Nonparametric End-to-End Probabilistic Forecasting of Distributed Generation Outputs Considering Missing Data Imputation
This addresses forecasting challenges for distributed renewable energy systems, but appears incremental as it combines existing techniques (nonparametric methods and end-to-end training).
The paper tackles probabilistic forecasting of distributed renewable generation outputs with missing data by introducing a nonparametric end-to-end method combining LSTM networks with iterative imputation and training, achieving superior performance compared to existing alternatives.
In this paper, we introduce a nonparametric end-to-end method for probabilistic forecasting of distributed renewable generation outputs while including missing data imputation. Firstly, we employ a nonparametric probabilistic forecast model utilizing the long short-term memory (LSTM) network to model the probability distributions of distributed renewable generations' outputs. Secondly, we design an end-to-end training process that includes missing data imputation through iterative imputation and iterative loss-based training procedures. This two-step modeling approach effectively combines the strengths of the nonparametric method with the end-to-end approach. Consequently, our approach demonstrates exceptional capabilities in probabilistic forecasting for the outputs of distributed renewable generations while effectively handling missing values. Simulation results confirm the superior performance of our approach compared to existing alternatives.