Title :
Distribution transformer mid-term heavy load and overload pre-warning based on logistic regression
Author :
Ming Li ; Qin Zhou
Author_Institution :
Technol. Labs., SMIEEE, Beijing, China
fDate :
June 29 2015-July 2 2015
Abstract :
in areas with rapid economic growth, distribution transformer heavy load and overload occur frequently, which may damage the equipment and even lead to power outages. Therefore, it is critical for the utilities to know which distribution transformers are more likely to have the heavy load /overload conditions in the next year in order to facilitate asset management in distribution network. However, current load forecasting methods are not suitable for handling the large amount of distribution transformers with a high variety of load patterns. Utilizing real data from a utility, a mid-term pre-warning analytics model has been developed to provide the heavy load and overload probabilities in the next year for each distribution transformer in an area. The mid-term pre-warning models have been implemented in a major utility in China.
Keywords :
asset management; distribution networks; load forecasting; power transformers; probability; regression analysis; asset management; distribution network; distribution transformer; heavy load conditions; heavy load pre-warning; load forecasting methods; load patterns; logistic regression; mid-term pre-warning analytics model; overload conditions; overload pre-warning; power outages; Data models; Load modeling; Loading; Logistics; Predictive models; Testing; Training; Distribution Transformer; Logistic Regression; Overload; Pre-warning;
Conference_Titel :
PowerTech, 2015 IEEE Eindhoven
Conference_Location :
Eindhoven
DOI :
10.1109/PTC.2015.7232418