Multiperiod-Ahead Wind Speed Forecasting Using Deep Neural Architecture and Ensemble Learning

Algorithm 1

Training the ensemble learner.

Input: the data output from SDAE

(1) Initialization: set the size of ensemble learners , the number of units in visible nodes,

   hidden nodes and output nodes in each ELM, the length of training samples for each ELM, threshold .

(2) The training procedure:

   while(the size of ensemble

     (1) select the training samples in bootstrap way

     (2) train the base predictor, namely, ELM.

     (3) Filter the test data and compute the error

     (4) if(error<)then

     Add it to the ensemble learner.

Output: the ensemble learner