基于CKL风电容量预测的可信度评估  

Credibility Evaluation Based on CKL Wind Power Capacity Prediction

作　　者：李天宇 马刚[1] 李豪 李伟康 孟宇翔 Li Tianyu;Ma Gang;Li Hao;Li Weikang;Meng Yuxiang(School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing Jiangsu 210046,China)

机构地区：[1]南京师范大学电气与自动化工程学院,江苏南京210046

出　　处：《电气自动化》2024年第5期4-7,共4页Electrical Automation

基　　金：2022年度江苏省碳达峰碳中和科技创新专项资金(产业前瞻与关键核心技术攻关)重点项目“新能源发电自组网运行与控制关键技术研发”(BE2022003);重点课题“双高电力系统新能源动态调节能力监测与功率预测技术研究”(BE2022003-5)。

摘　　要：由于风力发电受风速以及其他天气因素的影响极大,从而导致新能源发电产生波动性,因此,对风力发电容量可信度评估研究成为提高风力发电可靠性的重要内容之一。首先建立了CEEMD-KPCA-LSTM(CKL)预测模型,用CKL模型对考虑多环境变量情况下的风电容量进行预测;进而提出风电场可靠运行时的可信度评估方法;最后在IEEE-RTS97基础上进行仿真试验,将预测值进行可信度分析,得出未来断面的容量可信度,并研究可信度的影响因素。算例分析表明,CKL预测模型和可信度模型结合,可以实现风电场未来的可信度分析,并且验证了储能设备对容量预测可信度的影响,最终使得风电系统具备较为准确的容量预测功能。Due to the significant impact of wind speed and other weather factors on wind power generation,which leads to fluctuations in new energy generation,the reliability assessment of wind power generation capacity has become one of the important issues in improving the reliability of wind power generation.Established CEEMD-KPCA-LSTM(CKL)prediction model was used to predict the wind power capacity considering multiple environmental variables;furthermore,a reliability evaluation method for the reliable operation of wind farms was proposed.Finally,simulation experiments were conducted on the basis of IEEE-RTS97,to analyze the reliability of the predicted values,obtain the capacity reliability of future sections,and study the influencing factors of reliability.Case analysis shows that the combination of CKL prediction model and reliability model can achieve future reliability analysis of wind farms,and verify the impact of energy storage equipment on the reliability of capacity prediction,ultimately enabling the wind power system to have a more accurate capacity prediction function.

关 键 词：完全集成经验模态分解 核主成分分析 长短期预测神经网络 蒙特卡洛模拟法 预测容量可信度 

分 类 号：TM614[电气工程—电力系统及自动化]