A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm

•A hybrid load forecasting model with hyper-parameters optimization is proposed.•Nonlinear mapping is introduced to map the relevant factors.•Bayesian Optimization Algorithm (BOA) is used in hyperparameter optimization.•Proposed model periodically moves the data window which has high practicability.•Proposed method is validated by seven contrast methods in Keras python framework.