A quantum computing-based deep learning framework for power system fault diagnosis has been proposed by Cornell researchers.
The proposal in essence brings an artificial intelligence approach combining techniques for modelling multi-dimensional datasets with other machine learning techniques to overcome the complexities of the latter alone in quantum computing methodologies for power systems.
In a forthcoming paper in the December 1 issue of Applied Energy, the researchers state that the framework was tested on a simulated electrical power system with 30 buses and wide variations of substation and transmission line faults to test its applicability, efficiency and generalization capabilities.
There is demonstrated high computational efficiency in terms of computational effort required and quality of diagnosis performance over classical training methods. In addition, superior and reliable fault diagnosis performance with faster response time was achieved over state-of-the-art pattern recognition methods.
“Energy power system failures are an old problem and we are still using classic computational methods to resolve them,” says Fengqi You, Professor in Energy Systems Engineering in the College of Engineering at Cornell University, who led the research with doctoral student Akshay Ajagekar.
“Today’s power systems can benefit from AI and the computational power of quantum computing, so power systems can be stable and reliable.”
The researchers found that the quantum computing-based deep-learning approach can be scaled efficiently for quick diagnosis in larger power systems without loss of performance.
They believe that quantum computing and artificial intelligence can save most of the system failures, with the financial and other benefits that would ensue for both utilities and their customers.
The research used resources of the US Department of Energy’s Oak Ridge Leadership Computing Facility.
It follows an earlier work on quantum computing assisted deep learning for fault detection and diagnosis in industrial process systems, in which quantum computing was demonstrated to overcome the computational challenges of approaches on conventional computers.