A Data-driven Long-Term Dynamic Rating Estimating Method for Power Transformers

This paper presents a data-driven method for producing annual continuous dynamic rating of power transformers to serve the long-term planning purpose. Historically, research works on have been focused real-time/near-future system operations. There has lack oriented applications. Currently, most utility companies still rely static numbers when next few years. In response, this proposes novel and comprehensive analyze past 5-year temperature, loading load composition data existing in region. Based such forecasted area composition, future transformer profile can be constructed by using Gaussian Mixture Model. Then according IEEE std. C57.91-2011, thermal aging model established incorporate temperature profiles. As result, profiles under different scenarios determined. The reflect overloading risk much more realistic granular way, which significantly improve accuracy planning. A real application example Canada presented demonstrate practicality usefulness method.