基于mRMR-XGboost-IDM模型的两阶段可调鲁棒经济调度

doi:10.12204/j.issn.1000-7229.2022.09.015

摘要/Abstract

摘要：

源荷双端不确定性导致的频繁弃风切负荷现象严重影响微网运行经济性。为有效应对源荷不确定性,文章提出一种基于最小冗余最大相关-极限梯度提升算法改进非精确狄利克雷模型(minimum redundancy and maximum correlation-extreme gradient boosting improved imprecise Dirichlet model, mRMR-XGboost-IDM)的两阶段可调鲁棒微网经济调度模型。首先,针对基于非精确狄利克雷模型(imprecise dirichlet model, IDM模型的不确定模糊集高度依赖历史数据数量的不足,结合mRMR-XGboost预测方法对其进行改进,扩大历史数据体量以提高所得不确定区间的精确度。其次,基于得到的不确定区间,构建微网两阶段鲁棒经济调度模型,并引入可调鲁棒参数协调经济性和鲁棒性。最后,采用列约束生成算法(column-and-constraint generation,C&CG)、对偶理论以及大M法求解最优经济调度策略。算例验证了所提模型可提高不确定区间刻画准确度,有效应对源荷不确定性并提高系统运行经济性。

关键词: 可调鲁棒优化, 数据驱动, 极限梯度提升, 非精确狄利克雷模型, 风电不确定性

Abstract:

Frequent wind curtailment and load shedding caused by the uncertainty of both source and load seriously affects the economy of microgrid operation. To effectively deal with the uncertainty of both source and load, this paper proposes a two-stage adjustable robust microgrid economic dispatch model based on the mRMR-XGboost-IDM model. Firstly, aiming at the problem that the uncertain ambiguity set based on the IDM model is highly dependent on the amount of historical data, mRMR-XGboost prediction method is introduced, and the volume of historical data is enlarged to improve the accuracy of the obtained uncertainty interval. Secondly, on the basis of the obtained uncertainty interval, a two-stage robust economic dispatch model of the microgrid is constructed, and adjustable robust parameters are introduced to coordinate economy and robustness. Finally, the column-and-constraint generation algorithm, duality theory, and big-M method are used to solve the optimal economic dispatch strategy. The experimental cases verify that the proposed model can improve the accuracy of the uncertainty interval description, effectively deal with the uncertainty of source and load and improve the economy of system operation.

Key words: adjustable robust optimization, data-driven, extreme gradient boosting, imprecise Dirichlet model, wind power uncertainty

中图分类号:

TM73

滕家琛, 刘洋, 邬嘉雨, 王磊, 张杰. 基于mRMR-XGboost-IDM模型的两阶段可调鲁棒经济调度[J]. 电力建设, 2022, 43(9): 140-150.

TENG Jiachen, LIU Yang, WU Jiayu, WANG Lei, ZHANG Jie. Two-Stage Adjustable Robust Economic Dispatch Based on mRMR-XGboost-IDM Model[J]. ELECTRIC POWER CONSTRUCTION, 2022, 43(9): 140-150.

图/表 10

图1 mRMR-XGboost-IDM模型原理框架

Fig.1 Principle framework of mRMR-XGboost-IDM model

图2 模型迭代求解过程

Fig.2 Model iterative solution process

图3 基于IDM构建模糊集与盒式不确定集风电出力区间对比

Fig.3 Comparison of the wind power uncertainty interval between IDM based ambiguity set construction and cassette uncertainty set

图4 不同历史数据体量驱动下生成风电出力不确定区间对比

Fig.4 Comparison of the wind power uncertainty interval generated by different historical data volume

表1 风电出力不确定区间上下界平均偏移系数

Table 1 Average offset coefficient of upper and lower bounds of the wind power uncertainty interval %

表2 Comparison of operating costs in data-driven ARO and traditional ARO economic dispatch model 元

Table 2

表3 不同优化方法下经济调度策略运行成本对比

Table 3 Comparison of economic dispatch operating costs under different optimization methods

图5 随机场景下不同优化方法总运行成本散点图

Fig.5 Scatter plot of total operating costs using different optimization methods in random scenarios

图6 最优日前调度方案

Fig.6 Optimal day-ahead economic dispatch

表4 Comparison of economic dispatch operating costs under different adjustable robust parameter 元

Table 4

参考文献 27

[1]	孙黎霞, 鞠平, 白景涛, 等. 计及蓄电池寿命的冷热电联供型微电网多目标经济优化运行[J]. 发电技术, 2020, 41(1): 64-72.
	SUN Lixia, JU Ping, BAI Jingtao, et al. Multi-objective economic optimal operation of microgrid based on combined cooling, heating and power considering battery life[J]. Power Generation Technology, 2020, 41(1): 64-72.
[2]	刘畅, 卓建坤, 赵东明, 等. 利用储能系统实现可再生能源微电网灵活安全运行的研究综述[J]. 中国电机工程学报, 2020, 40(1): 1-18, 369.
	LIU Chang, ZHUO Jiankun, ZHAO Dongming, et al. A review on the utilization of energy storage system for the flexible and safe operation of renewable energy microgrids[J]. Proceedings of the CSEE, 2020, 40(1): 1-18, 369.
[3]	郭威, 杨鹏, 孙胜博, 等. 计及生物质能的热电联供系统经济运行优化策略[J]. 电力系统保护与控制, 2021, 49(11): 88-96.
	GUO Wei, YANG Peng, SUN Shengbo, et al. Optimization strategy of a rural combined heat and power system considering biomass energy[J]. Power System Protection and Control, 2021, 49(11): 88-96.
[4]	刘万福, 赵树野, 康赫然, 等. 考虑源荷双重不确定性的多能互补系统两阶段鲁棒优化调度[J]. 电力系统及其自动化学报, 2020, 32(12): 69-76.
	LIU Wanfu, ZHAO Shuye, KANG Heran, et al. Two-stage robust optimal scheduling for multi-energy complementary system considering source-load double uncertainties[J]. Proceedings of the CSU-EPSA, 2020, 32(12): 69-76.
[5]	HOSSEINI S M, CARLI R, DOTOLI M. Robust optimal energy management of a residential microgrid under uncertainties on demand and renewable power generation[J]. IEEE Transactions on Automation Science and Engineering, 2021, 18(2): 618-637. doi: 10.1109/TASE.2020.2986269 URL
[6]	刘梦依, 邱晓燕, 张楷, 等. 计及源-荷不确定性的高比例可再生能源系统协同优化运行[J]. 电力建设, 2018, 39(12): 55-62.
	LIU Mengyi, QIU Xiaoyan, ZHANG Kai, et al. Collaborative optimization operation of power systems with high proportion of renewable energy considering uncertainty of generation and load[J]. Electric Power Construction, 2018, 39(12): 55-62.
[7]	靳康萌, 张沛, 邓晓洋, 等. 基于K-means聚类技术改进的多线性蒙特卡洛概率能流算法[J]. 电网技术, 2019, 43(1): 65-74.
	JIN Kangmeng, ZHANG Pei, DENG Xiaoyang, et al. Improved multi-linear Monte Carlo probabilistic energy flow calculation method based on K-means clustering technique[J]. Power System Technology, 2019, 43(1): 65-74.
[8]	WEI W, LIU F, MEI S W. Distributionally robust co-optimization of energy and reserve dispatch[J]. IEEE Transactions on Sustainable Energy, 2016, 7(1): 289-300. doi: 10.1109/TSTE.2015.2494010 URL
[9]	刘一欣, 郭力, 王成山. 微电网两阶段鲁棒优化经济调度方法[J]. 中国电机工程学报, 2018, 38(14): 4013-4022.
	LIU Yixin, GUO Li, WANG Chengshan. Economic dispatch of microgrid based on two stage robust optimization[J]. Proceedings of the CSEE, 2018, 38(14): 4013-4022.
[10]	温俊强, 曾博, 张建华. 配电网中分布式风电可调鲁棒优化规划[J]. 电网技术, 2016, 40(1): 227-233.
	WEN Junqiang, ZENG Bo, ZHANG Jianhua. Adjustable robust optimization for distributed wind power planning in distribution network[J]. Power System Technology, 2016, 40(1): 227-233.
[11]	周玮, 胡姝博, 孙辉, 等. 考虑大规模风电并网的电力系统区间非线性经济调度研究[J]. 中国电机工程学报, 2017, 37(2): 557-564.
	ZHOU Wei, HU Shubo, SUN Hui, et al. Interval nonlinear economic dispatch in large scale wind power integrated system[J]. Proceedings of the CSEE, 2017, 37(2): 557-564.
[12]	朱嘉远, 刘洋, 许立雄, 等. 风电全消纳下的配电网储能可调鲁棒优化配置[J]. 电网技术, 2018, 42(6): 1875-1883.
	ZHU Jiayuan, LIU Yang, XU Lixiong, et al. Adjustable robust optimization for energy storage system in distribution network based on wind power full accommodation[J]. Power System Technology, 2018, 42(6): 1875-1883.
[13]	朱嘉远, 刘洋, 许立雄, 等. 考虑风电消纳的热电联供型微网日前鲁棒经济调度[J]. 电力系统自动化, 2019, 43(4): 40-48.
	ZHU Jiayuan, LIU Yang, XU Lixiong, et al. Robust day-ahead economic dispatch of microgrid with combined heat and power system considering wind power accommodation[J]. Automation of Electric Power Systems, 2019, 43(4): 40-48.
[14]	贺帅佳, 阮贺彬, 高红均, 等. 分布鲁棒优化方法在电力系统中的理论分析与应用综述[J]. 电力系统自动化, 2020, 44(14): 179-191.
	HE Shuaijia, RUAN Hebin, GAO Hongjun, et al. Overview on theory analysis and application of distributionally robust optimization method in power system[J]. Automation of Electric Power Systems, 2020, 44(14): 179-191.
[15]	XIONG P, JIRUTITIJAROEN P, SINGH C. A distributionally robust optimization model for unit commitment considering uncertain wind power generation[J]. IEEE Transactions on Power Systems, 2017, 32(1): 39-49. doi: 10.1109/TPWRS.2016.2544795 URL
[16]	税月, 刘俊勇, 高红均, 等. 考虑风电不确定性的电热综合系统分布鲁棒协调优化调度模型[J]. 中国电机工程学报, 2018, 38(24): 7235-7247.
	SHUI Yue, LIU Junyong, GAO Hongjun, et al. A distributionally robust coordinated dispatch model for integrated electricity and heating systems considering uncertainty of wind power[J]. Proceedings of the CSEE, 2018, 38(24): 7235-7247.
[17]	ZHAO C Y, JIANG R W. Distributionally robust contingency-constrained unit commitment[J]. IEEE Transactions on Power Systems, 2018, 33(1): 94-102. doi: 10.1109/TPWRS.2017.2699121 URL
[18]	WU J, LIU Y, CHEN X, et al. Data-driven adjustable robust day-ahead economic dispatch strategy considering uncertainties of wind power generation and electric vehicles[J]. International Journal of Electrical Power & Energy Systems. 2022. 138:107898. doi: 10.1016/j.ijepes.2021.107898 URL
[19]	ZHANG Y M, HAN X S, YANG M, et al. Adaptive robust unit commitment considering distributional uncertainty[J]. International Journal of Electrical Power & Energy Systems, 2019, 104: 635-644. doi: 10.1016/j.ijepes.2018.07.048 URL
[20]	段偲默, 苗世洪, 霍雪松, 等. 基于动态Copula的风光联合出力建模及动态相关性分析[J]. 电力系统保护与控制, 2019, 47(5): 35-42.
	DUAN Simo, MIAO Shihong, HUO Xuesong, et al. Modeling and dynamic correlation analysis of wind/solar power joint output based on dynamic Copula[J]. Power System Protection and Control, 2019, 47(5): 35-42.
[21]	杨少瑜, 黄国栋, 林星宇, 等. 基于拉格朗日插值法的概率建模方法及其在概率潮流分析中的应用[J]. 现代电力, 2021, 38(4): 378-385.
	YANG Shaoyu, HUANG Guodong, LIN Xingyu, et al. A Lagrange interpolation based probabilistic modeling method and its application in probabilistic power flow analysis[J]. Modern Electric Power, 2021, 38(4): 378-385.
[22]	唐子卓, 刘洋, 许立雄, 等. 基于负荷数据频域特征和LSTM网络的类别不平衡负荷典型用电模式提取方法[J]. 电力建设, 2020, 41(8): 17-24.
	TANG Zizhuo, LIU Yang, XU Lixiong, et al. Imbalanced-load pattern extraction method based on frequency domain characteristics of load data and LSTM network[J]. Electric Power Construction, 2020, 41(8): 17-24.
[23]	邱英强, 吴京龙, 陈俊, 等. 基于机器学习算法的风电机组故障预测系统设计[J]. 自动化与仪器仪表, 2021(9): 190-193.
	QIU Yingqiang, WU Jinglong, CHEN Jun, et al. Design of wind turbine fault prediction system based on machine learning algorithm[J]. Automation & Instrumentation, 2021(9): 190-193.
[24]	董骁翀, 孙英云, 蒲天骄. 基于条件生成对抗网络的可再生能源日前场景生成方法[J]. 中国电机工程学报, 2020, 40(17): 5527-5536.
	DONG Xiaochong, SUN Yingyun, PU Tianjiao. Day-ahead scenario generation of renewable energy based on conditional GAN[J]. Proceedings of the CSEE, 2020, 40(17): 5527-5536.
[25]	甘秀娜, 李明, 王月波. 基于信息粒化的区间值信息系统不确定性度量方法[J]. 计算机应用与软件, 2021, 38(8): 107-114.
	GAN Xiuna, LI Ming, WANG Yuebo. Uncertainty measurement method of interval-valued information system based on information granulation[J]. Computer Applications and Software, 2021, 38(8): 107-114.
[26]	PENG H C, LONG F H, DING C. Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226-1238. doi: 10.1109/TPAMI.2005.159 URL
[27]	CHEN T, GUESTRIN C. XGBoost:A Scalable Tree Boosting System[C]:// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco: ACM, 2016:785-794.