ARTIFICIAL NEURAL NETWORKS MODELS IN ENERGY FORECASTING – A REVIEW

Apstrakt

Many studies have focused on using artificial intelligence in energy systems. The aim of this review paper is providing the insides in methods based on Artificial intelligence used for buildings models in energy forecasting. This paper also provides a compregensive review of the advantages and disadvantages of available methods as well as the input parmeters used for modelling these models. This paper focuses on using Artificial Neural Networks (ANNs) for forecasting energy production in renewable energy sources, especially in hydropwer and photovoltaic sistems. The archicetures of ANN-s have also been briefly discussed, such as Multilayer perceptron neural network. Also, some statistical criteria that have been used to assess the performance of ANN modelling have been introduced.