Computer Networks

Distribuir contenido ScienceDirect Publication: Computer Networks
ScienceDirect RSS
Updated: hace 46 mins 38 segs

Joint cache resource allocation and request routing for in-network caching services

2 horas 54 mins ago
Publication date: 11 February 2018
Source:Computer Networks, Volume 131

Author(s): Weibo Chu, Mostafa Dehghan, John C.S. Lui, Don Towsley, Zhi-Li Zhang

In-network caching is recognized as an effective solution to offload content servers and the network. A cache service provider (SP) always has incentives to better utilize its cache resources by taking into account diverse roles that content providers (CPs) play, e.g., their business models, traffic characteristics, preferences. In this paper, we study the cache resource allocation problem in a Multi-Cache Multi-CP environment. We propose a cache partitioning approach, where each cache can be partitioned into slices with each slice dedicated to a content provider. We propose a content-oblivious request routing algorithm, to be used by individual caches, that optimizes the routing strategy for each CP. We associate with each content provider a utility that is a function of its content delivery performance, and formulate an optimization problem with the objective to maximize the sum of utilities over all content providers. We establish the biconvexity of the problem, and develop decentralized (online) algorithms based on convexity of the subproblem. The proposed model is further extended to bandwidth-constrained and minimum-delay scenarios, for which we prove fundamental properties, and develop efficient algorithms. Finally, we present numerical results to show the efficacy of our mechanism and the convergence of our algorithms.





Categorías: research

A comparative classification of information dissemination approaches in vehicular ad hoc networks from distinctive viewpoints: A survey

2 horas 54 mins ago
Publication date: 11 February 2018
Source:Computer Networks, Volume 131

Author(s): Reza Ghebleh

Vehicular ad hoc networks (VANET) have received tremendous attention due to their potential impact on scientific research and their numerous attractive applications. With the aim of getting the intelligent communication for vehicular networks, VANETs can significantly improve the safety and efficiency issues of road traffic without requiring fixed infrastructure or centralized administration. Information dissemination is the base of communication which plays an important role in VANETs and it has become an active area of research in the recent years. However, information dissemination in VANET environment is a challenging task, mainly due to the rapid changes in the network topology and frequent fragmentation. In this paper, we provide a comprehensive survey on information dissemination in vehicular networks by focusing on some critical issues such as security and privacy, adaptability, scalability and so on. For this, we classify the existing information dissemination solutions into eight new classes based on their design and optimization objectives and give a qualitative overview on each class based on their objectives, forwarding strategy, features and advantages. Finally, we present open research issues to improve the efficiency of information dissemination protocols as much as possible.





Categorías: research

Topology mapping algorithm for 2D and 3D Wireless Sensor Networks based on maximum likelihood estimation

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Ashanie Gunathillake, Andrey V. Savkin, Anura P. Jayasumana

Automation of many sensor network protocols requires maps indicating sensor locations. Physical coordinate based maps capture the physical layout including voids and shapes, but obtaining the required distance values is often not feasible or economical. Alternative is to use topological maps based only on connectivity Information. Due to lack of physical distances, they are not faithful representatives of the physical layout. Here we present Maximum Likelihood-Topology Maps (ML-TM) that provide a more accurate physical representation, by using the probability of signal reception, an easily measurable parameter that is sensitive to the distance. Approach is illustrated using a mobile robot that listens to signals transmitted by sensor nodes and maps the packet reception probability to a coordinate system using a signal receiving probability function. ML-TM is an intermediate map between exact physical maps and hop- based topology coordinates. Results show that ML-TM algorithm generates maps for various network shapes with voids/obstacles in different environmental conditions with an error less than 7%. Performance of the algorithm in 3D sensor networks is also illustrated.





Categorías: research

A fine-grained response time analysis technique in heterogeneous environments

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): A. Hafsaoui, A. Dandoush, G. Urvoy-Keller, M. Siekkinen, D. Collange

It is crucial for the network operators and Internet service providers (ISPs) to determine the reasons that cause large response time fluctuations. In this paper, we consider passive measurements from heterogeneous environment (ADSL, FTTH and 3G/3G+ access technologies) of an European ISP ‘Orange’. Through experimental analysis of real traces, the need of a fine-grained traffic analysis technique is demonstrated. We show that finding the root causes of the observed poor performance using simple metrics such as response time, RTT and packet loss is difficult. In view of this fact, the different factors that play a role in determining the resulting response time are described through examples. Then, a breakdown method that drills down into the passively observed TCP connections is proposed. The method decomposes the end-to-end response time into many time periods and maps each one to a specific parameter or a physical phenomenon. Thus, the impact of not only the network parameters but also the application configuration and user behavior is captured. The resulting time periods are given as input to a clustering algorithm in order to group together transfers with similar performance holding traffic of different application protocols over different access technologies. As a result, the contribution of each participant in the performance bottleneck is identified. The proposed technique is validated through extensive simulations and real passively measured traces and it is compared to other works. Exemplifying the technique on real traces from Internet and enterprise traffic is introduced and discussed to demonstrate the power of the approach and its simplicity. In contrast to some existing tools, ISPs and enterprise administrators do not need to modify their network architecture or to install a new software or a plugin at the client or at the server side in order to use our technique. In addition, data sampling is not used. This is particularly important in order to keep data consistency and to detect metrics peaks. Last, our tool deals with both long and short TCP connections.





Categorías: research

Analysing and improving convergence of quantized congestion notification in Data Center Ethernet

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Ran Shu, Fengyuan Ren, Jiao Zhang, Tong Zhang, Chuang Lin

Quantized Congestion Notification (QCN) has been approved as the standard congestion management mechanism for the Data Center Ethernet (DCE). However, lots of work pointed out that QCN suffers from the problem of unfairness among different flows. In this paper, we found that QCN could achieve fairness, merely the convergence time to fairness is quite long. Thus, we build a convergence time model to investigate the reasons of the slow convergence process of QCN. We validate the precision of our model by comparing with experimental data on the NetFPGA platform. The results show that the proposed model accurately well characterizes the convergence time to fairness of QCN. Based on the model, the impact of QCN parameters, network parameters, and QCN variants on the convergence time is analysed in detail. Results indicate that the convergence time of QCN can be decreased if sources have the same rate increase probability or the rate increase step becomes larger at steady state. Enlightened by the analysis, we proposed a mechanism called QCN-T, which replaces the original Byte Counter and Timer at sources with a single modified Timer to reduce the convergence time. Finally, evaluations show great improvements of QCN-T in both convergence and stability.





Categorías: research

Prediction-based protocols for vehicular Ad Hoc Networks: Survey and taxonomy

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Islam Tharwat Abdel-Halim, Hossam Mahmoud Ahmed Fahmy

The high mobility of vehicles as a major characteristic of Vehicular Ad Hoc Networks (VANETs) affects vividly the dynamic nature of the networks and results in additional overhead in terms of extra messages and time delay. The future movements of the vehicles are usually predictable. The predictability of the vehicles future movements is a result of the traffic conditions, the urban layout, and the driving requirements to observe the traffic constrains. Hence, predicting these future movements could play a considerable role for both building reliable vehicular communication protocols and solving several issues of intelligent transportation systems. In the literature, numerous prediction-based protocols are presented for VANETs. Therefore, this paper follows the guidelines of systematic literature reviews to provide a premier and unbiased survey of the existing prediction-based protocols and develop novel taxonomies of those protocols based on their main prediction applications and objectives. A discussion on each category of both taxonomies is presented, with a focus on the requirements, constrains, and challenges. Moreover, usage analysis and performance comparisons are investigated in order to derive the suitability of each prediction objective to the various applications. Also, the relevant challenges and open research areas are identified to guide the potential new directions of prediction-based research in VANETs. Throughout this paper, information is provided to developers and researchers to grasp the major contributions and challenges of the predictive protocols in order to pave the way for enhancing their reliability and robustness in VANETs.





Categorías: research

A Joint Power Efficient Server and Network Consolidation approach for virtualized data centers

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Antonio Marotta, Stefano Avallone, Andreas Kassler

Cloud computing and virtualization are enabling technologies for designing energy-aware resource management mechanisms in virtualized data centers. Indeed, one of the main challenges of big data centers is to decrease the power consumption, both to cut costs and to reduce the environmental impact. To this extent, Virtual Machine (VM) consolidation is often used to smartly reallocate the VMs with the objective of reducing the power consumption, by exploiting the VM live migration. The consolidation problem consists in finding the set of migrations that allow to keep turned on the minimum number of servers needed to host all the VMs. However, most of the proposed consolidation approaches do not consider the network related consumption, which represents about 10–20% of the total energy consumed by IT equipment in real data centers. This paper proposes a novel joint server and network consolidation model that takes into account the power efficiency of both the switches forwarding the traffic and the servers hosting the VMs. It powers down switch ports and routes traffic along the most energy efficient path towards the least energy consuming server under QoS constraints. Since the model is complex, a fast Simulated Annealing based Resource Consolidation algorithm (SARC) is proposed. Our numerical results demonstrate that our approach is able to save on average 50% of the network related power consumption compared to a network unaware consolidation.





Categorías: research

Power-aware gateway connectivity in battery-powered dynamic IoT networks

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Surabhi Abhimithra Karthikeya, Revathy Narayanan, Siva Ram Murthy C

The paradigm of Internet of Things (IoT) is on rapid rise in today’s world of communication. Every networking device is being connected to the Internet to develop specific and dedicated applications. Data from these devices, called as IoT devices, is transmitted to the Internet through IoT Gateways (IGWs). IGWs support all the technologies in an IoT network. In order to reduce the cost involved with the deployment of IGWs, specialized low-cost devices called Solution Specific Gateways (SSGWs) are also employed alongside IGWs. These SSGWs are similar to IGWs except they support a subset of technologies supported by IGWs. A large number of applications are being designed which require IGWs and SSGWs to be deployed in remote areas. More often than not, gateways in such areas have to be run on battery power. Hence, power needs to be conserved in such networks for extending network life along with maintaining total connectivity. In this paper, we propose a dynamic spanning tree based algorithm for power-aware connectivity called SpanIoTPower-Connect which determines (near) optimal power consumption in battery-powered IoT networks. SpanIoTPower-Connect computes the spanning tree in the network in a greedy manner in order to minimize the power consumption and achieve total connectivity. Additionally, we propose an algorithm to conserve power in dynamic IoT networks where the connectivity demand changes with time. Our simulation results show that our algorithm performs better than Static Spanning Tree based algorithm for power-aware connectivity (Static ST) and a naive connectivity algorithm where two neighboring SSGWs are connected through every available technology. To the best of our knowledge, our work is the first attempt at achieving power-aware connectivity in battery-powered dynamic IoT networks.





Categorías: research

Potentials, trends, and prospects in edge technologies: Fog, cloudlet, mobile edge, and micro data centers

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Kashif Bilal, Osman Khalid, Aiman Erbad, Samee U. Khan

Advancements in smart devices, wearable gadgets, sensors, and communication paradigm have enabled the vision of smart cities, pervasive healthcare, augmented reality and interactive multimedia, Internet of Every Thing (IoE), and cognitive assistance, to name a few. All of these visions have one thing in common, i.e., delay sensitivity and instant response. Various new technologies designed to work at the edge of the network, such as fog computing, cloudlets, mobile edge computing, and micro data centers have emerged in the near past. We use the name ``edge computing'' for this set of emerging technologies. Edge computing is a promising paradigm to offer the required computation and storage resources with minimal delays because of ``being near'' to the users or terminal devices. Edge computing aims to bring cloud resources and services at the edge of the network, as a middle layer between end user and cloud data centers, to offer prompt service response with minimal delay. Two major aims of edge computing can be denoted as: (a) minimize response delay by servicing the users’ request at the network edge instead of servicing it at far located cloud data centers, and (b) minimize downward and upward traffic volumes in the network core. Minimization of network core traffic inherently brings energy efficiency and data cost reductions. Downward network traffic can be minimized by servicing set of users at network edge instead of service provider's data centers (e.g., multimedia and shared data) Content Delivery Networks (CDNs), and upward traffic can be minimized by processing and filtering raw data (e.g., sensors monitored data) and uploading the processed information to cloud. This survey presents a detailed overview of potentials, trends, and challenges of edge computing. The survey illustrates a list of most significant applications and potentials in the area of edge computing. State of the art literature on edge computing domain is included in the survey to guide readers towards the current trends and future opportunities in the area of edge computing.





Categorías: research

On the goodput of flows in heterogeneous mobile networks

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Anand Seetharam, Arti Ramesh

In practice heterogeneous networks comprising of diverse nodes need to operate efficiently under a wide range of node mobility and link quality regimes. In this paper, we propose algorithms to determine the goodput of flows in heterogeneous mobile networks. We consider a scenario where some network nodes operate as routers while others operate as flooders, based on the underlying forwarding policy. When a node operates as a router, it forwards packets based on the routing table as determined by the underlying routing algorithm and when it operates as a flooder, it broadcasts packets to all its neighbors. We begin with the case of a single network flow and demonstrate that the problem of determining the goodput is challenging even for this simple setting. We construct a Bayesian network, and propose an algorithm based on the sum-product algorithm to determine the exact goodput. We extend the proposed Bayesian network model for exact goodput calculation to feed forward networks with multiple flows. For a general network with multiple flows, the problem becomes more challenging. The difficulty of the problem stems from the fact that node pairs can forward traffic to one another, resulting in cyclical dependencies. We propose a fixed-point approximation to determine the goodput in this case. Finally, we present an application scenario, where we leverage the fixed-point approximation to design a forwarding strategy adaptive-flood that adapts seamlessly to varying networking conditions. We perform simulations and show that adaptive-flood can effectively classify individual nodes as routers/flooders, achieving performance equivalent to, and in some cases significantly better than that of network-wide routing or flooding alone.





Categorías: research

Quality of service in delay tolerant networks: A survey

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Animesh Roy, Tamaghna Acharya, Sipra DasBit

Delay tolerant networks (DTNs) are characterized by the absence of the end-to-end path due to intermittent connectivity among the nodes. Such networks are potentially applicable in the challenging scenarios, e.g. interplanetary communication, post-disaster environment, where traditional communication infrastructure is partially or fully absent. Each application requires some quality of service (QoS) guarantees for the traffic flow. QoS support cannot be provided to a network without QoS provisioning. However, QoS provisioning in a DTN is more difficult task than traditional networks, because of its inherent characteristics. There exist various issues which affect QoS in DTNs. In this paper, we explore the issues that influence QoS in DTNs. Subsequently, we analyze the effects of the issues on the QoS in terms of delivery ratio, packet drop etc. We also review various QoS management solutions in DTNs. The schemes on the QoS issues are classified based on their underlying approaches and key features. The paper is concluded with a brief discussion on some of the open research issues regarding QoS in DTNs.





Categorías: research

A push-pull network coding protocol for live peer-to-peer streaming

2 horas 54 mins ago
Publication date: 15 January 2018
Source:Computer Networks, Volume 130

Author(s): Hoda Ayatollahi, Mohammad Khansari, Hamid R. Rabiee

In this paper, we propose a new peer-to-peer (P2P) video streaming protocol which presents an implementation of network coding with a new caching mechanism. It employs a push-pull mechanism for sending the video chunks between peers. More specifically, this push-pull mechanism gives priority to the video chunks according to their video layers. The video base layer is transmitted through a pushing mechanism while the enhancement layers employ a pulling mechanism. Moreover, in the network coding algorithm of this protocol, we introduce a caching mechanism to improve the network’s performance as well as the video streaming quality. The comprehensive simulations show that the proposed protocol outperforms the traditional random network coding protocol by demonstrating a high improvement in video quality, redundancy of bandwidth usage, and reduction of the average frames loss in various video layers.





Categorías: research

Editorial Board

2 horas 54 mins ago
Publication date: 24 December 2017
Source:Computer Networks, Volume 129, Part 1









Categorías: research

Editorial Board

2 horas 54 mins ago
Publication date: 24 December 2017
Source:Computer Networks, Volume 129, Part 2









Categorías: research

Optimized device centric aggregation mechanisms for mobile devices with multiple wireless interfaces

2 horas 54 mins ago
Publication date: 24 December 2017
Source:Computer Networks, Volume 129, Part 1

Author(s): Sanaa Sharafeddine, Karim Jahed, Marwan Fawaz

Wireless broadband technologies and services are witnessing exponential growth to meet the demands of mobile users. State-of-the-art wireless networks are evolving with enhancements spanning all protocol layers and all network components from radio access to core network nodes. This has been coupled with a tremendous transformation of end user mobile devices towards multi-purpose smartphones and tablets with multi-core processing power, extendable memory storage, large battery capacity, and support for a wide range of wireless connectivity options. A standard smartphone currently can support short range Bluetooth and WiFi-Direct connectivity, local area WiFi connectivity, and long range 2G/3G/4G mobile connectivity. This naturally provides opportunities for data aggregation utilizing multiple wireless interfaces simultaneously to enhance device and network performance. In this work, we present the design, implementation, and testing of optimized device-centric data aggregation mechanisms for both file downloading and video streaming applications. The main novelty of the proposed mechanisms is their device-centric design, which makes them practical and feasible without any changes to wireless standards; moreover, they are scalable to support any number of wireless interfaces whereas previous related work has dealt with devices having two interfaces only. To demonstrate the effectiveness of the proposed mechanisms in terms of performance gains and practical feasibility, we develop an experimental testbed using Android devices and perform extensive testing for several network scenarios.





Categorías: research

Change at the Helm Welcome, Farewell, Advice, Thanks Special Issues

2 horas 54 mins ago
Publication date: 24 December 2017
Source:Computer Networks, Volume 129, Part 2

Author(s): Harry Rudin







Categorías: research

Multipath mobile data offloading of deadline assurance with policy and charging control in cellular/WiFi networks

2 horas 54 mins ago
Publication date: 24 December 2017
Source:Computer Networks, Volume 129, Part 1

Author(s): Yi-Ting Peng, Sok-Ian Sou, Meng-Hsun Tsai, Chuan-Sheng Lin

A promising L4-approach known as multipath TCP (MPTCP) has recently been standardized which allows a single transport connection to use multiple paths simultaneously over multiple interfaces. The use of MPTCP in offloading (i.e., multipath offloading) provides the potential to both maintain service connectivity and maximize the usage of the cellular resource. However, current Long Term Evolution (LTE) Policy and Charging Control (PCC) system lacks the ability to realize the coexistence of a cellular path (i.e., primary path) and an alternative path (i.e., secondary path) belonging to the same application session. As a result, it always determines the guaranteed bit-rate to the user under the assumption that the user has only a single LTE connection, and hence the usage efficiency of the cellular resources is seriously impaired. This paper proposes an enhanced PCC system with the consideration of using multipath offloading in cellular/WiFi networks. We propose a transport-based multipath offloading approach in which the LTE PCC system is rendered aware of alternative connection paths and allocates the available network resources accordingly.





Categorías: research

Special Issue on 5G Wireless Networks for IoT and Body Sensors

2 horas 54 mins ago
Publication date: 24 December 2017
Source:Computer Networks, Volume 129, Part 2

Author(s): J.J.P.C. Rodrigues, S. Zeadally, N. Kumar, G. Han







Categorías: research

A secure ECC-based privacy preserving data aggregation scheme for smart grids

2 horas 54 mins ago
Publication date: 24 December 2017
Source:Computer Networks, Volume 129, Part 1

Author(s): Erfaneh Vahedi, Majid Bayat, Mohammad Reza Pakravan, Mohammad Reza Aref

Development of Smart Grid and deployment of smart meters in large scale has raised a lot of concerns regarding customers’ privacy. Consequently, several schemes have been proposed to overcome the above mentioned issue. These schemes mainly rely on data aggregation as a method of protecting users’ privacy from the grid operators. However, the main problem with most of these schemes is the fact that they require a large amount of processing power at the meter side. This, together with the fact that smart meters don’t usually have a powerful processor, can cause the unavailability of smart meter data at the required time for operators of the grid, and at the same time prevents smart meters from performing their other duties, such as managing the home area network. In this paper, we propose an efficient privacy preserving data aggregation scheme, based on elliptic curves. In our scheme, each smart meter signs its encrypted data and sends it to the aggregator. After receiving the data, the aggregator verifies the incoming messages and aggregates them, without the need to decrypt the data received from each smart meter. The aggregator signs the aggregated messages and sends it to the operation center. At the end, the smart meters’ data are obtained and verified by the operation center. In addition to providing efficient computation cost, for the users, our protocol also satisfies the security requirements of smart grid data aggregation schemes. We provide security analysis of the proposed scheme as well as comparisons to show the efficiency of our scheme on computation and communication overheads.





Categorías: research

An architecture and protocol for smart continuous eHealth monitoring using 5G

2 horas 54 mins ago
Publication date: 24 December 2017
Source:Computer Networks, Volume 129, Part 2

Author(s): Jaime Lloret, Lorena Parra, Miran Taha, Jesus Tomás

Continuous monitoring of chronic patients improves their quality of life and reduces the economic costs of the sanitary system. However, in order to ensure a good monitoring, high bandwidth and low delay are needed. The 5G technology offers higher bandwidth, lower delays and packets loss than previous technologies. This paper presents an architecture for smart eHealth monitoring of chronic patients. The architecture elements include wearable devices, to collect measures from the body, and a smartphone at the patient side in order to process the data received from the wearable devices. We also need a DataBase with an intelligent system able to send an alarm when it detects that it is happening something anomalous. The intelligent system uses machine learning in BigData taken from different hospitals and the data received from the patient to diagnose and generate alarms. Experiment tests have been done to simulate the traffic from many users to the DataBase in order to evaluate the suitability of 5G in our architecture. When there are few users (less than 200 users), we do not find big differences of round trip time between 4G and 5G, but when there are more users, like 1000 users, it increases considerably reaching 4 times more in 4G The Packet Loss is almost null in 4G until 300 users, while in 5G it is possible to keep it null until 700 users. Our results point out that in order to have high number of patients continuously monitored, it is necessary to use the 5G network because it offers low delays and guarantees the availability of bandwidth for all users.





Categorías: research