Future 5G-oriented system for urban rail transit: Opportunities and challenges

Zhao, Junhui; Liu, Jin; Yang, Lihua; Ai, Bo; Ni, Shanjin

doi:10.23919/jcc.2021.02.001

Cited by 98 publications

(29 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we evaluate the proposed D-DQN based offloading strategy with the conventional ones, in terms of latency and EnC. The wireless channels in the system are subject to the Rayleigh flat fading [35]- [38], where the average channels gains of the main and eavesdropping links are set to 0.9 and 0.2, respectively. The transmit power at the users is 2W, while the associated computational power is 3W.…”

Section: Simulation Results and Discussionmentioning

confidence: 99%

Intelligent Mobile Edge Computing Networks for Internet of Things

Chen

Kuang

Zhu³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In this work, an intelligent mobile edge computing (MEC) network is studied for Internet of Things (IoT) in the presence of eavesdropping environments, where there are multiple users who can offload their confidential tasks to the computational access point (CAP) for the assistance of computation. One unmanned aerial vehicle (UAV) attacker exists in the system and it can listen to the confidential data transmission from the users to the CAP. We optimize the system design of the intelligent MEC network, by adaptively allocating the offloading ratio and wireless bandwidth, to reduce the linearly weighted cost of the latency as well as energy consumption (EnC). Specifically, starting from the deep reinforcement learning, we devise a deep Q-network (DQN) network to adjust the offloading ratio and transmission bandwidth, which can help calculate the computational tasks and suppress the eavesdropping from the UAV efficiently. We finally provide some simulation results to validate the proposed offloading strategy. In particular, the proposed offloading strategy can achieve a much lower cost compared to the conventional ones, in the terms of latency and EnC.INDEX TERMS Deep reinforcement learning, Internet of Things, mobile edge computing, task offloading, unmanned aerial vehicles.

show abstract

Section: Simulation Results and Discussionmentioning

confidence: 99%

Intelligent Mobile Edge Computing Networks for Internet of Things

Chen

Kuang

Zhu³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The challenges that we have to face in our architecture are high transmission delay, appropriate object detection model, and model allocation method. Due to the development of the 5G communication technology and the support of millimeter wave (mm Wave), multiple-input multipleoutput (MIMO), and multiaccess edge computing (MEC), the data peak rate can reach 1 GB/s, and the transmission delay is limited in the range of 1-5 ms [15]. And communication transmission time can also be compensated by less inference time of ground servers, so the influence of data transmission can be reduced.…”

Section: Edge Computing Architecture Designed For Object Detectionmentioning

confidence: 99%

An Edge Computing‐Enabled Train Obstacle Detection Method Based on YOLOv3

Song

Zhao

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Rail transit is developing towards intelligence which takes lots of computation resource to perform deep learning tasks. Among these tasks, object detection is the most widely used, like track obstacle detection, catenary wear, and defect detection and looseness detection of train wheel bolts. But the limited computation capability of the train onboard equipment prevents running deep and complex detection networks. The limited computation capability of the train onboard equipment prevents conducting complex deep learning tasks. Cloud computing is widely utilized to make up for the insufficient onboard computation capability. However, the traditional cloud computing architecture will bring in uncertain heavy traffic load and cause high transmission delay, which makes it fail to complete real-time computing intensive tasks. As an extension of cloud computing, edge computing (EC) can reduce the pressure of cloud nodes by offloading workloads to edge nodes. In this paper, we propose an edge computing-based method. The onboard equipment on a fast-moving train is responsible for acquiring real-time images and completing a small part of the inference task. Edge computing is used to help execute the object detection algorithm on the trackside and carry most of the computing power. YOLOv3 is selected as the object detection model, since it can balance between the real-time and accurate performance on object detection compared with two-stage models. To save onboard equipment computation resources and realize the edge-train cooperative interface, we propose a model segmentation method based on the existing YOLOv3 model. We implement the cooperative inference scheme in real experiments and find that the proposed EC-based object detection method can accomplish real-time object detection tasks with little onboard computation resources.

show abstract

“…The amplitudes of the lower and upper sidebands of the IM products of a mixer are approximately symmetrical under narrow wireless communication. Modern communication [2,3] requires a higher width and more frequency bands, that is, the 5G communication system [4,5,6]. Therefore, the memory effects [7,8,9] of the mixer's IM products become more evident in 5G communication systems.…”

Section: Introductionmentioning

confidence: 99%

Analysing the characteristics of the memory effects of mixers using two-tone measurements

Zhang

Tong

Gao

et al. 2022

IEICE Electron. Express

View full text Add to dashboard Cite

With the development of communication systems, the memory effects of mixers, defined as frequency dependence and asymmetry of intermodulation (IM) products, have become prominent. Conventional mixer models cannot describe the changing characteristics of mixers' memory effects versus tone spacing. Thus, this study aims to analyse the characteristics of mixers' memory effects instead of developing a high-accuracy model to characterise memory effects. IM3 product characteristics are described using simplified generalised frequency-response functions and a multi-box behavioural mixer model. These characteristics show that the lower and upper IM3 products have inverse trends compared to tone spacing, except for frequency dependence and asymmetry.

show abstract

Future 5G-oriented system for urban rail transit: Opportunities and challenges

Cited by 98 publications

References 31 publications

Intelligent Mobile Edge Computing Networks for Internet of Things

Intelligent Mobile Edge Computing Networks for Internet of Things

An Edge Computing‐Enabled Train Obstacle Detection Method Based on YOLOv3

Analysing the characteristics of the memory effects of mixers using two-tone measurements

Contact Info

Product

Resources

About