Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 357 papers published in subject: > since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. An adaptive beam scheduling scheme based on graph reinforcement learning | |||
Li Chang-He, Zhao Zhong-Yuan | |||
Electrics, Communication and Autocontrol Technology 26 February 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The intelligent beam management method combined with AI has excellent performance in solving the traditional beam management problem, but the AI model has the problem of insufficient self-adaptation, which limits the deployment of AI-based algorithm in real-world communication systems. In order to provide some useful solutions and research ideas, this paper studies the adaptive beam management framework based on GRL in massive MIMO systems. Firstly, the user-beam-panel graph model in cellular Scenario is built, the beam scheduling problem is transformed into the problem of selecting the appropriate beam nodes in the graph, and an adaptive beam management algorithm is proposed. The same set of network parameters can be adapted to different user numbers and beam configurations. Aiming at improving spectral efficiency, the proposed scheme is trained on a system-level simulation platform in B5G/6G systems. Finally system-level simulation results show that the spectral efficiency of the proposed scheme is superior to the traditional PF algorithm. | |||
TO cite this article:Li Chang-He, Zhao Zhong-Yuan . An adaptive beam scheduling scheme based on graph reinforcement learning[OL].[26 February 2024] http://en.paper.edu.cn/en_releasepaper/content/4762177 |
2. Traffic Engineering in Segment Routing Network Based on Deep Reinforcement Learning | |||
Wang Yu-Qi,Zhang Xing | |||
Electrics, Communication and Autocontrol Technology 24 January 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:As a new routing paradigm, segment routing (SR) has gained significant attention in research. It offers various working modes, such as SRv6 TE Policy and SRv6 BE, which can be applied to IPv6 network to enable traffic engineering. However, updating from current IP network to SR network presents challenges of high costs and complex deployment. In this paper, we propose a traffic engineering algorithm called PUSR. We utilize a deep reinforcement learning algorithm within PUSR to reduce the maximum link utilization(MLU). The algorithm is based on routing node update and link weight setting. Simulation experiments are conducted to compare traditional routing protocols in two commonly used different topologies. The results demonstrate that PUSR achieves great performance and approaches the theoretical optimum more closely. | |||
TO cite this article:Wang Yu-Qi,Zhang Xing. Traffic Engineering in Segment Routing Network Based on Deep Reinforcement Learning[OL].[24 January 2024] http://en.paper.edu.cn/en_releasepaper/content/4761952 |
3. FGLST: Reducing Latency and System Cost for VR Live Streaming in Edge Networks | |||
Yuanlin Hu,Xing Zhang | |||
Electrics, Communication and Autocontrol Technology 29 December 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:To reduce the latency and system resource cost of VR live streaming transcoding, the paradigm of edge computing is usually applied to enhance computing speed and reduce the latency, while reducing the bandwidth pressure of the wide area network (WAN). In order to fully utilize the computing power of edge nodes, the task of VR live streaming transcoding needs to be scheduled to each edge node to assist transcoding. However, the current stream scheduling has the problem that the scheduling granularity of VR live streaming on edge nodes is too large. to address this problem, we proposes a fine-grained VR live streaming transcoding (FGLST) architecture. Although this architecture can reduce the scheduling granularity, increase parallelism, and reduce latency, it will generate a large number of tasks that need to be scheduled. Therefore, we further proposes a multi-task scheduling (MTS) algorithm based on the neural network, which introduces a temporary system state vector to solve the problem of not being able to obtain the system state in real time. Finally, we conduct simulation analysis and build a prototype system to evaluate the performance of this architecture, and the result shows that this architecture is superior to the SRS-based VR live streaming transcoding architecture, and this algorithm outperforms the MAB and the RANDOM algorithm. | |||
TO cite this article:Yuanlin Hu,Xing Zhang. FGLST: Reducing Latency and System Cost for VR Live Streaming in Edge Networks[OL].[29 December 2023] http://en.paper.edu.cn/en_releasepaper/content/4761836 |
4. Power Allocation Based on Non-Cooperative Game in LEO Beam-Hopping Satellite System | |||
XIAO Xuesong, Quan Qingyi | |||
Electrics, Communication and Autocontrol Technology 23 December 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Considering that low Earth orbit satellites adopt beam hopping technology for full frequency multiplexing, exacerbating the degree of co-frequency interference in the system, thereby reducing the capacity of the system, a power allocation algorithm of beam-hopping system based on non-cooperative game is proposed in this paper. First, a power resource allocation model based on non-cooperative game is established, and an alternate iterative algorithm is proposed to solve the Nash equilibrium. Then, OPNET is used to build a system-level simulation platform, and the performance of the power allocation algorithm is effectively evaluated. The simulation results show that the proposed power allocation algorithm achieves obvious improvement in interference suppression, spectral efficiency and fairness compared with water filling algorithm and power squaring pricing game. | |||
TO cite this article:XIAO Xuesong, Quan Qingyi. Power Allocation Based on Non-Cooperative Game in LEO Beam-Hopping Satellite System[OL].[23 December 2023] http://en.paper.edu.cn/en_releasepaper/content/4761762 |
5. A SNR Adaptive Semantic Communication System for Image Classification | |||
JIN Yu-Xin, HAO Jian-Jun | |||
Electrics, Communication and Autocontrol Technology 28 November 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper proposes an adaptive semantic communication method for image classification tasks. Based on the importance of semantic features, a dynamic feature selection network is proposed, which can select the transmitted features according to different SNR conditions, reducing the amount of data transmitted under low SNR conditions and the delay of image classification tasks. In addition, this paper constructs an adaptive SNR codec based on joint source-channel coding (JSCC), which allows the proposed model to flexibly adapt to different SNRs with just one training. Experiments have shown that the proposed scheme can flexibly adapt to different channel conditions. Compared with traditional communication methods for image classification tasks, the proposed scheme has lower latency and higher accuracy in executing image classification tasks. | |||
TO cite this article:JIN Yu-Xin, HAO Jian-Jun. A SNR Adaptive Semantic Communication System for Image Classification[OL].[28 November 2023] http://en.paper.edu.cn/en_releasepaper/content/4761588 |
6. A Spectrum Allocation Method for Aerospace TT&C Network Based on Automatic Machine Learning | |||
DAI Guangcai,ZHANG Luyong | |||
Electrics, Communication and Autocontrol Technology 15 May 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper proposes a spectrum allocation method based on automatic machine learning algorithms. The automatic machine learning algorithm based on Bayesian optimization search strategy has shown good performance in spectrum recognition. Based on its characteristics, this paper applies it to predict network traffic and thus completes the task of spectrum allocation for the communication model of the aerospace TT&C network. The experimental results show that applying automatic machine learning algorithms to spectrum allocation, although the main indicators such as network resource utilization rate and network bandwidth blocking rate are slightly inferior to the adaptive path idle degree algorithm with good recognition performance and manual parameter tuning, it still has strong practicality given that it can avoid the tedious and trivial manual parameter tuning work. | |||
TO cite this article:DAI Guangcai,ZHANG Luyong. A Spectrum Allocation Method for Aerospace TT&C Network Based on Automatic Machine Learning[OL].[15 May 2023] http://en.paper.edu.cn/en_releasepaper/content/4760796 |
7. Transmission Rate Optimization in Active RIS-Assisted UAV Communication System | |||
LI Tongjie,MIAO Jiansong | |||
Electrics, Communication and Autocontrol Technology 08 April 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Due to their low cost and flexible deployment, unmanned aerial vehicles (UAVs) have been widely used in existing networks to enhance coverage and alleviate network congestion. However, the complex environment poses challenges for UAV communication systems, such as blocked links and limited energy consumption. As a new technology for reconstructing communication environments, reconfigurable intelligent surfaces (RISs) can be applied to UAV communication systems. By adding controllable power amplifiers to the reflecting units, RISs can further improve system gain, which is of great significance for solving the problem of blocked links. In this paper, an active RIS-assisted UAV communication system is established and the transmission rate of the system are studied and analyzed. The simulation results show that the proposed scheme can significantly improve the system transmission capacity compared with other schemes. | |||
TO cite this article:LI Tongjie,MIAO Jiansong. Transmission Rate Optimization in Active RIS-Assisted UAV Communication System[OL].[ 8 April 2023] http://en.paper.edu.cn/en_releasepaper/content/4760254 |
8. Joint Optimization for UAV Supported Emergency Communications | |||
Jianning Zhang,Tao Peng,Deping Lin,Qingyi Quan | |||
Electrics, Communication and Autocontrol Technology 03 April 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:\ Unmanned \ aerial \ vehicles (UAVs) have attracted great interest \ in \ emergency communications application due to their high mobility, flexible deployment。In this paper, we \ study \ the \ effective deployment of multiple UAVs that act as aerial \ base \ stations to provide communication services to indoor users in emergency scenarios.To this end,this paper presents \ the \ problem \ of jointly optimizing \ indoor \ user \ association, \ bandwidth \ allocation, and \ 3D placement of UAVs,aiming to maximize the minimum throughput of all indoor users in uplink to improve user fairness. The problem is a challenging mixed integer non-convex optimization \ problem , \ and thus this paper proposes \ an \ efficient \ iterative \ algorithm, the joint user-UAV association, \ bandwidth \ allocation, \quad and \ placement \ optimization \ based \ on \ least \ squares \ gradient \ estimation (JABP-LSGE) algorithm , to solve the problem using LSGE \ estimation \ and \quad continuous \quad convex optimization techniques. Specifically, integer linear programming \ is \ used \ to \ obtain \quad indoor \ user \ association \ scheduling , convex \ optimization \ is used to achieve \quad bandwidth \ allocation, and LSGE \ is \ used \ to \ update \ the \ UAV \ 3D \ placement. Simulation \quad results \ show that \ the \ JABP-LSGE \ algorithm \ can improve \quad user \quad uplink throughput \quad more effectively \ and take better care of the fairness of each user than \quad other traditional methods. | |||
TO cite this article:Jianning Zhang,Tao Peng,Deping Lin, et al. Joint Optimization for UAV Supported Emergency Communications[OL].[ 3 April 2023] http://en.paper.edu.cn/en_releasepaper/content/4760162 |
9. Joint Offloading and Caching Based on UAV-Assisted Mobile Edge Computing | |||
Jiyankai | |||
Electrics, Communication and Autocontrol Technology 17 March 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the rapid development of Internet of Things devices,delay-sensitive and computationally intensive mobile applicationsmake computing resources inevitably insufficient.Thus, Unmanned Aerial Vehicles (UAVs) devices become a reliable relay nodedue to the mobility, which can provide users with extensive communications and more computing capabilities.Our proposed scheme aims to optimize the offloading decision ofthe computing tasks requested by all users and the allocation of computing resources to minimize overallenergy consumption within constrained computing and maximum delay.To solve the optimization problem, wepropose an efficient UAV-Cloud-Offloading-Caching (UCOC) algorithm,which includes an iterative algorithm for offloading decisions of user request and a remote system (the UAVs system and the cloud system)cache updating algorithm.Our simulation results show that the proposed algorithm can significantly reduce the overall energy consumption ofthe whole system by 13\% to 33\%. | |||
TO cite this article:Jiyankai. Joint Offloading and Caching Based on UAV-Assisted Mobile Edge Computing[OL].[17 March 2023] http://en.paper.edu.cn/en_releasepaper/content/4759718 |
10. Security Performance Analysis for mmWave Communication | |||
Zhu Hai-Dong | |||
Electrics, Communication and Autocontrol Technology 16 March 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Millimeter wave (mmWave) networks has been envisioned to satiate people’s growing need for high reliability and low delay of wireless networks. Besides reliability and delay, security in transmissions has also been gaining popularity due to the increasing exchange of critical and personal information. Existing studies mainly focus on the relations between only two of these performances, which is not comprehensive enough for future network design. In this paper, we analyze the relation among reliability, security and delay performance in large mmWave wireless networks, combining the tools of stochastic geometry and queueing theory. Our numerical results reveal that the all three performances get better for larger beamforming main lobe gain, while the increased blockage intensity only improves security performance but degrades reliability and delay performances when legitimate users are far from base stations, which indicates intricate relations among three performances. Our analysis provides important guidelines for designing networks applicable for various demands at quality of services in future applications. | |||
TO cite this article:Zhu Hai-Dong. Security Performance Analysis for mmWave Communication[OL].[16 March 2023] http://en.paper.edu.cn/en_releasepaper/content/4759370 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated