Photovoltaic power generation power short term prediction method based on mind evolution Elman neural network

Abstract

The invention discloses a photovoltaic power generation power short term prediction method based on a mind evolution Elman neural network. According to the good expandability, the good portability and the extremely strong global optimization capacity of the mind evolution algorithm, and the historical data state sensitivity and the strong self dynamic information processing capacity of the Elman neural network, a photovoltaic power generation power short term prediction algorithm by using the mind evolution algorithm to optimize the Elman neural network is brought forward. Through optimizing an Elman neural network weight and a threshold by the mind evolution algorithm, defects that the Elman neural network is likely to fall into local optimum and the like are overcome. The example result shows that the method is quick in convergence rate, strong in optimization capacity and convenient in dynamic information processing, and an important role is played in photovoltaic power short term prediction.

Description

technical field [0001] The invention relates to a short-term prediction method of photovoltaic power generation based on thinking evolution Elman neural network, which belongs to the technical field of new energy power generation and smart grid. Background technique [0002] Photovoltaic power generation, following wind power generation, is expected to be a renewable energy power generation technology that can replace traditional power generation. Since the output power of the photovoltaic power generation system has three obvious characteristics: intermittent, random, and fluctuating, and is closely related to meteorological conditions, its power generation characteristics are significantly different from other power generation methods. Predicting the photovoltaic output power in advance and improving the prediction accuracy can reduce the deviation of grid dispatching, reduce the impact of the uncertainty of photovoltaic power generation changes on the grid, and further im...

AI Technical Summary

Problems solved by technology

Time series analysis has a good prediction effect on linear systems, but it is difficult to find a suitable parameter estimation method to predict nonlinear systems; the gray prediction method model is simple, but if there are many factors affecting the data, the prediction effect is poor; support vector machine regression The algorithm is difficult to implement on large-scale training samples, and it is difficult to solve multi-classification problems; the BP neural network algorithm is easy to fall into local minimum points, and the iterative learning algorithm converges slowly

[0004] The Elman neural network algorithm is convenient for processing dynamic information and has the ability of global optimization, but the convergence speed is slow and may fall into a local optimal solution

Images