Beijing University of Posts and Telecommunications

About: Beijing University of Posts and Telecommunications is a education organization based out in Beijing, Beijing, China. It is known for research contribution in the topics: MIMO & Quality of service. The organization has 39576 authors who have published 41525 publications receiving 403759 citations. The organization is also known as: BUPT.

Edge Intelligence and Blockchain Empowered 5G Beyond for the Industrial Internet of Things

Abstract: Edge intelligence is a key enabler for IIoT as it offers smart cloud services in close proximity to the production environment with low latency and less cost. The need for ubiquitous communication, computing, and caching resources in 5G beyond will lead to a growing demand to integrate heterogeneous resources into the edge network. Furthermore, distributed edge services can make resource transactions vulnerable to malicious nodes. Ensuring secure edge services under complex industrial networks is a big challenge. In this article, we present an edge intelligence and blockchain empowered IIoT framework, which achieves flexible and secure edge service management. Then we propose a cross-domain sharing inspired edge resource scheduling scheme and design a credit-differentiated edge transaction approval mechanism. Numerical results indicate that the proposed schemes bring significant improvement in both edge service cost and service capacities.

Selective Offloading in Mobile Edge Computing for the Green Internet of Things

Abstract: Mobile edge computing provides the radio access networks with cloud computing capabilities to fulfill the requirements of the Internet of Things services such as high reliability and low latency. Offloading services to edge servers can alleviate the storage and computing limitations and prolong the lifetimes of the IoT devices. However, offloading in MEC faces scalability problems due to the massive number of IoT devices. In this article, we present a new integration architecture of the cloud, MEC, and IoT, and propose a lightweight request and admission framework to resolve the scalability problem. Without coordination among devices, the proposed framework can be operated at the IoT devices and computing servers separately, by encapsulating latency requirements in offloading requests. Then a selective offloading scheme is designed to minimize the energy consumption of devices, where the signaling overhead can be further reduced by enabling the devices to be self-nominated or self-denied for offloading. Simulation results show that our proposed selective offloading scheme can satisfy the latency requirements of different services and reduce the energy consumption of IoT devices.

Deep Reinforcement Learning-Based Mode Selection and Resource Management for Green Fog Radio Access Networks

Abstract: Fog radio access networks (F-RANs) are seen as potential architectures to support services of Internet of Things by leveraging edge caching and edge computing. However, current works studying resource management in F-RANs mainly consider a static system with only one communication mode. Given network dynamics, resource diversity, and the coupling of resource management with mode selection, resource management in F-RANs becomes very challenging. Motivated by the recent development of artificial intelligence, a deep reinforcement learning (DRL)-based joint mode selection and resource management approach is proposed. Each user equipment (UE) can operate either in cloud RAN (C-RAN) mode or in device-to-device mode, and the resource managed includes both radio resource and computing resource. The core idea is that the network controller makes intelligent decisions on UE communication modes and processors’ on–off states with precoding for UEs in C-RAN mode optimized subsequently, aiming at minimizing long-term system power consumption under the dynamics of edge cache states. By simulations, the impacts of several parameters, such as learning rate and edge caching service capability, on system performance are demonstrated, and meanwhile the proposal is compared with other different schemes to show its effectiveness. Moreover, transfer learning is integrated with DRL to accelerate learning process.

Mobile Wireless Sensor Network: Architecture and Enabling Technologies for Ubiquitous Computing

Abstract: A mobile wireless sensor network owes its name to the presence of mobile sink or sensor nodes within the network. The advantages of mobile WSN over static WSN are better energy efficiency, improved coverage, enhanced target tracking and superior channel capacity. In this paper we present and discuss hierarchical multi-tiered architecture for mobile wireless sensor network. This architecture is proposed for the future pervasive computing age. We also elaborate on the impact of mobility on different performance metrics in mobile WSN. A study of some of the possible application scenarios for pervasive computing involving mobile WSN is also presented. These application scenarios will be discussed in their implementation context. While discussing the possible applications, we also study related technologies that appear promising to be integrated with mobile WSN in the ubiquitous computing. With an enormous growth in number of cellular subscribers, we therefore place the mobile phone as the key element in future ubiquitous wireless networks. With the powerful computing, communicating and storage capacities of these mobile devices, the network performance can benefit from the architecture in terms of scalability, energy efficiency and packet delay, etc.

Intelligent constellation diagram analyzer using convolutional neural network-based deep learning

Abstract: An intelligent constellation diagram analyzer is proposed to implement both modulation format recognition (MFR) and optical signal-to-noise rate (OSNR) estimation by using convolution neural network (CNN)-based deep learning technique. With the ability of feature extraction and self-learning, CNN can process constellation diagram in its raw data form (i.e., pixel points of an image) from the perspective of image processing, without manual intervention nor data statistics. The constellation diagram images of six widely-used modulation formats over a wide OSNR range (15~30 dB and 20~35 dB) are obtained from a constellation diagram generation module in oscilloscope. Both simulation and experiment are conducted. Compared with other 4 traditional machine learning algorithms, CNN achieves the better accuracies and is obviously superior to other methods at the cost of O(n) computation complexity and less than 0.5 s testing time. For OSNR estimation, the high accuracies are obtained at epochs of 200 (95% for 64QAM, and over 99% for other five formats); for MFR, 100% accuracies are achieved even with less training data at lower epochs. The experimental results show that the OSNR estimation errors for all the signals are less than 0.7 dB. Additionally, the effects of multiple factors on CNN performance are comprehensively investigated, including the training data size, image resolution, and network structure. The proposed technique has the potential to be embedded in the test instrument to perform intelligent signal analysis or applied for optical performance monitoring.