Fsight provides today’s smart-metered utilities industry with an evolving software platform that offers solutions in the areas of distributed grid forecasting and customer segmentation using the most advanced AI and machine learning technologies. Fsight’s easy-to-use Big-data SaaS platform and scalable architecture help unlock new, custom revenue streams by predicting consumer behavior, leveraging consumption data for dynamic market segmentation, improving campaigns, and discovering futurable offerings. The patent-pending technology uses over 30 machine learning models, weighing both algorithmic analysis and live expert input, such as information about real-life events that might impact energy use within any day or hour. It constantly improves itself using feedback loop, incorporates new data within seconds, supports both short-term (hours to a week) and long-term (up to several years) forecasting within the same system – all to be able to provide energy suppliers with unrivaled predictive data accuracy. It also offers the ability to benchmark its forecasts against any other forecasting model, and outline the strengths and weaknesses of each approach. In its two years of operation, Fsight has rolled out its platform to over 20 customers globally. Led by a team of successful entrepreneurs, data scientists, and machine learning researchers, Fsight is a fast growing, early stage startup with offices in Austria and Israel. To learn more, please visit: https://www.fsight.io/
Field-proven machine learning and artificial intelligence capabilities provide an automatically tailored prediction model for each building and asset to create bottom-up predictions on a per-minute basis. A unique data recovery system supports both smart meters and legacy meters, and Big Data infrastructure scales up to a 1-second data logging interval.
Heuristic tailor-made algorithm for optimal strategy search takes into account price fluctuations, weather conditions, and available consumption flexibility. The system employs statistical techniques to handle different possible scenarios of nano-grid, micro-grid and Virtual Power Plant (VPP) level energy balance. The optimization engine supports multi-goal optimization of cost, emissions, and convenience as well as planning tools for the most efficient DER deployment.
An autonomous trading layer allows buying and selling behind-the-meter energy at optimal prices through traditional Peer-to-Grid trading or Blockchain-based Peer-to-Peer trading. The system integrates local retail time-of-use tariffs to minimize energy costs or Peer-to-Peer energy prices to maximize energy trading value.