design user scheduling, beam scheduling, and power allocation, with the ability to handle various optimization objectives. Simulation results demonstrate that the proposed method outperforms existing user scheduling schemes in terms of different optimization objectives.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Wanli Wen, Zihan Chen, Howard H. Yang, Wenchao Xia, Tony Q. S. Quek
Summary: This paper proposes a training algorithm for hierarchical federated edge learning (H-FEEL) system, which achieves helper scheduling and communication resource allocation through phases like local gradient computing, weighted gradient uploading, and model updating. By mathematical modeling and analyzing convergence bounds, the optimization problem considering wireless channel uncertainty and weighted gradient importance is solved. The effectiveness of the scheme is demonstrated through simulations.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Xihan Chen, Yunlong Cai, An Liu, Lajos Hanzo
Summary: This paper focuses on the joint user scheduling and resource allocation in mmWave uplink communication systems using adaptive-resolution analog-to-digital converters (RADCs). By maximizing system throughput of scheduled users through optimizing transmit power level, hybrid combiners, and quantization bits using fractional programming techniques, the proposed algorithm significantly enhances throughput compared to benchmark schemes. The specific structures in solutions are exploited with the Ky Fan n-norm, and the optimization problem is solved using a penalty block successive concave approximation (P-BSCA) algorithm.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Review
Chemistry, Analytical
Pulok Tarafder, Wooyeol Choi
Summary: With the increase in the number of connected devices, millimeter-wave (mmWave) technology has become a promising research field in both industry and academia. Traditional physical layer-based solutions are becoming outdated due to the advancement in 5G communication. This survey investigates the state-of-the-art MAC protocols for mmWave communication systems and provides a categorized qualitative comparison, as well as discusses possible approaches to address future challenges.
Article
Engineering, Electrical & Electronic
Wenqi Shi, Sheng Zhou, Zhisheng Niu, Miao Jiang, Lu Geng
Summary: In this paper, a joint device scheduling and resource allocation policy is proposed to maximize model accuracy within a given total training time budget for latency constrained wireless FL. The accuracy maximization problem is decomposed into two sub-problems and solved accordingly. Experimental results demonstrate the superiority of the proposed policy under various settings.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2021)
Article
Telecommunications
Chol Jong, Yong Chun Kim, Jun Ho So, Kum Chol Ri
Summary: This article surveys the scheduling and resource allocation algorithm to reduce packet loss rate while increasing energy efficiency in the uplink of the Long Term Evolution-Advanced system. It proposes a new framework that refers previous values as optimization values and defines a mathematical model as an NP-Hard problem. A user priority metric is proposed considering the different requirements for packet loss rate and packet delay based on Quality of Service (QoS) Class Identifier (QCI). Simulation results show that the proposed algorithm enhances energy efficiency and QoS provision for different types of services.
TELECOMMUNICATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Ali Belgacem, Kadda Beghdad-Bey, Hassina Nacer
Summary: Cloud computing is a popular paradigm for leasing IT services over the Internet, which requires dynamic allocation and release of resources to ensure service quality. A new dynamic resource allocation model is proposed along with the MOSOS algorithm to minimize completion time and cost for improved cloud performance.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)
Article
Chemistry, Analytical
Dimitrios Zorbas, Christelle Caillouet, Khaled Abdelfadeel Hassan, Dirk Pesch
Summary: This paper discusses the issue of data transmission in LoRa IoT technology when gateways are not always available, proposing a time-slotted transmission scheduling mechanism to improve data collection efficiency. Simulation experiments show that the mechanism can significantly reduce data collection time, achieving at least 10 times faster collection for networks with 100 or more nodes.
Article
Computer Science, Information Systems
Chia-Cheng Hu
Summary: This study proposes a strategy to maximize the profit of joint issue in C-RAN, using ILP and an algorithm with bounded approximation ratio for solving it. Simulation results show the algorithm's solution is very close to the ILP's optimal one, and another algorithm is introduced to control the tradeoff between performance and robustness of the solution.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Shuyi Shen, Ticao Zhang, Shiwen Mao, Gee-Kung Chang
Summary: A channel and latency aware radio resource allocation algorithm based on deep reinforcement learning was proposed to optimize the uplink scheduling for service-oriented multi-user millimeter wave (mmWave) radio access networks in the 5G era. Experimental results show that the proposed DRL algorithm can adapt to channel variations and achieve at least 12% average reward improvement compared to conventional schemes, providing joint improvement for bit error rate and latency performance.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2021)
Article
Telecommunications
Yueping Cai, Xiaowen Zhang, Shaoliu Hu, Xiaocong Wei
Summary: This paper proposes a dynamic QoS mapping method based on the improved K-means clustering algorithm and rough set theory (IKC-RQM) to ensure the end-to-end (E2E) QoS performance in 5G-TSN integrated networks. Additionally, an adaptive semi-persistent scheduling (ASPS) mechanism is introduced to guarantee the deterministic transmissions of time-sensitive flows in 5G-TSN networks through persistent resource allocation and dynamic resource allocation based on the max-min fair share algorithm.
CHINA COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Yi-Ting Mai, Chih-Chung Hu
Summary: This study proposes a smart and flexible EURA scheme for LTE network resource allocation, which improves QoS service, saves radio capacity, and enhances resource assignment efficiency by considering UE's CQI states.
EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING
(2022)
Article
Computer Science, Software Engineering
Kaifang Wan, Jianmei Wang, Bo Li, Daqing Chen, Linyu Tian
Summary: This paper proposes a feature selection method based on three-way decision to address the problem of target recognition with high-dimensional and few-shot data. By improving the existing algorithm to increase fault tolerance and reduce dimension, experimental results show that the proposed algorithm improves recognition accuracy and stability.
Article
Computer Science, Artificial Intelligence
Ruirui Nie, Bo Li
Summary: This paper investigates the detection, identification, and experimental simulation of quasi-frequency hopping signal under multi-fixed frequency interference. It utilizes the short-time Fourier transform and Wigner-Ville time-frequency analysis method to identify and simulate the interference signal. Additionally, the paper proposes a narrowband interference suppression strategy using a genetic algorithm-based design for radio high frequency (RHF) signal. Simulation results show that the time-frequency domain and joint method have a more obvious suppression effect compared to the traditional time-frequency domain method.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Thermodynamics
Bo Li, Zhaoyong Mao, Baowei Song, Yan-Feng Wang, Wenlong Tian, Chengyi Lu, Mengjie Li
Summary: This study proposes a method of using phase change material cooling to enhance the battery thermal management of autonomous underwater vehicles (AUVs), taking into account natural convection. The temperature behavior and melting behavior of the phase change material under different parameters were studied, and the enhanced heat transfer mechanism of the PCM melting process was revealed. Two quantitative evaluation factors were introduced to optimize the performance of this method.
APPLIED THERMAL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Bo Li, Meiqin Huang, Huanyu Zhang, Mi Lin, Shuyi He, Liming Chen
Summary: In optical fiber composite overhead ground wire (OPGW) networks, interference from aggressive frequency reuse in frequency-limited Internet of Things (IoT) networks plays a significant role in communication and monitoring systems. This article investigates the communication technology of OPGW line in a distribution network under an interference environment and analyzes its system performance by deriving an outage probability expression. Simulation results confirm the negative impact of interference on OPGW communication performance.
EAI ENDORSED TRANSACTIONS ON SCALABLE INFORMATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Peixia Li, Boyu Chen, Lei Bai, Lei Qiao, Bo Li, Wanli Ouyang
Summary: This paper proposes the Video-Guided Sampling Strategy to address the limitations of random sampling in visual object tracking. The strategy includes Modified Gaussian Sampling Strategy (MGSS) at the inter-video level and Farthest Image Pair Sampling Strategy (FPSS) at the intra-video level, which effectively improve tracking performance without compromising testing speed.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Chemistry, Physical
Bo Li, Shuangming Li, Bin Yang, Hong Zhong, Zhenpeng Liu, Dou Li
Summary: Solid-state cooling based on elastocaloric effect shows potential for refrigeration. This study focuses on the improvement of elastocaloric effect and thermal cycle stability using directional solidification technique to prepare single-crystal Ni50Mn31.6Ti18.4 shape-memory alloys. The results reveal that the single crystal solidified at 10 μm/s exhibits superior adiabatic temperature and cyclic stability compared to alloys solidified at higher rates. The findings highlight the significance of microstructure in enhancing the elastocaloric performance of shape-memory alloys.
JOURNAL OF ALLOYS AND COMPOUNDS
(2023)
Article
Mathematics
Lang Huyan, Ying Li, Dongmei Jiang, Yanning Zhang, Quan Zhou, Bo Li, Jiayuan Wei, Juanni Liu, Yi Zhang, Peng Wang, Hai Fang
Summary: In this study, a novel decomposed module called DecomResnet based on Tucker decomposition was proposed to deploy a CNN object detection model on a satellite. Tensors provide a natural and compact representation of CNN weights via suitable low-rank approximations. A remote sensing image object detection model compression framework based on low-rank decomposition was introduced, which achieved significant compression and speedup ratios with only slight decrease in mAP.
Article
Engineering, Aerospace
Zhaohui Yao, Yuanzhao Guo, Jun Niu, Zhiguang Jin, Tianhao Yu, Baojun Guo, Wenhao Pu, Xin Wei, Feng Jin, Bo Li, Mengying Liu
Summary: A model of a NUAA-PTRE pre-cooled air turbine engine was established and optimized for its design parameters. Key components exhibited high performance under various working conditions. The overall optimization design and adaptive design of the components were completed, achieving high performance of the engine in a wide range of flight conditions.
Article
Remote Sensing
Bo Li, Chao Song, Shuangxia Bai, Jingyi Huang, Rui Ma, Kaifang Wan, Evgeny Neretin
Summary: An intelligent algorithm integrating model predictive control and Standoff algorithm is proposed to solve trajectory planning for UAVs tracking a moving target cooperatively in a complex 3D environment. A fusion model using the combination of model predictive control and Standoff algorithm is constructed to ensure trajectory planning and formation maintenance. The simulation validation shows that the fusion algorithm is more capable of maintaining stable formation and detecting the target compared to the model predictive control algorithm alone in a complex 3D environment.
Article
Engineering, Civil
Jianhua Zhang, Rucen Wang, Ruyu Liu, Dongyan Guo, Bo Li, Shengyong Chen
Summary: IoT-based intelligent transportation, specifically traffic video monitoring, requires accurate vehicle and pedestrian detection. Deep learning methods have high accuracy but are computationally expensive for IoT devices. This study proposes optimization tactics for object detection CNN models on digital signal processors and evaluates the performance. Results show that the proposed method achieves faster speed with minimal accuracy loss compared to running the same model on a desktop CPU.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
Meiping Peng, Bo Li, Zhongjiang Yan
Summary: This paper proposes a multi-BSS multi-user full-duplex multiple access protocol (CMMFD) based on access point (AP) cooperation to solve the problems of overlapping coverage, low efficiency of BSR collection, and decline in system throughput in next-generation wireless local access networks (WLAN). The proposed protocol divides the STAs in the cooperative network area into overlapping STA and non-overlapping STA, and implements a bi-level channel resource allocation algorithm. It also designs a protocol framework for parallel BI information collection and multi-user full-duplex transmission. Theoretical analysis and simulation results demonstrate that the CMMFD protocol improves network throughput by 29.6% and 31.2% compared to existing protocols.
MOBILE NETWORKS & APPLICATIONS
(2023)
Article
Remote Sensing
Bo Li, Haohui Zhang, Pingkuan He, Geng Wang, Kaiqiang Yue, Evgeny Neretin
Summary: This paper proposes a hierarchical maneuver decision method based on the PG-option for the autonomous decision-making problem in a UAV pursuit-evasion game. Four maneuver decision options are designed and trained using the Soft Actor-Critic (SAC) algorithm. The policy gradient (PG) algorithm is combined with the traditional hierarchical reinforcement learning algorithm to address the issue of high dimensions in the state space. The delay selection of the policy selector and the introduction of expert experience improve the flexibility of switching policies. Simulation experiments demonstrate the effectiveness of the PG-option algorithm in UAV pursuit-evasion games and its adaptability to various environments.
Article
Computer Science, Artificial Intelligence
Bo Li, Shuangxia Bai, Shiyang Liang, Rui Ma, Evgeny Neretin, Jingyi Huang
Summary: This article proposes an autonomous manoeuvre decision model using an expert actor-based soft actor critic algorithm to solve the problem of unmanned aerial vehicles' limited autonomous manoeuvrability in air combat. The algorithm utilizes a small amount of expert experience to increase the diversity of samples, greatly improving the exploration and utilization efficiency of deep reinforcement learning. A one-to-one air combat model is established, and the concept of missile's attack region is introduced to simulate the complex battlefield environment. Simulation results show that the expert actor-based soft actor critic algorithm can find the most favorable policy for unmanned aerial vehicles to defeat the opponent faster and converge more quickly compared with the soft actor critic algorithm.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Randa El-Bialy, Daqing Chen, Souheil Fenghour, Walid Hussein, Perry Xiao, Omar H. Karam, Bo Li
Summary: This paper explores a classification schema for lip-reading sentences using phonemes and aims to enhance system performance. The proposed system achieves a 10% lower word error rate on average compared to state-of-the-art approaches in lip-reading sentences, based on testing with the BBC Lip Reading Sentences 2 (LRS2) benchmark dataset.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Bo Li, Jingyi Huang, Shuangxia Bai, Zhigang Gan, Shiyang Liang, Neretin Evgeny, Shouwen Yao
Summary: This study addresses the problem of manoeuvring decision-making in UAV air combat by establishing a one-to-one air combat model and using the SAC algorithm. It proposes the PSP-SAC algorithm to improve the generalisation performance of UAV control decisions. Simulation results demonstrate that the proposed algorithm can significantly enhance the generalisation ability of the model in various combat environments through sample and policy sharing.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Computer Science, Hardware & Architecture
Xiaolin Gu, Wenjia Wu, Yusen Zhou, Aibo Song, Ming Yang, Zhen Ling, Junzhou Luo
Summary: This study proposes a radio frequency fingerprint identification solution based on crystal oscillator temperature adjustment, which enhances the differences between Wi-Fi device fingerprints and mitigates collision. Experimental results demonstrate the effectiveness of the system in identifying smartphones under different scenarios.
Article
Computer Science, Hardware & Architecture
Yutong Wu, Jianyue Zhu, Xiao Chen, Yu Zhang, Yao Shi, Yaqin Xie
Summary: This paper proposes a quality-of-service-based SIC order method and optimizes power allocation for maximizing the rate in the uplink NOMA system. The simulation results demonstrate the superiority of the proposed method compared to traditional orthogonal multiple access and exhaustive search.
Article
Computer Science, Hardware & Architecture
Songshi Dou, Li Qi, Zehua Guo
Summary: Emerging cloud services and applications have different QoS requirements for the network. SD-WANs play a crucial role in QoS provisioning by introducing network programmability, dynamic flow routing, and low data transmission latency. However, controller failures may degrade QoS. To address this, we propose PREDATOR, a QoS-aware network programmability recovery scheme that achieves fine-grained per-flow remapping without introducing extra delays, ensuring QoS robustness for high-priority flows.
Article
Computer Science, Hardware & Architecture
Ke Wang, Xiaojuan Ma, Heng Kang, Zheng Lyu, Baorui Feng, Wenliang Lin, Zhongliang Deng, Yun Zou
Summary: This paper proposes a method based on a parallel network simulation architecture to improve the simulation efficiency of satellite networks. By effectively partitioning the network topology and using algorithms such as resource assessment and load balancing, the simulation performance is enhanced. Experimental results demonstrate the effectiveness of this method.
Article
Computer Science, Hardware & Architecture
Sijin Yang, Lei Zhuang, Julong Lan, Jianhui Zhang, Bingkui Li
Summary: This paper proposes a reuse-based online scheduling mechanism that achieves deterministic transmission of dynamic flows through dynamic path planning and coordinated scheduling of time slots. Experimental results show that the proposed mechanism improves the scheduling success rate by 37.3% and reduces time costs by up to 66.6% compared to existing online scheduling algorithms.
