A load prediction model for cloud computing using PSO-based weighted wavelet support vector machine

In order to reduce the energy consumption in the cloud data center, it is necessary to make reasonable scheduling of resources in the cloud. The accurate prediction for cloud computing load can be very helpful for resource scheduling to minimize the energy consumption. In this paper, a cloud load prediction model based on weighted wavelet support vector machine(WWSVM) is proposed to predict the host load sequence in the cloud data center. The model combines the wavelet transform and support vector machine to combine the advantages of them, and assigns weight to the sample, which reflects the importance of different sample points and improves the accuracy of load prediction. In order to find the optimal combination of the parameters, we proposed a parameter optimization algorithm based on particle swarm optimization(PSO). Finally, based on the WWSVM model, a load prediction algorithm is proposed for cloud computing using PSO-based weighted support vector machine. The Google cloud computing data set is used to verify the algorithm proposed in this paper by experiments. The experiment results indicate that comparing with the wavelet support vector machine, autoregressive integrated moving average, adaptive network-based fuzzy inference system and tuned support vector regression, the proposed algorithm is superior to the other four prediction algorithms in prediction accuracy and efficiency.     

绿色能源互补智能电厂云控制系统研究

针对现代电力系统中设施庞杂、多源异构海量数据难以有效处理、“信息孤岛”长期存在以及整体优化调度管理能力不足等问题, 基于云控制系统理论, 以智能电厂为研究对象, 本文提出了智能电厂云控制系统(Intelligent power plant cloud control system, IPPCCS)解决方案. 基于智能电厂云控制系统, 针对绿色能源发电波动性强、抗扰能力差的问题, 利用机器学习算法对采集到的风电、光伏输出功率进行短时预测, 获知未来风、光机组功率输出情况. 在云端使用经济模型预测控制(Economic model predictive control, EMPC)算法, 通过实时滚动优化得到水轮机组的功率预测调度策略, 保证绿色能源互补发电的鲁棒性, 充分消纳风、光两种能源, 减少水轮机组启停和穿越振动区次数, 在为用户清洁、稳定供电的同时降低了机组寿命损耗. 最后, 一个区域云数据中心的供电算例表明了本文方法的有效性.     

改进指数平滑预测的虚拟机自适应迁移策略

针对云数据中心虚拟机频繁迁移问题对虚拟机迁移时机进行研究,提出一种基于改进指数平滑预测的虚拟机自适应迁移策略.该策略采用双阈值和预测相结合的方法,连续判断负载状态触发负载预测,然后,根据历史负载值自适应地预测下一时刻主机负载状态并触发虚拟机迁移,实现主机负载平衡,提高迁移效率,降低能耗.经实验表明,该方法在能耗和虚拟机迁移次数方面分别可降低约7.34%和58.55%,具有良好的优化效果.     

面向移动云计算的自适应虚拟机调度算法

随着移动云计算的快速发展和应用普及,如何对移动云中心资源进行有效管理同时又降低能耗、确保资源高可用是目前移动云计算数据中心的热点问题之一.本文从CPU、内存、网络带宽和磁盘四个维度,建立了基于多目标优化的虚拟机调度模型VMSM-EUN(Virtual Machine Scheduling Model based on Energy consumption,Utility and minimum Number of servers),将最小化数据中心能耗、最大化数据中心效用以及最小化服务器数量作为调度目标.设计了基于改进粒子群的自适应参数调整的虚拟机调度算法VMSA-IPSO(Virtual Machine Scheduling Algorithm based on Improved Particle Swarm Optimization)来求解该模型.最后通过仿真实验验证了本文提出的调度算法的可行性与有效性.对比实验结果表明,本文设计的基于改进粒子群的自适应虚拟机调度算法在进行虚拟机调度时,能在降低能耗的同时提高数据中心效用.     

A Review of Energy-Related Cost Issues and Prediction Models in Cloud Computing Environments

With the expansion of cloud computing, optimizing the energy efficiency and cost of the cloud paradigm is considered significantly important, since it directly affects providers’ revenue and customers’ payment. Thus, providing prediction information of the cloud services can be very beneficial for the service providers, as they need to carefully predict their business growths and efficiently manage their resources. To optimize the use of cloud services, predictive mechanisms can be applied to improve resource utilization and reduce energy-related costs. However, such mechanisms need to be provided with energy awareness not only at the level of the Physical Machine (PM) but also at the level of the Virtual Machine (VM) in order to make improved cost decisions. Therefore, this paper presents a comprehensive literature review on the subject of energy-related cost issues and prediction models in cloud computing environments, along with an overall discussion of the closely related works. The outcomes of this research can be used and incorporated by predictive resource management techniques to make improved cost decisions assisted with energy awareness and leverage cloud resources efficiently.     

Cloud computing system risk estimation and service selection approach based on cloud focus theory

The main cloud computing service providers usually provide cross-regional and services of Crossing Multi-Internet Data Centers that supported with selection strategy of service level agreement risk constraint. But the traditional quality of service (QoS)-aware Web service selection approach cannot ensure the real-time and the reliability of services selection. We proposed a cloud computing system risk assessment method based on cloud theory, and generated the five property clouds by collecting the risk value and four risk indicators from each virtual machine. The cloud backward generator integrated these five clouds into one cloud, according to the weight matrix. So the risk prediction value is transferred to the risk level quantification. Then we tested the Web service selection experiments by using risk assessment level as QoS mainly constraint and comparing with LRU and MAIS methods. The result showed that the success rate and efficiency of risk assessment with cloud focus theory Web services selection approaches are more quickly and efficient.

     

Adaptive task scheduling strategy in cloud: when energy consumption meets performance guarantee

Energy efficiency of cloud computing has been given great attention more than ever before. One of the challenges is how to strike a balance between minimizing the energy consumption and meeting the quality of services such as satisfying performance and resource availability in a timely manner. Many studies based on the online migration technology attempt to move virtual machine from low utilization of hosts and then switch it off with the purpose of reducing energy consumption. In this paper, we aim to develop an adaptive task scheduling strategy. In particular, we first model the virtual machine energy from the perspective of the cloud task scheduling, then we propose a genetic algorithm to achieve adaptive regulations for different requirements of energy and performance in cloud tasks (E-PAGA). Then we design two types of the fitness function for choosing the next generation with different preferences on energy and performance. As a result, we can adaptively adjust the energy and performance target before assigning the task in cloud, which is able to meet various requirements from different users. From the extensive experiments, we pinpoint several important observations which are useful in configuring real cloud data centers: 1) we prove that guaranteeing the minimum total task time usually leads to low energy consumption to some extent; 2) we must pay the price of the sacrificed performance if only taking into account the energy optimization; 3) we come to the conclusion that there is always an optimal condition of energy-efficiency ratio in the cloud data center, and more importantly the specific conditions of the optimal energy-efficiency ratio can be obtained.     

可靠性云计算环境下能源效率的提高机制

针对当前云计算能源效率低以及电源故障等不可靠问题,提出了一种物理主机整合机制以及调度算法,在保障云计算可靠性的同时提高能源效率。能量优化机制可以察觉优化时机,在电源等故障时执行调度算法。算法调节虚拟机到物理主机的映射,同时将相应物理主机中空闲的CPU容量,分配到正在运行的虚拟机中,从而提高能源效率。实验结果表明,与传统的调度算法相比,该算法在工作效率上提高了15.8%,在能量消耗上降低了9.8%。     

虚拟机资源概率配置的云计算SEFFD算法

摘要：为增强虚拟机资源分配过程性能,有效解决云计算环境下虚拟资源分配的NP hard问题,利用模拟进化算法结合首次下降算法构建虚拟资源分配优化过程（SEFFD）。首先,构建全新的虚拟资源分配的评估方式,并结合模拟进化过程较强的算法寻优爬坡效果,采用迭代方式实现虚拟资源分配过程的个体选择、评估以及排序进化;其次,以模拟进化（SE）过程所获得资源分配结果为基础,结合首次下降（FFD）算法准则,实现物理主机及虚拟机资源的二次分配,从而获得资源分配效果和效率的同步提升;最后,利用CloundSim及Gridbus云计算仿真平台对算法性能进行对比测试,实验结果表明所提策略的内存利用率高于60%,处理器利用率大于55%,可有效减少所需物理主机数量,从而降低能耗。     

Comparative study between exact and metaheuristic approaches for virtual machine placement process as knapsack problem

In cloud computing, the virtual machine placement is a critical process which aims to identify the most appropriate physical machine to host the virtual machine. It has a significant impact on the performance, resource usage and energy consumption of the datacenters. In order to reduce the number of active physical machines in a datacenter, several virtual machine placement schemes have already been designed and proposed. This study investigates how do four different methods compare to each other in terms of accuracy and efficiency for solving the virtual machine placement as a knapsack problem. A new approach has been adopted which focuses on maximizing the use of a server’s central processing unit resource considering a certain capacity threshold. The compared methods are classified; two belong to the category of the exact methods, i.e., branch and bound and dynamic programming, while the other two represent the approximate approach, i.e., genetic algorithm and ant colony optimization algorithm. Experimental results show that the metaheuristic ant colony optimization algorithm outperforms the other three algorithms in terms of efficiency.

     

多智能体粒子群优化的SVR 模型预测控制

参数的优化选择对支持向量回归机的预测精度和泛化能力影响显著,鉴于此,提出一种多智能体粒子群算法(MAPSO)寻优其参数的方法,并建立MAPSO支持向量回归模型,用于非线性系统的模型预测控制,推导出最优控制率.采用该算法对非线性系统进行仿真,并与基于粒子群算法、基于遗传算法优化支持向量回归机的模型预测控制方法和RBF神经网络的预测控制方法进行比较,结果表明,所提出的算法具有更好的控制性能,可以有效应用于非线性系统控制中.     

基于混合群智能的节能虚拟机整合方法

数据中心的虚拟机（virtual machine,VM）整合技术是当今云计算领域的一个研究热点.要在保证服务质量（QoS）的前提下尽可能地降低云数据中心的服务器能耗,本质上是一个多目标优化的NP难问题.为了更好地解决该问题,面向异构服务器云环境提出了一种基于差分进化与粒子群优化的混合群智能节能虚拟机整合方法（HSI-VMC）.该方法包括基于峰值效能比的静态阈值超载服务器检测策略（PEBST）、基于迁移价值比的待迁移虚拟机选择策略（MRB）、目标服务器选择策略、混合离散化启发式差分进化粒子群优化虚拟机放置算法（HDH-DEPSO）以及基于负载均值的欠载服务器处理策略（AVG）.其中,PEBST,MRB,AVG策略的结合能够根据服务器的峰值效能比和CPU的负载均值检测出超载和欠载服务器,并选出合适的虚拟机进行迁移,降低负载波动引起的服务水平协议违约率（SLAV）和虚拟机迁移的次数;HDH-DEPSO算法结合DE和PSO的优点,能够搜索出更优的虚拟机放置方案,使服务器尽可能地保持在峰值效能比下运行,降低服务器的能耗开销.基于真实云环境数据集（PlanetLab/Mix/Gan）的一系列实验结果表明：HSI-VMC方法与当前主流的几种节能虚拟机整合方法相比,能够更好地兼顾多个QoS指标,并有效地降低云数据中心的服务器能耗开销.     

Online adaptive least squares support vector machine and its application in utility boiler combustion optimization systems

Boiler combustion optimization is a key measure to improve the energy efficiency and reduce pollutants emissions of power units. However, time-variability of boiler combustion systems and lack of adaptive regression models pose great challenges for the application of the boiler combustion optimization technique. A recent approach to address these issues is to use the least squares support vector machine (LS-SVM), a computationally attractive machine learning technique with rather legible training processes and topologic structures, to model boiler combustion systems. In this paper, we propose an adaptive algorithm for the LS-SVM model, namely adaptive least squares support vector machine (ALS-SVM), with the aim of developing an adaptive boiler combustion model. The fundamental mechanism of the proposed algorithm is firstly introduced, followed by a detailed discussion on key functional components of the algorithm, including online updating of model parameters. A case study using a time-varying nonlinear function is then provided for model validation purposes, where model results illustrate that adaptive LS-SVM models can fit variable characteristics accurately after being updated with the ALS-SVM method. Based on the introduction to the proposed algorithm and the case study, a discussion is then delivered on the potential of applying the proposed ALS-SVM method in a boiler combustion optimization system, and a real-life fossil fuel power plant is taken as an instance to demonstrate its feasibility. Results show that the proposed adaptive model with the ALS-SVM method is able to track the time-varying characteristics of a boiler combustion system.     

Power-saving mechanisms for energy efficient IEEE 802.16e/m

Efforts to reduce CO₂ emission regarded as a main reason of the green house effect are widely performed in Information and Communications Technology (ICT) industry. In particular, as fast growing mobile communications services consume more energy, there are wide efforts to increase energy efficiency in the area of Mobile Station (MS), radio Base Stations (BS), network controllers, and core networks. User's concern, however, is more focused on optimization of energy efficiency in MS with limited battery capacity, because MS consumes much energy for wide broadband data services in data-centric communications services with 4G technology rather than legacy voice-centric communications services.The key idea of power saving mechanism (PSM) in MS is to operate sleep-mode that the MS turns down main elements when there is no data to receive/transmit in order to save battery power. With legacy voice-centric communication services, traffic pattern is rather simple and well-known so that the sleep-mode of PSM is well operated. However, in 4G technology for various data-centric services power saving mechanism should be adaptive to changing traffic condition in order to achieve optimal energy efficiency. Thus, holistic perspective for power saving techniques is needed in consideration of characteristics of services and QoS constraints, multiple applications support, remained battery power, handover process, Multicast Broadcast Service (MBS) support, and so on.This paper surveys various power saving mechanisms proposed for IEEE 802.16e/m. We first present the basic operating mechanism of PSM and research issues for performance enhancement. Based on their limitations and potentials, we then review several proposals of PSM for IEEE 802.16m, an evolutional technology of IEEE 802.16e. It will be interesting for readers to observe that once PSM was standardized in IEEE 802.16e, many new ideas have been proposed to improve the performance of the original PSM, and some of them are survived and adopted to new standard technique in the advanced IEEE 802.16m.     

Energy-aware Virtual Machine Migration for Cloud Computing - A Firefly Optimization Approach

Energy efficiency has grown into a latest exploration area of virtualized cloud computing paradigm. The increase in the number and the size of the cloud data centers has propagated the need for energy efficiency. An extensively practiced technology in cloud computing is live virtual machine migration and is thus focused in this work to save energy. This paper proposes an energy-aware virtual machine migration technique for cloud computing, which is based on the Firefly algorithm. The proposed technique migrates the maximally loaded virtual machine to the least loaded active node while maintaining the performance and energy efficiency of the data centers. The efficacy of the proposed technique is exhibited by comparing it with other techniques using the CloudSim simulator. An enhancement in the average energy consumption of about 44.39 % has been attained by reducing an average of 72.34 % of migrations and saving 34.36 % of hosts, thereby, making the data center more energy-aware.     

监督学习模型指导的函数级编译优化参数选择方法研究

基于机器学习的迭代编译方法可以在对新程序进行迭代编译时,有效预测新程序的最佳优化参数组合。现有方法在模型训练过程中存在优化参数组合搜索效率较低、程序特征表示不恰当、预测精度不高的问题。因此,基于机器学习的迭代编译方法是当前迭代编译领域内的一个研究热点,其研究挑战在于学习算法选择、优化参数搜索以及程序特征表示等问题。基于监督学习技术,提出了一种程序优化参数预测方法。该方法首先通过约束多目标粒子群算法对优化参数空间进行搜索,找到样本函数的最佳优化参数;然后,通过动静结合的程序特征表示技术,对函数特征进行抽取;最后,通过由函数特征和优化参数形成的样本构建监督学习模型,对新程序的优化参数进行预测。分别采用k近邻法和softmax回归建立统计模型,实验结果表明,新方法在NPB测试集和大型科学计算程序上实现了较好的预测性能。     

Autonomic cloud resource provisioning and scheduling using meta-heuristic algorithm

We investigate that resource provisioning and scheduling is a prominent problem due to heterogeneity as well as dispersion of cloud resources. Cloud service providers are building more and more datacenters due to demand of high computational power which is a serious threat to environment in terms of energy requirement. To overcome these issues, we need an efficient meta-heuristic technique that allocates applications among the virtual machines fairly and optimizes the quality of services (QoS) parameters to meet the end user objectives. Binary particle swarm optimization (BPSO) is used to solve real-world discrete optimization problems but simple BPSO does not provide optimal solution due to improper behavior of transfer function. To overcome this problem, we have modified transfer function of binary PSO that provides exploration and exploitation capability in better way and optimize various QoS parameters such as makespan time, energy consumption, and execution cost. The computational results demonstrate that modified transfer function-based BPSO algorithm is more efficient and outperform in comparison with other baseline algorithm over various synthetic datasets.

     

基于BOA-ELM的混凝土抗压强度预测研究

为控制控制混凝土生产成本,在混凝土拌和期限制抗压强度不足的缺陷构建产出,可以有效降低原料的浪费,是节能降耗的关键方法之一。针对混凝土抗压强度的传统测量方法严重滞后的问题,提出了基于贝叶斯优化极限学习机(BOA-ELM)的混凝土抗压强度预测方法。首先,分析了混凝土拌和过程中对抗压强度预测值实时获得的需求。以各物料的用量为分析基础,28天标准养护后混凝土抗压强度值为预测目标,设计了基于极限学习机的强度预测模型。其次,为进一步提高模型的稳定性以及准确行,提出基于贝叶斯优化的极限学习机模型,根据模型超参数的分布特征,以高斯过程作为超参的先验分布,预测误差最小化作为目标,寻找最优的模型超参。最后,在实际施工产生的C50标号混凝土数据集上测试文中模型,并对比分析了其他预测模型和寻优算法。结果表明,结合了贝叶斯优化的极限学习机预测模型相较于经典算法具有更高的预测准确性和模型训练的高效性。     

Model-driven auto-scaling of green cloud computing infrastructure

Cloud computing can reduce power consumption by using virtualized computational resources to provision an application’s computational resources on demand. Auto-scaling is an important cloud computing technique that dynamically allocates computational resources to applications to match their current loads precisely, thereby removing resources that would otherwise remain idle and waste power. This paper presents a model-driven engineering approach to optimizing the configuration, energy consumption, and operating cost of cloud auto-scaling infrastructure to create greener computing environments that reduce emissions resulting from superfluous idle resources. The paper provides four contributions to the study of model-driven configuration of cloud auto-scaling infrastructure by (1) explaining how virtual machine configurations can be captured in feature models, (2) describing how these models can be transformed into constraint satisfaction problems (CSPs) for configuration and energy consumption optimization, (3) showing how optimal auto-scaling configurations can be derived from these CSPs with a constraint solver, and (4) presenting a case study showing the energy consumption/cost reduction produced by this model-driven approach.     

Heterogeneity and thermal aware adaptive heuristics for energy efficient consolidation of virtual machines in infrastructure clouds

Holistic datacenter energy minimization operation should consider interactions between computing and cooling source specific usage patterns. Decisions like workload type, server configuration, load, utilization etc., contributes to power consumption and influences datacenter's thermal profile and impacts the energy required to control temperature within operational thresholds. In this paper, we present an adaptive virtual machine placement and consolidation approach to improve energy efficiency of a cloud datacenter; accounting for server heterogeneity, server processor low-power SLEEP state, state transition latency and integrated thermal controls to maintain datacenter within operational temperature. Our proposed heuristic approach reduces energy consumption with acceptable level of performance.