Empirical prediction models for adaptive resource provisioning in the cloud

Cloud computing allows dynamic resource scaling for enterprise online transaction systems, one of the key characteristics that differentiates the cloud from the traditional computing paradigm. However, initializing a new virtual instance in a cloud is not instantaneous; cloud hosting platforms introduce several minutes delay in the hardware resource allocation. In this paper, we develop prediction-based resource measurement and provisioning strategies using Neural Network and Linear Regression to satisfy upcoming resource demands.Experimental results demonstrate that the proposed technique offers more adaptive resource management for applications hosted in the cloud environment, an important mechanism to achieve on-demand resource allocation in the cloud.     

基于粒子群优化算法的云计算资源调度策略研究

针对移动互联网用户具有移动性的特点,采用移动云的概念来分担计算任务.粒子群算法能够有效地寻找移动互联网的计算资源,从而提高云计算中各个计算资源的分配速度和计算效率.采用粒子群算法,兼顾用户的服务质量,高效调度异构网络中的计算资源,完成具有大计算量的科学计算的云计算资源调度方案.仿真结果表明,所提策略能够提高资源调度的速度,并且能提高云计算的效率.     

MidHDC: Advanced Topics on Middleware Services for Heterogeneous Distributed Computing. Part 1

Middleware solutions for Heterogeneous Distributes System aim to respond to high requirements of large scale distributed applications related to performance, flexibility, extensibility, portability, availability, reliability, safety, security, trust, and scalability, in the context of high number of users, and large geographic distribution of heterogeneous hardware and software resources. The solutions used in the design, implementation, and deployment of systems with such capabilities are based on monitoring, scheduling, optimization, sharing, balancing, discovery, and synchronization methods and techniques that are continuously improved.This special issue presents advances in virtual machine management solutions in Clouds, object storage platforms, HPC heterogeneous platforms, middleware for Android systems and reliability and performances in large scale distributed applications.     

混合云中的一个高效协调器

云计算提供了4种部署模型:公有云、私有云、社区云和混合云.通常,一个私有云中可用的资源是有限的,因此云用户不得不从公有云租用资源.这意味着云用户将会产生额外的费用.越来越多的企业选择混合云来部署它们的应用.在混合云中,为了实现用户的利益最大化,必须满足使用资源的费用最小化和用户的QoS,为此为混合云用户提供了一个既能最小化资源费用又能保证满足QoS的资源分配方法.实验结果表明,该算法在保持低操作成本的同时还满足了用户的QoS.     

云计算技术综述

云计算是基于互联网的一种新型的服务架构,本文对于云计算的定义、技术发展、分类进行了描述,分析了现有云计算发展中存在的问题,最后针对云计算的发展进行了展望。     

Cloudlet-based Efficient Data Collection in Wireless Body Area Networks

Wireless Body Area Networks (WBANs) have developed as an effective solution for a wide range of healthcare, military and sports applications. Most of the proposed works studied efficient data collection from individual and traditional WBANs. Cloud computing is a new computing model that is continuously evolving and spreading. This paper presents a novel cloudlet-based efficient data collection system in WBANs. The goal is to have a large scale of monitored data of WBANs to be available at the end user or to the service provider in reliable manner. A prototype of WBANs, including Virtual Machine (VM) and Virtualized Cloudlet (VC) has been proposed for simulation characterizing efficient data collection in WBANs. Using the prototype system, we provide a scalable storage and processing infrastructure for large scale WBANs system. This infrastructure will be efficiently able to handle the large size of data generated by the WBANs system, by storing these data and performing analysis operations on it. The proposed model is fully supporting for WBANs system mobility using cost effective communication technologies of WiFi and cellular which are supported by WBANs and VC systems. This is in contrast of many of available mHealth solutions that is limited for high cost communication technology, such as 3G and LTE. Performance of the proposed prototype is evaluated via an extended version of CloudSim simulator. It is shown that the average power consumption and delay of the collected data is tremendously decreased by increasing the number of VMs and VCs.     

Policy based resource allocation in IaaS cloud

In present scenario, most of the Infrastructure as a Service (IaaS) clouds use simple resource allocation policies like immediate and best effort. Immediate allocation policy allocates the resources if available, otherwise the request is rejected. Best-effort policy also allocates the requested resources if available otherwise the request is placed in a FIFO queue. It is not possible for a cloud provider to satisfy all the requests due to finite resources at a time. Haizea is a resource lease manager that tries to address these issues by introducing complex resource allocation policies. Haizea uses resource leases as resource allocation abstraction and implements these leases by allocating Virtual Machines (VMs). Haizea supports four kinds of resource allocation policies: immediate, best effort, advanced reservation and deadline sensitive. This work provides a better way to support deadline sensitive leases in Haizea while minimizing the total number of leases rejected by it. Proposed dynamic planning based scheduling algorithm is implemented in Haizea that can admit new leases and prepare the schedule whenever a new lease can be accommodated. Experiments results show that it maximizes resource utilization and acceptance of leases compared to the existing algorithm of Haizea.     

一种基于云存储的移动终端网络存储设计

随着移动互联网迅猛发展,移动终端的硬件资源如计算能力、存储能力及电池续航能力等等,已严重制约了移动互联网的发展。针对移动终端存储能力不足问题,结合目前集群技术及云存储技术,考虑到移动终端文件主要以小文件为主,提出一种基于云存储的移动终端网络存储模型,其体型结构包括基础设施层、基础管理层、应用接口层和访问层四部分,把信息的存储和处理移植到云上,从而为解决移动终端资源受限提供一种可行方案。     

面向智能电网的云计算技术研究

对面向智能电网的云计算技术进行了研究。首先,引入了云计算的基本概念,分析了它的关键特征。其次,将云计算和智能电网技术进行了融合,提出了智能云的概念。随后,深入研究了智能云的构建、资源管理和安全策略问题。最后,给出了结论和未来的研究工作。     

Mobile contact synchronous with cloud server

Mobile industry promotes new products every recent year. It is reported that consumers in high-income countries typically replace their mobile phones at intervals of between 12 and 18 months. How to transfer data from one mobile to another and how to share data between different mobile apps are taken into consideration. We build a cloud service to combine contacts from different mobiles and synchronize contacts in different mobiles. Some algorithms and data structures are designed to meet the needs of data combination and synchronization. The result shows that our method can provide more efficient result than other solutions.     

A field trial using Artificial Neural Networks to predict psychiatric in-patient Length-of-stay

Demands for health care reform will increase service utilization, much of which will fall on a system of expanded primary care providers, many of whom will not be specialists in psychiatry. These providers will need tools to augment their decision-making process. In this paper, we explore the use of Artificial Neural Networks (ANNs) in three different field sites to predict inpatient psychiatric Length-Of-Stay (LOS). This study describes the development and implementation of a runtime system in three different psychiatric facilities. Data was collected at these respective sites using the runtime system, and then this data was used to retrain the networks to determine if site-specific data would improve accuracy of prediction of LOS. The results indicate that ANNs trained with state hospital data could accurately predict LOS in two different community hospital psychiatric units. When the respective ANNs were retrained with approximately 10% new data from these specific hospitals, rates of improvement ranged from 3% to 15%. Our findings demonstrate that an ANN can adapt to different treatment settings and, when retrained, significantly improve prediction of LOS. Prediction rates by the ANN after retraining are comparable to results of a clinical team.     

基于Bagging的概率神经网络集成分类算法

目前的神经网络较多集中在以BP算法为基础的BP神经网络上。针对BP神经网络的不足,在分析研究概率神经网络和机器学习的基础上,结合集成学习的思想,提出了基于Bagging的概率神经网络集成分类算法。理论分析和实验结果都表明,提出的算法能够有效地降低分类误差,提高分类准确率,具有较好的泛化能力以及较快的执行速度,能够取得比传统的BP神经网络分类方法更好和更稳定的分类结果。