Communication-Censored Distributed Learning for Stochastic Configuration Networks

This paper aims to reduce the communication cost of the distributed learning algorithm for stochastic configuration networks (SCNs), in which information exchange between the learning agents is conducted only at a trigger time. For this purpose, we propose the communication-censored distributed learning algorithm for SCN, namely ADMMM-SCN-ET, by introducing the event-triggered communication mechanism to the alternating direction method of multipliers (ADMM). To avoid unnecessary information transmissions, each learning agent is equipped with a trigger function. Only if the event-trigger error exceeds a specified threshold and meets the trigger condition, the agent will transmit the variable information to its neighbors and update its state in time. The simulation results show that the proposed algorithm can effectively reduce the communication cost for training decentralized SCNs and save communication resources.

Modeling and Stability Analysis of a Communication Network System

In this work, the modeling and stability problem for a communication network system is addressed. The communication network system consists of a transmitter which sends messages to a receiver. The proposed model considers two possibilities. The first one, that messages are successfully received, while in the second one, during the sending process the transmitter breaks down and as a result the message does not reach the receiver. Timed Petrinets is the mathematical and graphical modeling technique utilized. Lyapunov stability theory provides the required tools needed to aboard the stability problem. Employing Lyapunov methods, a sufficient condition for stabilization is obtained. It is shown that it is possible to restrict the communication network system state space in such a way that boundedness is guaranteed. However, this restriction results to be vague. This inconvenience is overcome by considering a specific recurrence equation, in the max-plus algebra, which is assigned to the timed Petri net graphical model.

Balancing D2D Communication Relayed Traffic Offloading in Multi-Tier HetNets

In Heterogeneous Networks (HetNets), Integrating Device-to-Device communication (D2D) techniques presents as a promising solution for improving system performance by offloading traffic from heavily loaded macro cell (MC) to small cells (SCs). For instance, D2D can be used to offload traffic from heavily-loaded cells to light-loaded small cells. However, offloading new users may result in an unfair load distribution among small cells and consequently may affect the quality of service of some users. To achieve better performance and reduce blocking probability load balancing among small cells should be considered when we offload traffic from macro to small cells. In this paper, we consider a centralized offloaded relay selection scheme, in which a cellular provider can decide whether users can assist each other to relay their traffic to small cells. We propose a joint user-relay selection with dynamic load balancing scheme based on D2D communications using the Kuhn-Munkres (K-M) method. The offloading process considers the load from MC to SCs and among SCs. Compared to previous works, our simulation results show that the proposed scheme increases the number of admitted users in the system, and achieves a higher load balancing fairness index among small cells. Also, our scheme achieves a higher rate fairness index among users by adjusting the signal to interference plus noise ratio (SINR) threshold.

Spectrum Allocation and Protocol Based on Cognitive Acoustic Technique in Underwater Networks

In this paper, a strategy is developed for spectrum sharing among multiple cognitive users in underwater environment. This strategy requires all nodes to negotiate and reallocate the channels before sending data, and Hungarian method is used to maximize the sharing rewards. Simulation results show that the proposed strategy can avoid collisions between source-destination node pairs, and guarantee that the communication system gets maximum sharing rewards. Both the parameters of POMDP model and the number of available channels have influence on the system sharing rewards, and the rewards will increase when the channels have larger transition probabilities or more channels are available for communication. However, the channels with larger bandwidths can attract more nodes to access, and thus will lead to more collisions.

A PERFORMANCE EVALUATION INDEX SYSTEM FOR MULTIMEDIA COMMUNICATION NETWORKS AND FORECASTING FOR WEB-BASED NETWORK TRAFFIC

This paper presents a new index system for the performance evaluation and network planning of multimedia communication systems using measurement on actual systems to support several different traffic types. In this index system, we develop an expert system to evaluate the performance of such multimedia communication networks including channel utilization and call blocking probability and packet delay, and apply the network planning methods to optimize the networks and forecast the demand of the growing multimedia communications systems. Two important planning problems for the multimedia communication systems are presented: optimization problem for construction of the world system and forecast problem for increasing traffic demands. We first discuss analysis methods, performance measures for the multimedia communication systems. Then, we describe network planning methods for the multimedia communication systems and give some efficiency network planning methods. Finally, we present some results studied in traffic forecast for the campus network and show the effectiveness of these methods.

Cluster-Based Stable BSM Dissemination System for Safe Autonomous Platooning

Recently,the importance of vehicle safety supporting system has been highlighted as autonomous driving and platooning has attracted the researchers.To ensure driving safety,each vehicle must broadcast a basic safety message(BSM)every 100 ms.However,stable BSM exchange is difficult because of the changing environment and limited bandwidth of vehicular wireless communication.The increasing number of vehicles on the road increases the competition to access wireless networks for BSM exchange;this increases the packet collision rate.An increased packet collision rate impairs the transmission and reception of BSM information,which can easily cause a traffic accident.We propose a solution,the vehicular safety support system(V3S),which exchanges BSMs reliably even when many vehicles are on the road.The V3S uses a clustering scheme to decrease network traffic by reducing the amount of data exchanged between a vehicle and the roadside unit(RSU).In addition,the V3S reduces the collision rate of wireless network packets by broadcasting the vehicle’s BSM in an allocated timeslot using the time division multiple access(TDMA)MAC protocol.The V3S also deals with insufficient bandwidth for dedicated short-range communications(DSRC)by changing DSRC channels according to traffic flow.In evaluating the packet error rate for stable BSM packet delivery,the V3S demonstrates an excellent packet error rate of less than 1%,compared to the 802.11p with its packet error rate of 82%.

A Collaborative Machine Learning Scheme for Traffic Allocation and Load Balancing for URLLC Service in 5G and Beyond

Key challenges for 5G and Beyond networks relate with the requirements for exceptionally low latency, high reliability, and extremely high data rates. The Ultra-Reliable Low Latency Communication (URLLC) use case is the trickiest to support and current research is focused on physical or MAC layer solutions, while proposals focused on the network layer using Machine Learning (ML) and Artificial Intelligence (AI) algorithms running on base stations and User Equipment (UE) or Internet of Things (IoT) devices are in early stages. In this paper, we describe the operation rationale of the most recent relevant ML algorithms and techniques, and we propose and validate ML algorithms running on both cells (base stations/gNBs) and UEs or IoT devices to handle URLLC service control. One ML algorithm runs on base stations to evaluate latency demands and offload traffic in case of need, while another lightweight algorithm runs on UEs and IoT devices to rank cells with the best URLLC service in real-time to indicate the best one cell for a UE or IoT device to camp. We show that the interplay of these algorithms leads to good service control and eventually optimal load allocation, under slow load mobility. .

应用TOPSIS法综合评价传染病网络直报工作质量

目的传染病网络直报工作质量是一个多层次、多目标的系统工程。如何评价不同时空的传染病网络直报工作质量,需要寻求一种科学简便的综合评价方法。方法采用TOPSIS法,对宜昌市2006年各县、市(以下简称A、B、C、D、E、F、G、H、I、J)传染病网络直报工作的及时报告率、及时审核率、传染病漏报率和传染病报告卡填写完整率4项指标进行综合评价。结果经TOPSIS法对10个地区4项指标进行的综合评价,所得1～10位由好到差的排序结果依次为B、D、G、E、A、F、C、I、H、J;采用秩和比法由好到差排序为B、D、I、G、C、A、F、E、J、H。结论人们对传染病网络直报工作质量的评价多以各种单项指标的高低分别排名,往往失去很多信息,不能全面反映总体情况。而TOPSIS法对原始数据进行同趋势和归一化处理,消除了不同量纲的影响,充分利用原始数据信息,能定量反映不同评价单元的优劣程度。TOPSIS法借助秩和比法进一歩扩展后,将定性与定量融为一体,使评判结果更为直观、准确。

Compact triplexer in two-dimensional hexagonal lattice photonic crystals

We design a compact triplexer based on two-dimensional （2D） hexagonal lattice photonic crystals （PCs）. A folded directional coupler （FDC） is introduced in the triplexer beside the point-defect micro-cavities and line-defect waveguides. Because of the reflection feedback of the FDC, high channel drop efficiency can be realized and a compact size with the order of micrometers can be maintained. The proposed device is analyzed using the plane wave expansion method, and its transmission characteristics are calculated using the finite-difference time-domain method. The footprint of the triplexer is about 12 9 μm, and its extinction ratios are less than -20 dB for 1310 nm, approximately -20 dB for 1490 nm, and under -40 dB for 1550 nm, making it a potentially essential device in future fiber-to-the-home networks.