基于功率预测精度提升和市场交易的平抑新能源出力波动策略

doi:10.16183/j.cnki.jsjtu.2023.312

上海交通大学学报 ›› 2025, Vol. 59 ›› Issue (2): 221-229.doi: 10.16183/j.cnki.jsjtu.2023.312

• 新型电力系统与综合能源 • 上一篇下一篇

基于功率预测精度提升和市场交易的平抑新能源出力波动策略

梁以恒¹^,², 杨冬梅¹^,², 刘刚¹^,², 叶闻杰¹^,², 杨翼泽¹^,², 钱涛³, 胡秦然³()

1.南瑞集团有限公司(国网电力科学研究院有限公司),南京 211100
2.国电南瑞科技股份有限公司, 南京 211100
3.东南大学电气工程学院,南京 210096

收稿日期:2023-07-12 修回日期:2023-09-18 接受日期:2023-09-19 出版日期:2025-02-28 发布日期:2025-03-11
通讯作者: 胡秦然,教授,博士生导师;E-mail:qhu@seu.edu.cn.
作者简介:梁以恒(1997—),硕士,从事新能源功率预测研究.
基金资助:
2022年度江苏省碳达峰碳中和科技创新专项资金(产业前瞻与关键核心技术攻关)重点项目(BE2022003)

A Strategy for Smoothing Power Fluctuations of New Energy Based on Improved Power Prediction Accuracy and Market Transaction

LIANG Yiheng¹^,², YANG Dongmei¹^,², LIU Gang¹^,², YE Wenjie¹^,², YANG Yize¹^,², QIAN Tao³, HU Qinran³()

1. NARI Group Corporation (State Grid Electric Power Research Institute), Nanjing 211100, China
2. NARI Technology Co., Ltd., Nanjing 211100, China
3. School of Electrical Engineering, Southeast University, Nanjing 210096, China

Received:2023-07-12 Revised:2023-09-18 Accepted:2023-09-19 Online:2025-02-28 Published:2025-03-11

摘要/Abstract

摘要：

新能源的不确定性导致功率预测误差,造成新能源发电商因投标电量存在偏差而产生弃风损失和偏差惩罚.提出基于特征约束的多层感知机(MLP)功率预测算法结合储能双边交易提供电量支撑,降低投标偏差.首先,通过改进网络结构和自适应学习提高MLP隐含层关联度,加强对输入数据非线性规则的表征能力,提高功率预测精度.其次,提出新能源发电商与储能商在进入日前市场之前进行双边交易的模式,进一步降低因功率预测误差引起的偏差惩罚和弃风损失.最后,算例证明基于特征约束的MLP有效提高新能源功率预测精度,并且通过与储能商双边交易,有效提高新能源发电商的总体收益.

关键词: 新能源功率预测, 基于特征约束的多层感知机, 双边交易

Abstract:

The uncertainty of new energy results in power prediction errors, causing new energy producers to bear high wind curtailment losses and deviation penalties due to bidding deviations. To address these issues, this paper proposes a feature-constrained multi-layer perception (MLP) power prediction algorithm, combined with storage-based bilateral transactions, to provide power support and reduce bidding deviations. First, the MLP model is enhanced by improving the relevancy of the hidden layers through adaptive learning, which strengthens its ability to capture nonlinear rules in input data and improves power prediction accuracy. Then, the algorithm allows for bilateral transactions between new energy producers and storage enterprise before entering the day-ahead market, helping mitigate the penalties associated with prediction errors including deviation and curtailment costs. Finally, the case study demonstrates that the feature-constrained MLP effectively improves the power prediction accuracy. Additionally, engaging in bilateral transactions with storage enterprise significantly reduces the costs incurred by new energy producers due to bid deviations.

Key words: new energy power prediction, feature-constrained multi-layer perception (MLP), bilateral transaction

中图分类号:

X773

梁以恒, 杨冬梅, 刘刚, 叶闻杰, 杨翼泽, 钱涛, 胡秦然. 基于功率预测精度提升和市场交易的平抑新能源出力波动策略[J]. 上海交通大学学报, 2025, 59(2): 221-229.

LIANG Yiheng, YANG Dongmei, LIU Gang, YE Wenjie, YANG Yize, QIAN Tao, HU Qinran. A Strategy for Smoothing Power Fluctuations of New Energy Based on Improved Power Prediction Accuracy and Market Transaction[J]. Journal of Shanghai Jiao Tong University, 2025, 59(2): 221-229.

图/表 10

图1

图2

图3

图4

表1

图5

表2

图6

表3

图7

参考文献 19

[1]	习近平. 继往开来, 开启全球应对气候变化新征程: 在气候雄心峰会上的讲话[N]. 中华人民共和国国务院公报, 2020(35): 7.
	XI Jinping. Building on past achievements and launching a new journey for global climate actions—Statement at the climate ambition summit[N]. Gazette of the State Council of the People’s Republic of China, 2020(35): 7.
[2]	张扬科, 李刚, 李秀峰. 基于典型代表电站和改进SVM的区域光伏功率短期预测方法[J]. 电力自动化设备, 2021, 41(11): 205-210.
	ZHANG Yangke, LI Gang, LI Xiufeng. Short-term forecasting method for regional photovoltaic power based on typical representative power stations and improved SVM[J]. Electric Power Automation Equipment, 2021, 41(11): 205-210.
[3]	葛乐, 陆文伟, 袁晓冬, 等. 基于改进相似日和ABC-SVM的光伏电站功率预测[J]. 太阳能学报, 2018, 39(3): 775-782.
	GE Le, LU Wenwei, YUAN Xiaodong, et al. Power forecasting of photovoltaic plant based on improved similar day and ABC-SVM[J]. Acta Energiae Solaris Sinica, 2018, 39(3): 775-782.
[4]	马国锋. 基于机器学习的风电短期功率预测的研究与实现[D]. 呼和浩特: 内蒙古农业大学, 2021.
	MA Guofeng. Research and implementation of short-term wind power prediction based on machine learning[D]. Hohhot: Inner Mongolia Agricultural University, 2021.
[5]	刘颖明, 王维, 王晓东, 等. 结合风功率预测及储能能量状态的模糊控制策略平滑风电出力[J]. 电网技术, 2019, 43(7): 2535-2543.
	LIU Yingming, WANG Wei, WANG Xiaodong, et al. A fuzzy control strategy combined with wind power prediction and energy storage SOE for smoothing wind power output[J]. Power System Technology, 2019, 43(7): 2535-2543.
[6]	李大中, 李颖宇. 基于深度学习与误差修正的超短期风电功率预测[J]. 太阳能学报, 2021, 42(12): 200-205.
	LI Dazhong, LI Yingyu. Ultra-short term wind power prediction based on deep learning and error correction[J]. Acta Energiae Solaris Sinica, 2021, 42(12): 200-205.
[7]	柳杰, 苗宗成, 王清云. 数据驱动的锂离子电池全生命周期状态参数评估[J]. 科学通报, 2023, 68(6): 644-655.
	LIU Jie, MIAO Zongcheng, WANG Qingyun. Data-driven full life-cycle state parameter assessment of Li-ion batteries[J]. Chinese Science Bulletin, 2023, 68(6): 644-655.
[8]	MUHAMMAD EHSAN R, SIMON S P, VENKATESWARAN P R. Day-ahead forecasting of solar photovoltaic output power using multilayer perceptron[J]. Neural Computing & Applications, 2017, 28(12): 3981-3992.
[9]	张惠娟, 刘琪, 岑泽尧, 等. 基于GWO-MLP的光伏系统输出功率短期预测模型[J]. 电测与仪表, 2022, 59(7): 72-77.
	ZHANG Huijuan, LIU Qi, CEN Zeyao, et al. Short-term prediction model of output power of photovoltaic system based on GWO-MLP[J]. Electrical Measurement & Instrumentation, 2022, 59(7): 72-77.
[10]	雷珽, 欧阳曾恺, 李征, 等. 平抑风能波动的储能电池SOC与滤波协调控制策略[J]. 电力自动化设备, 2015, 35(7): 126-131.
	LEI Ting, OUYANG Zengkai, LI Zheng, et al. Coordinated control of battery SOC maintaining and filtering for wind power fluctuation smoothing[J]. Electric Power Automation Equipment, 2015, 35(7): 126-131.
[11]	夏清, 杨知方, 赖晓文, 等. 基于分时容量电价的新型电力现货市场设计[J]. 电网技术, 2022, 46(5): 1771-1779.
	XIA Qing, YANG Zhifang, LAI Xiaowen, et al. Electricity market design based on temporal pricing of renewable capacity[J]. Power System Technology, 2022, 46(5): 1771-1779.
[12]	FANG X, HU Q R, LI F X, et al. Coupon-based demand response considering wind power uncertainty: A strategic bidding model for load serving entities[J]. IEEE Transactions on Power Systems, 2016, 31(2): 1025-1037.
[13]	刘传斌, 矫文书, 吴秋伟, 等. 基于模型预测控制的风储联合电场参与电网二次调频策略[J]. 上海交通大学学报, 2024, 58(1): 91-101. doi: 10.16183/j.cnki.jsjtu.2022.217
	LIU Chuanbin, JIAO Wenshu, WU Qiuwei, et al. Strategy of wind-storage combined system participating in power system secondary frequency regulation based on model predictive control[J]. Journal of Shanghai Jiao Tong University, 2024, 58(1): 91-101.
[14]	杨波, 汤文成, 吴福保, 等. 考虑CVaR的“新能源+储能” 电厂日前市场投标策略[J]. 电力系统保护与控制, 2022, 50(9): 93-100.
	YANG Bo, TANG Wencheng, WU Fubao, et al. Day-ahead market bidding strategy for “renewable energy + energy storage” power plants considering conditional value-at-risk[J]. Power System Protection & Control, 2022, 50(9): 93-100.
[15]	马静, 沈玉明, 荣秀婷, 等. 考虑储能用户与新能源双边交易调峰服务的电力系统联合运营模式[J]. 电力自动化设备, 2023, 43(1): 113-120.
	MA Jing, SHEN Yuming, RONG Xiuting, et al. Joint operation mode of power system considering bilateral peak regulation service transaction between energy storage users and new energy[J]. Electric Power Automation Equipment, 2023, 43(1): 113-120.
[16]	胡珊珊, 张乐平, 王吉. 基于多层感知机的多维条件下电能表准确度预测模型[J]. 电测与仪表, 2018, 55(16): 125-131.
	HU Shanshan, ZHANG Leping, WANG Ji. Power meter accuracy forecast model based on multidimensional conditions by multi-layer perceptions[J]. Electrical Measurement & Instrumentation, 2018, 55(16): 125-131.
[17]	刘星斗. 基于WRF与深度神经网络的风电功率预测[D]. 济南: 山东大学, 2022.
	LIU Xingdou. Wind power prediction based on wrf and deep neural network[D]. Jinan: Shandong University, 2022.
[18]	TANG X L, LIU N C, WAN Y L, et al. Multi-step model predictive control based on online support vector regression optimized by multi-agent particle swarm optimization algorithm[J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(5): 607-612. doi: 10.1007/s12204-018-1990-1
[19]	杨建华, 张步涵, 李俊芳. 华中电力市场MCP与PAB竞价结算模式研究[J]. 水电能源科学, 2009, 27(6): 219-222.
	YANG Jianhua, ZHANG Buhan, LI Junfang. Research on bidding and clearing of PAB and MCP in power market of central China grid[J]. Water Resources & Power, 2009, 27(6): 219-222.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	7	9	0	35

来源	本网站	其他网站

次数	32	19
比例	63%	37%

摘要

301

最新录用	在线预览	正式出版

61	0	240

编号	最大功率/MW	最小功率/MW	爬坡功率/MW	成本常数项系数/元	成本一次项系数/ (元·MW^-1)	成本二次项系数/ (元·MW^-2)
1	80	20	20	3360	153	0.01
2	50	15	13	2450	164	0.01
3	35	10	9	3020	182	0.02
4	30	10	8	2970	177	0.01
5	40	12	10	2730	163	0.01

算法	均方根误差	平均绝对误差	平均绝对百分比误差/%
时序模拟	31.50	23.10	18.24
支持向量机	18.57	14.04	9.29
随机森林	15.14	10.80	7.21
MLP	15.72	11.57	7.37
基于特征约束的MLP	10.46	7.73	5.16

场景	弃风损失	惩罚成本	风电商收益	储能商收益
1	1.3	1.9	33.5	0.7
2	0.5	0.8	37.6	1.2

基于功率预测精度提升和市场交易的平抑新能源出力波动策略

A Strategy for Smoothing Power Fluctuations of New Energy Based on Improved Power Prediction Accuracy and Market Transaction

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 19

相关文章 0

编辑推荐 0

Metrics

本文评价