Recently, Cloud computing, as one of the hottest words in IT world, has drawn great attention. Many IT companies such as IBM, Google, Amazon, Microsoft, Yahoo and others vigorously develop cloud computing systems and ...
详细信息
Many recent applications involve processing and analyzing uncertain data. Recently, several research efforts have addressed answering skyline queries efficiently on massive uncertain datasets. However, the research la...
详细信息
Many recent applications involve processing and analyzing uncertain data. Recently, several research efforts have addressed answering skyline queries efficiently on massive uncertain datasets. However, the research lacks methods to compute these queries on uncertain data, where each dimension of the uncertain object is represented as an interval or an exact value. In this paper, we extensively study the problem of skyline query on these interval based uncertain objects, which has never been studied before. We first model the problem of querying the skylines on interval datasets. Typically, we address two efficient algorithms with I/O optimal for the conventional interval skyline queries and constrained interval skyline queries, respectively. Extensive experiments demonstrate the efficiency of all our proposed algorithms.
Botnets are threatening the Internet heavily, and more and more botnets are utilizing the P2P technology to build their C&C (Command and Control) mechanisms. Some research have been made to compare the resilience ...
详细信息
Botnets are threatening the Internet heavily, and more and more botnets are utilizing the P2P technology to build their C&C (Command and Control) mechanisms. Some research have been made to compare the resilience of structured P2P botnets and unstructured ones, against elimination of nodes, but the problem that which eliminating strategy is the best is rarely studied. In this paper, we proposed a new metric called the half point, to measure the effectiveness of different strategies. We also selected seven different eliminating strategies and compared them. Through extensive simulations, we find that RBC is the best eliminating strategy. Further analysis shows that for the strategy RBC, the average degree of nodes in the botnet have the most significant influence. The bigger the average degree is, the bigger the half point of RBC is, which implies that node eliminating may not be a reasonable choice for mitigating botnets with big average degree. Results of this paper can provide guidance for restraining structured P2P botnets.
As a complex, flexible and effective platform for network attacking, the botnet spreads widely in the Internet. Botnets can provide the botmasters with the ability to launch large-scale malicious activities such as sp...
详细信息
As a complex, flexible and effective platform for network attacking, the botnet spreads widely in the Internet. Botnets can provide the botmasters with the ability to launch large-scale malicious activities such as spamming and DDoS (distributed Denial of Service) attacks. Botnets are continuously bringing more and more severe threats, so that the study on botnets has already become one of the focuses in the field of network security. However, in recent years, some new developments of botnets are challenging the existing understanding on botnets. In this paper, according to the new conditions of botnets and the researches in existence, a definition of botnet is proposed based on the works of other researchers, taxonomies of botnets are introduced respectively from the views of network structure, dependency and delivery pattern of C&C (Command and Control) information. Then the techniques on detecting, measuring and restraining botnets are analyzed systematically. In the end, we give the evolution trends of botnets and the future research trends in this area.
Context situation, which means a snapshot of the status of the real world, is formed by integrating a large amount of contexts collected from various resources. How to get the context situation and use the situation t...
详细信息
Context situation, which means a snapshot of the status of the real world, is formed by integrating a large amount of contexts collected from various resources. How to get the context situation and use the situation to provide better services is a challenging issue. In this paper, we focused on this challenge on the basis of the mobile cloud computing architecture. An abstract model is proposed in this paper to uniformly collect the context and send them to cloud. A rule-based large-scale context aggregation algorithm is also proposed which utilizes the MapReduce computing paradigm. Finally, a large-scale context management framework based on the abstract model and the context aggregation algorithm is proposed, and a real-time traffic demo is implemented to verify the validity of the framework.
Message processing and data visualization are key technologies in a V2X system, influencing both real and perceived performance, and usability of a system. V2X safety applications require frequent exchange of position...
详细信息
Message processing and data visualization are key technologies in a V2X system, influencing both real and perceived performance, and usability of a system. V2X safety applications require frequent exchange of position information by means of so called Cooperative Awareness Messages (CAMs). These messages are generated, encoded and sent by all vehicles. Corresponding actions have to be executed on the receiving vehicles. The in-vehicle V2X system can be divided into several components to accomplish these tasks. Our approach is based on a "two-component" system, consisting of a vehicle-integrated V2X communication unit (onboard unit, OBU) and a personal portable device (PPD), such as a smartphone or tablet PC. Subject of this work is the investigation how to distribute the workload and functionality between the two components. Our goal is to find a flexible solution that maximizes the overall performance and reliability of the system. We investigate and compare several message processing approaches and try to combine the strengths of both components. To ensure comparability, tests are carried out on the same hardware platform. As a result, we present our final setup that can handle an up to 60 times higher message rate compared to other investigated solutions.
Spectrum trading is the promising method to improve spectrum efficiency from the perspective of economics. In this paper we propose a queueing-theory based spectrum trading model, where the primary user plays the serv...
详细信息
Spectrum trading is the promising method to improve spectrum efficiency from the perspective of economics. In this paper we propose a queueing-theory based spectrum trading model, where the primary user plays the server role providing spectrum to the secondary user who acts as the customer. The most significant challenge is how to optimize the spectrum trading model considering the server uncertainty which includes service state, service time, service area, service content and service price. We design a STACP queueing model according to the server attributes, so that the secondary user can choose the right queue quickly and reasonably according to its demand. Moreover, we further analyze the optimizing strategies for STACP model which can maximize the profit of the primary user and minimize the service cost of the secondary user. The simulation results demonstrate the analysis results.
A common way to construct a fault model is injecting the fault into the system and observing the subsequent symptoms, e. g. event logs. However, fault features would vary during the propagation period, and present dif...
详细信息
A common way to construct a fault model is injecting the fault into the system and observing the subsequent symptoms, e. g. event logs. However, fault features would vary during the propagation period, and present different symptoms at different stage of the fault propagation process. The exiting detection window based feature extraction methods can only identify the early symptoms of a fault, but fail to detect the latter symptoms and cause false alarms. To solve the problem, we present a fault feature extraction method, called Companion State Tracer (CSTracer), which consists of 3 integrated steps: (1) pre-process logs to remove the unrelated logs;(2) construct a general identifier for the early symptoms of a fault;(3) construct a finite state machine model for the fault to trace the latter symptoms. CSTracer can persistently monitor a fault after the fault has been identified. We have justified the effectiveness of CSTracer in an enterprise cloud system. Compared with the existing, the results show that CSTracer has a better detection accuracy.
Private BitTorrent community (PT), as known as "BitTorrent Darknet", has become a popular research spot in recent years. PTs can provide ultra-high download performance which is much better than public BitTo...
详细信息
Private BitTorrent community (PT), as known as "BitTorrent Darknet", has become a popular research spot in recent years. PTs can provide ultra-high download performance which is much better than public BitTorrent communities. The Sharing Ratio Enhancement (SRE) mechanism is the key to PTs' success. However, it also brings negative side effects to the registered users in PTs. In this paper, we crawl and analyze all of user profiles from three influential PTs which provide very detailed information. We show that the sharing ratio of members cannot represent their upload contribution in terms of upload time and amount. Members are forced to seed for a long time to maintain adequate sharing ratios to survive in the community. SRE mechanism's nature drawbacks induce inequity. Based on these measurements, we propose a unified two-track payment system to pay peers based on their contribution, which is an alternative mechanism to SRE. We consider the payment with inflation and transit process. Our systems can provide a fair and consistent environment, which is helpful to unify and to build sustainable development of private BitTorrent communities.
The availability of computers and communication networks allows us to gather and analyse data on a far larger scale than previously. At present, it is believed that statistics is a suitable method to analyse networks ...
详细信息
The availability of computers and communication networks allows us to gather and analyse data on a far larger scale than previously. At present, it is believed that statistics is a suitable method to analyse networks with millions, or more, of vertices. The MATLAB language, with its mass of statistical functions, is a good choice to rapidly realize an algorithm prototype of complex networks. The performance of the MATLAB codes can be further improved by using graphic processor units （GPU）. This paper presents the strategies and performance of the GPU implementation of a complex networks package, and the Jacket toolbox of MATLAB is used. Compared with some commercially available CPU implementations, GPU can achieve a speedup of, on average, 11.3x. The experimental result proves that the GPU platform combined with the MATLAB language is a good combination for complex network research.
暂无评论