LoadMind provides state-of-the-art accuracy electricity load (consumption) forecasts for asset owners, power traders and system operators. LoadMind combines both weather data (such as temperature, cloud coverage, wind speed, etc.) from numerical weather prediction (NWP) models, satellites and ground measurements and consumption behavior related to variations over day/night, week, seasons and holidays with advanced machine learning methods that learn both local and global weather patterns. Processing of spatio-temporal information allows LoadMind to produce forecast for individual assets and distributed region or country aggregation level electricity consumption with state-of-the-art accuracy. Compared to traditional forecasting methods, LoadMind achieves a significant reduction in forecast errors, which lowers the imbalance costs from trading operations and helps improve system stability. The specific asset characteristics are modeled implicitly by the machine learning method. Therefore, LoadMind does not rely on static data, such as building isolation and power grid layout but learns the influence of these parameters from observed data. This results in higher accuracy than compared to physical models where uncertainty regarding static variables is translated to the forecast.
LoadMind continuously incorporates the latest weather and electricity consumption information to provide frequent forecast updates. In addition, performance on the first few hours ahead can be further reduced by adding live electricity consumption data, although this is not a requirement. Through probabilistic power forecasts, the forecast uncertainty assessed. This gives higher degree of preparation for power market operations and allows for optimized intraday balancing of electricity consumption. LoadMind is provided as a cloud service and thus requires no installation, it can be easily integrated with your current system setup through API or SFTP-server.