A New Hyper-Parameter Optimization Method for Power Load Forecast Based on Recurrent Neural Networks

The selection of the hyper-parameters plays a critical role in task prediction based on recurrent neural networks (RNN). Traditionally, machine learning models are selected by simulations as well human experiences. In recent years, multiple algorithms Bayesian optimization (BO) developed to determine optimal values hyper-parameters. most these methods, gradients required be calculated. this work, particle swarm (PSO) is used under BO framework develop new method for hyper-parameter optimization. proposed algorithm (BO-PSO) free gradient calculation and particles can optimized parallel naturally. So computational complexity effectively reduced which means better obtained same amount calculation. Experiments done real world power load data, where outperforms existing state-of-the-art algorithms, with limit-BFGS-bound (BO-L-BFGS-B) truncated-newton (BO-TNC), terms accuracy. errors result different show that BO-PSO an effective method.