基于GAN场景模拟与条件风险价值的独立型微网容量随机优化配置模型
|
摘要
为了考虑风光不确定性给微网运行带来的风险,针对独立型微网的容量优化配置,提出一种基于生成对抗网络(generative adversarial network,GAN)场景模拟和条件风险价值(conditional value at risk,CVaR)的容量随机优化配置模型。首先利用GAN模拟大量风光出力场景,再用K-medoids聚类进行消减得到若干典型场景;其次,以微网供电可靠性为约束,以经济性和可再生能源利用率为目标函数,通过CVaR度量因风光资源不确定性给微网系统带来的运行风险,并将其以平均风险损失的形式与目标函数相结合,构建微网电源容量随机优化配置模型;最后,采用电源损失风险和负荷风险损失指标对配置结果进行评价。仿真算例表明,相比于仅采用典型年风光资源数据进行配置的传统方法,文中提出的模型对于规划周期内可能出现的运行场景适应性更好。
A stochastic optimization model based on scenario simulation using generative adversarial network(GAN) and conditional value at risk(CVaR) is proposed for stand-alone microgrid capacity configuration for the purpose of considering the operation risks resulted from the uncertainties of wind and solar resources. Firstly, we use GAN to generate a lot of scenarios of wind and solar outputs. Several typical scenarios are obtained through scenario reduction using K-medoids algorithm. Secondly, the power supply reliability is taken as a constraint, the economy and renewable energy utilization are regarded as objective functions, the operation risks caused by the uncertainties of wind and solar resources are measured by the CVaR. A stochastic capacity configuration optimization model is proposed by combining the risks(i.e. in the form of average risk loss) and the above objective functions. Finally, the results are evaluated with two risk indexes of power loss and load loss. Simulation results show that compared with the traditional methods performing capacity configuration only using wind and solar resource data in typical years, the proposed model can better adapt to possible operation scenarios during the planning period.
A stochastic optimization model based on scenario simulation using generative adversarial network(GAN) and conditional value at risk(CVaR) is proposed for stand-alone microgrid capacity configuration for the purpose of considering the operation risks resulted from the uncertainties of wind and solar resources. Firstly, we use GAN to generate a lot of scenarios of wind and solar outputs. Several typical scenarios are obtained through scenario reduction using K-medoids algorithm. Secondly, the power supply reliability is taken as a constraint, the economy and renewable energy utilization are regarded as objective functions, the operation risks caused by the uncertainties of wind and solar resources are measured by the CVaR. A stochastic capacity configuration optimization model is proposed by combining the risks(i.e. in the form of average risk loss) and the above objective functions. Finally, the results are evaluated with two risk indexes of power loss and load loss. Simulation results show that compared with the traditional methods performing capacity configuration only using wind and solar resource data in typical years, the proposed model can better adapt to possible operation scenarios during the planning period.
引文
[1]杨新法,苏剑,吕志鹏,等.微电网技术综述[J].中国电机工程学报,2014,34(1):57-70.Yang Xinfa,Su Jian,LüZhipeng,et al.Overview on microgrid technology[J].Proceedings of the CSEE,2014,34(1):57-70(in Chinese).
[2]刘娇扬,郭力,杨书强,等.配电网中多光储微网系统的优化配置方法[J].电网技术,2018,42(9):2806-2815.Liu Jiaoyang,Guo Li,Yang Shuqiang,et al.Optimal sizing for multi PV-ESS microgrids in distribution network[J].Power System Technology,2018,42(9):2806-2815(in Chinese).
[3]潘文霞,李建成,方坤豪.考虑补贴的独立微网容量配置优化方法[J].电网技术,2018,42(7):2206-2213.Pan Wenxia,Li Jiancheng,Fang Kunhao.Optimization method of capacity configuration of standalone microgrid considering subsidy[J].Power System Technology,2018,42(7):2206-2213(in Chinese).
[4]Wang F,Mi Z,Su S,et al.Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters[J].Energies,2012,5(5):1355-1370.
[5]陈青恒,袁晓杰,何宇俊,等.投资开放模式下基于全寿命周期分析的离网型微网投资与优化[J].电网技术,2018,42(8):2448-2457.Chen Qingheng,Yuan Xiaojie,He Yujun,et al.Investment and optimization of off-grid microgrid projects based on life-cycle cost/benefit analysis with open investment mode[J].Power System Technology,2018,42(8):2448-2457(in Chinese).
[6]周灿煌,郑杰辉,荆朝霞,等.面向园区微网的综合能源系统多目标优化设计[J].电网技术,2018,42(6):1687-1697.Zhou Canhuang,Zheng Jiehui,Jing Zhaoxia,et al.Multiobjective optimal design of integrated energy system for park-level microgrid[J].Power System Technology,2018,42(6):1687-1697(in Chinese).
[7]刘敦楠,徐尔丰,许小峰.面向园区微网的“源-网-荷-储”一体化运营模式[J].电网技术,2018,42(3):681-689.Liu Dunnan,Xu Erfeng,Xu Xiaofeng.“Source-network-load-storage”integrated operation model for microgrid in park[J].Power System Technology,2018,42(3):681-689(in Chinese).
[8]王守相,王慧,蔡声霞.分布式发电优化配置研究综述[J].电力系统自动化,2009,33(18):110-115.Wang Shouxiang,Wang Hui,Cai Shengxia.A review of optimization allocation of distributed generations embedded in power grid[J].Automation of Electric Power Systems,2009,33(18):110-115(in Chinese).
[9]丁明,王波,赵波,等.独立风光柴储微网系统容量优化配置[J].电网技术,2013,37(3):575-581.Ding Ming,Wang Bo,Zhao Bo,et al.Configuration optimization of capacity of standalone PV-wind-diesel-battery hybrid microgrid[J].Power System Technology,2013,37(3):575-581(in Chinese).
[10]郭力,刘文建,焦冰琦,等.独立微网系统的多目标优化规划设计方法[J].中国电机工程学报,2014,34(4):524-536.Guo Li,Liu Wenjian,Jiao Bingqi,et al.Multi-objective optimal planning design method for stand-alone microgrid system[J].Proceeds of the CSEE,2014,34(4):524-536(in Chinese).
[11]赵波,包侃侃,徐志成,等.考虑需求侧响应的光储并网型微电网优化配置[J].中国电机工程学报,2015,35(21):5465-5474.Zhao Bo,Bao Kankan,Xu Zhicheng,et al.Optimal sizing for gridconnected PV-and-storage microgrid considering demand response[J].Proceedings of the CSEE,2015,35(21):5465-5474(in Chinese).
[12]荆朝霞,胡荣兴,袁灼新,等.含风/光/抽水蓄能并计及负荷响应的海岛微网优化配置[J].电力系统自动化,2017,41(1):65-72.Jing Zhaoxia,Hu Rongxing,Yuan Zhuoxin,et al.Capacity configuration optimization for island microgrid with wind/solar/pumped storage considering demand response[J].Automation of Electric Power Systems,2017,41(1):65-72(in Chinese).
[13]Wang Z,Wang F,Su S.Solar irradiance short-term prediction model based on BP neural network[J].Energy Procedia,2011,12:488-494.
[14]Sun Y,Wang F,Wang B,et al.Correlation feature selection and mutual information theory based quantitative research on meteorological impact factors of module temperature for solar photovoltaic systems[J].Energies,2016,10(1):7.
[15]Sun Y,Wang F,Zhen Z,et al.Research on short-term module temperature prediction model based on BP neural network for photovoltaic power forecasting[C]//Power&Energy Society General Meeting.IEEE,2015.
[16]薛美东,赵波,张雪松,等.并网型微网的优化配置与评估[J].电力系统自动化,2015,39(3):6-13.Xue Meidong,Zhao Bo,Zhang Xuesong,et al.Integrated plan and evaluation of grid connected microgrid[J].Automation of Electric Power Systems,2015,39(3):6-13(in Chinese).
[17]余金龙,赵文会,赵波,等.基于多状态建模的独立型微网优化配置[J].电力系统自动化,2015,39(6):11-17.Yu Jinlong,Zhao Wenhui,Zhao Bo,et al.Optimal configuration of standalone micro-grid based on multistate modeling[J].Automation of Electric Power Systems,2015,39(6):11-17(in Chinese).
[18]鲜杏,范传光,文闪闪,等.考虑可再生能源随机性的孤岛微网容量优化配置方法[J].武汉大学学报:工学版,2016,49(1):100-104.Xian Xing,Fan Chuanguang,Wen Shanshan,et al.Optimal deployment for island micro-grid considering probabilistic factors of renewable energy generations[J].Engineering Journal of Wuhan University,2016,49(1):100-104(in Chinese).
[19]Goodfellow I,Pouget-Abadie J,Mirza M,et al.Generative adversarial nets[C]//International Conference on Neural Information Processing Systems,2014.
[20]王壬,尚金成,周晓阳,等.基于条件风险价值的购电组合优化及风险管理[J].电网技术,2006,30(20):72-76.Wang Ren,Shang Jincheng,Zhou Xiaoyang,et al.Conditional value at risk based optimization of power purchasing portfolio in multiple electricity markets and risk management[J].Power System Technology,2006,30(20):72-76(in Chinese).
[21]Chen Y,Wang Y,Kirschen D S,et al.Model-free renewable scenario generation using generative adversarial networks[J].IEEETransactions on Power Systems,2018,33(3):3265-3275.
[22]王群,董文略,杨莉.基于Wasserstein距离和改进K-medoids聚类的风电/光伏经典场景集生成算法[J].中国电机工程学报,2015,35(11):2654-2661.Wang Qun,Dong Wenlue,Yang Li.A wind power/photovoltaic typical scenario set generation algorithm based on Wasserstein distance metric and revised K-medoids cluster[J].Proceedings of the CSEE,2015,35(11):2654-2661(in Chinese).
[23]Wang F,Li K,Liu C,et al.Synchronous pattern matching principle based residential demand response baseline estimation:mechanism analysis and approach description[J].IEEE Transactions on Smart Grid,2018,9(6):6972-6985.
[24]Ni M,Mccalley J D,Vittal V,et al.Online risk-based security assessment[J].IEEE Power Engineering Review,2002,22(1):59-59.
[25]刘柏良,黄学良,李军.计及可时移负荷的海岛微网电源优化配置[J].中国电机工程学报,2014,34(25):4250-4258.Liu Bailiang,Huang Xueliang,Li Jun.Optimal sizing of distributed generation in a typical island microgrid with time-shifting load[J].Proceedings of the CSEE,2014,34(25):4250-4258(in Chinese).
[2]刘娇扬,郭力,杨书强,等.配电网中多光储微网系统的优化配置方法[J].电网技术,2018,42(9):2806-2815.Liu Jiaoyang,Guo Li,Yang Shuqiang,et al.Optimal sizing for multi PV-ESS microgrids in distribution network[J].Power System Technology,2018,42(9):2806-2815(in Chinese).
[3]潘文霞,李建成,方坤豪.考虑补贴的独立微网容量配置优化方法[J].电网技术,2018,42(7):2206-2213.Pan Wenxia,Li Jiancheng,Fang Kunhao.Optimization method of capacity configuration of standalone microgrid considering subsidy[J].Power System Technology,2018,42(7):2206-2213(in Chinese).
[4]Wang F,Mi Z,Su S,et al.Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters[J].Energies,2012,5(5):1355-1370.
[5]陈青恒,袁晓杰,何宇俊,等.投资开放模式下基于全寿命周期分析的离网型微网投资与优化[J].电网技术,2018,42(8):2448-2457.Chen Qingheng,Yuan Xiaojie,He Yujun,et al.Investment and optimization of off-grid microgrid projects based on life-cycle cost/benefit analysis with open investment mode[J].Power System Technology,2018,42(8):2448-2457(in Chinese).
[6]周灿煌,郑杰辉,荆朝霞,等.面向园区微网的综合能源系统多目标优化设计[J].电网技术,2018,42(6):1687-1697.Zhou Canhuang,Zheng Jiehui,Jing Zhaoxia,et al.Multiobjective optimal design of integrated energy system for park-level microgrid[J].Power System Technology,2018,42(6):1687-1697(in Chinese).
[7]刘敦楠,徐尔丰,许小峰.面向园区微网的“源-网-荷-储”一体化运营模式[J].电网技术,2018,42(3):681-689.Liu Dunnan,Xu Erfeng,Xu Xiaofeng.“Source-network-load-storage”integrated operation model for microgrid in park[J].Power System Technology,2018,42(3):681-689(in Chinese).
[8]王守相,王慧,蔡声霞.分布式发电优化配置研究综述[J].电力系统自动化,2009,33(18):110-115.Wang Shouxiang,Wang Hui,Cai Shengxia.A review of optimization allocation of distributed generations embedded in power grid[J].Automation of Electric Power Systems,2009,33(18):110-115(in Chinese).
[9]丁明,王波,赵波,等.独立风光柴储微网系统容量优化配置[J].电网技术,2013,37(3):575-581.Ding Ming,Wang Bo,Zhao Bo,et al.Configuration optimization of capacity of standalone PV-wind-diesel-battery hybrid microgrid[J].Power System Technology,2013,37(3):575-581(in Chinese).
[10]郭力,刘文建,焦冰琦,等.独立微网系统的多目标优化规划设计方法[J].中国电机工程学报,2014,34(4):524-536.Guo Li,Liu Wenjian,Jiao Bingqi,et al.Multi-objective optimal planning design method for stand-alone microgrid system[J].Proceeds of the CSEE,2014,34(4):524-536(in Chinese).
[11]赵波,包侃侃,徐志成,等.考虑需求侧响应的光储并网型微电网优化配置[J].中国电机工程学报,2015,35(21):5465-5474.Zhao Bo,Bao Kankan,Xu Zhicheng,et al.Optimal sizing for gridconnected PV-and-storage microgrid considering demand response[J].Proceedings of the CSEE,2015,35(21):5465-5474(in Chinese).
[12]荆朝霞,胡荣兴,袁灼新,等.含风/光/抽水蓄能并计及负荷响应的海岛微网优化配置[J].电力系统自动化,2017,41(1):65-72.Jing Zhaoxia,Hu Rongxing,Yuan Zhuoxin,et al.Capacity configuration optimization for island microgrid with wind/solar/pumped storage considering demand response[J].Automation of Electric Power Systems,2017,41(1):65-72(in Chinese).
[13]Wang Z,Wang F,Su S.Solar irradiance short-term prediction model based on BP neural network[J].Energy Procedia,2011,12:488-494.
[14]Sun Y,Wang F,Wang B,et al.Correlation feature selection and mutual information theory based quantitative research on meteorological impact factors of module temperature for solar photovoltaic systems[J].Energies,2016,10(1):7.
[15]Sun Y,Wang F,Zhen Z,et al.Research on short-term module temperature prediction model based on BP neural network for photovoltaic power forecasting[C]//Power&Energy Society General Meeting.IEEE,2015.
[16]薛美东,赵波,张雪松,等.并网型微网的优化配置与评估[J].电力系统自动化,2015,39(3):6-13.Xue Meidong,Zhao Bo,Zhang Xuesong,et al.Integrated plan and evaluation of grid connected microgrid[J].Automation of Electric Power Systems,2015,39(3):6-13(in Chinese).
[17]余金龙,赵文会,赵波,等.基于多状态建模的独立型微网优化配置[J].电力系统自动化,2015,39(6):11-17.Yu Jinlong,Zhao Wenhui,Zhao Bo,et al.Optimal configuration of standalone micro-grid based on multistate modeling[J].Automation of Electric Power Systems,2015,39(6):11-17(in Chinese).
[18]鲜杏,范传光,文闪闪,等.考虑可再生能源随机性的孤岛微网容量优化配置方法[J].武汉大学学报:工学版,2016,49(1):100-104.Xian Xing,Fan Chuanguang,Wen Shanshan,et al.Optimal deployment for island micro-grid considering probabilistic factors of renewable energy generations[J].Engineering Journal of Wuhan University,2016,49(1):100-104(in Chinese).
[19]Goodfellow I,Pouget-Abadie J,Mirza M,et al.Generative adversarial nets[C]//International Conference on Neural Information Processing Systems,2014.
[20]王壬,尚金成,周晓阳,等.基于条件风险价值的购电组合优化及风险管理[J].电网技术,2006,30(20):72-76.Wang Ren,Shang Jincheng,Zhou Xiaoyang,et al.Conditional value at risk based optimization of power purchasing portfolio in multiple electricity markets and risk management[J].Power System Technology,2006,30(20):72-76(in Chinese).
[21]Chen Y,Wang Y,Kirschen D S,et al.Model-free renewable scenario generation using generative adversarial networks[J].IEEETransactions on Power Systems,2018,33(3):3265-3275.
[22]王群,董文略,杨莉.基于Wasserstein距离和改进K-medoids聚类的风电/光伏经典场景集生成算法[J].中国电机工程学报,2015,35(11):2654-2661.Wang Qun,Dong Wenlue,Yang Li.A wind power/photovoltaic typical scenario set generation algorithm based on Wasserstein distance metric and revised K-medoids cluster[J].Proceedings of the CSEE,2015,35(11):2654-2661(in Chinese).
[23]Wang F,Li K,Liu C,et al.Synchronous pattern matching principle based residential demand response baseline estimation:mechanism analysis and approach description[J].IEEE Transactions on Smart Grid,2018,9(6):6972-6985.
[24]Ni M,Mccalley J D,Vittal V,et al.Online risk-based security assessment[J].IEEE Power Engineering Review,2002,22(1):59-59.
[25]刘柏良,黄学良,李军.计及可时移负荷的海岛微网电源优化配置[J].中国电机工程学报,2014,34(25):4250-4258.Liu Bailiang,Huang Xueliang,Li Jun.Optimal sizing of distributed generation in a typical island microgrid with time-shifting load[J].Proceedings of the CSEE,2014,34(25):4250-4258(in Chinese).