WRL: A Combined Model for Short-Term Load Forecasting

Load forecasting plays a vital role in economic construction and national security. The accuracy of short-term load forecasting will directly affect the quality of power supply and user experience, and will indirectly affect the stability and safety of the power system operation. In this paper, we present a novel short-term load forecasting model, which combines influencing factors analysis, Wavelet Decomposition feature extraction, Radial Basis Function (RBF) neural networks and Bidirectional Long Short-Term Memory (Bi-LSTM) networks (WRL below). The model uses wavelet decomposition to extract the main features of load data, analyzes its correlation with influencing factors, and then constructs corresponding adjustment factors. The RBF neural networks are used to forecast the feature subsequence related to external factors. Other subsequences are input into Bidirectional LSTM networks to forecast future values. Finally, the forecasting results are obtained by wavelet inverse transform. Experiments show that the proposed short-term load forecasting method is effective and feasible.

[1]  Reza Mohammadi,et al.  A new hybrid evolutionary based RBF networks method for forecasting time series: A case study of forecasting emergency supply demand time series , 2014, Eng. Appl. Artif. Intell..

[2]  Jun Wang,et al.  Forecasting energy fluctuation model by wavelet decomposition and stochastic recurrent wavelet neural network , 2018, Neurocomputing.

[3]  Eduard Muljadi,et al.  A Short-Term and High-Resolution Distribution System Load Forecasting Approach Using Support Vector Regression With Hybrid Parameters Optimization , 2018, IEEE Transactions on Smart Grid.

[4]  Ajay Shekhar Pandey,et al.  Short-term load forecasting methods: A review , 2016, 2016 International Conference on Emerging Trends in Electrical Electronics & Sustainable Energy Systems (ICETEESES).

[5]  Pierluigi Siano,et al.  A Review of Architectures and Concepts for Intelligence in Future Electric Energy Systems , 2015, IEEE Transactions on Industrial Electronics.

[6]  Zhigang Zeng,et al.  A short-term power load forecasting model based on the generalized regression neural network with decreasing step fruit fly optimization algorithm , 2017, Neurocomputing.

[7]  Jing Ma,et al.  Research and application of a combined model based on multi-objective optimization for electrical load forecasting , 2017 .

[8]  M. Ghofrani,et al.  Hybrid clustering-time series-bayesian neural network short-term load forecasting method , 2016, 2016 North American Power Symposium (NAPS).

[9]  Grzegorz Dudek.  Pattern-based local linear regression models for short-term load forecasting , 2016 .

[10]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[11]  Alexander N. Gorban,et al.  SOM: Stochastic initialization versus principal components , 2016, Inf. Sci..