摘要
为了使微电网建模更加精确,提出了一种基于优化回声状态网络(echo state network,ESN)的微电网等效建模方法。以微电网各种运行状态下并网接入端的电流和功率等数据分别作为网络的输入和输出,构建基于回声状态网络的微电网等效模型。由于回声状态网络初始化参数选取后就不再改变,缺乏自适应性,往往导致逼近能力不能达到最优;而烟花算法具有爆发性、瞬时性、分布并行性和可扩充性等优点;为了提高建模的精确性,故利用烟花算法对回声状态网络进行参数优化。通过模拟烟花的爆炸来建立数学模型,计算个体适应度值选择最优个体。建模结果与微电网并网仿真的实测数据对比,验证了该建模方法的合理型和准确性,说明所建模型具有较好的实际应用价值。
In order to make micro-grid modeling more accurate,an equivalent modeling method of micro-grid based on echo state network(ESN)is proposed.Under various operating conditions of the micro-grid,the micro-grid equivalent model based on the echo status network is constructed with the current and power data of the access terminal,which are taken as the input and output of the network respectively.Since the initialization parameter of echo state network no longer changes,and lacking adaptability,it lead to the inability to achieve optimal approximation.Fireworks algorithm has the advantages of explosiveness,instantaneousity,parallelism and scalability.In order to improve the accuracy of the modeling,the fireworks algorithm is used to optimize the parameters of the echo state network,a mathematical model by simulating the explosion of fireworks is established,and selects the best individual by calculating individual fitness values.By comparing with the measured simulation data of the micro-grid connected the grid,the rationality and accuracy of the modeling method are verified,which shows that the model has a good practical value.
作者
吴忠强
戚松岐
尚梦瑶
申丹丹
WU Zhong-qiang;QI Song-qi;SHANG Meng-yao;SHEN Dan-dan(Gollege of Electrical Engineerng,Yanshan University,Qinhuangdao,Hebei 066004,China)
出处
《计量学报》
CSCD
北大核心
2021年第7期923-929,共7页
Acta Metrologica Sinica
基金
河北省自然科学基金(F2020203014)。
关键词
计量学
微电网
回声状态网络
等效建模
并网
烟花算法
参数优化
metrology
micro-grid
echo state network
equivalent modeling
grid-connected
fireworks algorithm
parameter optimization
