www.国产在线,成年人网站免费看,国产黄色在线播放

基于預測-決策框架的綜合能源系統優化

來源：電工電氣發布時間：2025-01-23 15:23 瀏覽次數：279

基于預測-決策框架的綜合能源系統優化

崔國偉

(國網徐州市銅山區供電公司，江蘇徐州 221000)

摘要：隨著可再生能源滲透率的不斷提高，大量的不確定性設備給綜合能源系統(IES)的安全高效運行帶來了威脅。一般解決不確定型優化問題的過程是，依靠大量歷史數據并輔助一些人工智能技術進行可再生能源的預測分析，但通常預測和決策分開進行的過程會由于預測誤差過大而導致模型的優化目標產生嚴重惡化。提出了基于K-最近鄰(KNN)算法和魯棒優化(RO)相結合的預測- 決策方法改進 IES 的不確定型優化問題。通過 KNN+ 最小體積(KMV)橢球集的方法構建 KMV 橢球集，求解在該集合下的兩階段魯棒模型，得到最優的多能流解。其中，為了平衡 IES 的魯棒性和經濟性，采用魯棒可調參數表示不確定集的合適水平。通過仿真算例分析，證明了 KMV 橢球集的區間大小與可調參數的變化規律，以及該集合的優越性。

關鍵詞： 綜合能源系統；機器學習；魯棒優化；不確定型優化

中圖分類號：TM73 文獻標識碼：A 文章編號：1007-3175(2025)01-0026-10

The Optimization of Integrated Energy Systems Based on

Predictive & Prescriptive Framework

CUI Guo-wei

（State Grid Xuzhou Tongshan District Power Supply Company, Xuzhou 221000, China）

Abstract: With the increasing permeability of renewable energy, a large number of uncertain devices pose a threat to the safe and efficient operation of the integrated energy system (IES). In general, solving the uncertainty optimization problem relies on a large amount of historical data, and assists some artificial intelligence technology to predict the analysis of renewable energy, but the usual process of separate prediction and decision making can produce serious deterioration of the model's optimization objective due to excessive prediction errors. Therefore, this paper proposes a prediction-decision method based on K-nearest neighbor (KNN) and robust optimization(RO) to improve the uncertainty optimization problem of IES. Then, the KMV ellipsoid set is constructed using the KNN + minimum volume (KMV) ellipsoid set method, and the two-stage robust model under the set is solved to obtain the optimal multi-energy flow solution. In order to balance the robustness and economy of IES, robust adjustable parameters are used to represent the appropriate level of the uncertainty set. Finally, through the simulation example,the change rule of the interval size and the adjustable parameters of the KMV ellipsoid set is proved, and the superiority of the set is proved.

Key words: integrated energy system; machine learning; robust optimization; uncertain optimization

參考文獻

[1] 張蘇涵，顧偉，俞睿智，等. 綜合能源系統建模與仿真：綜述、思考與展望[J] . 電力系統自動化，2024，48(17) ：1-21.

[2] 卓振宇，張寧，謝小榮，等. 高比例可再生能源電力系統關鍵技術及發展挑戰[J] . 電力系統自動化，2021，45(9) ：171-191.

[3] 張金良，劉子毅. 基于混合模型的超短期風速區間預測[J]. 電力系統保護與控制，2022，50(22) ：49-58.

[4] 盛四清，張立. 考慮風光荷預測誤差的電力系統經濟優化調度[J] . 電力系統及其自動化學報，2017，29(9) ：80-85.

[5] BEN-TAL A, GHAOUI L E, NEMIROVSKI A.Robust Optimization(Princeton Series in Applied Mathematics)[M].Princeton ：Princeton University Press，2009.

[6] DRAGOON K, MILLIGAN M.Assessing wind integration costs with dispatch models: A case study of PacifiCorp[C]//American Wing Energy Association Conference，2003.

[7] SEOKHO S, SI-DOEK O, HO-YOUNG K.Wind turbine power curve modeling using maximum likelihood estimation method[J].Renewable Energy，2019，136(6) ：1164-1169.

[8] HUA W, JIANG J, Sun H, et al.Data-driven prosumer-centric energy scheduling using convolutional neural networks[J].Applied Energy，2022，308(15) ：118361.

[9] 彭虹橋，顧潔，宋柄兵，等. 基于多維變量篩選- 非參數組合回歸的長期負荷概率預測模型[J] . 電網技術，2018，42(6) ：1768-1775.

[10] MORADZADEH A, MOHAMMADI-IVATLOO B, ABAPOUR M,et al.Heating and Cooling Loads Forecasting for Residential Buildings Based on Hybrid Machine Learning Applications: A Comprehensive Review and Comparative Analysis[J].IEEE Access，2022(10) ：2196-2215.

[11] TAN Z, DE G, LI M, et al.Combined electricityheat-cooling-gas load forecasting model for integrated energy system based on multitask learning and least square support vector machine[J].Journal of Cleaner Production，2019，248(14) ：119252.

[12] LI T, SUN H, SHI Z, et al.Cooperative optimal configuration of integrated energy system considering uncertainty factors of sourceload[J].IOP Conference Series: Earth and Environmental Science，2022，983(1) ：012119.

[13] ALTMAN N S.An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression[J].The American Statistician，1992，46(3) ：175-185.

[14] WANG J, XU X, LI H, et al.Two-stage robust optimization of thermal-ESS units scheduling under wind uncertainty[J].Energy Reports，2022，8：1147-1155.

[15] LI S, HAN W, LIU L.Robust Optimization of the Hub Location Problem for Fresh Agricultural Products with Uncertain Demand[J].IEEE Access，2022(10) ：41902-41913.

[16] TAN B F, CHEN H Y, ZHENG X D, et al.Two-stage robus toptimization dispatch for multiple microgrids with electric vehicle loads based on a novel datadriven uncertainty set[J].International Journal of Electrical Power & Energy Systems，2022，134 ：107359.

[17] JIN X, WU Q, JIA H, et al.Optimal Integration of Building Heating Loads in Integrated Heating/Electricity Community Energy Systems ：A Bi-Level MPC Approach[J].IEEE Transactions onSustainable Energy，2021，12(3) ：1741-1754.

[18] JIANG S L, PENG G, BOGLE I D L, et al.A twostage robust optimization approach for flexible oxygen distribution under uncertainty in integrated iron and steel plants[J].Applied Energy，2022，306 ：118022.

[19] VATANI B, CHOWDHURY B, DEHGHAN S, et al.A critical review of robust self-scheduling for generation companies under electricity price uncertainty[J].International Journal of Electrical Power & Energy Systems，2018，97 ：428-439.

[20] WU W, WANG K, LI G, et al.Modeling Ellipsoidal Uncertainty Set Considering Conditional Correlation of Wind Power Generation[J].Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering，2017，37(9) ：2500-2507.

[21] QIU Z , JIANG N . An ellipsoidal Newton’s iteration method of nonlinear structural systems with uncertain-but-bounded parameters[J].Computer Methods in Applied Mechanics and Engineering，2021，373(1) ：113501.

[22] KURYATNIKOVA O , GHADDAR B , MOLZAHN D K .Adjustable Robust Two-Stage Polynomial Optimization with Application to AC Optimal Power Flow [EB/OL] . (2021-04-07) [2024-07-15] .https://doi.org/10.48550/arXiv.2014.03107arXiv preprint.

[23] 劉一欣，郭力，王成山. 微電網兩階段魯棒優化經濟調度方法[J] . 中國電機工程學報，2018，38(14) ：4013-4022.

[24] LI D, ZHANG S.Optimal Design of Distributed Energy Resource Systems under Uncertainties Based on Two-Stage Robust Optimization[J].Journal of Thermal Science，2021，30(1) ： 51-63.

[25] OHMORI S.A Predictive Prescription Using Minimum Volume k-Nearest Neighbor Enclosing Ellipsoid and Robust Optimization[J].Mathematics，2021，9(2) ：119.

[26] JI Y, XU Q, ZHAO J, et al.Day-ahead and intraday optimization for energy and reserve scheduling under wind uncertainty and generation outages[J].Electric Power Systems Research，2021， 195 ：107133.

[27] KOCUK B , DEY S S , SUN X A , Strong SOCP Relaxations for the Optimal Power Flow Problem[J].Operations Research，2016，64(6) ：1177-1196.

[28] LIU X, WU J, JENKINS N, et al.Combined analysis of electricity and heat networks[J].Applied Energy，2016，162 ：1238-1250.

[29] ZENG B , ZHAO L . Solving two-stage robust optimization problems using a column-andconstraint generation method[J].Operations Research Letters，2013，41(5) ：457-461.

[30] 朱嘉遠，劉洋，許立雄，等. 考慮風電消納的熱電聯供型微網日前魯棒經濟調度[J] . 電力系統自動化，2019，43(4) ：40-48.

[31] ZHENG L, LI Y, WEI C, et al.A data-driven method for operation pattern analysis of the integrated energy microgrid[J].Energy Conversion and Management: X，2021，11 ：100092.

[32] 李斯，周任軍，童小嬌，等. 基于盒式集合魯棒優化的風電并網最大裝機容量[J] . 電網技術，2011，35(12) ：208-213.

[33] VENZKE A, HALILBASIC L, MARKOVIC U, et al.Convex relaxations of chance constrained AC optimal power flow[J].IEEE Transactions on Power Systems，2018，33(3) ：2829-2841.

[34] WANG Shuai, LI Bin, LI Guanzheng, et al. Short-term wind power prediction based on multidimensional data cleaning and feature reconfiguration[J].Applied Energy，2021，292 ：116851.

返回索引列表

Article retrieval

文章檢索

基于預測-決策框架的綜合能源系統優化