Get access

An evolutionary-based adaptive neuro-fuzzy inference system for intelligent short-term load forecasting



The continuing growth in size and complexity of electric power systems requires the development of applicable load forecasting models to estimate the future electrical energy demands accurately. This paper presents a novel load forecasting approach called genetic-based adaptive neuro-fuzzy inference system (GBANFIS) to construct short-term load forecasting expert systems and controllers. At the first stage, all records of data are searched by a novel genetic algorithm (GA) to find the most suitable feature of inputs to construct the model. Then, determined inputs are fed into the adaptive neuro-fuzzy inference system to evolve the initial knowledge-base of the expert system. Finally, the initial knowledge-base is searched by another robust GA to induce a better cooperation among the rules by rule weight derivation and rule selection mechanisms. We show the superiority and applicability of our approach by applying it to the Iranian monthly electrical energy demand problem and comparing it with the most frequently adopted approaches in this field. Results indicate that GBANFIS outperforms its rival approaches and is a promising tool for dealing with short-term load forecasting problems.