Optimal Allocation of Active Power for Photovoltaic Power Station Based on Temporal Convolutional Network and Error Function

LI Zhenkun; ZHANG Tianyi; TIAN Fei; DU Haizhou; LI Xin; LI Jianpeng

doi:10.7500/AEPS20220426005

您当前的位置：

首页 >

文章列表页 >

Optimal Allocation of Active Power for Photovoltaic Power Station Based on Temporal Convolutional Network and Error Function

Basic Research | 更新时间：2025-06-16

- Optimal Allocation of Active Power for Photovoltaic Power Station Based on Temporal Convolutional Network and Error Function
- Automation of Electric Power Systems Vol. 47, Issue 6, Pages: 142-149(2023)
- 作者机构：
  
  1.上海电力大学电气工程学院，上海市 200090
  2.中国华电集团有限公司甘肃分公司，甘肃省兰州市 734000
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(52177098);Technology Project of China Huadian Corporation(CHDKJ21-02-138)
- DOI：10.7500/AEPS20220426005
  CLC：
- Received：26 April 2022，
  
  Revised：2022-08-25，
  
  Published Online：14 December 2022，
  
  Published：25 March 2023
- 稿件说明：
移动端阅览
李振坤,张天翼,田飞等.基于时间卷积网络和误差函数的光伏电站有功功率优化分配[J].电力系统自动化,2023,47(6):142-149.

LI Zhenkun,ZHANG Tianyi,TIAN Fei,et al.Optimal Allocation of Active Power for Photovoltaic Power Station Based on Temporal Convolutional Network and Error Function[J].Automation of Electric Power Systems,2023,47(6):142-149.
李振坤,张天翼,田飞等.基于时间卷积网络和误差函数的光伏电站有功功率优化分配[J].电力系统自动化,2023,47(6):142-149. DOI： 10.7500/AEPS20220426005.

LI Zhenkun,ZHANG Tianyi,TIAN Fei,et al.Optimal Allocation of Active Power for Photovoltaic Power Station Based on Temporal Convolutional Network and Error Function[J].Automation of Electric Power Systems,2023,47(6):142-149. DOI： 10.7500/AEPS20220426005.

摘要

随着新能源占比的不断提高，新能源场站通过功率调节参与调度响应逐渐成为新型电力系统的常态，为了减少对调度指令的稳态响应误差，对场站内有功功率分配方案的研究具有重要现实意义。首先，基于历史运行数据建立了光伏电站内各台逆变器的误差函数，引入时间卷积网络对历史数据进行深度学习，构建了逆变器的调度响应误差与有功出力值、目标功率值以及多个环境因素之间的函数映射关系。然后，基于各台逆变器的误差函数，以整个光伏电站对调度指令响应误差最小为目标，建立了有功功率分配模型。接着，为了提高模型的求解速度，提出了将逆变器分层排序的方法，有效减少了优化变量的数量，并采用自适应粒子群优化算法对模型进行了求解。最后，基于中国甘肃某光伏电站进行了仿真分析和现场实验，验证了基于所提模型和算法开发的功率分配模块可以有效提高光伏电站对调度指令的稳态响应精度。

Abstract

With the increasing proportion of renewable energy

it has gradually become a normal state for new power systems that renewable energy stations participate in dispatching response through power regulation. In order to reduce the steady-state response error to dispatching instructions

it is of great practical significance to study the active power allocation scheme in stations. First

the error function of each inverter in the photovoltaic (PV) power station is established based on the historical operation data; the temporal convolutional network is introduced to conduct deep learning based on the historical data; and the function mapping relationship between dispatching response error of the inverter

the active power output value

the target power value and multiple environmental factors is constructed. Then

based on the error function of each inverter

the active power allocation model is established to minimize the response error of the whole PV power station to the dispatching instruction. Moreover

in order to improve the solving speed of the model

a hierarchical sorting method of inverters is proposed to effectively reduce the number of optimization variables

and the adaptive particle swarm optimization algorithm is used to solve the model. Finally

simulation analysis and field experiments are carried out based on a PV power station in Gansu Province

China

which verify that the developed power allocation module based on the proposed model and algorithm effectively improves the steady-state response accuracy of the PV power station to dispatching instructions.

关键词

Keywords

references

孙骁强，刘鑫，程松，等 . 光伏逆变器参与西北送端大电网快速频率响应能力实测分析［J］. 电网技术， 2017 ， 41 （ 9 ）： 2792 - 2798 .

SUN Xiaoqiang ， LIU Xin ， CHENG Song ， et al . Actual measurement and analysis of fast frequency response capability of PV-inverters in northwest power grid ［J］. Power System Technology ， 2017 ， 41 （ 9 ）： 2792 - 2798 .

颜伟，赵瑞锋，赵霞，等 . 自动发电控制中控制策略的研究发展综述［J］. 电力系统保护与控制， 2013 ， 41 （ 8 ）： 149 - 155 .

YAN Wei ， ZHAO Ruifeng ， ZHAO Xia ， et al . Review on control strategies in automatic generation control ［J］. Power System Protection and Control ， 2013 ， 41 （ 8 ）： 149 - 155 .

魏世贵，刘双 . AGC/AVC在光伏电站的应用［J］. 江苏电机工程， 2013 ， 32 （ 2 ）： 35 - 37 .

WEI Shigui ， LIU Shuang . Application of AGC/AVC in photovoltaic power station ［J］. Jiangsu Electrical Engineering ， 2013 ， 32 （ 2 ）： 35 - 37 .

刘双，张明月 . 光伏电站AGC/AVC系统功能设计［EB/OL］.［ 2022-03-05 ］. https：//www.doc88.com/p-0012079229151.html https://www.doc88.com/p-0012079229151.html .

LIU Shuang ， ZHANG Mingyue . Functional design of PV power station AGC/AVC system ［EB/OL］. ［ 2022-03-05 ］. https：//www.doc88.com/p-0012079229151.html https://www.doc88.com/p-0012079229151.html .

王淑超，段胜朋，侯炜，等 . 光伏电站分层分布式自动功率控制技术［J］. 电力系统自动化， 2016 ， 40 （ 8 ）： 126 - 132 .

WANG Shuchao ， DUAN Shengpeng ， HOU Wei ， et al . Hierarchical distributed control structure based AGC technology for photovoltaic power plants ［J］. Automation of Electric Power Systems ， 2016 ， 40 （ 8 ）： 126 - 132 .

刘琳 . 光伏电站有功功率优化分配［J］. 热力发电， 2015 ， 44 （ 11 ）： 104 - 108 .

LIU Lin . Active power control in photovoltaic power plants ［J］. Thermal Power Generation ， 2015 ， 44 （ 11 ）： 104 - 108 .

王淑超，段胜朋，王健，等 . 光伏电站面向快速频率响应的优化控制技术研究与实践［J］. 电力系统保护与控制， 2019 ， 47 （ 14 ）： 59 - 70 .

WANG Shuchao ， DUAN Shengpeng ， WANG Jian ， et al . Research and practice of fast frequency response oriented control optimization technology of PV power stations ［J］. Power System Protection and Control ， 2019 ， 47 （ 14 ）： 59 - 70 .

BAI S J ， KOLTER J Z ， KOLTUN V . An empirical evaluation of generic convolutional and recurrent networks for sequence modeling ［EB/OL］. ［ 2022-03-05 ］. https：//www.doc88.com/p-9148411273738.html https://www.doc88.com/p-9148411273738.html .

符杨，任子旭，魏书荣，等 . 基于改进LSTM-TCN模型的海上风电超短期功率预测［J］. 中国电机工程学报， 2022 ， 42 （ 12 ）： 4292 - 4303 .

FU Yang ， REN Zixu ， WEI Shurong ， et al . Ultra-short-term power prediction of offshore wind power based on improved LSTM-TCN model ［J］. Proceedings of the CSEE ， 2022 ， 42 （ 12 ）： 4292 - 4303 .

张孝远，张金浩，蒋亚俊 . 基于改进TCN模型的动力电池健康状态评估［J］. 储能科学与技术， 2022 ， 11 （ 5 ）： 1617 - 1626 .

ZHANG Xiaoyuan ， ZHANG Jinhao ， JIANG Yajun . Power battery health evaluation based on improved TCN model ［J］. Energy Storage Science and Technology ， 2022 ， 11 （ 5 ）： 1617 - 1626 .

国家质量监督检验检疫总局，中国国家标准化管理委员会 . 光伏发电站接入电力系统技术规定： GB/T 19964—2012 ［S］. 北京：中国标准出版社， 2013 .

General Administration of Quality Supervision ， Inspection and Quarantine of the People’s Republic of China ， Standardization Administration of the People’s Republic of China . Technical requirements for connecting photovoltaic power station to power system ： GB/T 19964—2012 ［S］. Beijing ： Standards Press of China ， 2013 .

刘梦欣，王杰，陈陈 . 电力系统频率控制理论与发展［J］. 电工技术学报， 2007 ， 22 （ 11 ）： 135 - 145 .

LIU Mengxin ， WANG Jie ， CHEN Chen . Theory and development of power system frequency control ［J］. Transactions of China Electrotechnical Society ， 2007 ， 22 （ 11 ）： 135 - 145 .

杨国华，郑豪丰，张鸿皓，等 . 基于Holt-Winters指数平滑和时间卷积网络的短期负荷预测［J］. 电力系统自动化， 2022 ， 46 （ 6 ）： 73 - 82 .

YANG Guohua ， ZHENG Haofeng ， ZHANG Honghao ， et al . Short-term load forecasting based on Holt-Winters exponential smoothing and temporal convolutional network ［J］. Automation of Electric Power Systems ， 2022 ， 46 （ 6 ）： 73 - 82 .

OORD A ， DIELEMAN S ， ZEN H ， et al . Wavenet： a generative model for raw audio ［EB/OL］. ［ 2022-03-05 ］. https：//arxiv.org/abs/1609.03499 https://arxiv.org/abs/1609.03499 .

LEA C ， FLYNN M D ， VIDAL R ， et al . Temporal convolutional networks for action segmentation and detection ［C］// 2017 IEEE Conference on Computer Vision and Pattern Recognition ， July 21-26 ， 2017 ， Honolulu， USA .

ZHAO W ， TAO T ， ZIO E ， et al . A novel hybrid method of parameters tuning in support vector regression for reliability prediction： particle swarm optimization combined with analytical selection ［J］. IEEE Transactions on Reliability ， 2016 ， 65 （ 3 ）： 1393 - 1405 .

PEDREGOSA F ， VAROQUAUX G ， GRAMFORT A ， et al . Scikit-learn： machine learning in Python ［J］. The Journal of Machine Learning Research ， 2011 ， 12 ： 2825 - 2830 .

KETKAR N . Deep learning with Python ［M］. Berkeley， USA ： Apress ， 2017 .

FARHA Y A ， GALL J . MS-TCN： multi-stage temporal convolutional network for action segmentation ［C］// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）， June 15-20 ， 2019 ， Long Beach， USA .

KENNEDY J ， EBERHART R . Particle swarm optimization ［C］// Proceedings of ICNN’95-International Conference on Neural Networks ， November 27-December 1 ， 1995 ， Perth， Australia .

ABADI M ， BARHAM P ， CHEN J ， et al . TensorFlow： a system for large-scale machine learning ［C］// 12th USENIX Symposium on Operating Systems Design and Implementation ， November 2-4 ， 2016 ， Savannah， USA .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimal Allocation Method of Grid-connected Power for Renewable Energy Based on Newton Iterative Sensitivity Collaboration

Current Optimization Strategy for CLLC Resonant Converter Based on Over-resonant Frequency Modulation and Extended Phase-shift Control

Related Author

ZHENG Xin

QI Lei

SUN Xiaofeng

JIANG Haoyu

ZHAO Wei

WANG Yichen

WANG Feng

ZHUO Fang

Related Institution

School of Electrical Engineering, Yanshan University

School of Electrical Engineering, Xi’an Jiaotong University

Electric Power Research Institute of State Grid Hunan Electric Power Co., Ltd.

Electric Power Research Institution of China Southern Power Grid

School of Electrical and Information Engineering, Hunan University

⁰