一种可分负载WSN的能耗均衡负载调度算法

无线传感器网络的节点电源能量有限,其能耗均衡问题已成为研究热点。针对星型可分负载无线传感器网络的负载调度过程,在同时感知、顺序返回信息的工作模型下提出了一种以能耗均衡为目标的负载调度算法(DLEBS)。该算法以降低网络能耗标准差为优化目标,在保证网络总体传输时间及传输顺序的情况下,可以得到相应的负载调度策略。仿真实验表明,算法得到的负载调度可以有效降低网络的能耗标准差。并且随给定时间的增加,算法得到的负载调度使得能耗标准差相应地减小。     

基于粒子群优化算法的虚拟机部署策略

针对云计算基础设施即服务(IaaS)中的虚拟机部署问题,提出一种基于粒子群优化(PSO)算法的部署策略。由于PSO算法在处理虚拟机部署这类大规模复杂问题时,具有收敛速度慢且容易陷入局部最优的缺点,首先,引入多种群进化模式提高算法收敛速度,并在此基础上加入高斯学习策略避免局部最优,提出了一种多种群高斯学习粒子群优化(MGL-PSO)算法;然后,根据部署模型,使用轮询(RR)算法对MGL-PSO进行初始化,进而提出了一种以负载均衡为目标的虚拟机部署策略。通过在CloudSim中进行仿真实验,验证了在解决虚拟机部署问题时,MGL-PSO相比PSO算法,具有更快的收敛速度,并且负载不均衡度降低了13.1%。在两种实验场景下,所提算法相比随机负载均衡(OLB)算法,其负载不均衡度分别平均降低了25%和15%;相比贪婪算法(GA),使负载不均衡度分别平均降低了19%和7%。     

基于SDWN的负载感知终端多点关联方案研究

软件定义无线网络（SDWN）是一种控制与转发分离的无线网络架构。该架构可以快速获取全局拓扑并且其可编程性结合资源虚拟化技术可以对网络接入进行动态控制。针对现有WLAN网络接入负载不均衡问题及移动终端与AP硬关联导致的切换速度较慢的问题,基于SDWN架构提出了一种负载感知终端多点关联方案。该方案对SDWN网络架构下的终端接入算法进行改进,采用多点关联技术,即终端在感知AP负载数据后,可关联多个虚拟AP,达到动态分流并提高网络吞吐量的目的。最后在SDWN的开源Odin平台上验证了方案的可行性,实验表明相比无缝切换至另一AP,此方案可改变原有终端与AP接入一一对应的接入关系,根据AP负载动态接入,可有效提升网络吞吐量。     

基于蜜蜂采蜜机理的云计算负载均衡策略*

任务调度是云计算研究中的NP难优化问题,负载均衡问题是任务调度的热点研究内容之一。针对云计算环境中任务分配不够合理、用户服务质量低的问题,提出一种模拟蜜蜂采蜜机理的负载均衡策略。该策略模拟蜂群觅食行为,建立负载均衡模型,被迁移的任务作为“侦察蜂”更新虚拟机的负载信息,并采用贝叶斯分类算法对虚拟机负载状态进行分类,将任务从重负载虚拟机迁移至轻负载虚拟机,同时满足目标虚拟机中高优先级任务的数量最少,避免了大量任务被调度到同一性能较优的虚拟机上,能够有效减少任务等待时间。实验结果表明,基于蜜蜂采蜜机理的负载均衡策略,和传统算法相比,减少了任务响应时间、完工时间和迁移次数,同时更好地满足了用户服务质量需求。     

一种云计算资源的多目标优化的调度方法

云计算通过虚拟化技术将基础设施硬件资源虚拟化,以动态可缩放的方式提供给用户。云计算基础设施规模不断增加导致资源调度系统负载不均衡,从而造成资源浪费等问题。提出多目标优化资源调度策略和相应的算法,试图同时满足多个资源调度优化目标,如减少资源浪费,降低服务等级约定(SLA)违背率、保持系统负载均衡等。通过仿真实验,验证了多目标优化资源调度的策略能够在多个相互冲突的目标之间实现最优权衡。     

面向SLA的云计算负载均衡策略

云计算负载均衡是保障SLA协议的关键问题之一;针对云计算负载均衡问题,提出一种面向SLA的负载均衡策略;该策略引入人工神经网络思想,建立负载均衡模型,采用单层感知器算法(SLPA)将虚拟机负载状态进行分类,然后利用结合了动态加权轮询算法的BP神经网络算法(BPNNA-DWRRA)有针对性地对虚拟机负载权重进行预测更新,最后将任务调度到最小权重所对应的可行虚拟机上;应用CloudSim进行仿真实验,结果表明了该策略的可行性,同时,相比加权最小链接算法和粒子群算法,该策略的平均响应时间分别节省了43.6%和22.5%,SLA违反率分别降低了20.7%和14.4%;因此,所提策略在响应用户任务时,请求响应时间短,SLA违反率低,保障了SLA。     

云计算环境下基于用户和资源约束的免疫效用均衡任务调度算法

针对云计算中的任务调度问题, 提出了一种免疫均衡效用任务调度算法. 该算法将云计算环境下任务调度问题建模为一个多目标优化模型, 同时兼顾了用户任务的时间跨度和虚拟化资源的负载均衡. 仿真结果表明, 该任务调度算法提高了用户满意度的同时减少了任务的完成时间, 是云平台下一种有效的任务调度策略.     

基于三支决策的虚拟机节能迁移策略

虚拟机迁移技术作为云计算中降低数据中心能耗的重要手段被广泛应用。结合三支决策的分、治、效模型提出一种基于三支决策的虚拟机迁移调度策略（TWD-VMM）。首先,通过建立层次阈值树搜索所有可能取到的阈值,由此以数据中心能耗为优化目标得到总能耗最低的一对阈值,从而实现三分区域,即高负载区域、中负载区域和低负载区域。其次,针对不同负载的主机采取不同的迁移策略：对于高负载主机,以主机预迁出后的多维资源均衡度和主机负载下降幅度为目标;对于低负载主机,主要考虑主机预放置后的多维资源均衡度;对于中等负载主机,如果迁移过来的虚拟机依旧满足中负载特性,则可以接受迁入。实验采用CloudSim模拟器进行,将TWD-VMM算法分别与基于阈值调度算法（TVMS）、基于虚拟机迁移节能调度算法（EEVS）、云计算中心节能调度算法（REVMS）算法在主机负载、主机多维资源利用均衡度、数据中心总能耗等方面进行比较,结果表明TWD-VMM算法在提高主机资源利用率、均衡主机负载等方面有明显效果,且能耗平均降低了27%。     

干扰约束和负载均衡的无线Mesh网络网关部署策略

网关部署是无线Mesh网络规划面临的重要挑战之一.在Mesh路由器(MR)已完成部署的前提下,如何计算同时满足网络性能要求和用户流量需求的最小网关(GW)集合,已经被证明是一个NP-hard问题.文中提出了一种满足干扰约束和支持负载均衡的网关部署策略ICLB-GPS,在部署网关时消减链路干扰并实现网关负载均衡.ICLB-GPS策略综合网关选择、转发树构建和转发树间的节点迁移来完成负载均衡的网关部署,主要包含覆盖重叠和干扰消减的网关选择、基于树间节点迁移的网关负载均衡两个算法.仿真实验将ICLB-GPS算法与其它算法在网关数量、MR-GW路径长度、链路干扰程度及负载均衡指数方面进行比较,其结果表明该算法在不增加部署成本,不提高MR-GW路径长度的情况下,消减了链路干扰,实现了网关负载均衡.     

基于多维评价模型及改进蚁群优化算法的云计算资源调度策略

针对云计算环境下资源调度模型未充分考虑资源评价的问题,为更好适应不同节点计算性能和大规模数据环境的处理需求,提出了一种基于多维评价模型的虚拟机资源调度策略;首先,在云计算环境下建立包括网络性能在内的多维资源评价模型,在此基础上提出一种改进的蚁群优化算法实现资源调度策略;然后在云计算仿真平台CloudSim上进行实现。实验结果表明,该算法可以更好适应不同网络性能的计算环境,显著提高了资源调度的性能,同时降低了虚拟机负载均衡离差,满足了云计算环境下的虚拟机资源负载均衡需求。     

Channel measurement-based access point selection in IEEE 802.11 WLANs

With the wide deployment of IEEE 802.11 Wireless Local Area Networks, it has become common for mobile nodes (MNs) to have multiple access points (APs) to associate with. With the Received Signal Strength Indicator (RSSI)-based AP selection algorithm, which is implemented in most commercial IEEE 802.11 clients, the AP with the best signal strength is selected regardless of the candidate AP’s available throughput, resulting in unbalanced distribution of clients among the APs in the network. Several studies have shown performance improvement in not just the new MN (nMN), but also the network as a whole when the selection process considers the current load status of candidate APs. However, the proposed algorithms in these studies assume that there are no hidden terminal problems that severely affect the performance of the network. Hidden terminal problems frequently occur in wireless networks with unlicensed frequencies, like IEEE 802.11 in the 2.4 GHz band. Moreover, none of the previous studies have considered frame aggregation, a major improvement in transmission efficiency introduced and widely deployed with the IEEE 802.11n standard. In this paper, we propose a new AP selection algorithm based on the estimation of available throughput calculated with a model based on the IEEE 802.11 distributed coordination function in consideration of hidden terminal problems and frame aggregation. The proposed algorithm is evaluated through extensive simulation, and the results show that the nMN with the proposed AP selection algorithm can achieve up to 55.84% and 22.31% higher throughput compared to the traditional RSSI-based approach and the selection algorithm solely based on the network load, respectively.     

无线网络负载均衡技术浅析

随着无线局域网扩展服务集中的终端（STA）的移动和无线信道的时变,各个接入点（AP）上的负载会出现差异,需要加强负载均衡,平衡各个AP的差异,以达到最大化的网络资源利用。无线局域网中的负载均衡算法可以采用STA／AP主控负载均衡或接入式／切换式负载均衡技术。     

无线网络负载均衡技术浅析

随着无线局域网扩展服务集中的终端(STA)的移动和无线信道的时变,各个接入点(AP)上的负载会出现差异,需要加强负载均衡,平衡各个AP的差异,以达到最大化的网络资源利用。无线局域网中的负载均衡算法可以采用STA/AP主控负载均衡或接入式/切换式负载均衡技术。     

基于SDN的WLAN负载感知切换方案实现

基于软件定义网络将网络的控制平面与转发平面分离,并提供开放的可编程接口等特点,提出一种基于SDN的AP负载感知的切换算法,以减少网络中频繁切换并使AP间负载相对均衡。该方法利用SDN集中控制功能,实时监控AP的网络状态信息,并由控制器判断AP负载状态和预测终端运动状态来辅助切换过程。实验结果表明,该切换方法可以减少切换次数和平衡AP间的负载,保证用户网络服务质量。     

Distributed channel assignment algorithms for 802.11n WLANs with heterogeneous clients

As the latest IEEE 802.11 standard, 802.11n applies several new technologies, such as multiple input multiple output (MIMO), channel bonding, and frame aggregation to greatly improve the rate, range and reliability of wireless local area networks (WLANs). In 802.11n WLANs, access points (APs) are often densely deployed to provide satisfactory coverage. Thus nearby APs should operate at non-overlapping channels to avoid mutual interference. It is challenging to assign channels in legacy 802.11a/b/g WLANs due to the limited number of channels. Channel assignment becomes more complex in 802.11n WLANs, as the channel bonding in 802.11n allows WLAN stations (APs and clients) to combine two adjacent, non-overlapping 20MHz channels together for transmission. On the other hand, IEEE 802.11n is backward compatible, such that 802.11n clients will coexist with legacy clients in 802.11n WLANs. Legacy clients may affect the performance of nearby 802.11n clients, and reduce the effectiveness of channel bonding. Based on these observations, in this paper, we study channel assignment in 802.11n WLANs with heterogeneous clients. We first present the network model, interference model, and throughput estimation model to estimate the throughput of each client. We then formulate the channel assignment problem into an optimization problem, with the objective of maximizing overall network throughput. Since the problem is NP-hard, we give a distributed channel assignment algorithm based on the throughput estimation model. We then present another channel assignment algorithm with lower complexity, and aim at minimizing interference experienced by high-rate, 802.11n clients. We have carried out extensive simulations to evaluate the proposed algorithms. Simulation results show that our algorithms can significantly improve the network throughput of 802.11n WLANs, compared with other channel assignment algorithms.     

Load-balanced AP association in multi-hop wireless mesh networks

Wireless mesh networks (WMNs) provide high-bandwidth wireless access, which makes it capable for multimedia services. A user in a WMN may be covered by multiple APs, while it should be associated with only one to access the Internet. Conventional IEEE 802.11 user-AP association mechanism for WLANs employs signal strength as the sole metric. However, this may lead to network congestion and performance degradation in multi-hop networks such as WMNs, especially for multimedia services that require a large bandwidth and a low latency. Thus AP association in WMNs becomes an important research issue. In this paper we propose a novel AP association approach LBAA, taking AP’s load-balancing, WMN’s multi-hop characteristic, and user’s RSSI into consideration. We first propose a centralized algorithm and then extend it to a distributed one, with the latter one more practical and convenient for deployment. Network throughput and max–min user fairness are improved by LBAA. Performance evaluation demonstrating the benefits of our approach is given through a series of experiments in terms of collision probability, access bandwidth, end-to-end throughput, and average RSSI.     

IEEE 802.11宽带无线局域网负载均衡优化研究

在基于IEEE 802.11的宽带无线局域网中,随着终端STA的接入、移动和无线信道的时变性,各个接入点（AP）的负载将会产生差异,需要负载均衡优化机制平衡各个AP的差异,以达到网络资源的最大利用率。详细讨论了无线局域网中用到的几种负载均衡机制,分析了各自的优缺点,结合这些特点给出一种新的负载均衡机制。该机制能较准确地统计终端业务信息,降低切换失败风险,快速达到APs之间的负载均衡,优化提高网络整体性能。     

Efficient multicasting over large-scale WLANs through controlled association

Support for efficient multicasting in WLANs can enable new services such as streaming of TV channels, radio channels, and visitor’s information. With increasing deployments of large-scale WLANs, such services can be made available to a large number of users. However, any new multicast based services must minimally impact the existing unicast services which are currently the core services offered by most WLANs. In this paper, we leverage the flexibility of associating with different access-points (APs), which occurs often due to overlapping coverage of APs, to optimize the network’s objective. Motivated by different revenue functions and network scenarios, three different optimization objectives are considered which are: maximizing the number of admitted users (MNU), balancing the load among APs (BLA), and minimizing the load of APs (MLA). We show that these problems are NP-hard and present centralized approximation algorithms and distributed approaches to solve them. These algorithms compute which AP a user should be associated with. Using simulations we evaluate their performance and compare them to a naive approach in which users associate to the AP with the best RSSI (Received Signal Strength Indicator).     

基于演化博弈的用户接入机制

用户接入问题就是无线终端选择接入某个服务基站的问题。用户接入可以看作无线资源管理的第一步,对于网络性能有着重要的影响,在实现负载均衡、控制干扰、提高频谱和能量效率等方面起着非常重要的作用。针对包含宏基站和全双工小基站的多层异构网络特点,考虑了分离多接入机制,即允许一个终端在上行和下行接入到不同的多个基站,从而实现性能的提升。在此基础上,将异构网络中的上行下行分离多接入的用户接入问题建模成一个演化博弈问题,其中用户是博弈方,相互之间进行资源的竞争,基站的接入选择就是博弈中的策略,每个用户希望能通过策略的选择实现自身效用的最大化。此外,基于演化博弈和强化学习设计了低复杂度自组织用户接入算法,用户可以根据当前的策略选择收益来进行策略调整,并最终达到均衡状态,实现了用户公平性。最后通过大量的仿真实验验证了所提方法的有效性。