Makani was a project to develop a commercial-scale airborne wind turbine, culminating in a flight test of the Makani M600 off the coast of Norway. All Makani software has now been open-sourced. This repository contains the working Makani flight simulator, controller (autopilot), visualizer, and command center flight monitoring tools. Additionally, almost all avionics firmware is also included, albeit potentially not in a buildable state, due to the removal of some third-party proprietary code. We hope that this code will be inspirational and useful to the kite-based windpower and wider communities.

Main repository for the NREL-supported OpenFAST whole-turbine and FAST.Farm wind farm simulation codes.

A curated list of open wind turbine data sets and corresponding code

python scripts for wind turbine data cleaning

Wind Power Prediction with ECMWF Data as Input using Statistical Learning

Repository containing OpenAFPM wind turbine CAD model.

A Open-Source Horizontal axis-Aero-Wave-Turbulence Coupling(HawtC) Tool for dynamic simulation of floating offshore wind turbine(FOWT).And supports the dynamic coupling simulation of the tuned mass damper and tuned mass inertia damper for wind turbine blades and towers

Data portal for NREL's Renewable Energy Potential Model.

This repository is dedicated to wind turbines power curve modeling, from data cleansing to the actual power curve modeling with various approches.

Probabilistic Wind Power Forecasting with R

The potential for repowering US wind turbines

Comparative analysis of LSTM, XGBoost, Random Forest, SVR, and SARIMAX for wind power prediction using real-world turbine data. Covers preprocessing, time series modeling, and performance benchmarking.

Interactive maps of new windmills in Bayern and Germany

XGBoost-based wind power forecasting with multi-height meteorological data

Code for reproducing results of extended vertical wind profile–based farm-scale power forecasting study.

Real meteorological data (temperature, pressure, precipitation) were obtained from İSKİ. Eddy diffusivity, Monin-Obukhov length, and turbulence intensity were calculated from existing data and added to the dataset. Using 289,000 data points and 27 features, RF, SVM, LSTM, and CNN models were developed. LSTM achieved 98%, CNN 91% accuracy.

Results of the study on the wind power potential in Bulgaria, Hungary and Romania (funded by European Climate Foundation, ECF)

Mixture of Experts for Day-ahead Wind Power Time-series Forecasting