毛夏平,罗萍萍,姚海佳
MAO Xiaping,LUO Pingping,YAO Haijia

• 1:上海电力大学电气工程学部

摘要(Abstract)：

为准确刻画光伏能源出力的不确定性，同时针对去噪扩散概率模型存在的缺陷，提出一种基于条件去噪扩散隐式模型的光伏日前场景生成方法。通过改进模型逆向去噪过程，实现确定性采样，将日前预测功率作为条件信息，引导逆向去噪过程生成符合条件分布的光伏出力场景；同时采用滑动窗口交叉验证策略，提升模型对时序特征的学习和泛化能力。仿真结果表明，所提方法能有效提升生成效率，且在高采样步数时生成场景能较好地反映光伏出力的时序相关性与概率分布特性，验证了其在新能源不确定性表征方面的有效性与实用性。
To accurately characterize the uncertainty of photovoltaic(PV) power output and address the limitations of denoising diffusion probabilistic models(DDPM), a day-ahead PV scenario generation method based on a conditional denoising diffusion implicit model(CDDIM) is proposed. The method modifies the reverse denoising process to enable deterministic sampling, where day-ahead forecasted PV power is incorporated as conditional information to guide the reverse diffusion process and generate PV power scenarios consistent with the conditional distribution. In addition, a sliding-window cross-validation strategy is adopted to enhance the model's capability in learning temporal features and improve its generalization performance. Simulation results demonstrate that the proposed method effectively improves generation efficiency. Under a higher number of sampling steps, the generated scenarios can well capture the temporal correlations and probabilistic distribution characteristics of PV power output, verifying the effectiveness and practical applicability of the method in representing renewable energy uncertainty.

关键词(KeyWords)： 光伏能源;不确定性;场景生成;条件去噪扩散隐式模型
photovoltaic power;uncertainty;scenario generation;conditional denoising diffusion implicit model

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金（51177107）

作者(Author): 毛夏平,罗萍萍,姚海佳
MAO Xiaping,LUO Pingping,YAO Haijia

DOI: 10.19585/j.zjdl.202609006

参考文献(References)：

• [1]国务院.国务院关于应对气候变化和碳达峰碳中和工作情况的报告[R/OL].(2025-09-10).https：//www.mee.gov.cn/xxgk/hjyw/202509/t20250912＿1127354.shtml.
• [2]李夫刚，李夫海，琚承乾，等.新能源不确定性表征方法及关键技术问题研究现状、挑战及展望[J].电力系统保护与控制，2025,53(15):172-187.Li Fugang,Li Fuhai,Ju Chengqian,et al.Research status,challenges and prospects of characterization methods for new energy uncertainty and key technical issues[J].Power System Protection and Control,2025,53(15):172-187.
• [3]郑之轩，倪妮，吴思媛.计及光伏消纳和需求响应的典型农业园区调度优化[J].电力需求侧管理，2025,27(5):30-35.Zheng Zhixuan,Ni Ni,Wu Siyuan. Optimal dispatch of typical agricultural park considering photovoltaic consumption and demand response[J].Power Demand Side Management,2025,27(5):30-35.
• [4]冯松杰，魏韡.考虑新能源消纳和电力保供的电力系统多时间尺度平衡方法[J].电力系统自动化，2025,49(4):128-140.Feng Songjie,Wei Wei.Multi-timescale balancing method for power systems considering renewable energy accommodation and power supply support[J]. Automation of Electric Power Systems,2025,49(4):128-140.
• [5]李振坤，游胜苒，李景岳，等.计及动态定价机制和需求响应的社区综合能源系统优化运行[J].智慧电力，2025,53(9):56-63.Li Zhenkun,You Shengran,Li Jingyue,et al. Optimized operation of community integrated energy systems considering dynamic pricing mechanism and demand response[J].Smart Power,2025,53(9):56-63.
• [6]卢佳富，梁宁，徐慧慧，等.动态碳-绿证交易交互机制下多综合能源系统协调优化调度[J].电力系统自动化，2025,49(9):52-60.Lu Jiafu,Liang Ning,Xu Huihui,et al.Coordinated optimal dispatch of multiple integrated energy systems under dynamic carbon-green certificate trading interaction mechanism[J].Automation of Electric Power Systems,2025,49(9):52-60.
• [7]翟晶晶，冷昕，李承澳，等.考虑源荷不确定性的楼宇综合能源系统日前优化调度[J].电力需求侧管理，2025,27(5):71-77.Zhai Jingjing,Leng Xin,Li Cheng’ao,et al.Day-ahead optimal operation of building integrated energy system considering source and load uncertainty[J]. Power Demand Side Management,2025,27(5):71-77.
• [8]吴中孚，邓丽君，覃智君.计及多能灵活性的含光热电站综合能源系统多目标分布鲁棒优化调度[J].电力建设，2024,45(12):39-53.Wu Zhongfu,Deng Lijun,Qin Zhijun.Multi-objective distributionally robust optimal scheduling of integrated energy system with concentrated solar power plant considering multi-energy flexibility[J]. Electric Power Construction,2024,45(12):39-53.
• [9]米阳，卢长坤，申杰，等.基于条件生成对抗网络的风电功率极端场景生成[J].高电压技术，2023,49(6):2253-2263.Mi Yang,Lu Changkun,Shen Jie,et al.Generation of extreme scenarios for wind power based on conditional generative adversarial networks[J]. High Voltage Engineering,2023,49(6):2253-2263.
• [10]罗萍萍，盛奥，林济铿，等.基于可解释性条件生成对抗网络的台风气象负荷场景生成方法[J].电力系统自动化，2025,49(2):186-197.Luo Pingping,Sheng Ao,Lin Jikeng,et al.A method for generating typhoon meteorological load scenarios based on interpretable conditional generative adversarial networks[J].Automation of Electric Power Systems,2025,49(2):186-197.
• [11]董骁翀，张姝，李烨，等.电力系统中时序场景生成和约简方法研究综述[J].电网技术，2023,47(2):709-721.Dong Xiaochong,Zhang Shu,Li Ye,et al.A Review on research of temporal scenario generation and reduction methods in power systems[J]. Power System Technology,2023,47(2):709-721.
• [12]王玲玲，王昕，郑益慧，等.计及多个风电机组出力相关性的配电网无功优化[J].电网技术，2017,41(11):3463-3469.Wang Lingling,Wang Xin,Zheng Yihui,et al. Reactive power optimization of distribution network considering output correlation of multiple wind turbines[J]. Power System Technology,2017,41(11):3463-3469.
• [13]彭竹弈，宋杉，许偲轩，等.基于时序运行模拟的新能源电力系统典型场景生成方法[J].浙江电力，2025,44(5):66-75.Peng Zhuyi,Song Shan,Xu Sixuan,et al. A typical scenario generation method for renewable energy power systems based on time-sequenced operational simulations[J].Zhejiang Electric Power,2025,44(5):66-75.
• [14]赵书强，金天然，李志伟，等.考虑时空相关性的多风电场出力场景生成方法[J].电网技术，2019,43(11):3997-4004.Zhao Shuqiang,Jin Tianran,Li Zhiwei,et al.A method for generating output scenarios of multiple wind farms considering spatiotemporal correlation[J].Power System Technology,2019,43(11):3997-4004.
• [15]郭红霞，陈凌轩，张启，等.电力电量平衡视角下新型电力系统极端场景研究及应对综述[J].电网技术，2024,48(10):3975-3994.Guo Hongxia,Chen Lingxuan,Zhang Qi,et al.A review on research and response of extreme scenarios in new power systems from the perspective of power and electricity balance[J].Power System Technology,2024,48(10):3975-3994.
• [16]Kingma D P,Welling M.Auto-encoding variational bayes[Z].arXiv preprint arXiv:1312.6114,2013.
• [17]Goodfellow I J,Pouget-Abadie J,Mirza M,et al.Generative adversarial nets[C]//27th International Conference on Neural Information Processing Systems. Montreal,Canada:MIT Press,2014.
• [18]王新迎，李烨，董骁翀，等.基于变分自编码器的主动配电网多源-荷场景生成方法[J].电网技术，2021,45(8):2962-2969.Wang Xinying,Li Ye,Dong Xiaochong,et al. A method for generating multi-source-load scenarios of active distribution network based on variational autoencoder[J].Power System Technology,2021,45(8):2962-2969.
• [19]Yang D Y,Zhang Z H,Gao H,et al. Variational autoencoder-based learning intrinsic periodic-trend representations of power load series for short-term forecasting[J].Energy Reports,2025,13:6584-6595.
• [20]董骁翀，孙英云，蒲天骄.基于条件生成对抗网络的可再生能源日前场景生成方法[J].中国电机工程学报，2020,40(17):5527-5536.Dong Xiaochong,Sun Yingyun,Pu Tianjiao.A day-ahead scenario generation method for renewable energy based on conditional generative adversarial network[J].Proceedings of the CSEE,2020,40(17):5527-5536.
• [21]孟凡斌，南钰，武亚非，等.基于谱归一化生成对抗网络与谱聚类的典型风力发电场景生成[J].浙江电力，2024,43(12):86-94.Meng Fanbin,Nan Yu,Wu Yafei,et al.Generation of typical wind power scenarios based on spectral normalization generative adversarial networks and spectral clustering[J].Zhejiang Electric Power,2024,43(12):86-94.
• [22]邵振国，张承圣，陈飞雄，等.生成对抗网络及其在电力系统中的应用综述[J].中国电机工程学报，2023,43(3):987-1004.Shao Zhenguo,Zhang Chengsheng,Chen Feixiong,et al.A review of generative adversarial networks and their applications in power systems[J].Proceedings of the CSEE,2023,43(3):987-1004.
• [23]Luo C.Understanding diffusion models:a unified perspective[EB/OL].[2025-12-20]. arXiv preprint arXiv:2208.11970,2022.
• [24]刘润龙，李亦言，周正昊，等.基于扩散模型考虑用户行为的电动汽车充电场景生成[J].电力系统自动化，2026,50(3):135-144.Liu R L,Li Y Y,Zhou Z H,et al.Diffusion model-based electric vehicle charging scenario generation considering user behavior[J].Automation of Electric Power Systems,2026,50(3):135-144.
• [25]Ma W,He G,Che L. Conditional denoising diffusion probabilistic model based ante-hoc explainable scenario generation for power systems dispatch[J].Energy,2025,332:137115.
• [26]Song J M,Meng C L,Ermon S. Denoising diffusion implicit models[EB/OL].[2025-12-20]. arXiv preprint arXiv:2010.02502,2020. https：//arxiv. org/abs/2010.02502.
• [27]Hespeler S C.Temporal cross-validation impacts multivariate time series subsequence anomaly detection evaluation[EB/OL].[2025-12-20]. arXiv preprint arXiv:2506.12183,2025.
• [28]Ho J,Jain A,Abbeel P. Denoising diffusion probabilistic models[J].Advances in neural information processing systems,2020,33:6840-685
• [29]Lim B,Ar??k S??，Loeff N,et al. Temporal fusion transformers for interpretable multi-horizon time series forecasting[J].International journal of forecasting,2021,37(4):1748-1764.
• [30]马恒瑞，袁傲添，王波，等.基于深度学习的负荷预测研究综述与展望[J].高电压技术，2025,51(3):1233-1250.Ma Hengrui,Yuan Aotian,Wang Bo,et al.A Review and prospect of load forecasting research based on deep learning[J]. High Voltage Engineering,2025,51(3):1233-1250.
• [31]Nichol A Q,Dhariwal P. Improved denoising diffusion probabilistic models[C]//International Conference on Machine Learning.PMLR,2021.
• [32]Bergmeir C,Hyndman R J,Koo B.A note on the validity of cross-validation for evaluating autoregressive time series prediction[J]. Computational Statistics and Data Analysis,2018,120:70-83.
• [33]Lu C,Zhou Y,Bao F,et al. DPM-Solver:A fast ODE solver for diffusion probabilistic model sampling in around10 steps[C]//Advances in Neural Information Processing Systems(NeurIPS).Curran Associates Inc.,2022.