...
首页> 外文期刊>Multimedia Tools and Applications >Construction and maintenance of P2P overlays for live streaming
【24h】

Construction and maintenance of P2P overlays for live streaming

机译:P2P覆盖的建筑和维护用于直播

获取原文
获取原文并翻译 | 示例
           

摘要

P2P live streaming requires low latency and low media discontinuity to provide users good quality of experience. When peers are connected to a large number of partners, the communication overhead increases and sophisticated overlay maintenance strategies are required to maintain undisrupted media distribution. In order to deal with these challenges, we present the Peer Classification for Partnership Constraints technique for building and managing P2P overlays for live streaming. The proposed algorithm defines classes of peers based on their contribution to video chunk distribution. Classes are used to constrain partnerships among peers. The number of potential partners in each class is constrained, avoiding competition for partnerships between high-cooperation and low-cooperation peers. Since each peer has a given number of slots dedicated to high-cooperation and low-cooperation peers, we guarantee that the network keeps operating, even when incorporating a considerable share of free riders. The strategy is simple, significantly reducing system complexity. Moreover, it can also be used in conjunction with other strategies devised in the literature for greater gains in efficiency. Experiments show that our Peer Classification for Partnership Constraints technique allows a streaming system to handle 50% of free riders under flash crowd events with low latency and discontinuity.
机译:P2P直播需要低延迟和低媒体不连续性,为用户提供优质的体验。当对等体连接到大量合作伙伴时,需要通信开销增加,并且需要复杂的覆盖维护策略来维持未分区的媒体分布。为了应对这些挑战,我们介绍了建筑和管理P2P覆盖的伙伴关系限制技术的对等分类,以获得实时流。该算法基于对视频块分布的贡献来定义对等体的类。课程用于限制同行之间的合作伙伴关系。每个班级的潜在合作伙伴人数受到限制,避免在高合作和低合作同龄人之间进行伙伴关系的竞争。由于每个同行都有一批致力于高合作和低合作对等体的特定时隙,因此我们保证网络不断运营,即使结合了相当大的免费骑手。该策略简单,显着降低了系统复杂性。此外,它也可以与文献中的其他策略结合使用,以提高效率提高。实验表明,我们的伙伴关系结构的同行分类允许流系统处理50%的闪存人群事件下的免费骑手,低延迟和不连续性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号