Multivariate Irradiance LSTM Forecast Model - Training

0 ×

The University of Saskatchewan
Ph.D. in Interdisciplinary Studies

Created by: Carlos Enrique Diaz, MBM, B.Eng.
Email: carlos.diaz@usask.ca

Supervisor: Lori Bradford, Ph.D.
Email: lori.bradford@usask.ca

This is a simple example workflow for multivariant time series analysis using an LSTM based recurrent neural network and implemented via the KNIME Deep Learning - Keras Integration.

This workflow used GHI data from CWEEDS for Saskatoon and trains a model to predict the Global Horizontal Irradiance (GHI) in the next hour based on the values in the last 10 hours. The workflow was adapted from the following workflow:

https://hub.knime.com/-/spaces/-/~acxQcWj9lyHLyyrh/

URL: Workflow Template https://hub.knime.com/-/spaces/-/~acxQcWj9lyHLyyrh/
URL: CWEEDS Data https://climate.weather.gc.ca/prods_servs/engineering_e.html
URL: Multivariate Time Series Analysis: LSTMs & Codeless https://www.knime.com/blog/multivariate-time-series-analysis-lstm-codeless

Nodes

• Column Filter4 ×
• Column Appender3 ×
• Column List Loop Start2 ×
• Extract Column Header2 ×
• Column Splitter2 ×
• Show all 32 nodes

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Column Expressions (Labs)
• FeatureKNIME Data Generation
• FeatureKNIME Deep Learning - Keras Integration
• FeatureKNIME JavaScript Views
• FeatureKNIME Math Expression (JEP)

Links

• No links available