Prediction of Fiscal Decentralization Considerring Energy Consumption and Environmental Effects: By using Hybrid Intelligent Models Optimization Algorithms

Abstract

ABSTRACT: ABSTRACT: :Fiscal decentralization refers to the transfer of responsibility and authority of revenue and spending decisions from the central government to lower levels. In recent years, with the increase in energy consumption, global warming, carbon emissions, and climate change, the issue of fiscal decentralization and its environmental effects has received attention. Because fiscal decentralization has an important effect on promoting clean energy sources, reducing energy consumption and reducing carbon emissions. In the present study, Hybrid intelligent models have been used to developed to predict and analyze the effect of fiscal decentralization from two dimensions of expenditure and revenue on energy consumption and its environmental environment by combining particle swarm optimization algorithms, genetics and neural network. Controlled optimization algorithms enhance all prediction steps. For this purpose, seasonal data was used during the period 1996-2022. According to the research results, resilient backpropagation neural network in predicting revenue decentralization and Scaled conjugate gradient backpropagation neural network has a high power in predicting expenditure decentralization in the country. Also, the value of R statistic, which indicates the goodness of fit of the model, has the highest value for the revenue decentralization variable compared to the expenditure decentralization, and this indicates the better performance of the revenue decentralization model than the expenditure decentralization. The results of the combination optimizer model (GPA) and the neural simulation model (GAPSO) in predicting the decentralization of expenditure and revenue showed that the decentralization of revenue had the best performance compared to the model of decentralization of expenditure. a

Keywords

• fiscal decentralization
• artificial neural network
• energy consumption