Participatory learning in the neurofuzzy short-term load forecasting

摘要: This paper presents a new approach for shortterm load forecasting using the participatory learning paradigm. Participatory paradigm is training procedure that follows human mechanism adopting an acceptance to determine which observation used based upon its compatibility with current beliefs. Here, train class of hybrid neurofuzzy network forecast 24-h daily energy consumption series electrical operation unit located at Southeast region Brazil. Experimental results show requires less computational effort, more robust, and efficient than alternative neural methods. The particularly when data reflects anomalous conditions or contains spurious measurements. Comparisons approaches suggested in literature are also included effectiveness learning.