P2P Data Dissemination for Real-Time Streaming Using Load-Balanced Clustering Infrastructure in MANETs With Large-Scale Stable Hosts

In order to reduce the network overhead in data dissemination between large-scale stable users in mobile ad-hoc networks (MANETs), clustering is a typical method by partitioning the peers into a hierarchical infrastructure. In the article, a peer-to-peer data dissemination mechanism for real-time streaming based on the hierarchical infrastructure in MANETs will be proposed. First, a distinct strategy of peer clustering is adopted to maximize network capacity and meet peer traffic demand. The peer clustering problem is formulated as a 0/1 integer linear programming (ILP). Then, an approximation algorithm is proposed to determine the feasible solution of the 0/1 ILP. Second, in order to provide timely data dissemination among peers, another method for estimating propagation delay is proposed, where we use the estimated value and the actual historical value simultaneously to alleviate the incorrect problem of the estimated value. Third, based on the quality of service (QoS) requirement of the service, a different distributed data scheduling algorithm between peers is designed, which effectively utilizes the limited bandwidth of the network. The simulation results show that the proposed mechanism obtains a higher network capacity and higher data received rate than the previous works.