Researcher:
Cebeci, Sena Efsun

Profile Picture
ORCID

Job Title

Researcher

First Name

Sena Efsun

Last Name

Cebeci

Name

Name Variants

Cebeci, Sena Efsun

Email Address

Birth Date

Filters

2013 - 20155

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.dfb7a657-2d7e-4abe-996a-5f9bf29d8d04

Search Results

Now showing 1 - 5 of 5
  • Placeholder
    PublicationMetadata only
    Green proxy-based approaches for BitTorrent
    (IEEE, 2014) Anastasi, Giuseppe; Department of Computer Engineering; Department of Computer Engineering; Cebeci, Sena Efsun; Özkasap, Öznur; Researcher; Faculty Member; Department of Computer Engineering; College of Engineering; College of Engineering; N/A; 113507
    Energy efficiency in P2P systems has become a prominent issue due to significant portions of the Internet traffic devoted to P2P protocols. In this paper, we address the approaches for energy efficiency in BitTorrent Protocol. First, we provide a classification of the existing energy efficient BitTorrent studies, and then propose multi-proxy and private proxy approaches to minimize energy consumption. We develop energy cost formulations for our proposed protocols as well as the legacy BitTorrent. The performance of multi-proxy and private proxy BitTorrent is analyzed through a comprehensive set of simulations performed on Peersim for the energy consumption and average download time metrics. For the multi-proxy protocol, we investigate the effect of increasing the number of proxies on the overlay. We also present preliminary experimental results on large-scale scenarios revealing that the proxy-based schemes reduce the energy consumption up to 80% without any performance degradation in comparison to the legacy BitTorrent.
  • Placeholder
    PublicationMetadata only
    Flat and hierarchical epidemics in P2P systems: energy cost models and analysis
    (Elsevier, 2014) N/A; Department of Computer Engineering; N/A; N/A; Department of Computer Engineering; Özkasap, Öznur; Çem, Emrah; Cebeci, Sena Efsun; Koç, Tuğba; Faculty Member; PhD Student; PhD Student; Researcher; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; 113507; N/A; N/A; N/A
    In large scale distributed systems, epidemic or gossip-based communication mechanisms are preferred for their ease of deployment, simplicity, robustness against failures, load-balancing and limited resource usage. Although they have extensive applicability, there is no prior work on developing energy cost models for epidemic distributed mechanisms. In this study, we address power awareness features of two main groups of epidemics, namely flat and hierarchical. We propose a dominating-set based and power-aware hierarchical epidemic approach that eliminates a significant number of peers from gossiping. To the best of our knowledge, using a dominating set to build a hierarchy for epidemic communication and provide energy efficiency in P2P systems is a novel approach. We develop energy cost model formulations for flat and hierarchical epidemics. In contrast to the prior works, our study is the first one that proposes energy cost models for generic peers using epidemic communication, and examines the effect of protocol parameters to characterize energy consumption. As a case study protocol, we use our epidemic protocol ProFID for frequent items discovery in P2P systems. By means of extensive large scale simulations on PeerSim, we analyze the effect of protocol parameters on energy consumption, compare flat and hierarchical epidemic approaches for efficiency, scalability, and applicability as well as investigate their resilience under realistic churn.
  • Placeholder
    PublicationMetadata only
    Energy efficiency in P2P systems and applications
    (Wiley, 2015) Masoumzadeh, Seyed-Saeid; Brienza, Simone; Hlavacs, Helmut; Anastasi, Giuseppe; Department of Computer Engineering; Özkasap, Öznur; Cebeci, Sena Efsun; Faculty Member; PhD Student; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; 113507
    This chapter presents a general taxonomy to classify possible approaches to the energy problem in peer-to-peer (P2P) systems and applications. It provides a classification of energy-aware P2P approaches into three main classes, based on the techniques they use, namely, sleep/wakeup, hierarchical, and resource allocation. The chapter surveys the main solutions available in the literature, focusing on two relevant classes of P2P protocols, namely, file-sharing/distribution protocols (e.g., BitTorrent and Gnutella) and epidemic P2P protocols. It compares, in terms of energy efficiency, the two main approaches to file sharing, that is, client-server and P2P. The chapter also presents some techniques for optimizing the energy efficiency in P2P file sharing. BitTorrent implements an unstructured overlay network customized for file sharing. Designing energy-efficient epidemic (gossip-based) protocols and services has become significant because of their wide usage in large-scale distributed systems. There exist two main classes of epidemic algorithms, namely, flat and hierarchical.
  • Placeholder
    PublicationMetadata only
    Large scale analysis of bittorrent proxy for green internet file sharing
    (Springer-Verlag Berlin, 2013) Anastasi, Giuseppe; Department of Computer Engineering; Department of Computer Engineering; Cebeci, Sena Efsun; Özkasap, Öznur; Researcher; Faculty Member; Department of Computer Engineering; College of Engineering; College of Engineering; N/A; 113507
    Addressing energy efficiency in P2P services has the potential to make the Internet greener since they comprise a major source of the Internet data traffic. In this paper, we consider approaches for green Internet file sharing. We develop simulation models of proxy-based energy efficient BitTorrent as well as legacy BitTorrent on PeerSim P2P simulator, and explore their characteristics on large-scale scenarios. Our aim is first to identify the operating conditions where proxy-based BitTorrent outperforms the legacy protocol in terms of overall energy efficiency, and then to develop optimizations for the proxy-based approach.
  • Placeholder
    PublicationMetadata only
    A survey on energy efficiency in P2P systems: file distribution, content streaming, and epidemics
    (Association for Computing Machinery (ACM), 2015) Brienza, Simone; Masoumzadeh, Seyed Saeid; Hlavacs, Helmut; Anastasi, Giuseppe; Department of Computer Engineering; Department of Computer Engineering; Cebeci, Sena Efsun; Özkasap, Öznur; Researcher; Faculty Member; Department of Computer Engineering; College of Engineering; College of Engineering; N/A; 113507
    Several Peer-to-Peer (P2P) protocols and applications have been developed to allow file distribution/sharing, video and music streaming, and data and information dissemination. These P2P systems are regularly used by a large number of users, both in desktop and mobile environments, and they generate a remarkable portion of the overall Internet traffic. However, many common P2P protocols and applications were designed neglecting the energy problem. In fact, they often require always-on devices in order to work properly, thus producing significant energy waste. The problem is even more relevant in the mobile context, since the battery lifetime of mobile devices is limited. Therefore, energy efficiency in P2P systems is a highly debated topic in the literature. New P2P approaches-more energy efficient than traditional client/server solutions-have been proposed. In addition, several improvements to existing P2P protocols have been introduced to reduce their energy consumption. In this article, we present a general taxonomy to classify state-of-the-art approaches to the energy problem in P2P systems and applications. Then, we survey themain solutions available in the literature, focusing on three relevant classes of P2P systems and applications: file sharing/distribution, content streaming, and epidemics. Furthermore, we outline open issues and provide future research guidelines for each class of P2P systems.