基于人工鱼群优化BP神经网络的光伏功率预测算法

Photovoltaic Power Prediction Algorithm Based on Artificial Fish Swarm Optimization BP Neural Network

光伏发电的间歇性和不稳定性是影响光伏电能质量的重要因素之一。低质量电能并网会给电网安全运行带来巨大影响,导致电网消纳光伏的能力下降。光伏功率预测可以有效解决这一问题。然而,目前的光伏功率预测算法大多存在速度和精度不能兼顾的问题。为解决此问题,提出将人工鱼群算法与BP神经网结合,利用人工鱼群算法优化神经网络的权值和阈值。通过MATLAB软件建模和仿真运算,证明了光伏功率预测方法的运算速度较快,精度较高。

The intermittency and instability of photovoltaic power generation is the important factors affecting photovoltaic power quality.The grid-connection of low-quality power will have a huge impact on the safe operation of the power grid,leading to the decline of the power grid's ability to absorb photovoltaic energy.Photovoltaic power prediction can effectively solve this problem.However,most of the current photovoltaic power prediction algorithms cannot take both speed and accuracy into account.In order to solve this problem,this paper combines the artificial fish swarm algorithm with BP neural network,and uses the artificial fish swarm algorithm to optimize the weights and thresholds of the neural network.MATLAB software was used to build the model and simulation operation,which proved that the photovoltaic power prediction method is faster and more accurate.