目前虚拟电厂参与配电网调度多依赖物理模型,然而,由于虚拟电厂聚合成员的多元性、时变性、时序耦合性,导致其解析建模难度增大,难以满足配电网日内调度需求的时效性,且存在隐私安全问题。因此,提出一种基于加权K最近邻（WKNN）和核极限学习机-高斯过程回归（KELM-GPR）的虚拟电厂交互模型构建方法。首先为提升交互模型的预测精度,提出一种均匀生成训练集的方法;其次通过WKNN算法建立调度指令可行性模型,衡量虚拟电厂的可调度边界;接着引入GPR作为误差补偿模型,并与KELM结合,构建基于KELM-GPR的虚拟电厂交互成本模型,以参与配电网的经济调度;最后为验证所提方法的可行性,基于虚拟电厂调度指令可行性和交互成本模型,构建虚拟电厂参与配电网日内优化调度模型。仿真结果表明,所提方法能显著减少模型优化求解时间,并能保护虚拟电厂内部信息安全。
Abstract
Currently, the participation of the virtual power plant in distribution network dispatching mostly depends on physical model. However, due to the diversity, time-varying, and temporal coupling of the aggregated members of virtual power plant, its analytical modeling becomes more difficult, and it is difficult to meet the timeliness of the intra-day scheduling requirements of distribution network, and there are privacy security issues. Therefore, a virtual power plant interaction model construction method based on weighted K-nearest neighbor （WKNN） and kernel extreme learning machine-Gaussian process regression （KELM-GPR） is proposed. Firstly, to improve the prediction accuracy of the interactive model, a method of uniformly generating training sets is proposed; Secondly, a scheduling instruction feasibility model is established through the WKNN algorithm to measure the dispatchable boundary of the virtual power plant; Next, GPR is introduced as an error compensation model, and combined with KELM to construct a virtual power plant interaction cost model based on KELM-GRP to participate in the economic dispatch of the distribution network; Finally, to verify the feasibility of the proposed method, based on the model of scheduling instruction feasibility and interactive cost of virtual power plant, a virtual power plant participation in the intra-day optimization scheduling of the distribution network model is constructed. Simulation results show that the proposed method can significantly reduce the model optimization solution time and protect the internal information security of the virtual power plant.
关键词
虚拟电厂 /
机器学习 /
优化调度 /
误差补偿 /
建模方法
Key words
virtual power plant /
machine learning /
optimal scheduling /
error compensation /
modeling method
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 高虎. “双碳” 目标下中国能源转型路径思考[J]. 国际石油经济, 2021, 29(3): 1-6.
GAO H.China's energy transformation under the targets of peaking carbon emissions and carbon neutral[J]. International petroleum economics, 2021, 29(3): 1-6.
[2] 陈倩, 王维庆, 王海云. 含分布式能源的配电网双层优化运行策略[J]. 太阳能学报, 2022, 43(10): 507-517.
CHEN Q, WANG W Q, WANG H Y.Bi-level optimal operation strategy of distribution network with distributed energy[J]. Acta energiae solaris sinica, 2022, 43(10): 507-517.
[3] 舒印彪, 张智刚, 郭剑波, 等. 新能源消纳关键因素分析及解决措施研究[J]. 中国电机工程学报, 2017, 37(1): 1-8.
SHU Y B, ZHANG Z G, GUO J B, et al.Study on key factors and solution of renewable energy accommodation[J]. Proceedings of the CSEE, 2017, 37(1): 1-8.
[4] 张大海, 贠韫韵, 王小君, 等. 计及风光不确定性的新能源虚拟电厂多时间尺度优化调度[J]. 太阳能学报, 2022, 43(11): 529-537.
ZHANG D H, YUN Y Y, WANG X J, et al.Multi-time scale of new energy scheduling optimization for virtual power plant considering uncertainty of wind power and photovoltaic power[J]. Acta energiae solaris sinica, 2022, 43(11): 529-537.
[5] LIANG H S, MA J.Data-driven resource planning for virtual power plant integrating demand response customer selection and storage[J]. IEEE transactions on industrial informatics, 2022, 18(3): 1833-1844.
[6] 张冲标, 高博, 张卫康, 等. 基于面向新型配电网系统的虚拟电厂协同运行研究[J]. 电测与仪表, 2024, 61(11): 46-53.
ZHANG C B, GAO B, ZHANG W K, et al.Research on cooperative operation of virtual power plants in novel distribution network system[J]. 2024, 61(11): 46-53.
[7] MOUSAVI M, RAYATI M, RANJBAR A M.Optimal operation of a virtual power plant in frequency constrained electricity market[J]. IET generation, transmission & distribution, 2019, 13(11): 2123-2133.
[8] 张涛, 王成, 王凌云, 等. 考虑虚拟电厂参与的售电公司双层优化调度模型[J]. 电网技术, 2019, 43(3): 952-960.
ZHANG T, WANG C, WANG L Y, et al.A Bi-level optimal dispatching model of electricity retailers integrated with VPPs[J]. Power system technology, 2019, 43(3): 952-960.
[9] TANG W J, YANG H T.Optimal operation and bidding strategy of a virtual power plant integrated with energy storage systems and elasticity demand response[J]. IEEE access, 2019, 7: 79798-79809.
[10] 李昭昱, 艾芊, 张宇帆, 等. 数据驱动技术在虚拟电厂中的应用综述[J]. 电网技术, 2020, 44(7): 2411-2419.
LI Z Y, AI Q, ZHANG Y F, et al.Application of data-driven technology in virtual power plant[J]. Power system technology, 2020, 44(7): 2411-2419.
[11] BHUIYAN E A, HOSSAIN M Z, MUYEEN S M, et al.Towards next generation virtual power plant: technology review and frameworks[J]. Renewable and sustainable energy reviews, 2021, 150: 111358.
[12] 王志杨, 张靖, 何宇, 等. 数据与模型混合驱动的区域综合能源系统双层优化调度决策方法[J]. 电网技术, 2022, 46(10): 3797-3809.
WANG Z Y, ZHANG J, HE Y, et al.Hybrid data-driven and model-driven Bi-level optimal scheduling decision for regional integrated energy systems[J]. Power system technology, 2022, 46(10): 3797-3809.
[13] 王玉彬, 董伟, 陈源奕, 等. 基于数据驱动的家庭能量实时经济调控方法[J]. 电力系统自动化, 2022, 46(13): 21-29.
WANG Y B, DONG W, CHEN Y Y, et al.Data-driven real-time economic regulation method for household energy[J]. Automation of electric power systems, 2022, 46(13): 21-29.
[14] 王少波, 柴艳丽, 梁醒培. 神经网络学习样本点的选取方法比较[J]. 郑州大学学报(工学版), 2003, 24(1): 63-65, 69.
WANG S B, CHAI Y L, LIANG X P.Comparison of methods to produce sample points in training ANN[J]. Journal of Zhengzhou University (engineering science), 2003, 24(1): 63-65, 69.
[15] 蔡靖, 袁守国, 李锐, 等. 基于加权KNN算法的脑电信号情绪识别[J]. 电子技术应用, 2022, 48(10): 25-30, 35.
CAI J, YUAN S G, LI R, et al.Emotion recognition of EEG signals based on weighted KNN algorithm[J]. Application of electronic technique, 2022, 48(10): 25-30, 35.
[16] 袁建华, 谢斌斌, 何宝林, 等. 基于DTW-VMD-PSO-BP的光伏发电功率短期预测方法[J]. 太阳能学报, 2022, 43(8): 58-66.
YUAN J H, XIE B B, HE B L, et al.Short term forecasting method of photovoltaic output based on DTW-VMD-PSO-BP[J]. Acta energiae solaris sinica, 2022, 43(8): 58-66.
[17] 任家东, 张亚飞, 张炳, 等. 基于特征选择的工业互联网入侵检测分类方法[J]. 计算机研究与发展, 2022, 59(5): 1148-1159.
REN J D, ZHANG Y F, ZHANG B, et al.Classification method of industrial internet intrusion detection based on feature selection[J]. Journal of computer research and development, 2022, 59(5): 1148-1159.
[18] 冯磊华, 张杰, 詹毅. 基于改进麻雀搜索算法和核极限学习机的电站锅炉燃烧优化[J]. 热力发电, 2022, 51(9): 96-102.
FENG L H, ZHANG J, ZHAN Y.Combustion optimization of utility boilers based on ISSA and KELM[J]. Thermal power generation, 2022, 51(9): 96-102.
[19] 吕佳朋, 史贤俊, 王康. 基于高斯过程回归的电池容量预测模型[J]. 电子测量技术, 2020, 43(3): 43-48.
LYU J P, SHI X J, WANG K.Battery capacity prediction model based on Gaussian process regression[J]. Electronic measurement technology, 2020, 43(3): 43-48.
[20] 宋雨露, 樊艳芳, 刘牧阳, 等. 基于SC-DNN和多源数据融合的新能源电力系统状态估计方法[J]. 电力系统保护与控制, 2023, 51(9): 177-187.
SONG Y L, FAN Y F, LIU M Y, et al.State estimation method of a new energy power system based on SC-DNN and multi-source data fusion[J]. Power system protection and control, 2023, 51(9): 177-187.
[21] 赵丰明, 樊艳芳. 分时电价影响下的多能源虚拟电厂双层优化调度[J]. 电力系统保护与控制, 2019, 47(20): 33-40.
ZHAO F M, FAN Y F.Bi level optimal dispatching of multi energy virtual power plant influenced by TOU price[J]. Power system protection and control, 2019, 47(20): 33-40.
[22] 赵玲霞, 王兴贵, 丁颖杰, 等. 考虑分时电价及光热电站参与的多能源虚拟电厂优化调度[J]. 电力建设, 2022, 43(4): 119-129.
ZHAO L X, WANG X G, DING Y J, et al.Optimal dispatch of multi-energy virtual power plant considering time-of-use electricity price and CSP plant[J]. Electric power construction, 2022, 43(4): 119-129.
[23] 郑浩伟, 闫庆友, 尹哲, 等. 计及日前-实时交易和共享储能的VPP运行优化及双层效益分配[J]. 电力建设, 2022, 43(9): 34-46.
ZHENG H W, YAN Q Y, YIN Z, et al.VPP operation optimization and bilayer revenue distribution model considering the two-level market and shared energy storage[J]. Electric power construction, 2022, 43(9): 34-46.
[24] 解玄弘, 谢敬东. 基于纳什谈判的多能VPP群协同优化运行策略[J]. 储能科学与技术, 2022, 11(12): 3937-3949.
XIE X H, XIE J D.Coordinative optimal operation of multi-energy virtual power plants clusters based on Nash bargaining[J]. Energy storage science and technology, 2022, 11(12): 3937-3949.
基金
新疆维吾尔自治区自然科学基金（2022D01C365; 2022D01C662）; 2022天山英才培养计划（2022TSYCLJ0019）
PDF(2088 KB)
