This work is developed by Intelligent Sustainable Grid Lab @ KTH.

a unifying deep learning framework for short-term load forecasting

Official repository for CIC-PolyglOT, a data exchange layer for communicating with multiple OT protocols.

Turta LoRa HAT Libraries and Samples

Sistema Multiagente de Recomposição Automática desenvolvido com PADE

Offline local smartgrid transactions using LPWAN technology

Codesys code running in the switch container PLC

Jorge Fernandez's Code to compute the power flow of an electrical network with the fixed point method

Python toolkit for automating smartgrid data model project creation. Features code generation for model definitions, enums, XML data, converter methods, and server classes. Includes a CMS with CRUD operations for managing project specifications.

This project uses a Deep Neural Network (DNN) to forecast household appliance energy consumptionn based on the UCI Energy Dataset. The goal is to achieve a low Mean Squared Error (MSE) and capture realistic daily load patterns such as the evening energy peak between 17:00-20:00 when most families return home from work or other engagements.

DDS8558 smart meter Python module with examples.

achine learning–based load forecasting for smart grids using K-Nearest Neighbors (KNN) and Gradient Boosting Regressor (GBR), featuring data preprocessing, feature engineering, model comparison, and error analysis on historical energy demand data.