Energy-Efficient Virtual Network Embedding Algorithm Based on Hopfield Neural Network

To solve the energy-efficient virtual network embedding problem, this study proposes an algorithm based on Hopfield neural network. An model was established. Wavelet diffusion performed to take structural feature value into consideration and provide a candidate set for embedding. In addition, used in problem. The augmented Lagrangian multiplier method transform constraint problem unconstrained resulting as energy function of network, weight iteratively trained. scheme obtained when balanced. prove effectiveness proposed algorithm, we designed two experimental environments, namely, medium-sized scenario small-sized scenario. Simulation results show that achieved superior performance effectively decreased consumption relative other methods both scenarios. Furthermore, reduced number open nodes links leading reduction overall power process, while ensuring average acceptance ratio revenue cost.