文章基本信息

标题：HYBRID SOLUTION FOR WIND TURBINES POWER CURVE MODELING FOUNDED ON CASE BASED REASONING, MULTI-AGENT SYSTEM AND THE K-NEAREST NEIGHBORS ALGORITHM
本地全文：下载
作者：MOHAMED KOUISSI ; EL MOKHTAR EN-NAIMI ; ABDELHAMID ZOUHAIR 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2021
卷号：99
期号：12
语种：English
出版社：Journal of Theoretical and Applied
摘要：The aim of the wind turbines power curve is to represent the performance of a wind turbine, aids in wind power assessment and also helps in wind power forecasting. The wind turbines power curve captures the nonlinear relationship between wind speed and output power. In this paper, we present a hybrid approach of wind turbines power curve modeling based on Case Based Reasoning approach, multi agent system and a machine learning algorithm, which is the K-Nearest Neighbors method to propose a new adapted wind turbines power curve for our target case based on the wind turbines power curve of similar wind turbines. The K-Nearest Neighbors algorithm is used in the retrieve step of the case based reasoning cycle to search for similar wind turbines based on their characteristics. These wind turbines are then classified and sorted on the basis of features similarity measure. Then, a new wind turbines power curve of the target case is proposed based on the experiences of similar cases.
关键词：Case Based Reasoning (CBR);Multi Agents System (MAS);Wind Turbines Power Curve (WTPC);K-Nearest Neighbors algorithm (KNN);Modeling