• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권12호
• /
• pp.3117-3132
• /
• 2012

The tree topology in multicast systems has high transmission efficiency, low latency, but poor resilience to node failures. In our work, some nodes are selected as backbone nodes to construct a tree-like core overlay. Backbone nodes are reliable enough and have strong upload capacity as well, which is helpful to overcome the shortcomings of tree topology. The core overlay is organized into a spanning tree while the whole overlay is of mesh-like topology. This paper focuses on improving the performance of the application-layer multicast overlay by optimizing the core overlay which is periodically adjusted with the proposed optimization algorithm. Our approach is to construct the overlay tree based on the out-degree weighted reliability where the reliability of a node is weighted by its upload bandwidth (out-degree). There is no illegal solution during the evolution which ensures the evolution efficiency. Simulation results show that the proposed approach greatly enhances the reliability of the tree-like core overlay systems and achieves shorter delay simultaneously. Its reliability performance is better than the reliability-first algorithm and its delay is very close to that of the degree-first algorithm. The complexity of the proposed algorithm is acceptable for application. Therefore the proposed approach is efficient for the topology optimization of a real multicast overlay.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.1911-1930
• /
• 2017

Overlay routing has emerged as a promising approach to improve reliability and efficiency of the Internet. The key to overlay routing is the placement and maintenance of the overlay infrastructure, especially, the selection and placement of key relay nodes. Spurred by the observation that a few relay nodes with high betweenness centrality can provide more optimal routes for a large number of node pairs, we propose a resilient routing overlay network construction method by introducing Super-Relay nodes. In detail, we present the K-Minimum Spanning Tree with Super-Relay nodes algorithm (SR-KMST), in which we focus on the selection and connection of Super-Relay nodes to optimize the routing quality in a resilient and scalable manner. For the simultaneous path failures between the default physical path and the overlay backup path, we also address the selection of recovery path. The objective is to select a proper one-hop recovery path with minimum cost in path probing and measurement. Simulations based on a real ISP network and a synthetic Internet topology show that our approach can provide high-quality overlay routing service, while achieving good robustness.

• 한국통신학회논문지
• /
• 제30권12B
• /
• pp.818-830
• /
• 2005

최근 CAN, Chord, Pastry와 Tapestry 등과 같이 안전한 분산 시스템기반의 P2P (Peer to Peer) 오버레이 네트워크가 일반화되고 있다. 이러한 시스템은 효율적이고 결함에 허용적인 라우팅과 개체의 위치추정 및 스스로 초기화시킬 수 있는 오버레이 네트워크가 갖는 로드 밸런싱을 제공한다. CDN (Contents Delivery Network)온 네트워크 하부구조의 중간 단계로서 궁극적으로 CP(Contents Provider)가 고객에게 전달하고자하는 멀터미디어 데이터를 포함한 컨텐츠의 효율적인 전송을 돕는다. 본 논문에서는 CDN에 적합한 토폴로지-인식 P2P 오버레이 네트워크를 새롭게 제안하였다. 제안된 기법인 Rosary에서 CDN 서버는 구조화된 오버레이 네트워크상에서 두 단계의 Inter-pastry와 Intra-pastry 라우팅을 수행한다. Rosary는 기존의 Pastry 기법을 CDN 환경에 맞도록 적응적으로 수정, 보완 및 추가하였으며 언급한 Intra-pastry 방식과 동적인 랜드마크 토폴로지 기법에 기반을 둔 세미-해싱방법을 제공하고 토폴로지-인식 오버레이 네트워크의 구성과 운용에 이용되었다. NS-2를 이용한 시뮬레이션에서 Rosary 기법은 네트워크 구성 후 안정화 된 컨텐츠 전송에서 보다 전송실패가 적고 효율적이며 견고한 것으로 증명되었다.

• 정보처리학회논문지C
• /
• 제14C권4호
• /
• pp.359-364
• /
• 2007

이동 애드혹 네트워크(Mobile Ad Hoc Network; MANET)에서의 오버레이 멀티캐스트 기법에 대한 최근의 연구들은 동적으로 변화하는 MANET의 네트워크 토폴로지 정보를 유지하기 위해 심각한 오버헤드를 야기하는 문제가 있다. 본 논문에서는 그룹 멤버들의 지리 정보를 이용하는 영역(region) 기반의 새로운 오버레이 멀티캐스트 기법인 ROME(Region-based Overlay Multicast in MANET)을 제안한다. ROME에서는 토폴로지를 작은 영역들로 나누고 그룹 멤버들의 위치 갱신 범위를 하나의 영역으로 한정함으로써 위치 정보 유지와 관련된 오버헤드를 줄인다. ROME은 데이터 패킷의 목적지로서 해당 영역의 멤버들의 주소 목록이 아닌 목적지 영역의 중심점(center point)의 좌표를 사용함으로써 확장성을 제공한다. 시뮬레이션을 통해 ROME이 패킷 오버헤드 측면에서 다른 기법에 비해 성능이 우수함을 보인다.

• 한국컴퓨터정보학회논문지
• /
• 제13권6호
• /
• pp.233-241
• /
• 2008

최근 IP 멀티캐스팅 대신에 각광을 받고 있는 오버레이 멀티캐스팅은 다수의 사용자를 위하여 서버의 자원과 네트워크의 대역폭을 효율적으로 활용할 수 있는 스케줄링 기법이 필요하다. 따라서 본 논문에서는 효율적인 멀티미디어 서비스를 위하여 오버레이 멀티캐스팅 환경에서의 복합스트림 토폴로지 정책을 제안한다. 본 논문의 성능 평가를 위하여 본 논문과 유사성을 가진 Overcast[5]와 비교하여 멀티캐스트에 참여한 노드들의 RTT(Round Trip Time) 수치, 트리 구축시간에 따른 대역폭 소모량 측정, 그리고 수행시간에 따른 MOR 영향 실험을 하였다. 그 결과 약 $8{\sim}20%$의 성능의 향상을 보여 주었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.193-194
• /
• 2007

We propose The Fast Join Mechanism for overlay multicast. This mechanism is provided with RP(Rendezvous Point), SM(Session Manager) and overlay multicast nodes. The RP provides data transfer to overlay multicast nodes and the Session Manager controls overlay multicast nodes to maintain the overlay topology.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 한국컴퓨터종합학술대회논문집 Vol.34 No.1 (D)
• /
• pp.183-188
• /
• 2007

Peer-to-Peer (P2P) overlay networks have drawn much research interest in the past few years because they provide a good substrate for large-scale applications in the Internet. In this paper, we introduce the use of anycast, a new "one-to-one-of-many" communication method in the Internet, to solve the following common problems of P2P overlay networks: load-balancing, topology-awareness, system partitioning, and multi-overlay interconnection. We also give an analysis of the features and limitations of the recently deployed anycast infrastructures in the Internet for supporting P2P overlay networks.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1447-1458
• /
• 2020

This paper describes a structured overlay network scheme based on multiple different time intervals. Many types of data (e.g., sensor data) can be requested at specific time intervals that depend on the user and the system. These queries are referred to as "interval queries." A method for constructing an overlay network that efficiently processes interval queries based on multiple different time intervals is proposed herein. The proposed method assumes a ring topology and assigns nodes to a keyspace based on one-dimensional time information. To reduce the number of forwarded messages for queries, each node constructs shortcut links for each interval that users tend to request. This study confirmed that the proposed method reduces the number of messages needed to process interval queries. The contributions of this study include the clarification of interval queries with specific time intervals; establishment of a structured overlay network scheme based on multiple different time intervals; and experimental verification of the scheme in terms of communication load, delay, and maintenance cost.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.171-192
• /
• 2017

The change of any element in the network is possible to cause performance degradation of the multicast network. So it is necessary to optimize the topology path through the multicast update strategy, which directly affects the performance and user experience of the overlay multicast. In view of the above, a new multicast tree update strategy based on perturbation theory Musp (Multicast Update Strategy based on Perturbation theory) is proposed, which reduces the data transmission interruption caused by the multicast tree update and improves user experiences. According to the multicast tree's elements performance and the topology structure, the Musp strategy defines the multicast metric matrix and based on the matrix perturbation theory it also defines the multicast fluctuation factor. Besides it also demonstrates the calculability of the multicast fluctuation factor presents the steps of the Musp algorithm and calculates the complexity. The experimental results show that compared with other update strategies, as for the sensitivity of the multicast fluctuation factor's energized multicast tree to the network disturbance, the maximum delay of the Musp update strategy is minimal in the case of the local degradation of network performance.

• Journal of Communications and Networks
• /
• 제8권4호
• /
• pp.378-390
• /
• 2006

Many distributed applications build overlays on top of the Internet. Several unsolved issues at the network layer can explain this trend to implement network services such as multicast, mobility, and security at the application layer. On one hand, overlays creating basic topologies are usually limited in flexibility and scalability. On the other hand, overlays creating complex topologies require some form of application level addressing, routing, and naming mechanisms. Our aim is to design an efficient and robust addressing, routing, and naming infrastructure for these complex overlays. Our only assumption is that they are deployed over the Internet topology. Applications that use our middleware will be relieved from managing their own overlay topologies. Our infrastructure is based on the separation of the naming and the addressing planes and provides a convergence plane for the current heterogeneous Internet environment. To implement this property, we have designed a scalable distributed k-resilient name to address binding system. This paper describes the design of our overlay infrastructure and presents performance results concerning its routing scalability, its path inflation efficiency and its resilience to network dynamics.