The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Due to the raising importance of cloud computing and infrastructure as a service (IaaS), the first markets for the exchange of computational power over the internet are being implemented. As of today, bandwidth constraints are not explicitly embedded in these market mechanisms. In this paper, the problem of optimal allocation of the computing power and of the corresponding data flows, according to...
In decentralized systems, nodes often need to coordinate to access shared resources in a fair manner. One approach to perform such arbitration is to rely on auction mechanisms. Although there is an extensive literature that studies auctions, most of these works assume the existence of a central, trusted auctioneer. Unfortunately, in fully decentralized systems, where the nodes that need to cooperate...
In this work, an end-to-end TCP throughput control mechanism based on TCP throughput model is proposed to fulfill the users' QoS requirements. To control end-to-end TCP throughput at single point, it is necessary to enforce a TCP connection operating at a target rate. Therefore, a measurement mechanism is proposed to derive the values of the two control parameters - packet drop rate and round trip...
DVB-RCS2 is conceived to improve satellite channel flexibility in supporting a vast gamut of applications. In particular, a Bandwidth on Demand (BoD) MAC profile is allowed for bulk transfers typical of Internet applications. As assessed for previous DVB-RCS systems, TCP performance is seriously impaired in this context mainly because of large latency, further inflated by BoD access delay. In addition,...
In recent years, online social networks (OSN) have become very popular. These types of networks have been useful to find former classmates or to improve our interaction with friends. Currently, a huge amount of information is generated and consumed by millions of people from these types of networks. Most popular online social networks are based on centralized servers, which are responsible for the...
This Paper presents a telco's perspectives and experiences to design and implement open and flexible architecture for Transport SDN (T-SDN). We believe that this could be realized by adopting open source based SDN controllers because they already have widely accepted and referenced architecture with a rich ecosystem. Moreover, we could have further benefits from open source such as reducing time to...
This paper presents a hop-by-hop congestion control for highspeed networks. The control policy relies on the data exchange between adjacent nodes of the network (nearest-neighbour interaction). The novelty of this paper consists in the extensive use of Internal Model Control (IMC) to set the rates of the traffic flows. As a result, the proposed congestion control provides upper-bounds of the queue...
We proposed an algorithm for gateway and router to prevent DDoS attacks. The algorithm combines two simple congestion control methods. Simulation results show that our algorithm efficiently increases the throughput of normal flows under DDoS attacks comparing to common Drop Tail algorithm.
As an efficient parallel computing system based on MapReduce model, Hadoop is widely used for large-scale data analysis such as data mining, machine learning and scientific simulation. However, there are still some performance problems in MapReduce, especially the situation in the shuffle phase. In order to solve these problems, in this paper, a lightweight individual shuffle service component with...
The paper presents an approach to the transmission of large data flows from a PIV (Particle Image Velocimetry) system to a remote supercomputer via a high-speed optical network. The approach is based on the model of a direct entry of PIV measurements into the RAM of computational nodes of a supercomputer for parallel processing. We describe a network infrastructure designed using the proposed model...
The HPC community has seen a steady increase in the number of components in every generation of supercomputers. Assembling a large number of components into a single cluster makes a machine more powerful, but also much more prone to failures. Therefore, fault tolerance has become a major concern in HPC. To deal with node crashes in large systems, checkpoint/restart is by far the preferred method....
The largest-scale high-performance (HPC) systems are stretching parallel file systems to their limits in terms of aggregate bandwidth and numbers of clients. To further sustain the scalability of these file systems, researchers and HPC storage architects are exploring various storage system designs. One proposed storage system design integrates a tier of solid-state burst buffers into the storage...
IP-Mobility protocols provides robust and integrate connectivity while the Mobile Node (MN) is moving among wireless networks. Therefore running certain procedures are needed to perform the complete handover procedure which results in handover latency and consequently packet loss. The four main causes of handover latency are: 1) Movement Detection, 2) Neighbor Discovery, 3) Duplicate Address Discovery...
Given the high demand for Peer to Peer applications (P2P), it becomes essential to develop an architecture to operate this type of network to use efficiently the bandwidth and minimize the existing overhead for the maintenance of its topology. Among the existing architectures for P2P networks, the Chord is notable for possessing a powerful search system, but on the other hand it has a high overhead...
Seamless handover has become an important challenging issue among research groups over the past 5 years. Researchers and scientists have been making efforts to provide robust and integrated connectivity while the mobile node (MN) moves between networks. Running certain procedures such as movement detection (MD), neighbor discovery (ND), duplicate address detection (DAD) and sending binding updates...
Vehicular ad hoc networks (VANETs), which are a class of Mobile ad hoc networks, have recently been developed as a standard means of communication among moving vehicles. Since VANETs are vital to the safety of the vehicles, the infrastructure, and the humans involved, a deep analysis of their potential behaviours is clearly required. In this paper we provide this analysis through the use of formal...
This paper proposes an intelligent rate controller for the Internet traffic. Called the IntelRate (Intelligent Rate), it is a router-based controller and uses the fuzzy logic control approach to adjust the source sending rate based on the instantaneous queue size of the router. Unlike other explicit congestion control protocols, the IntelRate controller need not evaluate the link states (such as bottleneck...
The use of grid computing is becoming increasingly important in the areas requiring large quantity of data and calculation. To provide better access time and fault tolerance in such systems, the replication is one of the main issues for this purpose. The effectiveness of a replication model depends on several factors, including the replicas placement strategy. In this paper, we propose an a priori...
In this decade, peer-to-peer (P2P) applications have emerged as popular tools for sharing data and they have gained much attention. Such P2P applications build overlay networks on top of existing infrastructure networks and disseminate data in a peer-to-peer manner. How well the P2P overlay network maps onto the underlying physical network topology can significantly impact P2P application performances...
The secure sum protocol is a well-known protocol for computing the sum of private inputs from distributed entities such that the inputs remain private. In this paper we present protocols for computing reputation in a privacy preserving manner that are inspired by the secure sum protocol. We provide a protocol that is secure under the semi-honest adversarial model as well as one that is secure under...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.