(Contains Energy System Datasets) Integrated Energy System (IES) Condition Variation Prediction Model

Integrated Energy System (IES) Condition Variation Prediction Model

This repository contains a neural network model developed to predict and analyze condition variations in Integrated Energy Systems (IES). The model leverages deep learning techniques to handle complex IES dynamics, aiding in efficient management and optimization.

🌟 If you find this repository helpful, please give it a Star! 🌟

Your support encourages us to continue developing and improving the model. Thank you for helping us grow!

Repository Structure

The repository is organized as follows:

• Dataset 1 Folder: Contains preprocessed data specific to the first IES dataset.
• Dataset 2 Folder: Contains preprocessed data specific to the second IES dataset.

These datasets were generated using Apros, a simulation tool for process systems. The repository includes only the processed data required for model training. Original raw data can be accessed at Zenodo: https://doi.org/10.5281/zenodo.14058544.

Publication

The detailed research paper describing this model, its architecture, and applications in IES will be provided here upon publication.

How to Use

1. Clone the repository: Clone this repository to your local machine by running the following command:

   git clone https://github.com/Lirdon/Adaptive-Spatio-Temporal-Graph-Convolution-Network.git

2. Run the Model: To start the model, simply run main.py:

   python main.py