Deep learning hyperparameter optimization on power transformers lifetime prediction

• Main Authors: Ningrum, Ayu Ahadi, Ansari, Rudy, Setiawan, Ichwan, Maulida, Ihdalhubbi, Marleny, Finki Dona, Saubari, Nahdi, Pebriadi, Muhammad Syahid, Windarsyah, Windarsyah, Kamarudin, Kamarudin, Gazali, Mukhaimy
• Format: Conference Proceeding
• Language: English
• Subjects: Artificial intelligence; Customers; Datasets; Deep learning; Electricity; Machine learning; Optimization; Predictions; Transformers
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0154959

Since the global pandemic has significantly impacted all aspects of human life, technology has become vital in various sectors. The more technology is used, the more we need the electricity supply. The stability of the electricity supply is an absolute thing to customers. Power Transformer is essential equipment for delivering electricity to customers. So the condition of the power transformers should be an important thing that must be considered. Deep Learning is part of artificial intelligence widely applied to facilitate human needs. Based on its role, accuracy in the prediction results will be absolute. Hyperparameter optimization is one of the important methods in the machine learning process. Errors in assigning hypermeter values can negatively affect producing predictive values. This study discusses how to optimize the prediction results of the lifetime prediction on a power transformer. With optimal prediction results, it can help electricity management companies monitor conditions. Thereby it can minimize the risk of disruption of electricity supply to customers. Models are tested and verified using a real dataset from a power transformer in several locations. The best hyperparameter for this dataset is Random Search which produces 0.0022724 for Root Mean Square Error.