摘要
为了提高短期风电功率预测精度,提出一种改进蜣螂优化算法优化BP神经网络的短期风电功率预测模型。针对蜣螂算法中存在易陷入局部最优解的问题,采用最优拉丁超立方方法初始化蜣螂种群,使蜣螂种群分布更为均匀,以提高算法跳出局部最优解的可能性。利用改进后的蜣螂优化算法对BP神经网络的权值和阈值进行优化,并以内蒙古某电厂的风电功率数据为研究对象,进行模型搭建和仿真测试。经仿真验证,预测模型能有效提高风电功率的预测精度。
To improve the accuracy of short-term wind power prediction,a short-term wind power prediction model is proposed based on BP optimized by an improved dung beetle optimization algorithm.To avoid the problem of falling into the local optimal of the dung beetle algorithm,the optimal Latin hypercube method is employed to initialize the dung beetle population.So that the distribution of the dung beetle population is more uniform to increase the possibility of the algorithm jumping out of the local optimal solution.The improved dung beetle optimization algorithm is used to optimize the weights and thresholds of the BP neural network,and the wind power data of a power plant in Inner Mongolia is utilized as the research object for model construction and simulation testing.The simulation shows that the proposed prediction model can effectively improve the prediction accuracy of wind power.
作者
顾伟光
王芳(指导)
GU Weiguang;WANG Fang(School of Electrical Engineering,Shanghai Dianji University,Shanghai 201306,China)
出处
《上海电机学院学报》
2024年第3期161-166,180,共7页
Journal of Shanghai Dianji University
基金
上海市教育发展基金会和上海市教育委员会“晨光计划”项目(23CGA76)
轻工过程先进控制教育部重点实验室开放课题(江南大学)项目(APCLI2402)。
关键词
风电功率预测
BP神经网络
蜣螂优化算法
最优拉丁超立方
wind power prediction
BP neural network
dung beetle optimization algorithm
optimal latin hypercube
