Optimal Energy Management Strategy Considering Forecast Uncertainty Based on LSTM-Quantile Regression

Abstract

Due to the uncertainty of distributed energy and load in micro grid, the optimal scheduling scheme often fails in practice. This paper proposes an optimal energy management strategy considering forecast uncertainty based on LSTm-quantile regression. In this paper, firstly, load forecasting probability density method based on LSTM-quantile regression was proposed to describe the uncertainty of Load. Then, this paper has established an interval optimization model with distributed diesel engine, energy storage system and other controllable power sources, and taken the operating cost of micro grid as the target. Finally, a simulation has been carried out to verify the proposed model. The results show that the optimization method proposed in this paper can effectively improve the ability of the micro-network scheduling scheme to deal with uncertainties and avoid the scheme being too conservative.