Services

WindML Full Time Series
☸ Traditional Measure-Correlate-Predict (MCP) methods focus mainly on long term average wind speed. However, frequency distribution/time series are often linearly scaled from measured data period and do not fully capture long term variations (>=20 years).
☸ Our machine learning (ML) powered MCP solution provides long term time series output which greatly improves both point predictions and distributional accuracy.
☸ We provide tailored solution for hybrid optimization: Long-term subhourly time series

Climate Change Assessment
✱ Traditional wind resource assessments (WRA) are based on historical wind data and do not fully incorporate future climate change at wind project location.
✱ We utilize climate model predictions such as CMIP6 model scenarios to estimate effect of climate change on wind speed and temperature on project-specific basis.
✱ Effect of climate change is incorporated in the form of bias correction to historical long term time series.

Hybrid Optimization
◆ We offer numerical optimization service in which total project size and capacity mix for wind/solar/storage combinations are optimized to meet prescribed power load demand and to have lowest LCoE simultaneously.
◆ Optimization can be performed at subhourly intervals based on client specific requirements (either for typical meteorological year or full long term data period).
◆ We provide tailored solutions for tender requirements such as SECI/RTC/FDRE/Peak Power

Flagship Services

WindML Full Time Series

Climate Change Assessment

Hybrid Optimization