A heuristic approach to working and spare capacity optimization for survivable anycast streaming protected by p-cycles

Most of previous research in the field of network survivability has been focused on unicast transmissions. However, growing popularity of various concepts following the idea of content-oriented networks has triggered the need to develop new approaches to protect networks with other than unicast flows including multicast and anycast flows. In this paper, we consider the latter case and address the problem of working and spare capacity allocation in networks with anycast streaming, i.e., it is assumed that a set of replica servers is deployed in the network to serve streaming requests. To protect the network we propose to apply p-cycles—a relatively novel survivability approach combining capacity effectiveness of mesh restoration and ring-like restoration speed. To benefit from special properties of anycast flows, we use augmented version of p-cycles called Anycast-Protecting p-Cycles (APpC). We formulate the optimization problem as an ILP (Integer Linear Programming) model further applied to obtain optimal results using the GuRoBi solver. Due to high complexity of this optimization problem, we propose an effective heuristic algorithm based on the Simulated Annealing approach. Several versions of the algorithm are developed and examined—the best method yields on average results only 4.14 % worse than optimal ones. A wide range of experiments is conducted to verify performance of the proposed approach as a function of various network parameters including: p-cycle generator, p-cycle length, number of replica servers, number of clients. Moreover, we evaluate the Anycast-Protecting p-Cycles approach against classical p-cycle.