Skip to main content

A Probabilistic Load Forecasting Project.

Project description

pipeline status Python

Website | Docs | Install Guide | Tutorial

ProLoaF is a probabilistic load forecasting project.


ProLoaF makes use of the big data paradigm that allows machine learning algorithms, trained with data from the power system field. The core comprises a recurrent neural network (encoder-decoder architecture) to predict the target variable.

The targets can vary from timerseries of PV, Wind or other generators to most commonly the total energy consumption. Both, the relevant input data history and prediction horizon are arbitrarily long and customizable for any specific need.


First, clone this Repository and initialize the submodules:

git clone --recurse-submodule

or if you have already cloned the project and you are missing e.g. the open data directory for execution run:

git submodule update --init --recursive

To install all required packages first run:

pip install -r requirements.txt

On low RAM machines the option

pip install -r requirements.txt --no-cache-dir

might be necessary.

ProLoaF supports Python 3.8 and higher. For further information see Getting Started

Gettings started, Key Capabilities, Example Workflows & References

To keep all infos on what you can do with ProLoaF and how to get there, our user documentation, is the place where you'll find all answers.

Related Publications

We kindly ask all academic publications employing components of ProLoaF to cite one of the following papers:

  • G. Gürses-Tran, H. Flamme, and A. Monti, "Probabilistic Load Forecasting for Day-Ahead Congestion Mitigation," The 16th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2020, 2020-08-18 - 2020-08-21, Liège, Belgium, ISBN 978-1-7281-2822-1, [Access Online](Probabilistic Load Forecasting for Day-Ahead Congestion Mitigation)


2019-2021, Institute for Automation of Complex Power Systems, EONERC


This project is licensed to the Apache Software Foundation (ASF).

This program is free software: you can redistribute it and/or modify
it under the terms of the Apache License version 2 of the License, or
any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
Apache License for more details.

You should have received a copy of the Apache License
along with this program.  If not, see <>.

For other licensing options please consult Prof. Antonello Monti.



Institute for Automation of Complex Power Systems (ACS) EON Energy Research Center (EONERC) RWTH University Aachen, Germany

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

proloaf-0.2.0.tar.gz (59.5 kB view hashes)

Uploaded source

Built Distribution

proloaf-0.2.0-py3-none-any.whl (64.6 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page