Short term load forecasting based on feature extraction and improved general regression neural network model

• Published in: Energy (Oxford) Vol. 166; pp. 653 - 663
• Main Authors: Liang, Yi, Niu, Dongxiao, Hong, Wei-Chiang
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.01.2019; Elsevier BV
• Subjects: Algorithms; China; Correlation analysis; Deregulation; Economic forecasting; Electric power; Electricity consumption; Empirical analysis; Empirical mode decomposition (EMD); Extraction processes; Feature extraction; Forecasting; Fruit fly optimization algorithm (FOA); General regression neural network (GRNN); General regression neural networks; Meteorology; Minimal redundancy maximal relevance (mRMR); Neural networks; Redundancy; Regression analysis; Regression models; Renewable resources; Short term load forecasting (STLF); Stability; Sustainable yield; Temperature; Volatility; China; Minimal redundancy maximal relevance (mRMR); General regression neural network (GRNN); Fruit fly optimization algorithm (FOA); Empirical mode decomposition (EMD); Short term load forecasting (STLF)
• ISSN: 0360-5442; 1873-6785
• DOI: 10.1016/j.energy.2018.10.119

Along with the deregulation of electric power market as well as aggregation of renewable resources, short term load forecasting (STLF) has become more and more momentous. However, it is a hard task due to various influential factors that leads to volatility and instability of the series. Therefore, this paper proposes a hybrid model which combines empirical mode decomposition (EMD), minimal redundancy maximal relevance (mRMR), general regression neural network (GRNN) with fruit fly optimization algorithm (FOA), namely EMD-mRMR-FOA-GRNN. The original load series is firstly decomposed into a quantity of intrinsic mode functions (IMFs) and a residue with different frequency so as to weaken the volatility of the series influenced by complicated factors. Then, mRMR is employed to obtain the best feature set through the correlation analysis between each IMF and the features including day types, temperature, meteorology conditions and so on. Finally, FOA is utilized to optimize the smoothing factor in GRNN. The ultimate forecasted load can be derived from the summation of the predicted results for all IMFs. To validate the proposed technique, load data in Langfang, China are provided. The results demonstrate that EMD-mRMR-FOA-GRNN is a promising approach in terms of STLF. •A novel hybrid STLF model based on EMD-mRMR-FOA-GRNN is proposed.•The feature set is effectively selected by EMD and mRMR from original data.•The forecasting accuracy of GRNN is obviously enhanced by FOA.•The proposed model evidently receives higher forecasting accuracy than other models.