Short-period electric generation power forecasting method applied to photovoltaic electric generation system

Abstract

The invention relates to a short-period electric generation power forecasting method applied to a photovoltaic electric generation system. The short-period electric generation power forecasting method is characterized by comprising two states that 1, the original electric generation power signals are subjected to empirical mode decomposition; and 2, a BP neural network forecasting model based on the genetic algorithm is built for each decomposition component. The short-period electric generation power forecasting method has the following major advantages that the accurate photovoltaic electric generation power forecasting is carried out in advance, the current flowing direction of the traditional electric grid and a photovoltaic electric generation microgrid is determined, a scheduling plan of an electric power system is made, and the operation cost of the electric power system is reduced; and meanwhile, the energy source storage plan can also be made in advance, the adverse influence on a large electric grid caused by intermittency and uncontrollability of the photovoltaic electric generation is reduced, and the market competitive advantage of the photovoltaic electric generation is enhanced. Meanwhile, the system also belongs to a precedent for applying the computer technologies such as the manual neural network and the genetic algorithm into the photovoltaic electric generation power forecasting, and higher novelty and practicability are realized.

Description

technical field [0001] The present invention relates to a short-term generating power prediction method applied to a photovoltaic power generation system, specifically, to a method based on Empirical Mode Decomposition (EMD for short) and genetic algorithm-BP neural network (Genetic Algorithm-Back Propagation) NeuralNetwork (GA-BPNN for short) short-term photovoltaic power generation prediction method. Background technique [0002] Due to the depletion of fossil fuels and the resulting environmental pollution, countries all over the world are sparing no effort to develop and utilize renewable energy. The solar energy received by the earth only accounts for about 1 / 2 billion of the total energy emitted by the surface of the sun, but these energies are equivalent to 30,000 to 40,000 times the total energy required by the world, which is inexhaustible. inexhaustible. Unlike fossil fuels such as petroleum and coal, solar energy will not cause "greenhouse effect" and global cli...

AI Technical Summary

Problems solved by technology

From the perspective of power generation companies (photovoltaic farms), once photovoltaic power generation participates in market competition in the future, compared with other controllable power generation methods, the intermittent nature of photovoltaic power generation will greatly weaken the competitiveness of photovoltaic power generation. unreliability subject to economic loss

Images