MP2P traffic intelligent management model based on BP neural network

A Mobile Peer-to-Peer (MP2P) traffic intelligent management model (BP Neural Network and Intelligent Management, BP-IM) based on neural network is proposed. First, the whole MP2P network is modeled by the semi-distributed structure. Then the BP neural network is introduced to measure and control the MP2P flow effectively. In addition, the corresponding P2P traffic priority table is established and the assignment of the buffer flow is dynamically adjusted. The BP-IM model has the features of flexible configuration, efficient detection, and easy to be extended, reducing the complexity of the algorithm. Computer simulations based on OMNeT++ show that: compared to the traditional model, higher-level traffic processing delay is small by the proposed BP-IM model, which saves the limited MP2P bandwidth resources and avoids network congestion. MP2P traffic processing delay decreases with increase of the traffic priority, which reflects the intelligent traffic management concept for BP-IM model.