HEURISTIC ALGORITHMS FOR SURVIVABLE P2P MULTICASTING
Krzysztof M. Walkowiak, Michal W. Przewozniczek, Krzysztof Pająk · Applied Artificial Intelligence · 2013
The growing volume of Internet traffic, increasing popularity of streaming services, and limited scalability of existing network techniques trigger the need to develop new delivery solutions based on a multicasting approach. Multicasting—defined as a one-to-many delivery technique—enables effective distribution of many kinds of content to end users. In this article we focus on peer-to-peer (P2P) multicasting, which combines concepts of P2P systems and multicasting solutions; in other words, the multicast tree is constructed using end hosts (peers). Because P2P multicasting can be applied to deliver content with high reliability requirements, we introduce to P2P multicasting additional survivability constraints that guarantee delivery of content in the case of network failures. We formulate a mixed-integer programming (MIP) optimization problem of survivable P2P multicasting. Because the problem is nondeterministic polynomial time (NP)-hard and exact methods such as branch-and-cut can be applied for only a relatively small problem instance, we propose two heuristic algorithms based on evolutionary approach and Tabu Search methods. Extensive computational experiments show that both heuristic algorithms provide results close to optimal—the average gap to optimal results is 0.26% and 5.15% in the case of evolutionary and Tabu Search methods, respectively.