Control and automate hybrid renewable energy assets with real-time, data-driven recommendations for enhanced operational decision-making.

As the drive to decarbonization accelerates adoption of renewable energy sources, organizations are seeking new and smarter ways to effectively manage renewable assets. Artificial intelligence (AI) innovations are becoming increasingly critical to advancing the energy transition, giving rise to compelling new use cases for managing and automating renewable energy assets. One such example is CGI’s “hybridization model” which uses AI to evaluate, control and recommend actions to optimize the performance of hybrid renewable energy assets and enable timely, strategic operational decisions.

The hybridization model involves constructing supervised learning models using historical data and characteristics of wind turbines, photovoltaic inverters, batteries and electrolyzers (green hydrogen). The result is a robust system that can recommend and automate the source and destination of energy to be produced in a hybrid power plant according to various possible criteria (e.g., economic, regulatory, network management considerations).

With hybridization, renewable energy producers can take advantage of the seasonal and hourly complementarity of various types of energy to better utilize the grid, while at the same time evaluating the exploitation of alternative energy sources and the use of green hydrogen storage and production solutions.

Additionally, plant owners can evaluate different criteria influencing energy production and dispatch, including weather (wind and irradiance), energy prices, planned interventions and asset reliability.

The hybridization AI learning models calculate forecasts and recommendations one day ahead, plus monitor and adjust forecasts in real-time, with alerts and recommendations. This means organizations can effectively integrate recommendations in the control of hybrid plants in a timely, reliable manner.

Key benefits of hybridization:

  • Optimize grid utilization with data-led decision-making to determine the best renewable energy source to use for different situations, optimizing grid capacity.
  • Control energy loss by calculating recommendations to decide the most economic renewable asset for given scenarios.
  • Improve performance via system insights that provide greater predictability for the day-to-day control and operation of hybrid assets.

The hybridization model collects and ingests data from the field through CGI’s Renewable Management System (RMS) gateway, including raw data, ten-minutes data and KPIs, budgets and metadata. Ultimately, the aim is to obtain up-to-date production, asset status and faults information.

Increasingly, AI is proving to be transformative in helping to forecast and provide accurate, insights-led knowledge of renewable energy at a specific location, at a given time. Hybridization builds upon that operational transformation and enables decision-makers to determine the best type of renewable energy to use or exploit in order to improve efficiency, reduce downtime and optimize performance.