A novel combined model for probabilistic load forecasting based on deep learning and improved optimizer

As the transitions of the power industry to decarburization and distributed energy systems, the future uncertainty information of electric load is becoming essential in power systems planning and operation. However, a great number of studies focus on point forecasting, which only provides the expected value at each time step and it cannot provide uncertainty information. This paper proposed a novel probabilistic load forecasting model by combining quantile regression (QR) with a hybrid model to improve smart grid reliability. In addition, to further improve accuracy and solve the problem that the optimal model is not unique, we propose a new combined probabilistic forecasting model (CPFM). The CPFM employs the traditional statistical models and QR-machine learning models as alternative models; several alternative models with the best performance are combined through the improved multi-objective optimizer to obtain the final forecasting results. The ISO New England data is modeled as a case study to verify the effectiveness of the proposed CPFM. The comparative study includes 13 models, and the results show that the proposed CPFM has better performance in reliability, resolution, and sharpness.