Prediction of solar irradiance using grey Wolf optimizer least square support vector machine

Zuhaila Mat Yasin, Nur Ashida Salim, Nur Fadilah Ab Aziz, Hasmaini Mohamad, Norfishah Ab Wahab

Research output: Contribution to journalArticle

2 Citations (Scopus)


Prediction of solar irradiance is important for minimizing energy costs and providing high power quality in a photovoltaic (PV) system. This paper proposes a new technique for prediction of hourly-ahead solar irradiance namely Grey Wolf Optimizer Least Square Support Vector Machine (GWO-LSSVM). Least Squares Support Vector Machine (LSSVM) has strong ability to learn a complex nonlinear problems. In GWO-LSSVM, the parameters of LSSVM are optimized using Grey Wolf Optimizer (GWO). GWO algorithm is derived based on the hierarchy of leadership and the grey wolf hunting mechanism in nature. The main step of the grey wolf hunting mechanism are hunting, searching, encircling, and attacking the prey. The model has four input vectors: time, relative humidity, wind speed and ambient temperature. Mean Absolute Performance Error (MAPE) is used to measure the prediction performance. Comparative study also carried out using LSSVM and Particle Swarm Optimizer-Least Square Support Vector Machine (PSO-LSSVM). The results showed that GWO-LSSVM predicts more accurate than other techniques.

Original languageEnglish
Pages (from-to)10-17
Number of pages8
JournalIndonesian Journal of Electrical Engineering and Computer Science
Issue number1
Publication statusPublished - 01 Jan 2019

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications
  • Control and Optimization
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Prediction of solar irradiance using grey Wolf optimizer least square support vector machine'. Together they form a unique fingerprint.

  • Cite this