期刊文献+

基于综合概率模型与深度学习的智能电网功率-电压映射方法 被引量:4

Power-Voltage Mapping Method Based on Comprehensive Probability Model and Deep Learning for Smart Grid
原文传递
导出
摘要 随着新能源及分布式发电渗透率的增加,其间歇性强、波动性大等特性对电网电压波动造成较大影响,如何更加快速地计算包含复杂分布式电源接入的电力系统稳态电压具有重要意义。通过对大量风机、光伏真实出力数据采样,在传统概率模型的基础上改进生成综合概率模型,并通过马尔科夫转移概率矩阵修正因时空特性产生的概率分布偏差。然后,以中国南方某地区相邻光伏、风电场实际出力数据为样本,基于配电网拓扑结构,在不同场景下计算其各节点稳态电压。最后,算例结果表明,改进方法模拟生成的电网模型具有较高真实性和适用性,计算所得的电压具有较高准确率。并且,相较传统电力系统潮流计算,极大减少计算时间,从而在控制效果上具有更好的跟随性,适用于复杂新能源电力系统稳态电压的计算。 With the increase in the penetration rate of new energy based distributed power generation,its characteristics such as strong intermittent and high volatility will have a greater impact on grid voltage fluctuations.How to calculate the steady-state voltage of the power grid with complex distributed power access more quickly is of great significance.In this paper,by sampling a great deal of real output data of photovoltaic and wind power,a comprehensive probability model is improved and generated on the basis of the traditional probability model,and the probability distribution deviation caused by the temporal and spatial characteristics is corrected through the Markov transition probability matrix.Then,taking the actual output data of adjacent photovoltaic and wind power stations in a certain area of southern China as a sample,the steady-state voltage at each node of the distribution network under different scenarios is calculated in the distribution network topology.Finally,the results of the calculation example show that the power grid model generated by the improved method simulation in this paper has high authenticity and applicability,and the calculated voltages have high accuracy rate.Moreover,compared with the traditional power system flow calculation,the calculation time is greatly reduced,so that it has better follow-up in the control effect,and is suitable for the calculation of the steady-state voltage of the complex power system with new energy.
作者 李建宜 李鹏 徐晓春 施儒昱 曾平良 夏辉 LI Jianyi;LI Peng;XU Xiaochun;SHI Ruyu;ZENG Pingliang;XIA Hui(School of Electrical and Electronic Engineering,North China Electric Power University,Baoding 071003,Hebei Province,China;State Grid Huaian Power Supply Company,Huaian 223400,Jiangsu Province,China;State Grid Suzhou Power Supply Company,Suzhou 215000,Jiangsu Province,China;School of Automation,Hangzhou Dianzi University,Hangzhou 310018,China)
出处 《电力建设》 CSCD 北大核心 2022年第2期37-44,共8页 Electric Power Construction
基金 国家电网公司科技项目“含新能源、储能及柔性负荷的无功电压协调控制关键技术研究”(5108-202018028A-0-0-00)。
关键词 新能源 综合概率模型 马尔科夫链 蒙特卡洛模拟 人工智能 new energy comprehensive probability model Markov chain Monte Carlo simulation artificial intelligence
  • 相关文献

参考文献18

二级参考文献246

共引文献475

同被引文献81

引证文献4

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部