摘要
光伏发电因天气等的因素影响,其输出功率具有不确定性,接入配电网后可能会引起配电网馈线过电压。针对这一问题通过建立一种基于BP神经网络的预测模型,预测出不同时间段的输出功率,对比以往引起过电压时的输出功率,计算出需要削减的有功功率,进而防止馈线过电压的产生。该模型首先对大量历史数据进行学习分析,并不断更新迭代,从而得出较为准确的预测数据。计算出需要削减的有功功率后,该文提出通过调节光伏阵列模块和调节并网逆变器2种方案来调节光伏发电的输出功率,并对这2种方案进行对比。最后,使用MATLAB仿真软件对算例进行计算分析,结果证实了2种控制策略的可行性和有效性。
The output power of photovoltaic power generation is uncertain due to the weather and other factors. This may cause over-voltage of distribution network feeders when connected to the distribution network. In order to solve this problem, a prediction model based on BP neural network is established to predict the output power in different time periods. Then the active power that needs to be reduced can be calculated by comparing the output power caused by over-voltage in the past, so as to prevent the generation of feeder over-voltage. Through the study and analysis of a large number of historical data, the model is constantly updated in iterations, so as to get more accurate prediction data. After calculating the active power that needs to be reduced, this paper proposes and compares two schemes to adjust the output power of photovoltaic power generation by tuning photovoltaic array module and grid connected inverter. Finally, the MATLAB simulation software is used to calculate and analyze the example. The results verify the feasibility and effectiveness of the two control strategies.
作者
范家铭
夏向阳
FAN jia-ming;XIA Xiang-yang(China Electricity Council Beijing Henggong Testing Technology Research Institute Co.Ltd.,Beijing 100000,China;School of Electrical and Information Engineering,Changsha University of Science&Technology,Changsha 410114,China)
出处
《电力科学与技术学报》
CAS
北大核心
2019年第4期123-128,147,共7页
Journal of Electric Power Science And Technology
