Bandwidth Allocation with Minimum Rate Constraints in Cluster-based Femtocell Networks

 Inter-femtocell interference becomes serious when femtocells are densely deployed. To mitigate the inter-femtocell interference, this paper proposes a cluster-based bandwidth allocation algorithm. We create femtocell clusters by constructing a weighted interference graph and allocate bandwidth to each cluster based on a Nash bargaining solution (NBS). Simulation results show that the cluster-based bandwidth allocation algorithm can reduce the inter-femtocell interference and meet the minimum rate constraint of each cluster.     

密集家庭基站网络中基于分簇的资源分配方案

针对家庭基站密集部署情况下的下行干扰问题,提出一种基于分簇的资源分配方案。首先,采用部分频率复用（FFR）技术将网络中所有小区划分成不同的空间,既能抑制宏基站之间的同层干扰,又能降低边缘区域宏基站与家庭基站间的跨层干扰;然后,结合图论的知识及凸优化理论对家庭基站进行分簇,并采用基于用户速率公平的信道分配算法对家庭基站进行子信道分配,抑制家庭基站间的同层干扰;最后,采用分布式功率控制算法对家庭基站功率进行动态调整,进一步提升系统的性能。仿真结果表明：相比传统未分组算法,所提算法的信干噪比（SINR）和吞吐量有明显提高,其中,系统吞吐量低于4 Mb/s的概率降低为30%;同时,与未分组算法相比,所提算法公平性提高了12%,使用户获得更高的满意度。     

A Distributed PTX Virtual Machine on Hybrid CPU/GPU Clusters

Hybrid CPU/GPU cluster recently has drawn lots of attention from high performance computing because of excellent execution performance and energy efficiency. Many supercomputing sites in the newest TOP 500 and Green 500 are built by hybrid CPU/GPU clusters instead of CPU clusters. However, the programming complexity of hybrid CPU/GPU clusters is so high such that most of users usually hesitate to move toward to this new cluster computing platform. To resolve this problem, we propose a distributed PTX virtual machine called BigGPU on heterogeneous clusters in this paper. As named, this virtual machine physically is a distributed system which is aimed at parallel re-compiling and executing the PTX codes by aggregating CPUs and GPUs available in a computational cluster. With the support of this virtual machine, users can regard a hybrid CPU/GPU as a single large-scale GPU. Consequently, they can develop applications by using only CUDA without combining MPI and multithreading APIs while can simultaneously use distributed CPUs and GPUs for resolving the same problem. Moreover, they need not handle the problem of load balance among heterogeneous processors and the constraints of device memory and thread configuration existing in physical GPUs because BigGPU supports large-scale virtual device memory space and thread configuration. On the other hand, we have evaluated the execution performance of BigGPU in this paper. Our experimental results have shown that BigGPU indeed can effectively exploit the computational power of CPUs and GPUs for enhancing the execution performance of user's CUDA programs.     

CoMP clustering and backhaul limitations in cooperative cellular mobile access networks

Coordinated Multi-Point (CoMP) transmission and reception is a promising solution for managing interference and increasing performance in future wireless cellular systems. Due to its strict requirements in terms of capacity, latency, and synchronization among cooperating Base Stations (BSs), its successful deployment depends on the capability of the mobile backhaul network infrastructure.We deal with the feasibility of CoMP transmission/reception, in particular of Joint Transmission (JT). For this, we first evaluate which cluster sizes are reasonable from the wireless point-of-view to achieve the desired performance gains. Thereafter, we analyze how different backhaul topologies (e.g., mesh and tree structures) and backhaul network technologies (e.g., layer-2 switching and single-copy multicast capabilities) can support these desired clusters. We study for different traffic scenarios and backhaul connectivity levels, which part of the desired BS clusters are actually feasible according to the backhaul characteristics. We found out that a significant mismatch exists between the desired and feasible clusters. Neglecting this mismatch causes overheads in real JT implementations, which complicates or even prevents their deployment.Based on our findings, we propose a clustering system architecture that not only includes wireless information, as done in the state of the art, but also combines wireless and backhaul network feasibility information in a smart way. This avoids unnecessary signaling and User Equipment (UE) data exchange among BSs which are not eligible to take part in the cooperative cluster. Evaluations show that our scheme reduces the signaling and UE data exchange overhead by up to 85% compared to conventional clustering approaches, which do not take into account the backhaul network’s status.     

Resource allocation algorithms for virtualized service hosting platforms

Commodity clusters are used routinely for deploying service hosting platforms. Due to hardware and operation costs, clusters need to be shared among multiple services. Crucial for enabling such shared hosting platforms is virtual machine (VM) technology, which allows consolidation of hardware resources. A key challenge, however, is to make appropriate decisions when allocating hardware resources to service instances. In this work we propose a formulation of the resource allocation problem in shared hosting platforms for static workloads with servers that provide multiple types of resources. Our formulation supports a mix of best-effort and QoS scenarios, and, via a precisely defined objective function, promotes performance, fairness, and cluster utilization. Further, this formulation makes it possible to compute a bound on the optimal resource allocation. We propose several classes of resource allocation algorithms, which we evaluate in simulation. We are able to identify an algorithm that achieves average performance close to the optimal across many experimental scenarios. Furthermore, this algorithm runs in only a few seconds for large platforms and thus is usable in practice.     

基于虚拟力的WSNs能量高效分簇路由协议

作为无线传感器网络(wireless sensor networks,WSNs)的关键技术之一,分簇路由协议因其可扩展性较强及能耗较低等优势,逐渐成为WSNs路由协议的研究热点.如何对簇首进行最佳化选取,是提高分簇路由协议性能的关键.通过揭示不同场景中的簇首数量及网络能耗之间的映射关系,以能耗最小化为目标,构建了簇首最...     

Channel allocation and power control schemes for cross-tier 3GPP LTE networks to support multimedia applications

In this paper, we present the framework of a channel allocation (CA) and power control (PC) schemes for the minimization of interference in cross-tier 3GPP LTE networks that aim to support internet of multimedia things. Channel allocation scheme based on an interference graph preserving the minimum number of interfered MUEs by femtocells (IG-MIM) is proposed to mitigate interference amongst femtocells, and a game theory based power control algorithm is also proposed to reduce interference to surrounding macrocell users (MUEs). The proposed IG-MIM scheme constructs the interference graph based on a predefined threshold and allocates the subchannels to the femtocells that maintain the smallest number of interfered MUEs. For the power control, we design a payoff function based on the rewards from the achieved data rates and the penalties from the interference in regards to its adjacent femtocells. The simulation results show that the IG-MIM channel allocation significantly improves the SINR performance for the femtocell users (FUEs) being served; the game theory based power control decreases the power requirements of a femtocell and alleviates the interference to the MUEs.     

A novel Adaptive Cluster Transformation (ACT)-based intrusion tolerant architecture for hybrid information technology

Recently, the building of strong intrusion tolerant systems is in great demand since the openness and the distributed nature of information systems are easily used to compromise the systems by intentional attacks. To achieve intrusion tolerance by enabling the systems to survive various types of intrusions, we suggest a novel approach, Adaptive Cluster Transformation (ACT), in this paper. Instead of using a fixed cluster size as in conventional approaches, ACT adapts a variable cluster size depending on the system status. This is proved to maintain good quality of service (QoS). In addition, the early prediction of incoming massive packets makes ACT possible to replace any damaged clusters with new ones consisting of pristine virtual machines (VMs). This also contributes to defend the system against a Denial of Service (DoS). The performance of ACT is compared with other fixed sizes of VM cluster architectures by CSIM 20. And it is verified that the proposed method is more effective in maintaining the specific level of QoS as well as providing strong security to the targeted system.     

Cell ID extension in femtocell environments

In this paper, we solve a cell identification problem in a femtocell environment. Wireless communication standards specify physical cell identifiers (PCIs) for user entities (UEs) to discriminate data from different cells and for networks to identify cells. However, in the densely deployed area, the number of PCIs for femtocells may not be sufficient. The scarcity of PCIs results in identification ambiguity due to duplicated PCIs in a certain area, which may result in handover failure. Using time synchronization between femtocells and macro-cells, we propose a scheme to efficiently identify cells in a femtocell environment. The proposed scheme defines the virtual cell identifier (vID) of a femtocell as the system frame number offset of the femtocell with respect to a macro-cell and differentiates femtocells with combinations of vIDs and PCIs. Our scheme can increase the number of cell identifiers up to 1024 times using even coarse local time synchronization without changing the existing physical layer specification. The improvement in cell identification resolution reduces redundant message transactions, resulting in network performance enhancement. Since our scheme demands only local time synchronization between adjacent cells, it can be applied to asynchronous as well as synchronous wireless systems. We verify the proposed scheme via simulations in various environments.     

An elasticity model for High Throughput Computing clusters

Different methods have been proposed to dynamically provide scientific applications with execution environments that hide the complexity of distributed infrastructures. Recently virtualization has emerged as a promising technology to provide such environments. In this work we present a generic cluster architecture that extends the classical benefits of virtual machines to the cluster level, so providing cluster consolidation, cluster partitioning and support for heterogeneous environments. Additionally the capacity of the virtual clusters can be supplemented with resources from a commercial cloud provider. The performance of this architecture has been evaluated in the execution of High Throughput Computing workloads. Results show that, in spite of the overhead induced by the virtualization and cloud layers, these virtual clusters constitute a feasible and performing HTC platform. Additionally, we propose a performance model to characterize these variable capacity (elastic) cluster environments. The model can be used to dynamically dimension the cluster using cloud resources, according to a fixed budget, or to estimate the cost of completing a given workload in a target time.     

国产万亿次机群系统NPB性能测试分析

对3个国产万亿次机群系统进行了NPB性能测试分析,重点研究大规模并行处理时(处理器数目达到上千个)的性能特点和趋势．分析了不同的处理器、互连网络等系统配置对NPB性能的影响,发现NPB的8个程序在3个万亿次机器上的性能特点和表现并不一致,表明国产高性能机群在设计上正在逐渐走出同质化的趋势,向多样化发展．进一步分析表明,目前NPB程序的可扩展性可以达到几百个处理器,但尚不能达到上千个处理器,NPB程序能发挥出的系统峰值的百分比仍然徘徊在10％左右,机群系统的并行可扩展性和应用程序对机器运算潜能的利用还需要进一步提高．对于处理器数目达到上千个的万亿次机群系统来说,对集合通信和细粒度通信能力的支持亟需提高．     

A statistical model of cluster stability

In the current paper we present a method for assessing cluster stability. This method, combined with a clustering algorithm, yields an estimate of the data partition, namely, the number of clusters. We adopt the cluster stability standpoint where clusters are imagined as islands of “high” density in a sea of “low” density. Explicitly, a cluster is associated with its high density core. Our approach offers to evaluate the goodness of a cluster by the similarity amongst the entire cluster and its core. We propose to measure this resemblance by two-sample tests or by probability distances between appropriate probability distributions. The distances are calculated on clustered samples drawn from the source population according to two different distributions. The first law is the underlying set distribution. The second law is constructed so that it represents the clusters’ cores. Here, a variant of the k-nearest neighbor density estimation is applied, so that items belonging to cores have a much higher chance to be selected. As the sample distribution is unknown a distribution-free two-sample test is required to examine the mentioned correspondence. For constructing such a test, we use distance functions built on negative definite kernels. In practice, outliers in the samples and limitations of the clustering algorithm heavily contribute to the noise level. As a result of this shortcoming the distance values have to be determined for many pairs of samples and therefore an empirical distance's distribution is obtained. The distribution is dependent on the examined number of clusters. To prevent this property for biasing the results we normalize the distances. It is conjectured that the true number of clusters yields the most concentrated normalized distribution. To measure the concentration we use the sample mean and the sample 25th percentile. The paper exhibits the good performance of the proposed method on synthetic and real-world data.     

基于GSPN的拟态DNS构造策略研究

网络空间拟态防御系统（Cyberspace Mimic Defense System,CMDS）采用动态异构冗余架构以及多模表决机制将不确定威胁转化为概率可控的事件,从而实现了自主可控、安全可信。为进一步研究拟态构造策略在不同干扰场景下的稳态可用性和感知安全性,本文采用广义随机Petri网（Generalized Stochastic Petri Net,GSPN）建模,分析了不同干扰场景下采用不同拟态构造策略对系统性能和构造成本的影响,实验结果表明拟态防御系统可以根据反馈控制信息对不同干扰场景进行策略替换,从而实现系统的稳定可用性和感知安全性。同时通过反馈控制能有效控制不同服务器解析时延差值,对实际拟态DNS系统部署有重要指导意义。     

改进K-means聚类的云任务调度算法

针对云任务调度中存在的效率低、费用高等问题,提出一种基于改进K-means聚类算法的云任务调度算法。依据虚拟资源的硬件属性,使用改进聚类算法对虚拟资源进行聚类划分;计算任务偏好,使不同偏好的任务在不同的聚类中选择资源;考虑到调度费用问题,对每个聚类使用改进后的Min-min算法进行任务调度。针对K-means聚类算法初始聚类中心随机选取,易陷入局部最优解的问题,对聚类算法进行改进。最后,利用云仿真平台CloudSim进行实验,结果表明,与无聚类的调度算法相比,本文提出的算法在执行效率方面有所提高。     

Femtocell网络中基于联合传输的分簇与功率分配算法*

针对家庭基站(femtocell)密集部署时的下行干扰问题,提出一种基于多点协作联合传输的分簇与功率分配相结合的算法。首先根据受到的干扰程度进行分簇,将干扰强的家庭基站分到同一个簇,簇内所有家庭基站通过寻找对自身最有利的基站进行协作,将干扰信号转变有用信号,联合传输为用户提供服务,提升用户的信干噪比来保证用户性能,簇间则复用相同的频谱资源。然后通过给用户分配合适的功率使得总传输速率最大。仿真结果表示,所提算法能在抑制系统干扰的同时提高系统的吞吐量。     

Elastic management of web server clusters on distributed virtual infrastructures

Cluster‐based solutions are being widely adopted for implementing flexible, scalable, low‐cost and high‐performance web server platforms. One of the main difficulties to implement these platforms is the correct dimensioning of the cluster size, so as to satisfy variable and peak demand periods. In this context, virtualization is being adopted by many organizations as a solution not only to provide service elasticity, but also to consolidate server workloads, and improve server utilization rates. A virtualized web server can be dynamically adapted to the client demands by deploying new virtual nodes when the demand increases, and powering off and consolidating virtual nodes during periods of low demand. Furthermore, the resources from the in‐house infrastructure can be complemented with a cloud provider (cloud bursting), so that peak demand periods can be satisfied by deploying cluster nodes in the external cloud, on an on‐demand basis. In this paper, we analyze the scalability of hybrid virtual infrastructures for two different distributed web server cluster implementations: a simple web cluster serving static files and a multi‐tier web server platform running the CloudStone benchmark. Copyright © 2011 John Wiley & Sons, Ltd.     

Identification of Key Variables Using Fuzzy Average With Fuzzy Cluster Distribution

Identification of the significance of input variables is very important for complex systems with high-dimensional input space. In this paper, a method using fuzzy average with fuzzy cluster distribution is proposed. To avoid the interference of different distributions of the sampling data, the distribution of fuzzy clusters in the sampling data is considered, instead of the original data set. To discover the input-output relationship, the methods of fuzzy rules and fuzzy C-means are first used to partition the original sampling data set into fuzzy clusters. A new data set with the same distribution of the fuzzy clusters is produced. The fuzzy average method is then applied to the new data set. By doing so, the interference of distribution of the original sampling data is removed. This method is straightforward and computationally easy. The performance is tested on both benchmark data and real-world data.     

A survey on interference management techniques in femtocell self-organizing networks

The femtocell concept is an emerging technology for deploying the next generation of the wireless networks, aiming at indoor coverage enhancement, increasing capacity, and offloading the overlay macrocell traffic. Nevertheless, one of the most critical issues in femtocells is the potential interference between nearby femtocells and from femtocells to macrocells or to mobile handsets, thus mitigating the overall system capacity.In this paper, we have discussed mechanisms which can be deployed to lessen the interference and increase the user capacity. Therefore, we provide a survey on the different interference and resource management techniques in Self-Organizing Network according to specifics classification criteria. These techniques derive from the following approaches: power control, proper cell planning, frequency reuse, OFDMA, self-configuration and self-optimization, conventional TDD, etc. These techniques can be applied separately and can be used as hybrid. A qualitative comparison among the different approaches and techniques is provided at the end of this paper.     

CAMAS: A cluster-aware multiagent system for attributed graph clustering

Attributed graphs describe nodes via attribute vectors and also relationships between different nodes via edges. To partition nodes into clusters with tighter correlations, an effective way is applying clustering techniques on attributed graphs based on various criteria such as node connectivity and/or attribute similarity. Even though clusters typically form around nodes with tight edges and similar attributes, existing methods have only focused on one of these two data modalities. In this paper, we comprehend each node as an autonomous agent and develop an accurate and scalable multiagent system for extracting overlapping clusters in attributed graphs. First, a kernel function with a tunable bandwidth factor δ is introduced to measure the influence of each agent, and those agents with highest local influence can be viewed as the “leader” agents. Then, a novel local expansion strategy is proposed, which can be applied by each leader agent to absorb the most relevant followers in the graph. Finally, we design the cluster-aware multiagent system (CAMAS), in which agents communicate with each other freely under an efficient communication mechanism. Using the proposed multiagent system, we are able to uncover the optimal overlapping cluster configuration, i.e. nodes within one cluster are not only connected closely with each other but also with similar attributes. Our method is highly efficient, and the computational time is shown that nearly linearly dependent on the number of edges when δ ∈ [0.5, 1). Finally, applications of the proposed method on a variety of synthetic benchmark graphs and real-life attributed graphs are demonstrated to verify the systematic performance.