Daily maximum load forecasting of consecutive national holidays using OSELM-based multi-agents system with weighted average strategy

• Main Authors: Yap K.S., Yap H.J.
• Other Authors: 24448864400
• Format: Article
• Published: 2023
• Subjects: Gradient descent; Load forecasting; Multi-Agent System; Online Sequential Extreme Learning Machine; Weighted average; E-learning; Forecasting; Learning systems; Multi agent systems; Neural networks; Statistical methods; Data regression; Electrical load forecasting; Final decision; Gradient Descent method; Individual agent; Malaysia; Maximum load; Multi-agents systems; Online sequential extreme learning machine; Pattern classification problems; Weighted averages; article; correlation coefficient; data analysis; forecasting; intermethod comparison; learning algorithm; machine learning; mathematical model; online sequential extreme learning machine; priority journal; regression analysis; Electric load forecasting

In the previous research, a Multi-Agent System based on Online Sequential Extreme Learning Machine (OSELM) neural network and Bayesian Formalism (MAS-OSELM-BF) has been introduced for solving pattern classification problems. However this model is incapable of handling regression tasks. In this article, a new OSELM-based multi-agent system with weighted average strategy (MAS-OSELM-WA) is introduced for solving data regression tasks. A MAS-OSELM-WA consists of several individual OSELM (individual agent) and the final decision (parent agent). The outputs of the individual agents are sent to the parent agent for a final decision whereby the coefficients of parent agent are computed by a gradient descent method. The effectiveness of the MAS-OSELM-WA is evaluated by an electrical load forecasting problem in Malaysia for a month with consequent national holidays (i.e., during the month of Hari Raya-Malay New Year of Malaysia). The results demonstrated that the MAS-OSELM-WA is able to produce good performance as compared with the other approaches. � 2011 Elsevier B.V.