| 引用本文: | 边晓燕,印良云,丁炀,赵健,周歧斌,李东东.基于深度信念网络的低风速风电参与微电网频率优化控制[J].电力自动化设备,2020,40(6): |
| BIAN Xiaoyan,YIN Liangyun,DING Yang,ZHAO Jian,ZHOU Qibin,LI Dongdong.Frequency optimization control of microgrid with LWTGs based on deep belief network[J].Electric Power Automation Equipment,2020,40(6): |
|
| 摘要: |
| 低风速分散式风电接入微电网使得微电网能够利用低风速风资源为负荷供电，但其低惯量的特点也对微电网的频率稳定性提出了挑战。为了探究微电网中低风速风电机组(LWTG)如何有效参与抑制微电网频率波动，在LWTG中引入虚拟惯量控制、超速控制和下垂控制。针对风电机组最小转子转速限制，通过理论分析确定了合适的LWTG的参数；针对超速控制存在的盲区问题，利用深度信念网络来优化不同风速下的减载率以及虚拟惯量控制、下垂控制的控制参数；在低风速风况下验证了优化后的参数能够有效减少负荷波动引起的微电网动态频率跌落幅度，并获得较好的调频效果。 |
| 关键词: 微电网 低风速 深度信念网络 调频 超速控制 风电机组 |
| DOI：10.16081/j.epae.202005027 |
| 分类号:TM727;TM614 |
| 基金项目:国家自然科学基金资助项目(51907116)；上海市科学技术委员会“科技创新行动计划”青年科技英才扬帆计划项目(19YF1416900)；上海市科学技术委员会科技创新项目(17020500800) |
|
| Frequency optimization control of microgrid with LWTGs based on deep belief network |
|
BIAN Xiaoyan1, YIN Liangyun1, DING Yang2, ZHAO Jian1, ZHOU Qibin3, LI Dongdong1
|
|
1.College of Electric Power Engineering, Shanghai University of Electric Power, Shanghai 200090, China;2.State Grid Shanghai Maintenance Company, Shanghai 200122, China;3.School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
|
| Abstract: |
| The access of low-wind-speed dispersed wind farms into microgrid makes it possible that the low-wind-speed wind resources supply power for load. However, the frequency stability of microgrid has been challenged due to the low inertia characteristic of LWTGs(Low-wind-speed Wind Turbine Generators). In order to explore how LWTGs can effectively participate in suppressing the frequency fluctuation of microgrid, the virtual inertia control, over-speed control and droop control are introduced into LWTGs. In view of the limitation of minimum rotor speed for wind turbines, the appropriate parameters of LWTGs are determined by theoretical analysis. For the blind zone problem of over-speed control, the de-loading ratio, along with the control parameters of virtual inertia control and droop control under different wind speeds are all optimized with deep belief network. It is verified that the optimized parameters can effectively reduce the dynamic frequency drop of microgrid caused by load fluctuation under low-wind-speed condition, and obtain better frequency regulation effects. |
| Key words: microgrid low-wind-speed deep belief network frequency regulation over-speed control wind turbine generators |
