Short-term load forecasting by using a combined method of convolutional neural networks and fuzzy time series

• Main Authors: Sadaei, Hossein Javedani, de Lima e Silva, Petrônio Cândido, Guimarães, Frederico Gadelha, Lee, Muhammad Hisyam
• Format: Article
• Published: Elsevier Ltd. 2019
• Subjects: QA Mathematics
• Online Access: http://eprints.utm.my/id/eprint/87565/; http://dx.doi.org/10.1016/j.energy.2019.03.081
• Institution: Universiti Teknologi Malaysia

We propose a combined method that is based on the fuzzy time series (FTS) and convolutional neural networks (CNN) for short-term load forecasting (STLF). Accordingly, in the proposed method, multivariate time series data which include hourly load data, hourly temperature time series and fuzzified version of load time series, was converted into multi-channel images to be fed to a proposed deep learning CNN model with proper architecture. By using images which have been created from the sequenced values of multivariate time series, the proposed CNN model could determine and extract related important parameters, in an implicit and automatic way, without any need for human interaction and expert knowledge, and all by itself. By following this strategy, it was shown how employing the proposed method is easier than some traditional STLF models. Therefore it could be seen as one of the big difference between the proposed method and some state-of-the-art methodologies of STLF. Moreover, using fuzzy logic had great contribution to control over-fitting by expressing one dimension of time series by a fuzzy space, in a spectrum, and a shadow instead of presenting it with exact numbers. Various experiments on test data-sets support the efficiency of the proposed method.