Short-term wind power prediction method based on improved neural network

Abstract

The invention discloses a short-term wind power prediction method based on an improved neural network. In the method, a neural network algorithm is selected to be combined with a particle swarm optimization algorithm, the short-term wind power prediction method based on the improved neural network is built, and the method comprises the steps of optimizing off-line parameters and predicting an algorithm subject. A historical data set of the off-line parameter optimization contains two months of historical data and is updated one time every week, and the output optimal parameters are transferred to the predicted algorithm subject; a wind powder prediction model of the predicted algorithm subject is combined with the predicted wind speed and direction and the off-line optimized parameters, then the short-term wind power prediction is completed, and a wind power prediction result is output. The method is high in practicability and has the advantages of being fast in convergence speed, high in precision and globally optimal.

Description

technical field [0001] The invention belongs to the technical field of wind power forecasting, in particular to a short-term wind power forecasting method based on an improved neural network. Background technique [0002] A series of global problems such as global warming and the depletion of conventional fossil energy have aroused people's widespread attention to new energy. Compared with other renewable energy sources, wind power has more mature technology, higher efficiency and rapid development. By the end of 2014, the cumulative installed capacity of wind power in the world reached 359.7GW. It is estimated that after 2018, with the healthy development of the market, the annual installed capacity of onshore wind power in the world will exceed 55GW. [0003] However, wind power is volatile and intermittent. As the proportion of grid-connected wind power systems in the grid continues to increase, it poses severe challenges to the safe and stable operation of the power sy...

AI Technical Summary

Problems solved by technology

The continuation method is simple and easy to operate, but it is suitable for ultra-short-term forecasting, and its application range is narrow; the Kalman filter method is suitable for real-time online forecasting, but it needs to assume known statistical characteristics of noise, which is poor in practicability; the neural network method has nonlinearity, fault tolerance, Self-learning and self-adaptive capabilities, but they are essentially local optimization searches and may fall into local extremums; genetic algorithms have global optimization capabilities, but operations such as selection, hybridization, mutation, and evaluation are required, and calculations are complex

Images