Abstract: To meet the requirements of the rapidity and the accuracy of the aircraft cabin energy consumption prediction for bridge-load air conditioner when an aircraft berthing, a forecasting method based on the combination of neural network, particle swarm and coral reef is proposed. The energy consumption prediction model is established based on wavelet neural network, and the prediction model parameters are optimized using the united algorithm of coral reefs and particle swarm optimization. The united algorithm adopts a double-layer structure: the data of the first layer are grouped and optimized by the particle swarm optimization algorithm for a preliminary optimization, and the first layer optimization results are put into the second layer; the second layer makes use of coral reef algorithm for further optimization, so as to improve the prediction accuracy and solve the problem of slow convergence rate and easy to fall into local extremum. The simulation results show that the proposed united algorithm can effectively improve the prediction speed and accuracy of energy consumption.

Key words: united algorithm, wavelet neural network, particle swarm optimization, coral reef optimization, aircraft cabin, energy consumption prediction