PyTorch implementation of LSTM Model for Multi-time-horizon Solar Forecasting

How to Run

Conda environment for running the code

A conda environment file is provided for convenience. Assuming you have Anaconda python distribution available on your computer, you can create a new conda environment with the necessary packages using the following command:

conda env create -f multi-tscale-slim.yaml -n "multi_time_horizon"

Running the code

1. Clone (or download) the repository:

git clone https://github.com/sakshi-mishra/LSTM_Solar_Forecasting.git

Training/Testing Data

The training and testing data needs to be downloaded from the NOAA FTP server for the locations/sites. You can use GNU wget to automate the download process. The scripts assume that the data is in the data folder as per the structure outlined in the data_dir_struct.txt file.

Cite this work

If you find this code useful for your research, please cite the article associated with this code-base: Mishra, Sakshi; Palanisamy, Praveen. "An Integrated Multi-Time-Scale Modeling for Solar Irradiance Forecasting Using Deep Learning." *arxiv