Visit the Energy Systems Laboratory Homepage.
dc.creator | Dai, W. | |
dc.creator | Zou, P. | |
dc.creator | Yan, C. | |
dc.date.accessioned | 2007-05-07T20:42:53Z | |
dc.date.available | 2007-05-07T20:42:53Z | |
dc.date.issued | 2006 | |
dc.identifier.other | ESL-IC-06-11-107 | |
dc.identifier.uri | https://hdl.handle.net/1969.1/5246 | |
dc.description.abstract | As thermal inertia is the key factor for the lag of thermoelectric utility regulation, it becomes very important to forecast its short-term load according to running parameters. In this paper, dynamic radial basis function (RBF) neural network is proposed based on the RBF neural network with the associated parameters of sample deviation and partial sample deviation, which are defined for the purpose of effective judgment of new samples. Also, in order to forecast the load of sample with large deviation, sensitivity coefficients of input layer is given in this paper. To validate this model, an experiment is performed on a thermoelectric plant, and the experimental result indicates that the network can be put into extensive use for short-term load forecasting of thermoelectric utility. | en |
dc.format.extent | 88137 bytes | en |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.publisher | Energy Systems Laboratory (http://esl.tamu.edu) | |
dc.publisher | Texas A&M University (http://www.tamu.edu) | |
dc.subject | dynamic RBF neural network | en |
dc.subject | load forecasting | en |
dc.subject | partial sample deviation | en |
dc.subject | input layer sensitivity coefficient | en |
dc.subject | thermoelectric boiler | en |
dc.title | Research on Short-term Load Forecasting of the Thermoelectric Boiler Based on a Dynamic RBF Neural Network | en |
This item appears in the following Collection(s)
-
ICEBO - International Conference for Enhanced Building Operations
International Conference for Enhanced Building Operations