基于数据驱动具有自我学习能力的机组组合智能决策方法研究
|
摘要
在能源技术变革日新月异、人工智能技术快速发展的背景下,研究具有高适应性、高精度的机组组合决策方法具有重要意义。该文基于长短时记忆网络,通过构建面向机组组合问题的深度学习模型,提出一种基于数据驱动具有自我学习能力的机组组合智能决策方法。首先基于K-means算法对历史调度数据进行聚类预处理;然后构建基于长短时记忆网络的机组组合深度学习模型,通过历史数据训练建立系统负荷与调度决策结果之间的映射模型,以此为基础进行机组组合决策;最后通过积累历史数据实现对模型的持续修正,从而赋予其自我进化、自我学习的能力。基于标准算例、实际电网数据的一系列仿真结果表明:相比于传统决策方法,该方法不仅可以在实际使用过程中不断提升其决策精度或效率,且在面对不同类型的机组组合问题时适应性更好。
It is now a background of the energy technologies change rapidly and the artificial intelligence technologies develop quickly. It is significant to study the dispatching methods of unit commitment with high adaptability and high precision. A data-driven intelligent securityconstrained unit commitment dispatching method with self-learning ability was proposed. In the method, the long-short term memory neural network was utilized to construct a deep learning model, which was focus on the problem of the unit commitment. Firstly, the K-means algorithm was used to do a cluster preprocessing for the historical dispatching data. Then, the unit commitment deep learning model was constructed by long-short term memory neural network. The mapping model between system load and dispatching results was constructed by historical data training. After that, the all above process was used as a foundation to do the unit commitment dispatching. Finally, the model was kept revised through the accumulation of historical data, which may give it the abilities of selfevolution and self-learning. A series of simulation results based on the standard calculation example and the practical grid data indicate some information. Compared with traditional dispatching methods, the method can not only improve the accuracy and efficiency of the method in practical usage, but also adapt to different kinds of unit commitment problems.
It is now a background of the energy technologies change rapidly and the artificial intelligence technologies develop quickly. It is significant to study the dispatching methods of unit commitment with high adaptability and high precision. A data-driven intelligent securityconstrained unit commitment dispatching method with self-learning ability was proposed. In the method, the long-short term memory neural network was utilized to construct a deep learning model, which was focus on the problem of the unit commitment. Firstly, the K-means algorithm was used to do a cluster preprocessing for the historical dispatching data. Then, the unit commitment deep learning model was constructed by long-short term memory neural network. The mapping model between system load and dispatching results was constructed by historical data training. After that, the all above process was used as a foundation to do the unit commitment dispatching. Finally, the model was kept revised through the accumulation of historical data, which may give it the abilities of selfevolution and self-learning. A series of simulation results based on the standard calculation example and the practical grid data indicate some information. Compared with traditional dispatching methods, the method can not only improve the accuracy and efficiency of the method in practical usage, but also adapt to different kinds of unit commitment problems.
引文
[1]李整,秦金磊,谭文,等.基于目标权重导向多目标粒子群的节能减排电力系统优化调度[J].中国电机工程学报,2015,35(S1):67-74.Li Zheng,Qin Jinlei,Tan Wen,et al.Optimizing schedule for electric power system of energy-saving and emissionreducing based upon objective-weight oriented multiobjective particle swarm optimization[J].Proceedings of the CSEE,2015,35(S1):67-74(in Chinese).
[2]Aditi Upadhyay,Hu Bingqian,Li Jie,et al.Achance-constrained wind range quantification approach to robust scuc by determining dynamic uncertainty intervals[J].CSEE Journal of Power and Energy Systems,2016,2(1):54-64.
[3]Wang C,Fu Y.Fully parallel stochastic securityconstrained unit commitment[J].IEEE Transactions on Power Systems,2016,31(5):3561-3571.
[4]Wu Hongyu,Ibrahim Krad,Anthony Florita,et al.Stochastic multi-timescale power system operations with variable wind generation[J].IEEE Transactions on Power Systems,2017,32(5):3325-3337.
[5]Shao C,Wang X,Shahidehpour M,et al.Securityconstrained unit commitment with flexible uncertainty set for variable wind power[J].IEEE Transactions on Sustainable Energy,2017,8(3):1237-1246.
[6]Wu L,Shahidehpour M,Li Z.Comparison of scenariobased and interval optimization approaches to stochastic SCUC[J].IEEE Transactions on Power Systems,2012,27(2):913-921.
[7]Li Dashuang,Zhang Chaoyong,Tian Guangdong,et al.Multiobjective program and hybrid imperialist competitive algorithm for the mixed-model two-sided assembly lines subject to multiple constraints[J].IEEETransactions on Systems,Man and Cybernetics,Systems,2018,48(1):119-129.
[8]包宇庆,王蓓蓓,李扬,等.考虑大规模风电接入并计及多时间尺度需求响应资源协调优化的滚动调度模型[J].中国电机工程学报,2016,36(17):4589-4599.Bao Yuqing,Wang Beibei,Li Yang,et al.Rolling dispatch model considering wind penetration and multi-scale demand response resources[J].Proceedings of the CSEE,2016,36(17):4589-4599(in Chinese).
[9]王晗,徐潇源,严正.考虑柔性负荷的多目标安全约束机组组合优化模型及求解[J].电网技术,2017,41(6):1904-1911.Wang Han,Xu Xiaoyuan,Yan Zheng.Multi-objective optimization of security constrained unit commitment model and solution considering flexible load[J].Power System Technology,2017,41(6):1904-1911(in Chinese).
[10]Li Y F,Pedroni N,Zio E.A memetic evolutionary multi-objective optimization method for environmental power unit commitment[J].IEEE Transactions on Power Systems,2013,28(3):2660-2669.
[11]梅生伟,郭文涛,王莹莹,等.一类电力系统鲁棒优化问题的博弈模型及应用实例[J].中国电机工程学报,2013,33(19):47-56.Mei Shengwei,Guo Wentao,Wang Yingying,et al.Agame model for robust optimization of power systems and its application[J].Proceedings of the CSEE,2013,33(19):47-56(in Chinese).
[12]李整,谭文,秦金磊.一种用于机组组合问题的改进双重粒子群算法[J].中国电机工程学报,2012,32(25):189-195.Li Zheng,Tan Wen,Qin Jinlei.An improved dual particle swarm optimization algorithm for unit commitment problem[J].Proceedings of the CSEE,2012,32(25):189-195(in Chinese).
[13]Attaviriyanupap P,Kita H,Tanaka E,et al.A hybrid LR-EP for solving new profit-based UC problem under competitive environment[J].IEEE Power Engineering Review,2007,22(12):62-62.
[14]韦化,吴阿琴,白晓清.一种求解机组组合问题的内点半定规划方法[J].中国电机工程学报,2008,28(1):35-40.Wei Hua,Wu Aqin,Bai Xiaoqing.An interior point semidefinite programming for unit commitment problems[J].Proceedings of the CSEE,2008,28(1):35-40(in Chinese).
[15]韦化,龙丹丽,黎静华.求解大规模机组组合问题的策略迭代近似动态规划[J].中国电机工程学报,2014,34(25):4420-4429.Wei Hua,Long Danli,Li Jinghua.Policy iterationapproximate dynamic programming for large scale unit commitment problems[J].Proceedings of the CSEE,2014,34(25):4420-4429(in Chinese).
[16]Silbernagl M,Huber M,Brandenberg R.Improving accuracy and efficiency of start-up cost formulations in MIP unit commitment by modeling power plant temperatures[J].IEEE Transactions on Power Systems,2014,31(4):2578-2586.
[17]杨楠,王波,刘涤尘,等.考虑柔性负荷调峰的大规模风电随机优化调度方法[J].电工技术学报,2013,28(11):231-238.Yang Nan,Wang Bo,Liu Dichen,et al.Large-scale wind power stochastic optimization scheduling method considering flexible load peaking[J].Transactions of China Electrotechnical Society,2013,28(11):231-238(in Chinese).
[18]Dai C,Wu L,Wu H.A multi-band uncertainty set based robust SCUC with spatial and temporal budget constraints[J].IEEE Transactions on Power Systems,2016,31(6):4988-5000.
[19]杨楠,王波,刘涤尘,等.计及大规模风电和柔性负荷的电力系统供需侧联合随机调度方法[J].中国电机工程学报,2013,33(16):63-69.Yang Nan,Wang Bo,Liu Dichen,et al.An integrated supply-demand stochastic optimization method considering large-scale wind power and flexible load[J].Proceedings of the CSEE,2013,33(16):63-69(in Chinese).
[20]Kuo C C.A novel coding scheme for practical economic dispatch by modified particle swarm approach[J].IEEETransactions on Power Systems,2008,23(4):1825-1835.
[21]Fu Y,Shahidehpour M,Li Z.AC contingency dispatch based on security-constrained unit commitment[J].IEEETransactions on Power Systems,2006,21(2):897-908.
[22]Cabria I,Gondra I.Potential-$K$-means for load balancing and cost minimization in mobile recycling network[J].IEEE Systems Journal,2017,11(1):242-249.
[23]林俐,潘险险,张凌云,等.基于免疫离群数据和敏感初始中心的K-means算法的风电场机群划分[J].中国电机工程学报,2016,36(20):5461-5468,5722.Lin Li,Pan Xianxian,Zhang Lingyun,et al.The K-means clustering algorithm for wind farm based on immuneoutlier data and immune-sensitive initial center[J].Proceedings of the CSEE,2016,36(20):5461-5468,5722(in Chinese).
[24]Mets K,Depuydt F,Develder C.Two-stage load pattern clustering using fast wavelet transformation[J].IEEETransactions on Smart Grid,2016,7(5):2250-2259.
[25]Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[26]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735.
[27]Kingma D P,Ba J.Adam:A method for stochastic optimization[C]//International Conference on Learning Representations.San Diego,USA:IEEE,2015.
[28]Wu H,Shahidehpour M.Stochastic SCUC solution with variable wind energy using constrained ordinal optimization[J].IEEE Transactions on Sustainable Energy,2014,5(2):379-388.
[2]Aditi Upadhyay,Hu Bingqian,Li Jie,et al.Achance-constrained wind range quantification approach to robust scuc by determining dynamic uncertainty intervals[J].CSEE Journal of Power and Energy Systems,2016,2(1):54-64.
[3]Wang C,Fu Y.Fully parallel stochastic securityconstrained unit commitment[J].IEEE Transactions on Power Systems,2016,31(5):3561-3571.
[4]Wu Hongyu,Ibrahim Krad,Anthony Florita,et al.Stochastic multi-timescale power system operations with variable wind generation[J].IEEE Transactions on Power Systems,2017,32(5):3325-3337.
[5]Shao C,Wang X,Shahidehpour M,et al.Securityconstrained unit commitment with flexible uncertainty set for variable wind power[J].IEEE Transactions on Sustainable Energy,2017,8(3):1237-1246.
[6]Wu L,Shahidehpour M,Li Z.Comparison of scenariobased and interval optimization approaches to stochastic SCUC[J].IEEE Transactions on Power Systems,2012,27(2):913-921.
[7]Li Dashuang,Zhang Chaoyong,Tian Guangdong,et al.Multiobjective program and hybrid imperialist competitive algorithm for the mixed-model two-sided assembly lines subject to multiple constraints[J].IEEETransactions on Systems,Man and Cybernetics,Systems,2018,48(1):119-129.
[8]包宇庆,王蓓蓓,李扬,等.考虑大规模风电接入并计及多时间尺度需求响应资源协调优化的滚动调度模型[J].中国电机工程学报,2016,36(17):4589-4599.Bao Yuqing,Wang Beibei,Li Yang,et al.Rolling dispatch model considering wind penetration and multi-scale demand response resources[J].Proceedings of the CSEE,2016,36(17):4589-4599(in Chinese).
[9]王晗,徐潇源,严正.考虑柔性负荷的多目标安全约束机组组合优化模型及求解[J].电网技术,2017,41(6):1904-1911.Wang Han,Xu Xiaoyuan,Yan Zheng.Multi-objective optimization of security constrained unit commitment model and solution considering flexible load[J].Power System Technology,2017,41(6):1904-1911(in Chinese).
[10]Li Y F,Pedroni N,Zio E.A memetic evolutionary multi-objective optimization method for environmental power unit commitment[J].IEEE Transactions on Power Systems,2013,28(3):2660-2669.
[11]梅生伟,郭文涛,王莹莹,等.一类电力系统鲁棒优化问题的博弈模型及应用实例[J].中国电机工程学报,2013,33(19):47-56.Mei Shengwei,Guo Wentao,Wang Yingying,et al.Agame model for robust optimization of power systems and its application[J].Proceedings of the CSEE,2013,33(19):47-56(in Chinese).
[12]李整,谭文,秦金磊.一种用于机组组合问题的改进双重粒子群算法[J].中国电机工程学报,2012,32(25):189-195.Li Zheng,Tan Wen,Qin Jinlei.An improved dual particle swarm optimization algorithm for unit commitment problem[J].Proceedings of the CSEE,2012,32(25):189-195(in Chinese).
[13]Attaviriyanupap P,Kita H,Tanaka E,et al.A hybrid LR-EP for solving new profit-based UC problem under competitive environment[J].IEEE Power Engineering Review,2007,22(12):62-62.
[14]韦化,吴阿琴,白晓清.一种求解机组组合问题的内点半定规划方法[J].中国电机工程学报,2008,28(1):35-40.Wei Hua,Wu Aqin,Bai Xiaoqing.An interior point semidefinite programming for unit commitment problems[J].Proceedings of the CSEE,2008,28(1):35-40(in Chinese).
[15]韦化,龙丹丽,黎静华.求解大规模机组组合问题的策略迭代近似动态规划[J].中国电机工程学报,2014,34(25):4420-4429.Wei Hua,Long Danli,Li Jinghua.Policy iterationapproximate dynamic programming for large scale unit commitment problems[J].Proceedings of the CSEE,2014,34(25):4420-4429(in Chinese).
[16]Silbernagl M,Huber M,Brandenberg R.Improving accuracy and efficiency of start-up cost formulations in MIP unit commitment by modeling power plant temperatures[J].IEEE Transactions on Power Systems,2014,31(4):2578-2586.
[17]杨楠,王波,刘涤尘,等.考虑柔性负荷调峰的大规模风电随机优化调度方法[J].电工技术学报,2013,28(11):231-238.Yang Nan,Wang Bo,Liu Dichen,et al.Large-scale wind power stochastic optimization scheduling method considering flexible load peaking[J].Transactions of China Electrotechnical Society,2013,28(11):231-238(in Chinese).
[18]Dai C,Wu L,Wu H.A multi-band uncertainty set based robust SCUC with spatial and temporal budget constraints[J].IEEE Transactions on Power Systems,2016,31(6):4988-5000.
[19]杨楠,王波,刘涤尘,等.计及大规模风电和柔性负荷的电力系统供需侧联合随机调度方法[J].中国电机工程学报,2013,33(16):63-69.Yang Nan,Wang Bo,Liu Dichen,et al.An integrated supply-demand stochastic optimization method considering large-scale wind power and flexible load[J].Proceedings of the CSEE,2013,33(16):63-69(in Chinese).
[20]Kuo C C.A novel coding scheme for practical economic dispatch by modified particle swarm approach[J].IEEETransactions on Power Systems,2008,23(4):1825-1835.
[21]Fu Y,Shahidehpour M,Li Z.AC contingency dispatch based on security-constrained unit commitment[J].IEEETransactions on Power Systems,2006,21(2):897-908.
[22]Cabria I,Gondra I.Potential-$K$-means for load balancing and cost minimization in mobile recycling network[J].IEEE Systems Journal,2017,11(1):242-249.
[23]林俐,潘险险,张凌云,等.基于免疫离群数据和敏感初始中心的K-means算法的风电场机群划分[J].中国电机工程学报,2016,36(20):5461-5468,5722.Lin Li,Pan Xianxian,Zhang Lingyun,et al.The K-means clustering algorithm for wind farm based on immuneoutlier data and immune-sensitive initial center[J].Proceedings of the CSEE,2016,36(20):5461-5468,5722(in Chinese).
[24]Mets K,Depuydt F,Develder C.Two-stage load pattern clustering using fast wavelet transformation[J].IEEETransactions on Smart Grid,2016,7(5):2250-2259.
[25]Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[26]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735.
[27]Kingma D P,Ba J.Adam:A method for stochastic optimization[C]//International Conference on Learning Representations.San Diego,USA:IEEE,2015.
[28]Wu H,Shahidehpour M.Stochastic SCUC solution with variable wind energy using constrained ordinal optimization[J].IEEE Transactions on Sustainable Energy,2014,5(2):379-388.