A Predictive Stress-Strength Model Addressing the Dynamic Transformer Rating

Abstract

Operating distribution networks by the dynamic thermal rating of lines and transformers allows for reaching the operational excellence and for optimizing the power delivery. However, due to the intrinsic uncertainties involved in the dynamic thermal rating estimation, the problem should be framed within a probabilistic environment. This paper focuses on distribution transformers; a novel non-parametric stress-strength model is presented in order to estimate the probability of the stress (i.e., the transformer loading current) to be smaller than the strength (i.e., the dynamic transformer rating). The model is based on a logistic regression of the companion binomial regression problem. Numerical experiments based on actual data collected at an Italian industrial facility are presented to estimate the performances of the stress-strength model.