基于改进闭环预测-优化互嵌技术的含水风光电力系统两阶段调度方法

刘继春; 肖煜瑾; 邱高; 唐伦; 孙毅; 李凌昊

PDF(1055 KB)

电力建设 ›› 2025

基于改进闭环预测-优化互嵌技术的含水风光电力系统两阶段调度方法

刘继春¹, 肖煜瑾¹, 邱高¹, 唐伦^2,3, 孙毅³, 李凌昊⁴

作者信息 +

An Improved Closed-loop Predict-and-optimize Intertwined Framework-based Two-stage Dispatch for Hydropower-wind-photovoltaic Involved Power Systems

LIU Jichun¹, XIAO Yujin¹, QIU Gao¹, TANG Lun^2,3, SUN Yi³, LI Linghao⁴

Author information +

文章历史 +

摘要

【目的】水风光强随机性加剧了常用开环预测后优化(open-looped predict-then-optimize, OPO)调度方法在计算复杂度和运行经济性方面的矛盾。【方法】对此,提出含水风光电力系统下基于改进闭环预测-优化互嵌技术(closed-loop predict-and-optimize intertwined framework, CPO)的两阶段调度方法。首先,构建了考虑串、并、混联多类水电群的含水风光电力系统两阶段调度模型;然后,以水风光实际和预测曲线在两阶段调度模型下计算所得系统成本的绝对偏差作为损失函数,训练以经济性为导向的水风光预测模型;最终,结合方差、布林带和自相关函数量化新能源出力及水电站入库流量的波动强度,以构建融入弹性网络回归的混合正则化策略,在优化CPO训练复杂度的同时,保证其在多重不确定性下的性能。【结果】Matlab仿真结果表明,在丰、枯、平水期典型月内,采用改进CPO方法得到的月平均实际系统成本相较传统OPO方法分别降低了0.74%、0.57%、0.66%,验证了该方法在提升电力调度经济性方面的有效性。【结论】文章所提的改进CPO方法在水风光总体预测精度下降不大且部分时段精度提升的情况下显著降低了实际系统成本,优化了调度经济性,且在不确定性程度更高的场景中,该方法提升经济性的效果更为突出。

Abstract

[Objective] The strong randomness of hydropower, wind power and photovoltaic power exacerbates the contradiction between computational complexity and operational economy of the traditional open-loop predict-then-optimize (OPO) dispatch. [Methods] To conquer this, a two-stage dispatch method based on the improved closed-loop predict-and-optimize intertwined framework (CPO) for hydropower-wind-photovoltaic involved power systems is proposed. Firstly, a two-stage dispatch model for hydropower-wind-photovoltaic power systems involving series, parallel and hybrid-connected hydropower groups is constructed. Then, to train an economy-oriented prediction model for inflow and renewable energy generation, a loss function is established by taking absolute deviation between the system cost calculated by the ground truths and predictions of inflow and renewable energies. Finally, by combining the variance, Bollinger bands and autocorrelation function, the fluctuation intensities of renewable energy generation and hydropower inflow are quantified, such that a hybrid regularization strategy involving Elastic Net Regression is constructed to balance the training complexity and performance of CPO under multiple uncertainties. [Results] The Matlab simulation results show that, during the typical months of the wet, dry, and normal water periods, the monthly average actual system cost obtained by using the improved CPO method is reduced by 0.74%, 0.57%, and 0.66%, respectively, compared with the traditional OPO method, which verifies the effectiveness of this method in improving the economic efficiency of power dispatch. [Conclusions] The improved CPO method proposed in this paper significantly reduces the actual system cost and optimizes the economic efficiency of dispatch when the overall prediction accuracy of hydropower inflow, wind power, and photovoltaic power decreases slightly and the accuracy increases in some periods. Moreover, in scenarios with a higher degree of uncertainty, the effect of this method in improving economic efficiency is even more prominent.

导出引用

刘继春, 肖煜瑾, 邱高, 唐伦, 孙毅, 李凌昊. 基于改进闭环预测-优化互嵌技术的含水风光电力系统两阶段调度方法[J]. 电力建设. 2025

LIU Jichun, XIAO Yujin, QIU Gao, TANG Lun, SUN Yi, LI Linghao. An Improved Closed-loop Predict-and-optimize Intertwined Framework-based Two-stage Dispatch for Hydropower-wind-photovoltaic Involved Power Systems[J]. Electric Power Construction. 2025

中图分类号： TM73

参考文献

[1] 弭辙, 胡健祖, 郭珍妮, 等. 新型电力系统体系下新能源发展态势及市场化消纳研究[J]. 山东电力技术, 2023, 50(10): 1-8.
MI Zhe, HU Jianzu, GUO Zhenni, et al.Research on the development situation and market-oriented consumption of renewable energy under new power system architecture[J]. Shandong Electric Power, 2023, 50(10): 1-8.
[2] 李建林, 丁子洋, 游洪灏, 等. 构网型储能支撑新型电力系统稳定运行研究[J]. 高压电器, 2023, 59(07): 1-11.
LI Jianlin, DING Ziyang, YOU Honghao, et al.Research on stable operation of new power system supported by grid-forming energy storage system[J]. High Voltage Apparatus, 2023, 59(07): 1-11.
[3] 王雪林, 钟海旺. 新型电力系统背景下抽水蓄能和新型储能协同发展研究[J].全球能源互联网, 2024, 7(04): 363-371.
WANG Xuelin, ZHONG Haiwang.Research on the synergetic development of pumped storage and new energy storage under the background of new power system[J]. Journal of Global Energy Interconnection, 2024, 7(04): 363-371.
[4] 郭婷婷, 曹蕃. 低碳能源系统发展趋势与应用实践[J].分布式能源, 2025, 10(01): 1-13.
GUO Tingting, CAO Fan.Development trend and application of low-carbon energy system[J]. Distributed Energy, 2025, 10(01): 1-13.
[5] 上官甲天, 茅云寿. 计及新能源不确定性微能源网优化运行研究[J]. 供用电, 2023, 40(08): 92-99.
SHANGGUAN Jiatian, MAO Yunshou.Optimal operation of micro-energy networks considering new energy uncertainty[J]. Distribution & Utilization, 2023, 40(8): 92-99.
[6] 黄河, 王建学, 肖云鹏, 等. 新型电力系统电力电量平衡分析关键技术与研究框架[J]. 电力建设, 2024, 45(9): 1-12.
HUANG He, WANG Jianxue, XIAO Yunpeng, et al.Key technologies and research framework for the power and energy balance analysis in new-type power systems[J]. Electric Power Construction, 2024, 45(9): 1-12.
[7] 陈皇森, 石立宝. 考虑多风电场出力预测误差分布特征的随机机组组合[J]. 电网技术, 2023, 47(12): 5026-5040.
CHEN Huangsen, SHI Libao.Stochastic unit commitment considering output forecast error distribution characteristics of multiple wind farms[J]. Power System Technology, 2023, 47(12): 5026-5040.
[8] VELLOSO A, STREET A, POZO D, et al.Two-stage robust unit commitment for co-optimized electricity markets: an adaptive data-driven approach for scenario-based uncertainty sets[J]. IEEE Transactions on Sustainable Energy, 2020, 11(2): 958-969.
[9] 钟富城, 王星华, 黎子律, 等. 计及时空分布特性的光-荷典型场景提取方法[J]. 广东电力, 2024, 37(02): 25-32.
ZHONG Fucheng, WANG Xinghua, LI Zilv, et al.A method for extracting typical scenes of photovoltaic and load considering temporal and spatial distribution characteristics[J]. Guangdong Electric Power, 2024, 37(02): 25-32.
[10] 刘海涛, 仲聪, 马佳伊, 等. 考虑条件风险价值和阶梯碳交易的综合能源系统优化调度[J]. 电测与仪表, 2024, 61(04): 100-108.
LIU Haitao, ZHONG Cong, MA Jiayi, et al.Optimal dispatching of integrated energy system considering conditional value at risk and ladder carbon trading[J]. Electrical Measurement & Instrumentation, 2024, 61(04): 100-108.
[11] 李嘉森, 王进, 杨蒙, 等. 基于随机优化的虚拟电厂热电联合经济优化调度[J]. 太阳能学报, 2023, 44(9): 57-65.
LI Jiasen, WANG Jin, YANG Meng, et al.Virtual power plant thermal electric combined economic optimization scheduling based on stochastic optimization[J]. Journal of Solar Energy, 2023, 44(9): 57-65.
[12] 张伟, 吴敏, 白婷. 考虑需求侧资源的改进轻鲁棒虚拟电厂运行方法[J]. 广东电力, 2024, 37(12): 111-118.
ZHANG Wei, WU Min, BAI Ting.An improved light robust virtual power plant operation method considering demand-side resources[J]. Guangdong Electric Power, 2024, 37(12): 111-118.
[13] 刘亚鑫, 蔺红, 马越, 等. 考虑分时碳价的虚拟电厂分布鲁棒竞标方法[J]. 电测与仪表, 2024, 61(8): 12-19.
LIU Yaxin, LIN Hong, MA Yue, et al.A robust bidding method for virtual power plant distribution considering time-shared carbon price[J]. Electrical Measurement & Instrumentation, 2024, 61(8): 12-19.
[14] 张亚超, 刘开培, 秦亮, 等. 基于聚类经验模态分解-样本熵和优化极限学习机的风电功率多步区间预测[J]. 电网技术, 2016, 40(7): 2045-2051.
ZHANG Yachao, LIU Kaipei, QIN Liang, et al.Wind power multi-step interval prediction based on ensemble empirical mode decomposition-sample entropy and optimized extreme learning machine[J]. Power System Technology, 2016, 40(7): 2045-2051.
[15] 黎敏, 林湘宁, 张哲原, 等. 超短期光伏出力区间预测算法及其应用[J]. 电力系统自动化, 2019, 43(3): 10-16.
LI Min, LIN Xiangning, ZHANG Zheyuan, et al.Interval prediction algorithm for ultra-short-term photovoltaic output and its application[J]. Automation of Electric Power Systems, 2019, 43(3): 10-16.
[16] 何常新, 彭旭, 方福东, 等. 基于LASSO回归和QRLSTM的来水预测方法研究[J]. 人民长江, 2024, 55(11): 138-145+165.
HE Changxin, PENG Xu, FANG Fudong, et al. Incoming water prediction method based on LASSO regression and QRLSTM[J]. Yangtze River, 2024, 55(11): 138-145+165.
[17] 王辉, 陈攀, 李乃慧, 等. 计及源-荷多类型备用的虚拟电厂双层优化运行[J]. 电测与仪表, 2024, 61(11): 31-39.
WANG Hui, CHEN Pan, LI Naihui, et al.Double-layer optimized operation of virtual power plant considering source-load multiple standby[J]. Electrical Measurement & Instrumentation, 2024, 61(11): 31-39.
[18] BADESA L, TENG F, STRBAC G.Economic value of inertia in low-carbon power systems[C] // Proceedings of the 2017 IEEE PES Innovative Smart Grid Technologies Conference Europ(ISGT-Europe). Turin, Italy: IEEE, 2017: 1-6.
[19] YAMIN W, LEI W.Improving economic values of day-ahead load forecasts to real-time power system operations[J]. IET Generation, Transmission & Distribution, 2017, 11(17): 4238-4247.
[20] GUO Y, XU Y-P, XIE J, et al.A weights combined model for middle and long-term streamflow forecasts and its value to hydropower maximization[J]. Journal of Hydrology, 2021, 602: 126794.
[21] LEE D, NG J Y, GALELLI S, et al.Unfolding the relationship between seasonal forecast skill and value in hydropower production: a global analysis[J]. Hydrol Earth Syst Sci, 2022, 26(9): 2431-2448.
[22] SHU X, DING W, PENG Y, et al.Value of long-term inflow forecast for hydropower operation: a case study in a low forecast precision region[J]. Energy, 2024, 298: 131218.
[23] VANDERSCHUEREN T, VERDONCK T, BAESENS B, et al.Predict-then-optimize or predict-and-optimize? An empirical evaluation of cost-sensitive learning strategies[J]. Inf Sci, 2022, 594: 400-415.
[24] ELMACHTOUB A N, GRIGAS P.Smart “Predict, then Optimize”[J]. Management Science, 2022, 68(1): 9-26.
[25] BERTSIMAS D, VAN PARYS B.Bootstrap robust prescriptive analytics[J]. Mathematical Programming, 2022, 195(1): 39-78.
[26] 赵长飞. 新能源电力系统概率预测-决策一体化研究[D]. 杭州: 浙江大学, 2022.
Zhao Changfei.Integrated probabilistic forecasting and decision for power system with renewables[D]. Zhejiang University, 2022.
[27] GUO L, DONG C H.Toward cost-oriented forecasting of wind power generation[J]. IEEE Transactions on Smart Grid, 2018, 9(4): 2508-2517.
[28] STRATIGAKOS A, CAMAL S, MICHIORRI A, et al.Prescriptive trees for integrated forecasting and optimization applied in trading of renewable energy[J]. IEEE Transactions on Power Systems, 2022, 37(6): 4696-4708.
[29] CHEN X, YANG Y, LIU Y, et al.Feature-Driven economic improvement for network-constrained unit commitment: a closed-loop predict-and-optimize framework[J]. IEEE Transactions on Power Systems, 2022, 37(4): 3104-3118.
[30] 王佳, 吴任博, 肖健, 等. 新型电力系统能源调度与碳排放计价优化方法研究[J]. 电测与仪表, 2024, 61(10): 17-25.
WANG Jia, WU Renbo, XIAO Jian, et al.Research on the optimization method of energy dispatching and carbon emission pricing for novel power system[J]. Electrical Measurement & Instrumentation, 2024, 61(10): 17-25.
[31] FELIPE B, WELINGTON D O, CRISTIAN F E.Application of scenario tree reduction via quadratic process to medium-term hydrothermal scheduling problem[J]. IEEE Transactions on Power Systems, 2017, 32(6): 4351-4361.
[32] 加鹤萍, 郭宇辰, 马乾鑫, 等. 基于机器学习方法的现货电价预测研究综述[J]. 电力建设, 2025, 46(2): 160-179.
JIA Heping, GUO Yuchen, MA Qianxin, et al.Review of spot electricity price prediction studies based on machine learning methods[J]. Electric Power Construction, 2025, 46(2): 160-179.
[33] MALLIK N, BERGMAN E, HVARFNER C, et al. PriorBand: Practical hyperparameter optimization in the age of deep learning[EB/OL]. (2023-11-15)[2025-03-05]. https://doi.org/10.48550/arXiv.2306.12370.
[34] XU Y, YIN M, DONG Z Y, et al.Robust dispatch of high wind power-penetrated power systems against transient instability[J]. IEEE Transactions on Power Systems, 2018, 33(1): 174-186.
[35] XU Y, KORKALI M, MILI L, et al.An Iterative Response-Surface-Based Approach for Chance-Constrained AC Optimal Power Flow Considering Dependent Uncertainty[J]. IEEE Transactions on Smart Grid, 2021, 12(3): 2696-2707.
[36] 侯慧, 甘铭, 吴细秀, 等. 考虑移动氢能存储的港口多能微网两阶段分布鲁棒优化调度[J]. 中国电机工程学报, 2024, 44(8): 3078-3093.
HOU Hui, GAN Ming, WU Xixiu, et al.Two-stage distributionally robust optimal scheduling for port multi-energy microgrid considering mobile hydrogen energy storage[J]. Proceedings of the CSEE, 2024, 44(8): 3078-3093.
[37] 杜刚, 赵冬梅, 刘鑫. 计及风电不确定性优化调度研究综述[J]. 中国电机工程学报, 2023, 43(7): 2608-27.
DU Gang, ZHAO Dongmei, LIU Xin.Research review on optimal scheduling considering wind power uncertainty[J]. Proceedings of the CSEE, 2023, 43(7): 2608-2627.