基于软件定义网络的数据中心网络负载均衡算法研究

针对传统网络的分布式架构使得负载均衡技术难以满足低成本、高灵活性、自适应调整的要求,提出一种基于SDN的数据中心网络负载均衡算法。首先,根据路径当前负载状况和链路负载波动为路径设置了一个权重,并以此作为路径选择依据;其次,设置了一个负载均衡度用于衡量网络负载状况;最后,针对需要调度的流,进一步限定了其流量大小范围,保证了高效的流调度。仿真结果表明,与其他算法相比,所提算法能有效提高网络资源利用率并均衡全网负载。     

数据中心网络四层负载均衡技术综述

针对数据中心难以适应流量增长进行横向扩展并保证连接一致性的问题,阐述了四层负载均衡技术在应对高并发访问和提高资源利用率方面的重要作用,梳理了国内外四层负载均衡模块的设计与算法,总结了负载均衡器以不同方式进行部署分别存在的优缺点,同时分析了网络可编程转发技术在四层负载均衡领域中的应用与最新进展.最后,对网络新形势下负载均...     

BiTE: a dynamic bi-level traffic engineering model for load balancing and energy efficiency in data center networks

Applied Intelligence - With the recent significant growth of virtualization and cloud services, the data center network (DCN) as the underlying infrastructure is more important. The increasing and...     

Replica-aided load balancing in overlay networks

In recent years, there have been rapid advances in network infrastructure and technologies for end-user communication. However, because of network dynamics and resource limitation, providing scalable end-user communication services is challenging when the applications are utilized on a large-scale. To address this challenge, a replica-aided load balancing scheme (RALB) is proposed for enabling the nodes in an overlay networks to support the communication applications for a large number of users. This paper makes three unique contributions. First, we study the existing load balancing schemes and identify their weakness in handling time-varying workloads with frequent load fluctuations. Second, we introduce a sophisticated cost model for load balancing cost estimation, which captures the dependencies between the factors (e.g., the load, message number, and link latency). Third, we propose a performance tuning technique to minimize the load balancing cost. The extensive experiments show that RALB effectively reduces the load imbalance and eliminates the load balancing cost when compared to the existing load balancing schemes.     

Quantum load balancing in ad hoc networks

This paper presents a novel approach in targeting load balancing in ad hoc networks utilizing the properties of quantum game theory. This approach benefits from the instantaneous and information-less capability of entangled particles to synchronize the load balancing strategies in ad hoc networks. The quantum load balancing (QLB) algorithm proposed by this work is implemented on top of OLSR as the baseline routing protocol; its performance is analyzed against the baseline OLSR, and considerable gain is reported regarding some of the main QoS metrics such as delay and jitter. Furthermore, it is shown that QLB algorithm supports a solid stability gain in terms of throughput which stands a proof of concept for the load balancing properties of the proposed theory.     

The load balancing problem in OTIS-Hypercube interconnection networks

An interconnection network architecture that promises to be an interesting option for future-generation parallel processing systems is the OTIS (Optical Transpose Interconnection System) optoelectronic architecture. Therefore, all performance improvement aspects of such a promising architecture need to be investigated; one of which is load balancing technique. This paper focuses on devising an efficient algorithm for load balancing on the promising OTIS-Hypercube interconnection networks. The proposed algorithm is called Clusters Dimension Exchange Method (CDEM). The analytical model and the experimental evaluation proved the excellence of OTIS-Hypercube compared to Hypercube in terms of various parameters, including execution time, load balancing accuracy, number of communication steps, and speed.

Fine grained load balancing in multi-hop wireless networks

In this paper we address the problem of local balancing in multi-hop wireless networks. We introduce the notion of proactive routing: after a short pre-processing phase in which nodes build their routing tables by exchanging messages with neighbors, we require that nodes decide the relay of each message without any further interaction with other nodes. Besides delivering very low communication overhead, proactive routing protocols are robust against some well known active attacks to network routing. In this framework, we develop a proactive routing protocol that is able to balance the local load. Experiments show that our protocol improves network lifetime up to 98% and that it delivers a network that is more robust against attacks that have the goal of getting control over a large part of the network traffic.     

MooseFS中chunkserver负载均衡算法研究

作为云存储的核心基础平台,分布式文件系统的重要性日益凸显.分布式文件系统中数据存储在多台计算机节点上,必然会出现负载均衡问题.首先,对MooseFS的系统架构进行了研究,然后分析了MooseFS分布式文件系统中chunkserver选择算法,研究了chunkserver算法的负载均衡性能,最后对其进行了改进.经过实验测试对比,实验结果显示改进算法能显著提高chunkserver的负载均衡性能.     

Synchronous distributed load balancing on dynamic networks

In this paper, three distributed load-balancing algorithms for dynamic networks are investigated. Dynamic networks are networks in which the topology may change dynamically. The definition of a dynamic network is introduced and its graph model is presented. The main result of this study consists in proving the convergence toward the uniform load distribution of the diffusion algorithm on an arbitrary dynamic network despite communication link failures. We also give two adaptations of this algorithm (the GAE and the relaxed diffusion). Note that the hypotheses of our result are realistic and that for example the network does not have to be maintained connected. To study the behavior of these algorithms, we compare the load evolution by several simulations.     

混合型异构传感器网络中移动数据收集器的路径优化

针对周期工作-事件驱动混合型异构传感器网络, 设计一种基于静态Sink 搭配移动数据收集器(MDC) 的数据收集策略. 为了解决MDC访问规划问题, 提出一种最小能耗访问节点集搜索算法. 首先, 基于节点相对边缘度从整体层面去除适量边缘节点; 然后, 依据节点排除优先度, 迭代排除当前节点集中相对能效最低的节点, 从而逐步获得优化的访问节点集. 仿真实验结果表明, 所提出的新数据收集策略具有优异的能效性、负载均衡性和实时性.

     

Training deep neural networks: a static load balancing approach

The Journal of Supercomputing - Deep neural networks are currently trained under data-parallel setups on high-performance computing (HPC) platforms, so that a replica of the full model is charged...     

Dynamic load balancing in IP-over-WDM optical burst switching networks

In this paper, we consider the problem of dynamic load balancing in wavelength division multiplexing (WDM)-based optical burst switching (OBS) networks. We propose a load balancing scheme based on adaptive alternate routing aimed at reducing burst loss. The key idea of adaptive alternate routing is to reduce network congestion by adaptively distributing the load between two pre-determined link-disjoint alternative paths based on the measurement of the impact of traffic load on each of them. We develop two alternative-path selection schemes to select link-disjoint alternative paths to be used by adaptive alternate routing. The path selection schemes differ in the way the cost of a path is defined and in the assumption made about the knowledge of the traffic demands. Through extensive simulation experiments for different traffic scenarios, we show that the proposed dynamic load balancing algorithm outperforms the shortest path routing and static alternate routing algorithms.     

一种基于负载平衡的网络接入选择方法

针对异构无线环境,提出了一种基于负载平衡的网络选择算法。采用"终端辅助,网络决策"的策略,首先利用修正权重后的层次分析法得到网络参考向量,然后终端用户根据向量间的几何关系挑选出可接入网络集合,最后网络侧基于负载平衡的前提下为终端用户选择最终接入网络。通过仿真对比,验证了该算法的有效性。     

Practical load balancing for content requests in peer-to-peer networks

This paper studies the problem of balancing the demand for content in a peer-to-peer network across heterogeneous peer nodes that hold replicas of the content. Previous decentralized load balancing techniques in distributed systems base their decisions on periodic updates containing information about load or available capacity observed at the serving entities. We show that these techniques do not work well in the peer-to-peer context; either they do not address peer node heterogeneity, or they suffer from significant load oscillations which result in unutilized capacity. We propose a new decentralized algorithm, Max-Cap, based on the maximum inherent capacities of the replica nodes. We show that unlike previous algorithms, it is not tied to the timeliness or frequency of updates, and consequently requires significantly less update overhead. Yet, Max-Cap can handle the heterogeneity of a peer-to-peer environment without suffering from load oscillations. Mema Roussopoulos is an Assistant Professor of Computer Science on the Gordon McKay Endowment at Harvard University. Before joining Harvard, she was a Postdoctoral Fellow in the Computer Science Department at Stanford University. She received her PhD and Master’s degrees in Computer Science from Stanford, and her Bachelor’s degree in Computer Science from the University of Maryland at College Park. Her interests are in the areas of distributed systems, networking, and mobile and wireless computing. Mary Baker is a Senior Research Scientist at HP Labs. Her research interests include distributed systems, networks, mobile systems, security, and digital preservation. Before joining HP Labs she was on the faculty of the computer science department at Stanford University where she ran the MosquitoNet project. She received her PhD from the University of California at Berkeley.     

Agent-based load balancing routing for LEO satellite networks

To ensure an intelligent engineering of traffic over entire satellite networks, a distributed routing scheme for low-earth orbit (LEO) satellite networks, agent-based load balancing routing (ALBR), is presented. Two kinds of agents are used. Mobile agents migrate autonomously to explore the path connecting source and destination, to gather inter-satellite link (ISL) cost, identifier and latitude of visited satellites. Meanwhile, stationary agents employ exponential forgetting function to estimate ISL queueing delay, calculate ISL cost using the sum of propagation and queueing delays; evaluate path cost considering satellite geographical position as well as ISL cost, finally update routing items. Through simulations on a Courier-like system, the proposed scheme is shown to achieve better load balancing, and can especially decrease packet loss ratio efficiently, guarantee better throughput and end-to-end delay bound in case of high traffic load. Furthermore, results from the implementation complexity analysis demonstrate that with the aid of agent technology, ALBR has lower on-board computation, storage, signaling requirements than other on-board routing schemes.     

基于负载感知的数据流动态负载均衡策略

针对大数据流式计算平台中存在节点间负载不均衡、节点性能评估不全面的问题,提出基于负载感知算法的动态负载均衡策略,并将算法应用于Flink数据流计算平台中。首先通过有向无环图的深度优先搜索算法获取节点的计算延迟时间作为评估节点性能的依据,并制定负载均衡策略;然后基于数据分块管理策略实现流式数据的节点间负载迁移技术,通过反馈实现全局和局部的负载调优;最后通过实验评估时空代价论证算法的可行性,并讨论重要参数对算法执行效果的影响。经实验验证算法通过优化流式计算任务的负载分配提高了任务的执行效率,与采用Flink平台现有的负载均衡策略相比,任务执行时间平均缩短6.51%。     

基于SDN的动态负载均衡最优路径算法研究

在传统网络中,转发路径由各路由节点的动态协议决定,传统路径分配算法的全局性差、效率不高,对网络负载平衡的考虑不够,而且管理员难以确定业务报文所走路径。利用SDN改变传统网络对数据流控制的方式,提出一种H-Dijkstra负载均衡最优路径算法。该算法在传统Dijkstra算法的基础上设定一个动态负载均衡阈值,当检测到负载均衡参数超过此阈值,则触发动态调度策略对路径分配算法进行调整。通过反复实验与传统网络对比分析,结果表明,本文算法不仅发挥了SDN在转发与控制分离架构上的速度优势,而且避免了网络资源的浪费,提高了网络性能。     

On scheduling data access with cooperative load balancing in vehicular ad hoc networks (VANETs)

For overcoming the vehicle to vehicle frequent disconnection problem in VANETs data dissemination, several approaches have been proposed, including the provision of Road Side Units (RSUs). Due to the short wireless transmission range of RSUs and vehicle mobility, a vehicle spends only a short period of time inside the range of an RSU. This limitation, together with possible overload of RSUs sited near busy road junctions, may mean that requests from vehicles are not served within the prescribed deadlines. In this paper, we propose a cooperative load balancing approach among RSUs, in which an RSU can transfer the overload requests to other RSUs. Load transfer is done based on a number of factors: request delay tolerance, current load of the transferee RSU, and the direction in which the vehicle is heading. Using a series of simulation experiments, we demonstrate that the proposed cooperative load balancing approach outperforms the non-cooperative (stand-alone) approaches in a wide range of scenarios based on our performance metrics.     

Improving the performance of load balancing in software-defined networks through load variance-based synchronization

Software-Defined Networking (SDN) is a new network technology that decouples the control plane logic from the data plane and uses a programmable software controller to manage network operation and the state of network components. In an SDN network, a logically centralized controller uses a global network view to conduct management and operation of the network. The centralized control of the SDN network presents a tremendous opportunity for network operators to refactor the control plane and to improve the performance of applications. For the application of load balancing, the logically centralized controller conducts Real-time Least loaded Server selection (RLS) for multiple domains, where new flows pass by for the first time. The function of RLS is to enable the new flows to be forwarded to the least loaded server in the entire network. However, in a large-scale SDN network, the logically centralized controller usually consists of multiple distributed controllers. Existing multiple controller state synchronization schemes are based on Periodic Synchronization (PS), which can cause undesirable situations. For example, frequent synchronizations may result in high synchronization overhead of controllers. State desynchronization among controllers during the interval between two consecutive synchronizations could lead to forwarding loops and black holes. In this paper, we propose a new type of controller state synchronization scheme, Load Variance-based Synchronization (LVS), to improve the load-balancing performance in the multi-controller multi-domain SDN network. Compared with PS-based schemes, LVS-based schemes conduct effective state synchronizations among controllers only when the load of a specific server or domain exceeds a certain threshold, which significantly reduces the synchronization overhead of controllers. The results of simulations show that LVS achieves loop-free forwarding and good load-balancing performance with much less synchronization overhead, as compared with existing schemes.     

传感器网络中考虑负载平衡的节点密度控制策略

基于多跳路由的传感器网络具有集中式数据收集和多对一数据通信模式等特点,这容易导致数据通信出现漏斗效应,即离汇聚节点越近,网络越拥塞,节点能耗也越大,结果使某些节点甚至整个网络过早死亡。针对节点呈带状分布的同构单跳分簇网络,提出了两种能有效均衡网络负载的节点密度控制策略,通过控制各簇活动节点数量以及增加备用节点的方式,实现网络能耗的平衡。理论分析给出了两种策略下各簇活动节点数量以及所需备用节点数量的定量关系。两种策略均适合于网络负载动态变化的情况,而且不要求所有节点都能直接与基站通信,因此有着更广泛的应用场合。实验结果验证了两种策略的有效性。