Hybrid Approach for Wind Turbines Power Curve Modeling Founded on Multi-Agent System and Two Machine Learning Algorithms, K-Means Method and the K-Nearest Neighbors, in the Retrieve Phase of the Dynamic Case Based Reasoning

Authors

  • Mohamed Kouissi LIST Laboratory, Faculty of Sciences and Technologies, Abdelmalek Essaâdi University (UAE), Tetouan, Morocco
  • El Mokhtar En-Naimi LIST Laboratory, Faculty of Sciences and Technologies, Abdelmalek Essaâdi University (UAE), Tetouan, Morocco
  • Abdelhamid Zouhair LIST Laboratory, Faculty of Sciences and Technologies, Abdelmalek Essaâdi University (UAE), Tetouan, Morocco

DOI:

https://doi.org/10.3991/ijoe.v18i06.29565

Keywords:

Dynamic Case Based Reasoning (DCBR), Multi Agents System (MAS), Wind Turbines Power Curve (WTPC), Machine Learning Algorithms, K-Means method, K-Nearest Neighbors algorithm (KNN)

Abstract


Wind turbine power curve (WTPC) plays an important role for energy assessment, power forecasting and condition monitoring. The WTPC captures the nonlinear relationship between wind speed and output power. Many modeling approaches have been proposed by researches to improve the WTPC model performance. In this paper, we present a hybrid approach of wind turbines power curve modeling based on Case Based Reasoning approach, multi agent system, the K-Means unsupervised machine learning method, and then the supervised machine learning algorithm, which is the K-Nearest Neighbors KNN method. The both of the Machine Learning algorithms, K-means and KNN, are used in the retrieve step of the Dynamic Case Based Reasoning (DCBR) cycle to facilitate the search of wind turbines with similar characteristics to our target case. These wind turbines are first grouped into homogeneous classes and then sorted on the basis of a feature similarity measure using the K-Nearest Neighbors supervised machine learning method. Finally, a set of WTPC with similar characteristics of the target case are proposed.

Author Biographies

Mohamed Kouissi, LIST Laboratory, Faculty of Sciences and Technologies, Abdelmalek Essaâdi University (UAE), Tetouan, Morocco

Mohamed Kouissi Is a PhD student in List (Laboratoire d’informatique, Systèmes et Télécommunications) laboratory, Faculty of Sciences and Technologies, Tangier, Morocco. He is an Engineer in computer Science and Specialized in software mobile development. Laureate of Tangier National School of Applied Sciences in 2011. He had also, more than 10 years of experience in developing mobile applications. In addition, He is performed in a Lead developer role for the Android project in a multinational company. The research topics of interest are Multi-Agent Systems (MAS), Case Based Reasonning (CBR), Machine Learning, Smart cities, eLearning…etc.

El Mokhtar En-Naimi, LIST Laboratory, Faculty of Sciences and Technologies, Abdelmalek Essaâdi University (UAE), Tetouan, Morocco

Dr. El Mokhtar EN-NAIMI is a Full Professor in the University of Abdelmalek Essaâdi (UAE), Faculty of Sciences and Technologies of Tangier (FSTT), Department of Computer Sciences. (He was Temporary Professor: from 1999 to 2003 and Permanent Professor: since 2003/2004 until Now. Actually, He is a Full Professor in UAE, FST of Tangier). He was a Head of Computer Sciences Department, since October 2016 until the end of December 2020. He was responsible for a Licence of Science and Technology, LST Computer Engineering (“Licence LST-GI”), from January 2012 to October 2016. He is also a founding member of the Laboratory LIST (Laboratoire d'Informatique, Systèmes et Télécommunications), the University of Abdelmalek Essaâdi, FST of Tangier, Morocco. He is also an Expert Evaluator with the ANEAQ, since the academic year 2016/2017 until now, that an Expert of the Private Establishments belonging to the territory of the UAE and also an Expert of the Initial or Fundamental Formations and Formations Continuous at the Ministry of Higher Education, Scientific Research and Executive Training and also at the UAE University and the FST Tangier since 2012/2013 until Now. He is an Author/Co-Authors of several Articles, published in The International Journals in Computer Sciences, in particular, in Multi-Agent Systems (MAS), Cases Based Reasoning (CBR), Artificial Intelligent (AI), Machine Learning (ML), Deep Learning (DL), eLearning, MOOC/SPOC, Big DATA, Data-mining, Wireless Sensor Network, VANet, MANet, Smart City, …, etc. He is also Director of several Doctoral Theses in Computer Sciences. In addition, he is an associate member of the ISCN - Institute of Complex Systems in Normandy, the University of the Havre, France, since 2009 until Now

Abdelhamid Zouhair, LIST Laboratory, Faculty of Sciences and Technologies, Abdelmalek Essaâdi University (UAE), Tetouan, Morocco

Dr. Zouhair Abdelhamid is a Professor in the University of AbdelmalekEssaâdi, Faculty of Sciences and Technologies of Tangier, Department of Computer Science, since mars 2020. Since March 2012-10 May 2016: Quality Project Manager, Geographic Information System and Computer head at the Urban Agency of Tetouan, Ministry of Urban Planning and Development. August 2011- March 2012: Senior Executive at the Urban Agency of Tetouan. July 2003- September 2008: IT Manager at Tronico Atlas, Tangier, Morocco. PhD in Computer Science at the University of The Havre, laboratory LITIS, France, and at the Faculty of Sciences and Technologies of Tangier, University of Abdelmalek Essaâdi, Tangier, Morocco (cotutelle doctoral program) in October 2014. He is an author of several articles in Computer Science.

Downloads

Published

2022-05-17

How to Cite

Kouissi, M., En-Naimi, E. M., & Zouhair, A. (2022). Hybrid Approach for Wind Turbines Power Curve Modeling Founded on Multi-Agent System and Two Machine Learning Algorithms, K-Means Method and the K-Nearest Neighbors, in the Retrieve Phase of the Dynamic Case Based Reasoning. International Journal of Online and Biomedical Engineering (iJOE), 18(06), pp. 110–122. https://doi.org/10.3991/ijoe.v18i06.29565

Issue

Section

Papers