Forecasting Solar Irradiance using Hybrid Stationary Wavelet Transform- Quaternion Valued Neural Network with a Softplus AMSGrad Learning Algorithm

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Efficient use of solar energy requires reliable forecasting values. In this paper, we propose a forecasting system combining the stationary wavelet transform and quaternion-valued neural networks (SWT-QVNN) and use it to forecast solar irradiance. In addition, a quaternion variant of the softplus AMSGrad learning algorithm is developed and used in optimizing the developed neural network. The proposed system was tested using irradiance data from two cities Abu Dhabi, UAE, and Tamanrasset, Algeria. It did reduce Root Mean Squared Error (RMSE) by more than 60% compared to the baseline model that uses a real-valued neural network.

Original languageBritish English
Title of host publication2022 IEEE International Conference on Power Systems Technology
Subtitle of host publicationEmbracing Advanced Technology in Power and Energy Systems for Sustainable Development, POWERCON 2022
EditorsHaroon Rashid
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665417754
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Power Systems Technology, POWERCON 2022 - Kuala Lumpur, Malaysia
Duration: 12 Sep 202214 Sep 2022

Publication series

Name2022 IEEE International Conference on Power Systems Technology: Embracing Advanced Technology in Power and Energy Systems for Sustainable Development, POWERCON 2022

Conference

Conference2022 IEEE International Conference on Power Systems Technology, POWERCON 2022
Country/TerritoryMalaysia
CityKuala Lumpur
Period12/09/2214/09/22

Keywords

  • AMSGrad algorithm
  • Forecasting
  • Quaternion Neural Network
  • Solar irradiance

Fingerprint

Dive into the research topics of 'Forecasting Solar Irradiance using Hybrid Stationary Wavelet Transform- Quaternion Valued Neural Network with a Softplus AMSGrad Learning Algorithm'. Together they form a unique fingerprint.

Cite this