A Comparative Analysis of Deep Learning Models for Short-Term Load Forecasting

Electric utility companies use short term load forecasting for day ahead operations to maintain the balance between generation and anticipated load. In addition, with the advancement of smart grid technology the need for short term load forecasting is even more significant, to plan demand side management, integrate electric vehicles and other renewable energy resources such as offshore wind energy, solar energy. Load forecasting can be done using statistical methods and artificial intelligence models. The later technique is more accurate and powerful and therefore researchers have and worked on its improvement using different models especially in the last two decades. To get the best possible match between original load values and anticipated values, four DL models long short-term memory, gated recurrent unit, hybrid CNN-LSTM and hybrid CNN-GRU have been studied in the paper. The objective of the study is to find out the best DL model by comparing them on three different publicly available datasets and it is observed that the LSTM and GRU models are effective on simple and small datasets while hybrid models are performing well in complex and large datasets.