Deep Neural Network-based Optimal Path Selection for Propagation Information and Its Enhancement on Data Flow Efficiency

The rapid development of the information age has prompted the exchange and sharing of information resources more and more frequently.Aiming at the problem of propagating information data in the center of data network, which is easy to cause congestion and delay, this paper uses deep neural network to research on the optimal path selection method for propagating information.A network traffic prediction model is designed based on multi-task learning and LSTM, and a dynamic multipath load balancing algorithm (FNN-LB) based on feed-forward neural network is proposed to solve the problem of scheduling and allocation of network traffic.The traffic prediction accuracy and generalization ability of the MT-LSTM model are verified, and the prediction mean square error is only 0.573%.Analyzed from several performance metrics, the FNN-LB algorithm improves the network throughput by 2.34% to 10.35% relative to other algorithms, effectively reduces the number of idle and overloaded links, as well as the average network delay and packet loss rate of the rat flow, while the first packet round-trip delay of the rat flow is reduced by more than 12.58%.Therefore, the proposed method in this paper can ensure the transmission quality of communication information data and improve the efficiency of data flow of communication information.