A hybrid forecasting approach applied in the electrical power system based on data preprocessing, optimization and artificial intelligence algorithms

Data processing, analysis and forecasting by applying artificial intelligence algorithms plays a pivotal role in the big data era. Hybrid forecasting of time series data is considered to be a potentially viable alternative compared with the conventional single forecasting modeling approaches. However, to perform forecasting in the electrical power system has been proven to be a challenging task due to various unstable factors, such as high fluctuations, autocorrelation and stochastic volatility. In this paper, a novel hybrid model that combines denoising methods and optimization algorithms with forecasting techniques is developed to solve the upper problems and forecast the key indicators in the electrical power system, including short-term wind speed, electrical load and electricity price. The proposed model can be applied to forecast the complex electrical power system with a high rate of convergence, forecasting accuracy and a fast computing speed. One of features of this paper is to integrate the already existing algorithms and models, which show a good forecasting performance. The results of three experiments confirm that the proposed hybrid model can satisfactorily approximate the actual value, and it can also be used as an effective and simple tool for planning for smart grids.