Temporal Convolutional Network applied for Forecasting Individual Monthly Electric Energy Consumption

• Main Authors: Lemos, Victor H. B., Almeida, Joao D. S., Paiva, Anselmo C., Junior, Geraldo B., Silva, Aristofanes C., Neto, Stelmo M. B., Lima, Alan C. M., Cipriano, Carolina L. S., Fernandes, Eduardo C., Silva, Marcia I. A.
• Format: Conference Proceeding
• Language: English
• Subjects: Energy consumption; Forecasting; Optimization; Power systems; Statistical analysis; Task analysis; Temporal Convolutional Network; Time Series; Time series analysis
• ISSN: 2577-1655
• DOI: 10.1109/SMC42975.2020.9282960

The task of predicting energy consumption is a problem of great interest in electric power companies. A minimal error prediction is essential for identifying inconsistencies in the monthly consumption reading process. This paper presents a methodology applied to electric consumption prediction and was performed with and without a hyperparameter optimization strategy using a TCN network. We apply these strategies to indi-vidual electric consumption time series. The TCN approach had superior results when compared to SES, ARIMA, and Gradient Boosting. The results show that the proposed process obtained low efficiency with approximately 1% or less improvement than the use of no optimization. However, the TCN itself showed promising results being the best approach in many of our tests.