Researchers at the Department of Energy’s Oak Ridge National Laboratory (ORNL) have developed a dynamic modeling method that uses machine learning to provide accurate simulations of grid behavior and maintains a black box approach.
The technique does not require details about the proprietary technology inside the equipment, like an inverter in this case. Engineers incorporated the new modeling capability into an open-source software tool and demonstrated its success with different scenarios and inverter brands.
The ORNL model uses a deep learning algorithm to deal with challenges. Researchers trained the model using test cases reflecting changes in power flow sudden shifts in voltage. The team conducted a simulation based on a specific vendor’s equipment, repeating the process with data from another vendor to compare results for consistency.
The team found that their black box model with free open-source software produced results with an average error rate below 5% over a range of operating conditions. This exceeded industry standards for grid system planning and operation, design testing and field deployment. The model worked 10 to 20 times faster as compared to more energy-intensive conventional methods.
The method will allow producers of power electronics to easily evaluate the role of new controls and protection designs to function in full power distribution systems. The insight is expected to minimize product development timelines to help new technologies reach the grid faster.
The modeling capability is also anticipated to build utility confidence in diversifying energy sources to enhance the overall power resilience and reliability. The black box model is part of a larger project, led by Pacific Northwest National Laboratory (PNNL), for improving models showing the impact of fleeting changes in voltage or current on full-sized power distribution systems.
For the black box modeling portion, PNNL contributed the open-source software and vendor data and will test the model in a section of the grid operated by Commonwealth Edison, or ComEd.
