Transformer Oil Temperature Prediction Based on Long and Short-term Memory Networks

Abstract

In terms of transformer oil temperature prediction, it has been a challenge to effectively predict oil temperature by using time series data. In this paper, we focus on the problem of predicting transformer oil temperature to accurately get the running state of transformer. Firstly, we analyze the correlation between several data and the oil temperature, and then the data with the higher correlation were selected for the experiment. Secondly, we make predictions via the multi-layer perceptron and the LSTM networks. Finally, we can learn that LSTM networks has better performance than the multi-layer perceptron via the comparison experiment. Compared to the existing prediction strategies, the LSTM networks can also get better results and make more effective and efficient prediction.