hydropower-fatigue-damage-reduction

Code for EPFL PTMH & SDSC's paired-hydro project

https://github.com/till-m/hydropower-fatigue-damage-reduction

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Committers with academic emails
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (11.9%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Code for EPFL PTMH & SDSC's paired-hydro project

Basic Info
  • Host: GitHub
  • Owner: till-m
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: master
  • Size: 37.8 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

hydropower-fatigue-damage-reduction

This repository contains code to model stress in hydraulic machines and trajectory optimization code developed during the EPFL PTMH & SDSC's paired-hydro project.

System Requirements/Environment

The provided Dockerfile specifies an environment to run this code in. Alternatively, you can launch a renku session by clicking the Start button on this projects renku page. Toy data is tracked using git LFS. Please run git lfs pull to ensure these files are present. Specific dependencies are otherwise specified in requirements.txt. The software has been tested using the associated Docker image.

Hardware

Due to the underlying deep learning model, this software runs faster if GPUs are present. The demo-script demo.ipynb is however designed to run solely CPU resources as well.

Installation

To install, clone the repository and install the dependencies, e.g. via pip by running pip install -r requirements.txt. This should not take more than several minutes.

Use and Demo

A demo notebook is present as demo.ipynb and shows the end-to-end process of training a model and running the optimization. On a normal machine with no GPU present, this notebook can take up to several hours to execute.

However, you can also execute standalone scripts main.py and optimize_dijkstra.py to train and optimize respectively.

Training the model

To train the model, ensure appropriate training data is present in the input directory (IN_FOLDER which can be set in CONFIG.py), then run main.py. Training the model should take a few hours on e.g. a NVIDIA P100 GPU. We have added some toy data to showcase the expected structure of the input files.

Dijkstra-based trajectory optimization

To run the optimization procedure, execute optimize_dijkstra.py. Using a NVIDIA P100 GPU, the optimization procedure can take a few days to complete on the original grid spacing. On a more coarse, grid, it can be significantly faster. An example of how to adjust the grid size is given in the optimization file.

Owner

  • Login: till-m
  • Kind: user
  • Location: Zurich, CH
  • Company: @SwissDataScienceCenter

Data Scientist @ SDSC / ETH Zurich

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Muser"
  given-names: "Till"
- family-names: "Krymova"
  given-names: "Ekaterina"
- family-names: "Morabito"
  given-names: "Alessandro"
- family-names: "Seydoux"
  given-names: "Martin"
- family-names: "Vagnoni"
  given-names: "Elena"
orcid: https://orcid.org/0000-0002-9856-4554
title: "Fatigue Damage Reduction in Hydropower Startups with Machine Learning"
doi: 10.5281/zenodo.14628160
version: v1.0.0
date-released: 2025-01-10
url: "https://github.com/till-m/hydropower-fatigue-damage-reduction"

GitHub Events

Total
  • Release event: 1
  • Watch event: 1
  • Push event: 2
  • Create event: 3
Last Year
  • Release event: 1
  • Watch event: 1
  • Push event: 2
  • Create event: 3

Committers

Last synced: 7 months ago

All Time
  • Total Commits: 18
  • Total Committers: 1
  • Avg Commits per committer: 18.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 18
  • Committers: 1
  • Avg Commits per committer: 18.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Till Muser m****l@g****m 18

Issues and Pull Requests

Last synced: 7 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels