فهرست نشریات علمی دسترسی آزاد ایران

Energy commodities including both fossil fuels and renewable sources are vital for driving economic activities worldwide. Energy price forecasting is crucial for informing policy decisions and establishing mechanisms to stabilize prices in the energy market. To deal with nonlinear and complex relationships, machine learning methods can be employed for energy price forecasting. An extensive bibiliometric analysis through visualization and mapping was carried out from 1994-March 2023 in response to capturing recent applications of soft computing in energy price forecasting studies. A total of 773 documents from the WOS and Scopus databases were analyzed using bibliometrix R-Tool and VOSviewer. The results showed CHINA has the most publications in this field, with the production of 241 documents (31.2%). Six clusters were identified based on the analysis of the most frequent keywords. According to two parameters of centrality and density, 'neural network', 'electricity price forecasting', and 'forecasting' were the motor themes with the most attention in the literature. According to the analysis of word growth, the term "neural network" has experienced rapid growth throughout all periods. This suggests that neural networks have become increasingly popular and widely discussed in recent years. Secondly, there has been a simultaneous and parallel increase in the occurrence of the words "electricity price forecasting" and "forecasting" in the last few years.