基于GRU的光伏发电功率短期预测数字孪生模型研究  

Research on Digital Twin Model for Short-term Prediction of Photovoltaic Power Based on GRU

作　　者：熊慕文 汤震宇 XIONG Mu-wen;TANG Zhen-yu(Nanrui Jibao Electric Limited,Nanjing 210000,China)

机构地区：[1]南瑞继保电气有限公司,江苏南京210000

出　　处：《电脑与信息技术》2025年第1期27-32,共6页Computer and Information Technology

摘　　要：光伏发电作为新能源发电的核心组成部分,因其具有绿色环保、持续长久等特性,近年来受到了广泛关注与应用。然而,其输出功率易受气象条件影响,具有波动性等特点,给电力系统的调度与正常运行带来了挑战。基于此,提出了一种基于门控循环单元(Gate Recurrent Unit,GRU)的光伏发电功率短期预测数字孪生模型,该模型以构造基于GRU的预测组件为核心架构,采用优化后的GRU网络对光伏发电功率进行深度分析与预测,并在多组采集到的孪生数据上进行结果验证。实验结果表明,所提模型显著提高了短期光伏发电功率预测的精确度,相较于传统预测方法具有更高的准确性与鲁棒性。Photovoltaic power generation,as a core component of new energy generation,has received widespread attention and application in recent years due to its green and sustainable characteristics.However,its output power is generally characterized by intermittency and fluctuation,which poses challenges to the scheduling and management of the power system.Based on this,a digital twin model for short-term prediction of photovoltaic power generation based on Gated Recurrent Unit(GRU)was proposed.The model adopted digital twin technology as the core architecture,and used an optimized GRU network to deeply analyze and predict photovoltaic power generation.The results were verified on multiple sets of collected twin data.The experimental results show that the proposed model significantly improves the accuracy of short-term photovoltaic power prediction,and has higher accuracy and robustness compared to traditional prediction methods.

关 键 词：光伏发电 数字孪生 功率预测 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]