A novel electrical net-load forecasting model based on deep neural networks and wavelet transform integration

Mohammadali Alipour, Jamshid Aghaei*, Mohammadali Norouzi, Taher Niknam, Sattar Hashemi, Matti Lehtonen

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

17 Citations (Scopus)


The increasing growth of renewable energy resources (RESs) in microgrids and the uncertainty associated with their generation have led to problems in the management of smart active distribution networks. One of the main challenges in the planning for the operation of renewable power systems is net electrical load forecasting, therefore, increasing the accuracy of net-load forecasting is a vital issue. In this study, a deep neural network model is used to forecast the net-load. The structure of the deep neural network used in the proposed forecasting model has been constituted by several autoencoders and a cascade neural network. The net-load forecasting has been done in the presence of uncertainties arising from wind and photovoltaic (PV) generation and electrical load consumption. To improve the net-load forecasting precision, the wavelet transform has been applied to the inputs of the proposed model. The net-load forecast in different scenarios is conducted on an open dataset from 37 central European countries, from the perspective of different types of forecasting strategies and changes in the neural network architecture. The simulation results significantly confirm the accuracy of the proposed forecasting model by different indices.

Original languageEnglish
Article number118106
Number of pages16
Publication statusPublished - 15 Aug 2020
MoE publication typeA1 Journal article-refereed


  • Autoencoder
  • Cascade neural network
  • Deep neural network
  • Net-load forecasting strategies
  • Renewable power system
  • Wavelet transform


Dive into the research topics of 'A novel electrical net-load forecasting model based on deep neural networks and wavelet transform integration'. Together they form a unique fingerprint.

Cite this