专题:智能网络技术

内容导读随着人工智能技术的快速发展,AI赋予了传统网络技术更多可能,物联网、5G、工业互联网等带来的通信基础设施的改善,成为了智慧网络技术的主要驱动力;同时,数据平面可编程芯片、智能网卡等技术的发展为智能网络的发展提供了硬件基础,也成为数据中心网络、行业专网的发展趋势,促进了网络虚拟化、智能运维、安全检测与防护等技术的跨越式发展。     

论无线网络技术在智能交通系统中的应用

无线网络技术在交通系统中的应用,不仅改善了我国的交通管理,同时还在一定程度上方便了智能交通系统的信息采集.此外,通过无线网络技术,还能对相关路段的车辆进行监测,交通部门则依据相关监测结果,对该路段的交通状况进行治理,以便从根本上提高该路段的交通管理效率.     

专题:新一代宽带移动通信创新技术 专题导读

移动通信从3G走向LTE,信息传输的速率越来越高,但随着移动互联网应用的蓬勃兴起,移动通信技术又面临着新的挑战。因此LTE仍需继续发展,以满足日益增长的需求。近年来,ITU加快了新一代宽带移动通信IMT-Advanced(或称4G)标准的制订工作,目前该标准已基本形成。在新一代移动通信标准的制订过程中,     

物联网无线网络技术在智能交通中的应用

随着现代社会的发展,我国的信息化通信技术也在逐步进步,并且由此带动了整体交通领域向智能化方向发展。交通领域的智能化与多元化升级,将为整体交通行业带来更新型的创新技术,并积极促进整体交通行业的多元化发展。在新型的智能化交通技术中,物联网无线网络技术为目前科技研究人员所关注的热门应用技术。将物联网无线网络技术与整体交通行业相融合,将更加快速地推进交通行业的智能化发展。并且随着5G技术的逐渐普及,以物联网技术为基础的智慧交通技术也将更加完善。对物联网通信技术进行阐释,并对物联网技术应用于智慧交通的各个方面进行分析,进而提出物联网技术在智慧交通中的重要地位,并基于此提出物联网技术应用于智慧交通的解决方案。     

移动通信网络中的智能交通应用

对智能交通体系框架进行了简单介绍,并对其在移动通信网络中的应用进行了研究,重点对信息采集和信息发布进行了分析。     

认知电子战发展趋势:从单体智能到群体智能

随着人工智能、通信技术、无人系统等技术的快速发展,通信对抗装备智能水平不断提高,无人集群作战也在持续地深化和落地应用,这给认知电子战技术的研究带来了新的机遇和挑战,推动了认知电子战内涵从单体化向群体化演进。为促进认知电子战发展有效适应未来新型智能作战装备和新型无人集群作战样式,在综述认知电子战概念、内涵以及认知电子战单体智能研究的基础上,从无人集群作战背景出发,结合群体智能算法,提出了认知电子战群体智能的概念并对其内涵进行详细的阐述,指明了其对认知电子战的研究价值、应用价值以及发展前景。最后,在体系对抗的视角下,进一步对认知电子战群体智能未来可能的发展方向进行了较为全面的展望。     

人工智能在智能消防系统中的研究与应用

针对目前消防系统信息化、智能化的需求及目标,归纳总结人工智能技术在消防指挥调度系统中的研究现状及应用瓶颈.在此基础上提出以大数据为基础、人工智能技术赋能的消防救援一体化系统,并详细介绍智能消防系统的主要架构平台、逻辑功能以及全生命周期中的数据管理.同时,对人工智能技术与智能消防融合的研究挑战(包括数据融合、预警决策、态...     

无线通信系统中的智能天线技术

文章就智能天线的两大类,多波束天线和自适应天线阵,阐明了智能天线的定义、组成和实现方式,比较了智能天线中智能算法,进而分析了智能天线在视距和多径环境下的性能。最后结合应用进展,文章探讨了实现智能天线的难点和发展前景。     

无线系统中的智能天线

本文介绍了智能天线在未来移动通信系统中的重要作用.分别介绍了多波束天线和自适应天线阵,阐明了智能天线的定义、组成.着重介绍了在自适应天线阵通信系统中的时空信号模型、空间信道模型和时空通信理论,比较了智能天线中的智能算法.最后,结合智能天线技术的应用进展,探讨了实现智能天线的难点和发展前景.     

Energy-Efficient Hierarchical Routing for Wireless Sensor Networks: A Swarm Intelligence Approach

Wireless Personal Communications - Energy efficient routing in wireless sensor networks (WSNs) require non-conventional paradigm for design and development of power aware protocols. Swarm...     

Biological Swarm Intelligence Based Opportunistic Resource Allocation for Wireless Ad Hoc Networks

Particle swarm optimization (PSO) is one of the most important biological swarm intelligence paradigms. However, the standard PSO algorithm can easily get trapped in the local optima when solving complex multimodal problems. In this paper, an improved adaptive particle swarm optimization (IAPSO) is presented. Based on IAPSO, a joint opportunistic power and rate allocation (JOPRA) algorithm is proposed to maximize the sum of source utilities while minimize power allocation for all links in wireless ad hoc networks. It is shown that the proposed JOPRA algorithm can converge fast to the optimum and reach larger total data rate and utility while less total power is consumed by comparison with the original APSO. This thanks to the dynamic change of the maximum movement velocity of the particles, the use of the modified replacement procedure in constraint handling, and the consideration of the state of the optimization run and the population diversity in stopping criteria. Numerical simulations further verify that our algorithm with the IAPSO outperforms that with the original APSO.     

IPv6 for Future Wireless Networks

The functionalities of the next generation Internet protocol, IPv6, havebecome increasingly interesting due to the current merging of the traditionalcellular mobile communications and the traditional data-communications intothe future wireless systems, as e.g., UMTS. IPv6 provides several enhancedfunctionalities requested for the future mobile systems. In this article thelargest advantages in relation to mobile systems are presented. Variousaspects of introducing IP throughout the entire mobile network (core, accessand termainals) are also presented along with an illustration of the abilitiesof the future wireless network.     

RSS-Based Self-Localization Framework for Future Wireless Networks

The localization is an important asset in all existing and emerging wireless networking solutions since it can extend the radio environmental awareness and assist in providing better network operation. The received signal strength (RSS) based non-Bayesian transmitter localization is especially interesting due to the inherent presence of the RSS observations in all commercial radio devices and the instantaneous estimations without the need for extensive training/learning phases. The existing RSS based localization solutions neglect the problems arising from the inherent sensing network topology uncertainty. The sensors, usually assumed to have a-priori known positions, are often a subject of a previous estimation which propagates errors in the transmitter localization procedure, and, hence, results in significant transmitter localization performance degradation. This paper presents a recently developed generic RSS based joint transmitter/sensors localization framework, founded on the assumption of uncertain topology information. The derived joint maximum likelihood (JML) algorithm simultaneously estimates the transmitter and uncertain sensor positions providing twofold gains: improving the transmitter localization and reducing the network topology uncertainty. The paper broadly evaluates the JML algorithm, emphasizing the substantial localization gains originating from the joint transmitter/sensor position estimation. The results prove up to 85 % sensor position uncertainty reduction with the general system model with multiple transmitters locations and multiple previous estimations of the sensors positions. The paper also derives the theoretical lower bounds of the joint estimation framework, and proves the convergence of the JML algorithm. The presented joint estimation framework is applicable to a variety of wireless networking applications. It can provide self-awareness in future wireless networks and cope with the environment and topology dynamism in wireless ad-hoc networks.     

WSNs中基于粒子群优化的信宿移动路径规划算法

感测数据,再将数据传输至信宿是无线传感网络(WSNs)中节点的首要任务。传感节点由电池供电,它们的多数能量用于传输数据,越靠近信宿的节点,传输的数据量越大。因此,这些节点的能耗速度快,容易形成能量-空洞问题。而通过移动信宿收集数据能够缓解能量-空洞问题。为此,提出基于粒子群优化的信宿移动路径规划(PSO-RPS)算法。PSO-RPS算法结合数据传递时延和信息速率两项信息选择驻留点,并利用粒子群优化算法选择最优的驻留点,进而构建时延有效的信宿收集数据的路径。仿真结果表明,提出的PSO-RPS算法有效地控制路径长度,缩短了收集数据的时延。     

传感器网络的粒子群优化定位算法

无线传感器网络定位问题是一个基于不同距离或路径测量值的优化问题。由于传统的节点定位算法采用最小二乘法求解非线性方程组时很容易受到测距误差的影响,为了提高节点的定位精度,将粒子群优化算法引入到传感器网络定位中,提出了一种传感器网络的粒子群优化定位算法。该算法利用未知节点接收到的锚节点的距离信息,通过迭代方法搜索未知节点位置。仿真结果表明,该算法有效地抑制了测距误差累积对定位精度的影响,提高了节点的定位精度。     

混合无线传感网络覆盖优化的粒子群算法

为提高随机部署的传感网络覆盖性能,提出基于动态克隆粒子群的移动节点部署控制算法,用每个粒子表示所有移动节点的一种部署方案,在经典粒子群算法基础上,每次迭代结束后,粒子依据自身的覆盖性以及与群体中粒子的相似性决定其克隆数量和变异幅度,有效避免陷入早熟陷阱.通过与其他算法的对比仿真实验,表明该优化算法能更有效地提高网络覆盖性能.     

Reducing Hard Handover Overhead in Future All-IP Wireless Access Networks

In host-based routing (HBR) domains such as cellular IP, handover can be executed implicitly via path update packets from the new location of the mobile host (MH). The direction of the flow of packets destined to the MH is diverted at the crossover node (CoN), thereby reducing to a minimum the handover delay and associated packet loss. As the depth of the network increases so does the path update time to the CoN. To reduce the handover overhead, an architectural extension is proposed to the path update process, by adding a multi-homed base-station (MHOBS) at certain points in the wireless access network where the path update delay becomes severe. Two scenarios are investigated. The first scenario is one in which the old and new paths to the MH are equal in length or symmetrical, the second, when the paths are unequal, or asymmetrical.