基于相似日和CAPSO-SNN的光伏发电功率预测
发布时间：2018-10-29 18:20
【摘要】：针对光伏发电功率预测精度不高的问题,提出一种基于相似日和云自适应粒子群优化(CAPSO)算法优化Spiking神经网络(SNN)的发电功率预测模型。考虑到季节类型、天气类型和气象等主要影响因素,提出以综合相似度指标进行相似日选取;以SNN强大的计算能力和其善于处理时间序列问题的特点为基础,结合CAPSO算法搜索的随机性和稳定性优化SNN的多突触连接权值,减少对权值的约束,提高算法的收敛精度。根据某光伏电站的实测功率数据对所提模型进行测试和评估,结果表明,该模型比传统预测模型具有更高的预测精度和更好的适用性。
[Abstract]:In order to solve the problem of low precision of photovoltaic power prediction, a generation power prediction model based on similar day and cloud adaptive particle swarm optimization (CAPSO) algorithm to optimize Spiking neural network (SNN) is proposed. Considering the main influencing factors such as season type, weather type and meteorology, a comprehensive similarity index is proposed to select similar days. Based on the strong computing power of SNN and its ability to deal with time series problems, combined with the randomness and stability of CAPSO algorithm, the multi-synaptic connection weights of SNN are optimized, which reduces the constraints on weights and improves the convergence accuracy of the algorithm. The proposed model is tested and evaluated according to the measured power data of a photovoltaic power plant. The results show that the proposed model has higher prediction accuracy and better applicability than the traditional model.
【作者单位】： 河海大学能源与电气学院;ALSTOM
【基金】：国家自然科学基金资助项目(51277052,51507052)~~
【分类号】：TM615
[Abstract]:In order to solve the problem of low precision of photovoltaic power prediction, a generation power prediction model based on similar day and cloud adaptive particle swarm optimization (CAPSO) algorithm to optimize Spiking neural network (SNN) is proposed. Considering the main influencing factors such as season type, weather type and meteorology, a comprehensive similarity index is proposed to select similar days. Based on the strong computing power of SNN and its ability to deal with time series problems, combined with the randomness and stability of CAPSO algorithm, the multi-synaptic connection weights of SNN are optimized, which reduces the constraints on weights and improves the convergence accuracy of the algorithm. The proposed model is tested and evaluated according to the measured power data of a photovoltaic power plant. The results show that the proposed model has higher prediction accuracy and better applicability than the traditional model.
【作者单位】： 河海大学能源与电气学院;ALSTOM
【基金】：国家自然科学基金资助项目(51277052,51507052)~~
【分类号】：TM615
【相似文献】
相关期刊论文 前10条
1 刘士荣;李松峰;宁康红;周啸波;荣延泽;;基于极端学习机的光伏发电功率短期预测[J];控制工程;2013年03期
2 ;科技文摘[J];中学物理教学参考;1994年08期
3 王丽婕;廖晓钟;高阳;高爽;;风电场发电功率的建模和预测研究综述[J];电力系统保护与控制;2009年13期
4 田丽;邓阅;;联合条件下风力发电风速预测[J];安徽工程大学学报;2012年03期
5 卢静;翟海青;刘纯;王晓蓉;;光伏发电功率预测统计方法研究[J];华东电力;2010年04期
6 徐星;张虹;乐海洪;徐敏;;采用气象信息的神经网络应用于短期风力发电功率预测[J];南昌大学学报(工科版);2011年01期
7 阿碧;;身背核电站移民外星[J];发明与创新(综合科技);2011年11期
8 许昌;李e，
本文编号：2298442
本文链接：https://www.wllwen.com/kejilunwen/dianlidianqilunwen/2298442.html
