Hydrogen Load Demand Prediction in Unified Energy System Based on Grey Ridgelet Neural Network.

Hydrogen will play critical pole in industrial field, heating field and transportation field, which can achieve mutual conversion of different energies. Hydrogen load prediction demand is important for establishing unified energy system, a novel prediction model is established based on particle swarm algorithm (PSA) and grey Ridgelet neural network (GRNN) to improve medium and long term hydrogen load demand prediction accuracy. Firstly hydrogen load demand prediction model in unified energy system is established, which concludes hydrogen load demand prediction models in industrial field, heating field and transportation field, and then total hydrogen demand model is deduced. Secondly, model of GRNN is constructed based on grey system theory and Ridgelet neural network, analysis procedure of GRNN is established. Structure of GRNN is confirmed, and mathematical model is constructed. To enhance prediction effectiveness of GRNN, PSA is used to optimize parameters of GRNN. Finally hydrogen load demand data in a province is selected to carry out prediction simulation, results show that prediction error of proposed PSA-GRNN ranges from 1.88% to 3.02%, which is less than that of other three prediction models, and fit goodness of proposed PSA-GRNN ranges from 0.958 to 0.985, which is also less than that of other three prediction models. Therefore proposed PSA-GRNN has better prediction precision and efficiency, which can obtain better precision effect and applicability. Hydrogen load demand prediction results in heating field based on PSAGRNN are closer to real value than that based on other three prediction models, results show that proposed PSA-GRNN has better prediction accuracy that other three prediction models. [ABSTRACT FROM AUTHOR]