深度信念网络在水火电力系统一次调频能力预测中的应用

崔伟 1; 李武璟 1; 王聪 1; 薛晨 1; 段建东 2; 魏嵬 3

doi:10.7652/xjtuxb202103012

您当前的位置：

首页 >

文章列表页 >

深度信念网络在水火电力系统一次调频能力预测中的应用

更新时间：2025-07-09

- 深度信念网络在水火电力系统一次调频能力预测中的应用
- Research on Application of Deep Belief Network in Primary Frequency Modulation Capability of Hydrothermal Power System
- 西安交通大学学报 2021年55卷第3期页码：99-108
- 作者机构：
  
  国家电网公司西北分部,西安,710048
- 作者简介：
- 基金信息：
  
  : 2020-07-27。作者简介: 崔伟(1987—),男,工程师;李武璟(通信作者),男,工程师。基金项目: 国家自然科学基金资助项目(51877174)
- DOI：10.7652/xjtuxb202103012
  中图分类号： TM734
- 网络首发：2021-03-10，
  
  纸质出版：2021
- 稿件说明：
移动端阅览
崔伟 1, 李武璟 1, 王聪 1, 等. 深度信念网络在水火电力系统一次调频能力预测中的应用[J]. 西安交通大学学报, 2021,55(3):99-108.

Research on Application of Deep Belief Network in Primary Frequency Modulation Capability of Hydrothermal Power System[J]. 2021, 55(3): 99-108.
崔伟 1, 李武璟 1, 王聪 1, 等. 深度信念网络在水火电力系统一次调频能力预测中的应用[J]. 西安交通大学学报, 2021,55(3):99-108. DOI： 10.7652/xjtuxb202103012.

Research on Application of Deep Belief Network in Primary Frequency Modulation Capability of Hydrothermal Power System[J]. 2021, 55(3): 99-108. DOI： 10.7652/xjtuxb202103012.

摘要

为了准确地预测电力系统一次调频能力

提出了一种采用深度信念网络的水火电力系统一次调频能力预测方法。以新英格兰39节点系统和某电力公司水火电力系统2016—2019年历史数据作为仿真算例

将系统频率、有功负荷、功率缺额、扰动类型、负荷水平、发电机组惯性时间常数、备用容量与总备用容量作为网络的输入特征值

为网络参数训练提供数据支撑; 使用无监督预训练与有监督参数微调相结合来训练网络参数

构建深度信念网络

输出系统一次调频的出力调节曲线

预测水火电力系统一次调频能力。与传统的网络模型进行了对比

结果表明:在新英格兰39节点系统中

最大功率补偿量平均相对误差和均方根误差分别为1.49%和4.04 MW; 在电力公司水火电力系统中

最大功率补偿量平均误差和均方根误差分别为1.18%和18.3 MW

均小于循环神经网络的平均误差1.41%和均方根误差21.6 MW。所提深度信念网络的逐层训练解决了传统网络预测方法的参数优化问题

能够避免陷入局部最优和训练周期过长

应可在突发性故障时为调度中心后续制定防护控制故障策略提供信息支撑。

Abstract

In order to accurately predict the primary frequency regulation capability of the power system

a method for predicting the primary frequency regulation capability of hydrothermal power systems using a deep belief network is proposed. System frequency

active load

power vacancy

disturbance type

load level

generator set inertia time constant

reserve capacity and total reserve capacity are used as input characteristic values of the network to provide data support for network parameter training. The combination of unsupervised pre-training and supervised parameter fine-tuning is used to train the network parameters

build a deep belief network

output the output adjustment curve of the system's primary frequency modulation to predict the primary frequency modulation ability of the hydrothermal power system. Compared with the traditional network model

the results show that: in the New England 39-bus system

the average relative error and root mean square error of the maximum power compensation are 1.49% and 4.04 MW

respectively. In the hydrothermal power system of the electric power company

the average error and the root mean square error of the maximum power compensation are 1.18% and 18.3 MW

respectively

which are smaller than the average error of 1.41% and the root mean square error of the cyclic neural network of 21.6 MW. Compared with the traditional network prediction methods

the layer-by-layer training of deep belief networks solves the problem of parameter optimization and avoids falling into local optimality and long training periods. This model can provide information support for the dispatch center to formulate protection and control failure strategies in the event of sudden failures.

关键词

Keywords

references

高林, 戴义平, 王江峰, 等. 机组一次调频参数指标在线估计方法 [J]. 中国电机工程学报, 2012, 32(16): 62-69.

GAO Lin, DAI Yiping, WANG Jiangfeng, et al. An online estimation method of primary frequency regulation parameters of generation units [J]. Proceedings of the CSEE, 2012, 32(16): 62-69.

张艳军, 高凯, 曲祖义. 基于发电机组出力曲线特征的一次调频性能评价方法 [J]. 电力系统自动化, 2012, 36(7): 99-103.

ZHANG Yanjun, GAO Kai, QU Zuyi. An evaluation method of primary frequency modulation performance based on characteristics of unit output power curves [J]. Automation of Electric Power Systems, 2012, 36(7): 99-103.

曾庆达. 电力系统频率动态特性与一次调频控制 [D]. 广州: 广东工业大学, 2014: 23-38.

王蕊. 火电机组一次调频特性的分析及仿真研究 [D]. 北京: 北京交通大学, 2009: 5-56.

DU L, LIU J Y, LEI X. The primary frequency regulation dynamic model based on power network [C]∥Proceedings of the International Conference on Power System Technology. Piscataway, NJ, USA: IEEE, 2007: 4116197.

陶骞, 贺颖, 潘杨, 等. 电力系统频率分布特征及改进一次调频控制策略研究 [J]. 电力系统保护与控制, 2016, 44(17): 133-138.

TAO Qian, HE Ying, PAN Yang, et al. Characteristics of power system frequency abnormal distribution and improved primary frequency modulation control strategy [J]. Power System Protection and Control, 2016, 44(17): 133-138.

ZHAO Changhong, TOPCU U, LI Na, et al. Design and stability of load-side primary frequency control in power systems [J]. IEEE Transactions on Automatic Control, 2014, 59(5): 1177-1189.

孙辰辰. 发电机组一次调频与二次调频策略及其优化 [D]. 北京: 华北电力大学, 2015: 7-38.

郑涛, 高伏英. 基于PMU的机组一次调频特性参数在线监测 [J]. 电力系统自动化, 2009, 33(11): 57-61, 71.

ZHENG Tao, GAO Fuying. On-line monitoring and computing of unit PFR characteristic parameter based on PMU [J]. Automation of Electric Power Systems, 2009, 33(11): 57-61, 71.

于达仁, 郭钰锋. 电网一次调频能力的在线估计 [J]. 中国电机工程学报, 2004, 24(3): 72-76.

YU Daren, GUO Yufeng. The online estimate of primary frequency control ability in electric power system [J]. Proceedings of the CSEE, 2004, 24(3): 72-76.

贺颖, 潘杨, 陶骞, 等. 考虑调频死区的电网一次调频能力评价指标 [J]. 电力系统保护与控制, 2016, 44(19): 85-90.

HE Ying, PAN Yang, TAO Qian, et al. Evaluation index of power grid primary frequency modulation considering dead zone [J]. Power System Protection and Control, 2016, 44(19): 85-90.

张琦兵, 徐春雷, 刘栋, 等. 基于广域相量测量系统的电网一次调频能力预测 [J]. 电力工程技术, 2019, 38(2): 64-68.

ZHANG Qibing, XU Chunlei, LIU Dong, et al. Ability of primary frequency regulation estimate based on wide area measurement system [J]. Electric Power Engineering Technology, 2019, 38(2): 64-68.

叶圣永, 王晓茹, 刘志刚, 等. 基于受扰严重机组特征及机器学习方法的电力系统暂态稳定评估 [J]. 中国电机工程学报, 2011, 31(1): 46-51.

YE Shengyong, WANG Xiaoru, LIU Zhigang, et al. Power system transient stability assessment based on severely disturbed generator attributes and machine learning method [J]. Proceedings of the CSEE, 2011, 31(1): 46-51.

周艳真, 吴俊勇, 于之虹, 等. 基于转子角轨迹簇特征的电力系统暂态稳定评估 [J]. 电网技术, 2016, 40(5): 1482-1487.

ZHOU Yanzhen, WU Junyong, YU Zhihong, et al. Power system transient stability assessment based on cluster features of rotor angle trajectories [J]. Power System Technology, 2016, 40(5): 1482-1487.

ABDEL-NASSER M, MAHMOUD K. Accurate photovoltaic power forecasting models using deep LSTM-RNN [J]. Neural Computing and Applications, 2019, 31(7): 2727-2740.

仉怡超, 闻达, 王晓茹, 等. 基于深度置信网络的电力系统扰动后频率曲线预测 [J]. 中国电机工程学报, 2019, 39(17): 5095-5104.

ZHANG Yichao, WEN Da, WANG Xiaoru, et al. A method of frequency curve prediction based on deep belief network of post-disturbance power system [J]. Proceedings of the CSEE, 2019, 39(17): 5095-5104.

朱乔木, 党杰, 陈金富, 等. 基于深度置信网络的电力系统暂态稳定评估方法 [J]. 中国电机工程学报, 2018, 38(3): 735-743.

ZHU Qiaomu, DANG Jie, CHEN Jinfu, et al. A method for power system transient stability assessment based on deep belief networks [J]. Proceedings of the CSEE, 2018, 38(3): 735-743.

周念成, 廖建权, 王强钢, 等. 深度学习在智能电网中的应用现状分析与展望 [J]. 电力系统自动化, 2019, 43(4): 180-191.

ZHOU Niancheng, LIAO Jianquan, WANG Qianggang, et al. Analysis and prospect of deep learning application in smart grid [J]. Automation of Electric Power Systems, 2019, 43(4): 180-191.

HINTON G E. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-507.

ZHU Chengzhang, YIN Jianping, LI Qian. A stock decision support system based on DBNs [J]. Journal of Computational Information Systems, 2014, 10(2): 883-893.

PAI M A. Energy function analysis for power system stability [M]. Cham, Germany: Springer, 1989: 256.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

新型冠状病毒肺炎传播动力学模型构建与分析

多工况下离心压气机叶轮-机匣一体联合设计优化

冷库水平空气幕热湿阻隔性能数值模拟研究

电子级超纯氮深冷空分流程节能优化研究

超临界水异常区域热力学特性研究