An efficient clustering and load balancing of distributed cloud data centers using graph theory

The prime focus of the Cloud Service Providers is enhancing the service delivery performance of the distributed cloud data centers. The clustering and load balancing of distributed cloud data centers have significant impact on its service delivery performance. Hence, this paper models distributed cloud data center environment as a network graph and proposes a two‐phase cluster‐based load balancing (CLB) algorithm based on a graph model. The first phase proposes a Cloud Data Center Clustering algorithm to cluster the distributed cloud data centers based on their proximity. The second phase proposes a Client‐Cluster Assignment algorithm to perform uniform distribution of the client requests across the clusters to enable load balancing. To assess the performance, the proposed algorithms are compared with other K‐constrained graph‐based clustering algorithms namely, graph‐based K‐means and K‐spanning tree algorithms on a simulated distributed cloud data center environment. The experimental results reveal that the proposed CLB algorithm outperforms the compared algorithms in terms of the average clustering time, load distribution, and fairness index and hence improves the service delivery performance of the distributed cloud data centers.     

时分波分无源光网络与云无线接入网联合架构中负载平衡的用户关联与资源分配策略

在时分波分无源光网络(TWDM-PON)与云无线接入网(C-RAN)的联合架构中,由于无线域的负载不均衡问题,限制了网络整体的传输效率。为了充分利用TWDM-PON与C-RAN联合架构的网络资源,并保证用户的服务质量(QoS),该文提出一种负载平衡的用户关联与资源分配算法(LBUARA)。首先根据不同用户的服务质量需求以及分布式无线射频头端(RRH)的负载对用户的影响,构建用户收益函数。进而,在保证用户服务质量的前提下,根据网络状态建立随机博弈模型,并基于多智能体Q学习提出负载均衡的用户关联和资源分配算法,从而获得最优的用户关联与资源分配方案。仿真结果表明,所提的用户关联和资源分配策略能够实现网络的负载均衡,保证用户的服务质量,并提高网络吞吐量。     

An Energy-Aware Hybrid Approach for Wireless Sensor Networks Using Re-clustering-Based Multi-hop Routing

In recent years, cloud computing provides a spectacular platform for numerous users with persistent and alternative varying requirements. In the cloud environment, security and service availability are the two most significant factors during the data encryption process. For providing optimal service availability, it is necessary to establish a load balancing technique that is capable of balancing the request from diverse nodes present in the cloud. This paper aims in establishing a dynamic load balancing technique using the APMG approach. Here in this paper, we integrated adaptive neuro-fuzzy interference system-polynomial neural network as well as memory-based grey wolf optimization algorithm for optimal load balancing. The memory-based grey wolf optimization algorithm is employed to enhance the precision of ANFIS-PNN and to maximize the locations of the membership functions respectively. Also, two significant factors namely the turnaround time and CPU utilization involved in optimal load balancing scheme are evaluated. Finally, the performance evaluation of the proposed MG-ANFIS based dynamic load balancing approach is compared with various other load balancing approaches to determine the system performances.

     

Hybrid model for dynamic evaluation of trust in cloud services

Cloud computing, a new paradigm in distributed computing, has gained wide popularity in a relatively short span of time. With the increase in the number, functionality and features of cloud services, it is more and more mind-boggling for the cloud users to find a trustworthy provider. Cloud users need to have confidence in cloud providers to migrate their critical data to cloud computing. There must be some means to determine reliability of service providers so that users can choose services with the assurance that the provider will not act malignantly. An effort has been made in this paper to formulate a hybrid model to calculate the trustworthiness of service providers. Cloud services are evaluated and trust value is calculated based on compliance and reputation. Service logs based compliance reflects dynamic trust. The reputation has been computed from collective user feedback. Feedback rating is the view of each user about the invoked services. The discovered services that fulfill the user requirements are ranked based on their trust values and top-k cloud services are recommended to the user. The proposed approach is efficient and considerably improves service-selection process in cloud applications.     

面向服务可靠性的云资源调度方法

随着云计算成为重要的信息基础设施,越来越多的应用迁移到云上,云服务的可靠性日益重要,尤其是边缘计算新模式的引入,对云服务可靠性提出了更高的要求.如何通过资源调度保障服务可靠性成为了当前研究的热点.为此,针对云-边协同的应用场景,开展面向服务可靠性的云资源调度方法研究,提出基于马尔科夫预测模型的云资源调度算法,实现节点负载判断、待迁移任务和节点选择、迁移路由的决策,以解决云服务节点失效情况下的任务调度和负载均衡问题,实现快速的云服务故障恢复,提高云服务的可靠性.实验结果表明,本文所提方法能够有效保证节点失效情况下的服务可靠性.     

Error Rate Analysis of Uplink MC-CDMA Systems using Complementary Codes in Rayleigh Fading Channels

Cloud computing is a global technology for data storage and retrieving. Many organizations are switching their companies to cloud technology, so that they can lease cloud services for use on a membership or pay as you go basis rather than creating their own systems. Cloud service provider and the Cloud service accessibility are the two major problems in cloud computing. The Economic Denial of Sustainability (EDoS) attack is an important attack towards the cloud service providers. The attackers may send continuous requests to the cloud in a particular second. Hence the legitimate user cannot access the data due to heavy cloud traffic. Hence the paid user cannot access the data. However, this problem makes an economical issue to the users. So this paper presented a new technique as, ADS-PAYG (Attack Defense Shell- Pay As You Go) approach using Trust Factor method against the EDoS attack is proposed to improve more number of authenticated users by fixing a threshold value. The algorithm produced an effective result based on response time, accuracy and CPU utilization. The ADS-PAYG solution is applied using MATLAB, which outperforms other Trust factor estimation methods and effectively distinguishes attackers from legitimate users. The detection accuracy is 83.43% for the given dataset and it is high when compared to the existing algorithms.

     

An Approach Towards Amelioration of an Efficient VM Allocation Policy in Cloud Computing Domain

Cloud computing is on the horizon of the domain of information technology over the recent few years, giving different remotely accessible services to the cloud users. The quality-of-service (QoS) maintaining of a cloud service provider is the most dominating research issue today. The QoS embraces with different issues like virtual machine (VM) allocation, optimization of response time and throughput, utilizing processing capability, load balancing etc. VM allocation policy deals with the allocation of VMs to the hosts in different datacenters. This paper highlights a new VM allocation policy that distributes the load of VMs among hosts which improves the utilization of hosts’ processing capability as well as makespan and throughput of cloud system. The experimental results are obtained by utilizing trace based simulation in CloudSim 3.0.3 and compared with existing VM allocation policies.     

异构云无线接入网架构下面向混合能源供应的动态资源分配及能源管理算法

针对面向混合能源供应的 5G 异构云无线接入网(H-CRANs)网络架构下的动态资源分配和能源管理问题,该文提出一种基于深度强化学习的动态网络资源分配及能源管理算法。首先,由于可再生能源到达的波动性及用户数据业务到达的随机性,同时考虑到系统的稳定性、能源的可持续性以及用户的服务质量(QoS)需求,将H-CRANs网络下的资源分配以及能源管理问题建立为一个以最大化服务提供商平均净收益为目标的受限无穷时间马尔科夫决策过程(CMDP)。然后,使用拉格朗日乘子法将所提CMDP问题转换为一个非受限的马尔科夫决策过程(MDP)问题。最后,因为行为空间与状态空间都是连续值集合,因此该文利用深度强化学习解决上述MDP问题。仿真结果表明,该文所提算法可有效保证用户QoS及能量可持续性的同时,提升了服务提供商的平均净收益,降低了能耗。     

一种基于分层多代理的云计算负载均衡方法

针对现有云计算系统中负载均衡方法的不足,借鉴系统逻辑分层和多代理的思想,提出一种基于分层多代理的云计算负载均衡方法.通过对云计算平台逻辑分层,在任务代理层设置任务监控代理和任务子代理,根据用户任务的差异性,采用基于任务优先级和QoS目标约束的调度策略协同完成任务调度;在资源代理层设置资源监控代理和资源子代理,考虑物理节点的异构性,采用基于启发式贪婪的资源分配策略协同完成虚拟机到物理节点的映射.通过评估对比仿真实验,结果表明该方法在任务调度效率、任务完成时间、截止时间违背率和负载均衡度方面表现更优,多代理有效地分担了中心管理节点的管理负载,使云计算平台的任务处理能力、资源利用率及鲁棒性均得到了进一步的提升.     

An autonomic risk‐ and penalty‐aware resource allocation with probabilistic resource scaling mechanism for multilayer cloud resource provisioning

Cloud computing environment allows presenting different services on the Internet in exchange for cost payment. Cloud providers can minimize their operational costs by auto‐scaling of the computational resources based on demand received from users. However, the time and cost required to increase and decrease the number of active computational resources are among the biggest limitations of scalability. Thus, auto‐scaling is considered as one of the most important challenges in the field of cloud computing. The present study aimed to present a new solution to automatic scalability of resources for multilayered cloud applications under the Monitor‐Analysis‐Plan‐Execute‐Knowledge loop. In addition, the Google penalty payment model was used to model the penalty costs in the problem and to accurately evaluate the earned profit. A hybrid resource load prediction algorithm was proposed to evaluate the future of resources in each cloud layer. Further, we used statistical solution to determine the statuses of VMs in addition to presenting a risk‐aware algorithm to allocate the user requests to active resources. The experimental results by Cloudsim indicated the improvement of the proposed approach in terms of operational costs, the number of used resources, and the amount of profit.     

A hierarchical approach for resource allocation in hybrid cloud environments

Cloud computing is a key technology for online service providers. However, current online service systems experience performance degradation due to the heterogeneous and time-variant incoming of user requests. To address this kind of diversity, we propose a hierarchical approach for resource management in hybrid clouds, where local private clouds handle routine requests and a powerful third-party public cloud is responsible for the burst of sudden incoming requests. Our goal is to answer (1) from the online service provider’s perspective, how to decide the local private cloud resource allocation, and how to distribute the incoming requests to private and/or public clouds; and (2) from the public cloud provider’s perspective, how to decide the optimal prices for these public cloud resources so as to maximize its profit. We use a Stackelberg game model to capture the complex interactions between users, online service providers and public cloud providers, based on which we analyze the resource allocation in private clouds and pricing strategy in public cloud. Furthermore, we design efficient online algorithms to determine the public cloud provider’s and the online service provider’s optimal decisions. Simulation results validate the effectiveness and efficiency of our proposed approach.     

Efficient Resource Management for Cloud-enabled Video Surveillance over Next Generation Network

The next generation video surveillance systems are expected to face challenges in providing computation support for an unprecedented amount of video streams from multiple video cameras in a timely and scalable fashion. Cloud computing offers huge computation resources for large-scale storage and processing on demand, which are deemed suitable for video surveillance tasks. Cloud also provides quality of service guaranteed hardware and software solutions with the virtual machine (VM) technology using a utility-like service costing model. In cloud-based video surveillance context, the resource requests to handle video surveillance tasks are translated in the form of VM resource requests, which in turn are mapped to VM resource allocation referring to physical server resources hosting the VMs. Due to the nature of video surveillance tasks, these requests are highly time-constrained, heterogeneous and dynamic in nature. Hence, it is very challenging to actually manage the cloud resources from the perspective of VM resource allocation given the stringent requirements of video surveillance tasks. This paper proposes a computation model to efficiently manage cloud resources for surveillance tasks allocation. The proposed model works on optimizing the trade-off between average service waiting time and long-term service cost, and shows that long-term service cost is inversely proportional to high and balanced utilization of cloud resources. Experiments show that our approach provides a near-optimal solution for cloud resource management when handling the heterogeneous and unpredictable video surveillance tasks dynamically over next generation network.     

云环境下任务调度算法对比研究

云计算是完全基于互联网的新兴技术。云计算环境中的任务调度问题一直都是该领域的研究热点。合理高效的任务调度算法在云环境中能有效的缩短任务完成时间,提高系统负载均衡,更好的满足用户与云提供商的需求。本文研究了云平台的任务调度机制,探究了任务调度过程中的关键性指标。通过云仿真平台CloudSim实现并分析了顺序调度算法、Min-Min算法和Max-Min算法,对比其在随机生成用户任务负载与虚拟机计算资源的情况下的任务完成时间,实验证明Min-Min算法与Max-Min算法均优于顺序调度算法。以此为未来研究提供实验支撑和方向。     

基于云模型的负载均衡问题研究

云环境是一个复杂多变的环境,其不同层次提供不同的服务,在处理服务请求时其服务类型与服务器节点供给都是一个动态,随机的变化过程,如何高效的组织以及利用这些节点的处理能力,是该环境中负载技术应该考虑的关键问题.本文对云计算中私有云模型做了概括总结;并对负载均衡调度问题在不同平台中的研究现状做了相关描述,最后、指出了负载均衡调度问题在私有云中未来的研究方向.     

Dynamic resource allocation in cloud download service

Cloud download service, as a new application which downloads the requested content offline and reserves it in cloud storage until users retrieve it, has recently become a trend attracting millions of users in China. In the face of the dilemma between the growth of download requests and the limitation of storage resource, the cloud servers have to design an efficient resource allocation scheme to enhance the utilization of storage as well as to satisfy users' needs like a short download time. When a user's churn behavior is considered as a Markov chain process, it is found that a proper allocation of download speed can optimize the storage resource utilization. Accordingly, two dynamic resource allocation schemes including a speed switching (SS) scheme and a speed increasing (SI) scheme are proposed. Both theoretical analysis and simulation results prove that our schemes can effectively reduce the consumption of storage resource and keep the download time short enough for a good user experience.     

An energy‐saving algorithm for cloud resource management using a Kalman filter

Cloud computing has emerged as a promising technique to provide storage and computing component on‐demand services over a network. In this paper, we present an energy‐saving algorithm using the Kalman filter for cloud resource management to predict the workload and to further achieve high resource availability with low service level agreement. Using the proposed algorithm, one can estimate the potential future workload trend then predict the computing component workload utilizations and further retrench energy consumption and achieve load balancing in a cloud system. Experimental results show that the proposed algorithm achieves more than 92.22% accuracy in the computing component workload prediction, improves 55.11% energy in energy consumption, and has 3.71% in power prediction error rate, respectively. Copyright © 2013 John Wiley & Sons, Ltd.     

Network virtualization for cloud computing

Cloud computing enables a transparent access to information technology (IT) services such that the users do not need to know the location and characteristics of the relevant resources. While IT resource virtualization and service abstraction have been widely investigated, data transport within the cloud and its efficient control have not received much attention in the technical literature. In fact, connectivity is, itself, a service that contributes to the overall performance of the cloud. This paper introduces a novel classification of the Network as a Service (NaaS) such that it can be orchestrated with other cloud services. Then, it proposes a network virtualization platform (NVP) as the mediation layer able to provide NaaS to cloud computing by exploiting the functionality provided by control plane (CP)-enabled networks. In particular, the proposed NVP maps the end-point addresses and perceived Quality of Service parameters of a NaaS requests in the parameters characterizing the connectivity as viewed by transport networks using the information obtained from the CP at the boundary of the network. The NVP uses these parameters to fulfill connectivity requests to the CP. Finally, this paper presents a complete design from both the software implementation and network signaling perspective of two use cases in which NaaS is involved as stand-alone facility for the connectivity service provisioning or is combined with other cloud services for a storage service provisioning.     

Performance of MIMO-UWB for LOS and N-LOS Propagation

Mobile cloud computing (MCC) enables ubiquitous access to a diverse range of Internet multimedia services in a pay-as-you-go economic model. In an MCC environment with highly mobile users, the migration of service requests from one cloud server to another due to user movement may frequently occur. We note that when the load offered to the cloud server is increased beyond the capacity limit, particularly when migrated traffic due to user movement suddenly appears, the probability to disrupt existing services gets higher, consequently resulting in the degradation of user quality of experience (QoE). To keep the service disruption probability at an acceptable level so as to maintain a high user-perceived QoE for different classes of multimedia services, this paper proposes a QoE-aware service continuity strategy for the cloud server in an MCC environment. The strategy is based on the buffer-occupancy threshold policy that differentiates newly arriving service requests coming from the mobile users and offers effective protection for migrated service requests against traffic fluctuation in newly arriving service requests. With the proposed strategy, the cloud server can dynamically change the buffer thresholds for different classes of service requests based on the offered traffic load and the user mobility to improve resource utilization, and, most importantly, to keep the service disruption probability at an acceptable level. Besides, by taking the effect of migrated traffic into account, we develop an analytical model to study the performance of the cloud server using the proposed strategy. With the analytical model, we propose an iterative method to determine the optimal buffer thresholds that maximize resource utilization while keeping an acceptable user QoE for different classes of services.

     

5G Mobile Virtual Reality Optimization Solution for Communication and Computing Integration

5G network is an inevitable trend in the development of mobile communications. Mobile cloud computing is a more promising technology for 5G networks. This paper proposes a hierarchical distributed cloud service network model, which is composed of three layers: “access cloud + distributed micro cloud + core cloud”. On the basis of access to the cloud, a distributed micro cloud system is deployed to migrate the service capabilities of the remote core cloud server to the local area. This paper proposes a task offloading assignment algorithm in a small cell cloud scenario. This algorithm establishes a SCC (Small Cell Cloud) based on the channel quality between small cells and the remaining available computing resources, and allocates the load to each small cell in the SCC according to the channel quality and the remaining available computing resources. Simulation results show that this solution can improve the utilization of wireless and computing resources in the small cell cloud computing scenario, and improve the user QoE (Quality of Experience). In order to make the system operate normally under heavy load, this paper proposes a feedback adaptive random access strategy based on the adaptive random access model. This can ensure that the throughput rate does not decrease under heavy load conditions, and at the same time, the average access delay of the existing system is reduced. When the arrival rate of user requests gradually increases, the throughput rate of RA-RACH access will continue to decrease due to collisions until it approaches below 0.1. In the state where the number of users is low and the load is lighter, both RA-RACH, AC-RACH, and FC-RACH have a higher access success rate. But as the load continues to increase, RA-RACH will quickly drop to 0.

     

中国联通信息化云计算工作探讨

在云计算时代,运营商需要将自身网络智能和控制能力与云服务有机结合,提出集成、高效、可靠的云平台信息化发展战略。文章以中国联通云平台试验工作为依托,分析目前运营商信息化云计算发展思路和标准化工作,并根据实际情况介绍桌面云和绿色数据中心的建设情况,为电信级的云服务运营提供参考依据。