File Dissemination Research Articles

Intelligent deep reinforcement learning-based scheduling in relay-based HetNets

We consider a fundamental file dissemination problem in a two-hop relay-based heterogeneous network consisting of a macro base station, a half-duplex relay station, and multiple users. To minimize the dissemination delay, rateless code is employed at the base station. Our goal is to find an efficient channel-aware scheduling policy at the half-duplex relay station, i.e., either fetch a packet from the base station or broadcast a packet to the users at each time slot, such that the file dissemination delay is minimized. We formulate the scheduling problem as a Markov decision process and propose an intelligent deep reinforcement learning-based scheduling algorithm. We also extend the proposed algorithm to adapt to dynamic network conditions. Simulation results demonstrate that the proposed algorithm performs very close to a lower bound on the dissemination delay and significantly outperforms baseline schemes.

Optimal File Dissemination and Beamforming for Cache-Enabled C-RANs

In this paper, we investigate the joint design of transmit beamforming over physical layer and file dissemination strategy at base stations (BSs) over transport layer in the cache-enabled cloud radio access networks. Our objective is to minimize the total user file download delay while satisfying each BS’s power constraint and file dissemination proportion constraints. This problem is very challenging because of the highly coupled optimization variables in the objective function. To address the untractable non-convex problem, the original problem is decomposed into two subproblems. The first subproblem is a non-convex fractional program problem, and by transforming it into a second-order cone program, an iterative algorithm based on an inner approximation method is proposed to achieve the optimal beamforming vectors. For the other subproblem, we propose a sparse optimization algorithm and prove that there exists a closed-form solution in terms of $l_{0}$ -norm. Then, the original non-convex problem is addressed in an iterative manner by employing the two proposed sub-algorithms. Numerical results demonstrate that the proposed cross-layer optimization algorithms can efficiently reduce the total user download delay.

File Dissemination in Dynamic Graphs

In this article, we investigate the traversal time of a file across N communication links subject to stochastic changes in the sending rate of each link. Each link’s sending rate is modeled by a finite-state Markov process. Two cases, one where links evolve independently of one another ( N mutually independent Markov processes) and the second where their behaviors are dependent (these N Markov processes are not mutually independent), are considered. A particular instance where the above is encountered is ad hoc delay/tolerant networks where links are subject to intermittent unavailability.

An OPNET simulation model for peer-to-peer networks

Peer-to-peer (P2P) traffic has increased rapidly over the past few years, with file sharing providing the main drive behind such traffic. Therefore, modeling P2P systems and studying their impact on the performance of the underlying network is a vital research topic. In this work we describe a flexible, efficient and easily expandable P2P simulation framework developed for the OPNET simulation package. The framework can be used to study a wide variety of issues regarding the packet-level and/or the flow-level performance of P2P systems, including the impact of cooperation incentives on file dissemination; mobility and quality of service (QoS) support in P2P distribution; and the effects of free-riding, resource pollution, and malicious attacks on P2P networks.

Fast file dissemination in peer-to-peer networks with upstream bandwidth constraint

How to minimize the time of disseminating a large file from a single source to a large number of users is a fundamental question in peer-to-peer applications. Most previous works do not present a lower bound on the dissemination time, and fail to show how close the dissemination time of their algorithms are to the lower bound. In this paper, we analyze how to decrease the dissemination time by efficiently utilizing the upstream bandwidths of nodes. We first present a tight lower bound on the dissemination time that can serve as a benchmark for evaluating the performance of peer-to-peer file transfer algorithms. Then we find an equivalent condition along with a sufficient condition for fully utilizing the upstream bandwidths of nodes, in the networks where only the upstream bandwidths of nodes can constrain the transfer rates between nodes. Based on the theoretical analysis, we also design an algorithm called Receiver-schedule for fast dissemination, which can efficiently utilize the upstream bandwidths of nodes by dynamically adjusting the chunk distribution among nodes. Our simulation results show that, by using the algorithm the dissemination time is more than the lower bound by at most four percent in many cases in the networks with the upstream bandwidth constraint.

Measurement-based study on the relation between users’ watching behavior and network sharing in P2P VoD systems

P2P-based Video on Demand (P2P VoD) systems can provide higher quality video services than P2P live systems. However, owing to the unavailability of open source codes, the characteristics of P2P VoD systems have not been fully explored. For this purpose, in this paper, we first implemented reverse engineering to the protocols of two most popular VoD systems used in China. Peers' watching behavior and network sharing were then studied through the measured buffer messages. Based on our study, we found that uploading-only peers were more than downloading peers, and smooth-watching peers were more than randomly-seeking peers in the current P2P VoD systems. This finding is significantly different from the existing P2P-based file dissemination systems and the results obtained in the previous work on VoD systems. Furthermore, this study revealed the relations between watching behavior and network sharing. It has been observed that randomly-seeking peers will provide more regular as well as rare chunks than smooth-watching peers. A simple mathematical model was established to analytically demonstrate the relation between the watching index (WI) distribution and network-sharing profile, and this relation was also validated by our measured data.

Defending passive worms in unstructured P2P networks based on healthy file dissemination

Propagation of passive worms in unstructured peer-to-peer (P2P) networks can result in significant damages and the loss of network security. This paper obtains the average delay for all peers in the entire transmitting process, and proposes a mathematical model for simulating unstructured P2P networks-based passive worms' propagation taking into account network throughput. According to the file popularity which follows the Zipf distribution, we propose a new healthy file dissemination-based defense strategy. Some parameters related to the propagation of passive worms are studied based on the proposed model. Finally, the simulation results verify the effectiveness of our model, which can provide an important guideline in the control of passive worms in unstructured P2P networks.

Cooperative mobile-to-mobile file dissemination in cellular networks within a unified radio interface

In this paper, a data dissemination technique is introduced for cellular networks by embedding peer-to-peer data transfer into the hierarchical architecture of UMTS (Universal Mobile Telecommunication Systems) for cooperative sharing of data among mobile terminals. Our concept is based on the uplink/downlink traffic imbalance in 3G wireless networks and clearly confirms the social principle “real egoistic behavior is to cooperate”. It boosts the spectral efficiency of UMTS by enabling direct mobile-to-mobile data transfer and by dynamically allocating users to temporarily unused uplink channels. The results indicate a substantial increase in service probability and overall system throughput, as well as a significant reduction of the expected file download time.

Optimal scheduling of peer-to-peer file dissemination

Peer-to-peer (P2P) overlay networks such as BitTorrent and Avalanche are increasingly used for disseminating potentially large files from a server to many end users via the Internet. The key idea is to divide the file into many equally-sized parts and then let users download each part (or, for network coding based systems such as Avalanche, linear combinations of the parts) either from the server or from another user who has already downloaded it. However, their performance evaluation has typically been limited to comparing one system relative to another and has typically been realized by means of simulation and measurements. By contrast, we provide an analytic performance analysis that is based on a new uplink-sharing version of the well-known broadcasting problem. Assuming equal upload capacities, we show that the minimal time to disseminate the file is the same as for the simultaneous send/receive version of the broadcasting problem. For general upload capacities, we provide a mixed integer linear program (MILP) solution and a complementary fluid limit solution. We thus provide a lower bound which can be used as a performance benchmark for any P2P file dissemination system. We also investigate the performance of a decentralized strategy, providing evidence that the performance of necessarily decentralized P2P file dissemination systems should be close to this bound and, therefore, that it is useful in practice.

Under storage constraints of epidemic backup node selection using HyMIS architecture for data replication in mobile peer-to-peer networks

The attainment of high reliability and availability is very difficult to be achieved in very complex wireless infrastructureless networks. Reliability concept describes essentially the transmission characteristics of infrastructureless networks, such as packet loss probability, packet duplication, data misinsertion, and corruption of packets. Some other metrics nowadays, aggregate and contribute to the aggravation of end to end reliability. In this work a new scheme for end to end reliable file/resource sharing is studied, among mobile peer-to-peer users. The proposed scheme uses the Hybrid Mobile Infostation System (HyMIS) to maintain and enhance the reliability of file/resource sharing process among wireless devices. Under various storage constraints the epidemic backup node selection is adopted, merging the advantages of epidemic file dissemination through purely mobile Infostations, using the HyMIS architecture. Examination through simulation is performed, taking into account many newly introduced storage metrics, for the performance evaluation of the proposed scheme. These storage metrics are tuned into certain bounded values to enable high packet delivery ratio. Results show that this scheme under certain storage requirements offer a reliable and robust solution for sharing resources of any capacity in dynamic mobile peer-to-peer wireless environments.

Analysis of peer-to-peer file dissemination

In recent years, overlay networks have proven a popular way of disseminating potentially large files from a single server S to a potentially large group of N end users via the Internet. A number of algorithms and protocols have been suggested, implemented and studied. In particular, much attention has been given to peer-to-peer (P2P) systems such as BitTorrent [5], Slurpie [20], SplitStream [4], Bullet [11] and Avalanche [6]. The key idea is that the file is divided into M parts of equal size and that a given user may download any one of these - or, for Avalanche, linear combinations of these - either from the server or from a peer who has previously downloaded it.

Analysis of peer-to-peer file dissemination amongst users of different upload capacities

In recent years, overlay networks have proven an effective way of disseminating a file from a single source to a group of end users via the Internet. A number of algorithms and protocols have been suggested, implemented and studied. In particular, much attention has been given to peer-to-peer (P2P) systems such as BitTorrent [2], Slurpie [10], SplitStream [1] and Bullet [5]. The key idea is that the file is divided into M parts of equal size and that a given user may download any one of these either from the server or from a peer who has previously downloaded it. More recently, a scheme based on network coding [3] has been suggested. Here, users down-load linear combinations of file parts rather than individual file parts.

Content-access QoS in peer-to-peer networks using a fast MDS erasure code

This paper describes an enhancement of content access Quality of Service in peer to peer (P2P) networks. The main idea is to use an erasure code to distribute the information over the peers. This distribution increases the users' choice on disseminated encoded data and therefore, statistically enhances the overall throughput of the transfer. A performance evaluation based on an original model using the results of a measurement campaign of sequential and parallel downloads in a real P2P network over Internet is presented. Based on a bandwidth distribution, statistical content-access QoS are guaranteed in function of both the content replication level in the network and the file dissemination strategies. A simple application in the context of media streaming is proposed. Finally, the constraints on the erasure code related to the proposed system are analysed and a new fast MDS erasure code is proposed, implemented and evaluated.