An interactive tool to browse, detect and localize appliance patterns in electricity consumption time series
DeviceScope is a Python web interactive application that facilitates the understanding of aggregate smart meter data (i.e., time series of electricity consumption). It enables the detection and localization of individual appliance patterns within a given time period using a weakly supervised approach: the solutions used inside our system required only the knowledge of the existence of an appliance in a household to be trained. This substantially reduces the number of labels needed and, therefore, the manual effort required, as it obviates the need to monitor each appliance in a house with a specific meter to obtain ground-truth individual appliance data.
- Adrien Petralia, EDF R&D, Université Paris Cité
- Paul Boniol, Inria, ENS, PSL University, CNRS
- Philippe Charpentier, EDF R&D
- Themis Palpanas, Université Paris Cité, IUF
Step 1: Clone this repository using git and change into its root directory.
git clone https://github.com/adrienpetralia/devicescope.git
cd devicescope/
Step 2: Create and activate a conda environment and install the dependencies.
conda create -n devicescope python=3.8
conda activate devicescope
pip install -r requirements.txt
Step 3: You can use our tool in two different ways:
- Access online: https://devicescope.streamlit.app/
- Run locally (preferable for faster interaction). To do so, run the following command:
streamlit run Hello.py
Work supported by EDF R&D and ANRT French program.