Lifecycle cost forecast of 110 kV power transformers based on support vector regression and gray wolf optimization

Power transformers are an important asset of power companies. To improve the economic benefits of power companies, it is of great significance to accurately predict the lifecycle cost of each power transformer. Based on the historical operating data on 83 110 kV power transformers, this paper estimates the lifecycle costs of different transformers, and then creates a dataset containing the estimated lifecycle costs and multiple features of the transformers, namely, bid price, transformer capacity, no-load loss, load loss, silicon steel cost, copper wire cost, annual failure frequency (AFF) of major repair, and AFF of minor repair. Based on the dataset, a lifecycle cost prediction model was established for power transformers, which couples grey wolf optimization (GWO) with support vector regression (SVR). The GWO-SVR model was simulated on the prepared dataset. The results show that the mean absolute percentage error (MAPE) of the model was merely 5.20% on the test set. The proposed model provides a new method for power companies to accurately predict and evaluate the lifecycle cost of power transformers. (C) 2021 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University.