基于余弦相似度和TSO-BP的短期光伏预测方法
A short-term PV power forecasting method based on cosine similarity and TSO-BP neural network
陆毅 1薛枫 1唐小波 1杨坤 1李益 1马刚1
作者信息
- 1. 南京师范大学 电气与自动化工程学院,南京 210000
- 折叠
摘要
对光伏出力的精准预测在配电网安全稳定运行中起着至关重要的作用.因此,提出了一种基于余弦相似度和TSO-BP(金枪鱼群优化-反向传播)神经网络的短期光伏预测方法.首先,利用余弦相似度算法筛选出与预测日具有强相似度的历史数据作为训练样本;然后,采用TSO算法寻找BP神经网络的最优初始权值与阈值,训练TSO-BP短期光伏预测模型;最后,利用TSO-BP模型分别预测平缓天气与波动天气下的光伏出力.仿真结果表明:在平稳和波动两种不同天气情况下,该方法相较于传统预测方法精度更高.
Abstract
Accurate photovoltaic(PV)output power forecasting plays a crucial role in ensuring the secure and stable operation of distribution networks.In light of this,the paper proposes a short-term PV power forecasting method using cosine similarity and a hybrid TSO(tuna swarm optimization)and BP(back propagation)neural net-work.Firstly,the cosine similarity algorithm is utilized to identify historical data with strong resemblance to the fore-cast day as training samples.Subsequently,the TSO algorithm is employed to search for optimal initial weights and thresholds for the BP neural network.The TSO-BP model is then trained for short-term PV power forecasting.Fi-nally,the TSO-BP model is applied to predict PV output power under both stable and fluctuating weather condi-tions.Simulation results indicate that,the proposed method,compared to traditional forecasting methods,achieves higher accuracy in predictions for both steady and fluctuating weather scenarios.
关键词
光伏预测/皮尔逊相关系数/余弦相似度/金枪鱼群优化算法/反向传播神经网络Key words
PV power forecasting/Pearson correlation coefficient/cosine similarity/TSO/BP neural network引用本文复制引用
基金项目
江苏省碳达峰碳中和科技创新专项(产业前瞻与关键核心技术攻关)重点项目(BE2022003)
出版年
2024
国家科技期刊平台
NSTL
万方数据