基于卷积神经网络的含分布式光伏配电网静态等值

doi:10.6040/j.issn.1672-3961.0.2022.308

摘要/Abstract

摘要： 为提升含分布式光伏配电网静态等值的运行方式适应性,提出一种基于卷积神经网络(convolutional neural networks,CNN)的含分布式光伏配电网静态等值方法。考虑源荷不确定性及相关性,基于核密度估计和Copula函数生成光伏、负荷功率场景并计算配网潮流。针对各单一运行方式下的等值问题,构造含分布式光伏配电网的等值模型,采用粒子群优化(particle swarm optimization, PSO)辨识变压器和线路参数。为提高模型参数计算效率,提出一种基于CNN的含分布式光伏配电网静态等值参数估计模型。在某省配电网算例下验证了所提方法的有效性。相较于其他方法,基于CNN的静态等值考虑了源荷功率的波动性及相关性,且提高了等值参数辨识效率,能够应用于静态等值参数的在线计算。

关键词: 分布式光伏, 配电网, 静态等值, 卷积神经网络, 粒子群优化

中图分类号:

TM71

范海雯,郝旭东,赵康,邢法财,蒋哲,李常刚. 基于卷积神经网络的含分布式光伏配电网静态等值[J]. 山东大学学报 (工学版), 2023, 53(4): 140-148.

FAN Haiwen, HAO Xudong, ZHAO Kang, XING Facai, JIANG Zhe, LI Changgang. Static equivalent of distribution network with distributed photovoltaic based on convolutional neural network[J]. Journal of Shandong University(Engineering Science), 2023, 53(4): 140-148.

参考文献

[1] 董梓童. 2021年上半年新增装机规模远超集中式电站分布式光伏势头强劲[J]. 新能源科技, 2021(8): 19-20. DONG Zitong. In the first half of 2021, the newly installed capacity far exceeded that of centralized power station[J]. New Energy Technology, 2021(8): 19-20.
[2] ABAD M S, MA Jin. Photovoltaic hosting capacity sensitivity to active distribution network management[J]. IEEE Transactions on Power Systems, 2020, 36(1): 107-117.
[3] 刘小恺, 范晓龙, 房文轩, 等. 含多类型分布式电源的主动配电网三相动态潮流算法[J]. 山东电力技术, 2021, 48(6): 44-49. LIU Xiaokai, FAN Xiaolong, FANG Wenxuan, et al. Three-phase dynamic power flow algorithm for active distribution networks with multiple types of distributed power sources[J]. Shandong Electronic Power, 2021, 48(6): 44-49.
[4] 尤毅, 刘东于, 文鹏,等. 主动配电网技术及其进展[J]. 电力系统自动化, 2012, 36(18): 10-16. YOU Yi, LIU Dongyu, WEN Peng, et al. Active distribution network technology and its progress[J]. Automation of Electric Power Systems, 2012, 36(18): 10-16.
[5] MILANOVIC J V, YAMASHITA K, MARINEZ VILLANUEVA S, et al. International Industry Practice on Power System Load Modeling[J]. IEEE Transactions on Power Systems, 2013, 28(3): 3038-3046.
[6] DAI Wei, YU Juan, LIU Xuan, et al. Two-tier static equivalent method of active distribution networks considering sensitivity, power loss and static load characteristics[J]. International Journal of Electrical Power & Energy Systems, 2018, 100(9): 193-200.
[7] JEONG M G, KIM Y J, MOON S I, et al. Optimal voltage control using an equivalent model of a low-voltage network accommodating inverter-interfaced distributed generators[J]. Energies, 2017, 10(8):1180.
[8] ZHAO J, WANG Z, WANG J. Robust time-varying load modeling for conservation voltage reduction assessment[J]. IEEE Transactions on Smart Grid, 2018, 9(4): 3304-3312.
[9] WANG Z, WANG J. Time-varying stochastic assessment of conservation voltage reduction based on load modeling[J]. IEEE Transactions on Power Systems, 2014, 29(5): 2321-2328.
[10] SADEGHI M, SARVI G A. Determination of ZIP parameters with least squares optimization method[C] //2009 IEEE Electrical Power & Energy Conference(EPEC). Montreal, Canada: IEEE, 2009: 1-6.
[11] WEN J, JIANG L, WU Q, et al. Power system load modeling by learning based on system measurements[J]. IEEE Transactions on Power Delivery, 2003, 18(2): 364-371.
[12] 李国庆, 陆为华, 边竞, 等. 基于自适应扩散核密度估计的时序相关概率最优潮流计算方法[J]. 中国电机工程学报, 2021, 41(5): 1655-1664. LI Guoqing, LU Weihua, BIAN Jing, et al. An adaptive diffusion kernel density estimation method for calculating temporal correlation probability optimal power flow[J]. Proceeding of the CSEE, 2021, 41(5): 1655-1664.
[13] 宋宇, 李涵. 基于核密度估计和Copula函数的风、光出力场景生成[J]. 电气技术, 2022, 23(1): 56-63. SONG Yu, LI Han. Wind and light output scene generation based on kernel density estimation and Copula function[J]. Electrical Engineering, 2022, 23(1): 56-63.
[14] 李文升, 王宪, 米元泽, 等. 考虑风光多维时空相关性的电源规划方法[J]. 山东大学学报(工学版), 2022, 52(1): 111-119. LI Wensheng, WANG Xian, MI Yuanze, et al. Method for generation planning with the temporal and spatial correlation of wind and solar power[J]. Journal of Shandong University(Engineering Science), 2022, 52(1): 111-119.
[15] 白凯峰, 顾洁, 彭虹桥, 等. 融合风光出力场景生成的多能互补微网系统优化配置[J]. 电力系统自动化, 2018, 42(15): 133-141. BAI Kaifeng, GU Jie, PENG Hongqiao, et al. Optimal configuration of multi-energy complementary micro-grid system generated by combining landscape output scenarios[J]. Automation of Electric Power Systems, 2018, 42(15): 133-141.
[16] LI Changgang, WU Yue, ZHANG Hengxu, et al. STEPS: a portable dynamic simulation toolkit for electrical power system studies[J]. IEEE Transactions on Power Systems, 2020, 36(4): 3216-3226.
[17] LI Mi, CHEN Huan, WANG Xiaodong, et al. An improved particle swarm optimization algorithm with adaptive inertia weights[J]. International Journal of Information Technology & Decision Making, 2019, 18(3): 833-866.
[18] 李娜, 王晓亮. 基于PSO算法改进的经济调度优化[J]. 山东电力技术, 2015, 42(3): 12-15. LI Na, WANG Xiaoliang. Optimization of Economic Scheduling Based on PSO Algorithm[J]. Shandong Electric Power Technology, 2015, 42(3): 12-15.
[19] 李洋麟, 江全元, 颜融, 等. 基于卷积神经网络的电力系统小干扰稳定评估[J]. 电力系统自动化, 2019, 43(2): 50-67. LI Yanglin, JIANG Quanyuan, YAN Rong, et al. Stability evaluation of power system with small disturbance based on convolutional neural network[J]. Automation of Electric Power Systems, 2019, 43(2): 50-57.
[20] 刘威, 张东霞, 王新迎, 等. 基于深度强化学习的电网紧急控制策略研究[J].中国电机工程学报, 2017, 38(1): 109-119. LIU Wei, ZHANG Dongxia, WANG Xinying, et al. Research on emergency control strategy of power network based on intensive reinforcement learning[J]. Proceedings of the CSEE, 2017, 38(1): 109-119.
[21] 王智伟, 徐海超, 郭相阳, 等. 基于卷积神经网络和层次分析的新能源电源调频能力智能预测方法[J]. 山东大学学报(工学版), 2022, 52(5): 70-76. WANG Zhiwei, XU Haichao, GUO Xiangyang, et al. Intelligent method based on convolutional neural network and analytic hierarchy process to predict frequency regulation ability of renewable energy power[J]. Journal of Shandong University(Engineering Science), 2022, 52(5): 70-76.

相关文章 15

[1]	杨思,王艳,赵斌成,韩学山,刘冬,孙东磊. 含分布式电源的配电网三阶段协同优化调度[J]. 山东大学学报 (工学版), 2022, 52(5): 55-69.
[2]	王智伟,徐海超,郭相阳,马炯,褚云龙,陈前昌,卢治. 基于卷积神经网络和层次分析的新能源电源调频能力智能预测方法[J]. 山东大学学报 (工学版), 2022, 52(5): 70-76.
[3]	孙东磊, 鉴庆之, 李智琦, 韩学山, 王明强, 陈博, 付一木. 源网协调的电力系统均匀性规划[J]. 山东大学学报 (工学版), 2022, 52(5): 92-101.
[4]	刘振,孙媛媛,李亚辉,许庆燊,于涛,庞延庆. 基于用户行为预测的分布式光伏智能社区需求响应策略[J]. 山东大学学报 (工学版), 2022, 52(5): 24-34.
[5]	张学思,张婷,刘兆英,江天鹏. 基于轻量型卷积神经网络的海面红外显著性目标检测方法[J]. 山东大学学报 (工学版), 2022, 52(2): 41-49.
[6]	王心哲,邓棋文,王际潮,范剑超. 深度语义分割MRF模型的海洋筏式养殖信息提取[J]. 山东大学学报 (工学版), 2022, 52(2): 89-98.
[7]	尹旭,刘兆英,张婷,李玉鑑. 基于弱监督和半监督学习的红外舰船分割方法[J]. 山东大学学报 (工学版), 2022, 52(2): 99-106.
[8]	陶亮,刘宝宁,梁玮. 基于CNN-LSTM 混合模型的心律失常自动检测[J]. 山东大学学报 (工学版), 2021, 51(3): 30-36.
[9]	廖锦萍,莫毓昌,YAN Ke. 基于C-LSTM的短期用电预测模型和应用[J]. 山东大学学报 (工学版), 2021, 51(2): 90-97.
[10]	刘新锋, 张旖旎,徐惠三,宋玲,陈梦雅. 基于随机森林和专家系统的分布式光伏电站阴影遮挡诊断[J]. 山东大学学报 (工学版), 2021, 51(2): 98-104.
[11]	李志,余绍峰,苏毅方,王蔚,蒋宏图,张伟. 基于RTDS的配电网一二次融合仿真技术[J]. 山东大学学报 (工学版), 2020, 50(6): 112-117.
[12]	廖南星,周世斌,张国鹏,程德强. 基于类激活映射-注意力机制的图像描述方法[J]. 山东大学学报 (工学版), 2020, 50(4): 28-34.
[13]	宋士瞻,陈浩宇,张健,王坤,郝庆水. 考虑路灯充电桩接入的城市配电网电压控制方法[J]. 山东大学学报 (工学版), 2020, 50(3): 104-110.
[14]	李春阳,李楠,冯涛,王朱贺,马靖凯. 基于深度学习的洗衣机异常音检测[J]. 山东大学学报 (工学版), 2020, 50(2): 108-117.
[15]	宋士奇,朴燕,蒋泽新. 基于改进YOLOv3的复杂场景车辆分类与跟踪[J]. 山东大学学报 (工学版), 2020, 50(2): 27-33.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed