移动边缘计算卸载技术综述

移动边缘计算(Mobile Edge Computing,MEC)将云服务器的计算资源扩展到更靠近用户一侧的网络边缘,使得用户可以将任务卸载到边缘服务器,从而克服原先云计算中将任务卸载到云服务器所带来的高时延问题。首先介绍了移动边缘计算的基本概念、基本框架和应用场景,然后围绕卸载决策、联合资源分配的卸载决策分别从单MEC服务器和多MEC服务器两种场景总结了任务卸载技术的研究现状,最后结合当前MEC卸载技术中存在的不足展望了未来MEC卸载技术的研究。     

Privacy-Preserving Data Communication Through Secure Multi-Party Computation in Healthcare Sensor Cloud

In recent years, wireless medical sensor networks meet the web to enable exciting healthcare applications that require data communication over the Internet. Often these applications suffer from data disclosure due to malicious users’ activities. To prevent such data disclosure in the healthcare systems, many public key cryptographic techniques have been used. However, most of them are too expensive to implement in the web-enabled wireless medical sensor networks. In 2013, Xun et al. introduced a lightweight encryption algorithm to protect communication between the sensor node and the data servers. Their scheme is based on the Sharemind framework. However, Sharemind framework has a limitation on the number of data storage servers (ie., three servers only). In addition, Xun et al’s scheme does not support privacy-preserving patient data analysis for distributed databases of different hospitals. In this paper, we introduce a new practical approach to prevent data disclosure from inside attack. Our new proposal is based on FairplayMP framework which enables programmers who are not experts in the theory of secure computation to implement such protocols. In addition, it support any number of n participants and is suitable for distributed environments. Moreover, in our new scheme, each sensor node needs only one secret key stored in advance to communicate with n different data servers, whereas three secret keys are embedded in advance into each sensor in order to communicate with three data servers in Xun et al’s scheme.     

网络负载均衡的控制理论及实践战略

网络负载均衡技术NLB（Network Load Balancing）采用完全分配算法来为集群中的服务器分配进入的访问流量,当集群中的某台服务器失效时,NLB会自动转发数据到其他可用的服务器上。负载均衡由多台服务器以对称的方式组成一个服务器集合,每台服务器都具有等价的地位,都可以单独对外提供服务而无须其他服务器的辅助。通过某种负载分担技术,将外部发送来的请求均匀分配到对称结构中的某一台服务器上,而接收到请求的服务器独立地回应客户的请求。均衡负载能够平均分配客户请求到服务器列阵,籍此提供快速获取重要数据,解决大量并发访问服务问题。     

基于分布式文件系统的图片存储服务的研究

详细分析了分布式文件系统的三个基本特点,分别为节点服务器的分类,数据分布和节点服务器间的通信。在这个前提下,提出了基于分布式文件系统架构实现图片存储服务的方法,并详细说明了该方法的Java实现。此方法以Hadoop为基础,利用HDFS（Hadoop Distributed File System）的特点,充分运用现有低端硬件设备的处理能力,简化了分布式图片存储服务系统的设计,并提高了系统的性能和可靠性。     

基于QA-NIZK证明系统的高效简短可验证洗牌方案

电子投票中为保护投票者的隐私,要由一系列混合服务器对选票进行洗牌操作,为保证洗牌操作的诚实性,需要可验证洗牌方案。现有简短可验证洗牌方案的证明大小要依赖于混合服务器的数量和投票者的数量,效率较低。基于近来的一个高效的QA-NIZK证明系统构建了一个高效的简短可验证洗牌方案,不管有多少混合器和投票者其证明大小都是O(1),即常量大小。具有其独立的意义是在构建中指出原QA-NIZK证明系统是可变的。     

CExp: secure and verifiable outsourcing of composite modular exponentiation with single untrusted server

Outsourcing computing allows users with resource-constrained devices to outsource their complex computation workloads to cloud servers that may not be honest. In this paper, we propose a new algorithm for securing the outsourcing of composite modular exponentiation, which is one of the most complex computing tasks in discrete-log based cryptographic protocols. Unlike algorithms based on two untrusted servers, we outsource modular exponentiation operation to only a single server, which eliminates the potential for a collusion attack when using two servers. Moreover, our proposed algorithm can hide the base and exponent of the outsourced data, which prevents the exposure of sensitive information to cloud servers. In addition, compared with the state-of-the-art algorithms, our scheme has remarkably better checkability. The user could detect any misbehavior with a probability of one if the server returns a fault result.     

基于P2P技术的AKA认证机制研究

移动互联网中基于AKA认证的现有架构容易导致单点失效,服务器遭受恶意注册攻击,而且3GPP—AKA协议本身存在安全缺陷,文章对原有认证模型进行改进,提出基于P2P架构的认证服务器部署方案,同时改进AKA的认证流程,最后对本方案的安全性进行分析。     

基于XMPP的智能服务器管理系统

With the increasing importance of cloud services worldwide, the cloud infrastructure and platform management has become critical for cloud service providers. In this paper, a novel architecture of intelligent server management framework is proposed. In this framework, the communication layer is based on the Extensible Messaging and Presence Protocol (XMPP), which was developed for instant messaging and has been proven to be highly mature and suitable for mobile and large scalable deployment due to its extensi-bility and efficiency. The proposed architec-ture can simplify server management and increase flexibility and scalability when managing hundreds of thousands of servers in the cloud era.     

视频失真优化的分布式视频点播服务系统及性能分析

本文提出一种用于分布式视频点播服务系统的速率分配算法和实现框架。在考虑负载均衡与满足服务器带宽限制的前提下,速率分配能将以失真为度量的全局视频质量最优化。确定各服务结点的输出码率被建模成一个最优化问题：优化目标是最小化多个视频总失真,限制条件为最低可接受视频质量、服务器带宽限制以及发送速率对客户端TCP流量的友好性。根据优化算法的计算结果,视频节目使用可变码率编码,由多个视频分发服务器同时向客户端传输;同时服务器检测与客户端之间端到端链路的时变特性和估计网络拥塞情况,使优化速率分配结果适应网络状态的变化。本方案应用跨层设计的思想,将应用层视频质量建模为网络层参数的函数,当网络状态波动时,动态调整编码码率和发送速率以适应带宽变化,提前避免链路拥塞,降低接收端解码器丢包率,从而使总体视频质量得到提升。     

P2P技术应用于分布式数据库的研究探讨

文中论述了如下概念：基于P2P网络上保证在网络出现故障时,“顺利读取数据。基于数据安全,提出数据冗余的概念,包括在本地设置多个备份数据库服务器,在主服务器故障的时候,可以使用备份数据。还有在不同的地方,设置服务器。提出分布式系统后,就出现分布式数据库,这样只能保证在服务器端的数据库的数据完整性。但是,对于客户机是没有保证的,一旦与主机的连接出现问题的时,分布式数据库就发挥不出优势。现在,P2P的技术加上的分布式数据库的技术,就可以解决分布式数据库的网络与数据库的问题。     

Intelligent network control middleware platform

As multivendor, multitechnology networks are deployed in a carrier's network, a network operator must integrate these networks to have a unified control platform to lower operational costs and deliver customer-specified QoS. An intelligent network control middleware framework for multivendor networks is described in this article. The architectural framework is designed to control and manage next generation network elements as well as legacy telecom networks. The layers within the framework include mediation, control plane, network resource management, and application programmable interfaces. An independent, distributed control plane aims at service interoperability and network scalability. An experimental study on circuit provisioning using the proposed middleware framework is conducted on Sun Lab servers. The middleware performance results are reported. Experimentation architecture and metrics can be extended to a performance benchmark upon which the control plane products can be evaluated.     

A comparison of load balancing techniques for scalable Web servers

Scalable Web servers can be built using a network of workstations where server capacity can be extended by adding new workstations as the workload increases. The topic of our article is a comparison of different method to do load-balancing of HTTP traffic for scalable Web servers. We present a classification framework the different load-balancing methods and compare their performance. In addition, we evaluate in detail one class of methods using a prototype implementation with instruction-level analysis of processing overhead. The comparison is based on a trace driven simulation of traces from a large ISP (Internet Service Provider) in Norway. The simulation model is used to analyze different load-balancing schemes based on redirection of request in the network and redirection in the mapping between a canonical name (CNAME) and IP address. The latter is vulnerable to spatial and temporal locality, although for the set of traces used, the impact of locality is limited. The best performance is obtained with redirection in the network     

基于地理信息系统的城市供热信息管理系统的设计与实现

结合设计和开发,介绍了基于地理信息系统的城市供热信息管理系统的整体结构、整体功能、硬件结构。将实时数据、空间拓扑数据、设备属性数据以及对这些数据操作的函数封装为空间实体类,建立了空间实体对象。采用中间件技术,构建了数据图形中间平台,作为整个系统的枢纽将数据、图形与GIS平台,将服务器、工作站有机的联系起来,并对其进行合理的调度。实际运行表明,系统能为供热企业降低成本,提高经济效益。     

Verifiable Multi-Party Universal Blind Quantum Computing in Distributed Networks

Blind quantum computing (BQC) ensures that a classical client could delegate complex computing tasks to a remote quantum server safely.In order to detect the dishonest behavior of the participants,we present a verifiable multi-party universal BQC protocol in distributed networks.By using the stabilizer formalism,we propose an honesty check method to test the correctness of the graph states generated by the servers.The honesty of both the clients and the servers can be judged fairly with the help of the arbitrator.Moreover,a load balancer is introduced to control the possible breakdown of servers in the network.No-signaling principle ensures the unconditional security of the protocol.Through the use of universal resource states,our protocol can be applied in more multi-party verifiable universal BQC protocols.The failure management and workload balancing of the protocol also provide a promising prospect for the future BQC network.     

Who owns your e-mail?

Issues of privacy and security are central to the effective use of E-mail, particularly in institutional settings. When this service is used as a component of education within a larger institutional framework, additional issues arise involving ethics of information monitoring, and the storage of personal materials on university-owned mainframes, minicomputers, or network servers. In this article the author examines recent findings that could influence the use of E-mail on campuses. National privacy legislation is discussed, as is the inviolability of student records. The position is taken that more effective safeguards are necessary, and that the current steps are inadequate for the protection of students' rights.     

基于openssl的CA认证及SSL加密通信

CA认证技术和SLL加密通信被认为是抵抗网络攻击的最有效手段。为了保证服务器之间通信的安全,采用基于openssl的CA认证中心生成CA证书和SSL加密通信的的方法,建立了一种服务器间安全通信的模式,使用C＋＋和Java模拟实现了该方案,结果证明了该方案的安全可靠性。最后还指出该方案的优缺点和改进的方法。     

A Solution of Grid Computing Flow Using MDA Methodology

1IntroductionWith rapid advances in network technology and dis-tributed computing,grid computing becomes the focusand preceding field to be studied in current world.Atpresent the researches of grid computing mainly containas follows[1]:Research the bottom…     

Client-server-based mobile robot control

A control architecture for an autonomous mobile robot usually consists of two components: (1) intelligent control software and (2) an operating system for resource access. From the point of view of a computer scientist, it is desirable to achieve a certain level abstraction from the resource (be it sensor or effector). Here, this is achieved by introducing a client-server framework for realizing abstract resource access and intelligent control. Hardware details are hidden in a middleware layer, which is inserted in between operating system and applications. In this paper, we present the most important features of our client-server approach. The servers decouple hardware and software dependencies. Communication is realized through the use of classes, offering a wide variety of client-server interaction. Event-driven servers and clients lead to quick responses in dynamic environments. Our approach gives reusability, portability, testability, and maintainability through data abstraction. It was successfully applied in our experimental platform ARS     

Topic allocation method on edge servers for latency-sensitive notification service

The importance of real-time notification has been growing for social services and Intelligent Transporting System (ITS). As an advanced version of Pub/Sub systems, publish-process-subscribe systems, where published messages are spooled and processed on edge servers, have been proposed to achieve data-driven intelligent notifications. In this paper, we present a system that allows a topic to be managed on multiple edge servers so that messages are processed near the publishers, even when publishers spread over a wide area. Duplicating messages on geographically distributed servers could enable immediate notification to neighboring subscribers. However, the duplicated message spool may cause exhaustion of resources. We prepare a formal model of our publish-process-subscribe system and formulate the topic allocation as an optimization problem under the resource constraints of edge servers. As the optimization problem is NP-hard, we propose heuristics leveraging the locality and the pub/sub relationships observed between clients to use the edge server resources efficiently. Our performance evaluation shows that our method reduces the delay to deliver notifications and the effectiveness of the strategy exploiting the relationships between clients.     

MEC系统中基于多智能体深度增强学习的协作式任务卸载和资源分配

移动边缘计算(MEC)通过将计算任务卸载到MEC服务器上,在缓解智能移动设备计算负载的同时,可以降低服务时延。然而目前在MEC系统中,关于任务卸载和资源分配仍然存在以下问题：1)边缘节点间缺乏协作;2)计算任务到达与实际环境中动态变化的特征不匹配;3)协作式任务卸载和资源分配动态联合优化问题。为解决上述问题,文章在协作式MEC架构的基础上,提出了一种基于多智能体的深度确定性策略梯度算法(MADDPG)的任务卸载和资源分配算法,最小化系统中所有用户的长期平均成本。仿真结果表明,该算法可以有效降低系统的时延及能耗。