|
|
基于扩散模型的数据中心虚拟电厂分布鲁棒优化调度策略
|
Abstract:
具有强不确定性的可再生能源并网给包含数据中心的虚拟电厂的安全运行带来了巨大的挑战。为此，本文提出一种基于扩散模型的数据中心虚拟电厂分布鲁棒优化调度模型。首先，为了更准确地刻画光伏的不确定性，采用扩散模型对辐照度–温度联合场景数据进行泛化处理，提高光伏出力数据的准确性和多样性。然后，通过高斯混合聚类模型对光伏出力数据进行削减，并将得到的场景作为分布鲁棒优化集合的初始场景。再次，为进一步挖掘数据中心的需求响应潜力，建立了包含可转移批处理负载的数据中心虚拟电厂的数学模型。最后，为了求解min-max-min分布鲁棒优化问题，通过列和约束生成算法进行求解。仿真结果表明，本文所提出的基于扩散模型的光伏出力场景生成方法能更准确、更有效地刻画光伏的不确定性。此外，本文所提的分布鲁棒优化模型能平衡经济运行和鲁棒性之间的关系。
The integration of highly uncertain renewable energy into the grid poses significant challenges to the secure operation of virtual power plants (VPPs) that include data centers. To address this issue, this paper proposes a distributionally robust optimization (DRO) scheduling model for data center VPPs based on a diffusion model. First, to more accurately characterize the uncertainty of photovoltaic (PV) power generation, a diffusion model is employed to generalize irradiance-temperature joint scenario data, enhancing both the accuracy and diversity of PV output data. Then, a Gaussian mixture clustering model is applied to reduce the dimensionality of PV output data, and the resulting scenarios are used as the initial set for DRO. Furthermore, to further explore the demand response potential of data centers, a mathematical model for data center VPPs incorporating transferable batch processing loads is developed. Finally, the min-max-min DRO problem is solved using the column-and-constraint generation algorithm. Simulation results demonstrate that the proposed diffusion model-based PV output scenario generation method in this paper can more accurately and effectively capture the uncertainty of PV. Additionally, the proposed DRO model in this paper can effectively balance the relationship between economic operation and robustness.
| [1] | Liu, X., Li, Y., Wang, L., Tang, J., Qiu, H., Berizzi, A., et al. (2024) Dynamic Aggregation Strategy for a Virtual Power Plant to Improve Flexible Regulation Ability. Energy, 297, Article ID: 131261. https://doi.org/10.1016/j.energy.2024.131261 |
| [2] | Chang, H., Ghaddar, B. and Nathwani, J. (2022) Shared Community Energy Storage Allocation and Optimization. Applied Energy, 318, Article ID: 119160. https://doi.org/10.1016/j.apenergy.2022.119160 |
| [3] | Dong, Y., Zhang, H., Ma, P., Wang, C. and Zhou, X. (2023) A Hybrid Robust-Interval Optimization Approach for Integrated Energy Systems Planning under Uncertainties. Energy, 274, Article ID: 127267. https://doi.org/10.1016/j.energy.2023.127267 |
| [4] | Fusco, A., Gioffrè, D., Francesco Castelli, A., Bovo, C. and Martelli, E. (2023) A Multi-Stage Stochastic Programming Model for the Unit Commitment of Conventional and Virtual Power Plants Bidding in the Day-Ahead and Ancillary Services Markets. Applied Energy, 336, Article ID: 120739. https://doi.org/10.1016/j.apenergy.2023.120739 |
| [5] | Alabi, T.M., Lu, L. and Yang, Z. (2022) Data-Driven Optimal Scheduling of Multi-Energy System Virtual Power Plant (MEVPP) Incorporating Carbon Capture System (CCS), Electric Vehicle Flexibility, and Clean Energy Marketer (CEM) Strategy. Applied Energy, 314, Article ID: 118997. https://doi.org/10.1016/j.apenergy.2022.118997 |
| [6] | 李虹, 韩雨萌. 基于LSTM-CGAN的多微网数据驱动分布鲁棒协同优化运行策略[J]. 电力系统保护与控制, 2024, 52(18): 133-148. |
| [7] | Huang, W., Qian, T., Tang, W. and Wu, J. (2025) A Distributionally Robust Chance Constrained Optimization Approach for Security-Constrained Optimal Power Flow Problems Considering Dependent Uncertainty of Wind Power. Applied Energy, 383, Article ID: 125264. https://doi.org/10.1016/j.apenergy.2024.125264 |
| [8] | Gao, H., Yin, B., He, S. and Liu, J. (2025) A Distributionally Robust-Based Information Gap Decision Theory Optimization Method for Energy Station Considering Low-Carbon Demand Response. Sustainable Energy Technologies and Assessments, 73, Article ID: 104129. https://doi.org/10.1016/j.seta.2024.104129 |
| [9] | Son, Y.G. and Kim, S.Y. (2024) Optimal Planning and Operation of Integrated Energy Systems in South Korea: Introducing a Novel Ambiguity Set Based Distributionally Robust Optimization. Energy, 307, Article ID: 132503. https://doi.org/10.1016/j.energy.2024.132503 |
| [10] | Dolatabadi, A., Abdeltawab, H. and Mohamed, Y.A.I. (2023) A Novel Model-Free Deep Reinforcement Learning Framework for Energy Management of a PV Integrated Energy Hub. IEEE Transactions on Power Systems, 38, 4840-4852. https://doi.org/10.1109/tpwrs.2022.3212938 |
| [11] | Ma, M., Long, Z., Liu, X. and Lee, K.Y. (2025) Distributionally Robust Optimization of Electric-Thermal-Hydrogen Integrated Energy System Considering Source-Load Uncertainty. Energy, 316, Article ID: 134568. https://doi.org/10.1016/j.energy.2025.134568 |
| [12] | Liu, X. (2024) Research on Collaborative Scheduling of Internet Data Center and Regional Integrated Energy System Based on Electricity-Heat-Water Coupling. Energy, 2024, Article ID: 130462. https://doi.org/10.1016/j.energy.2024.130462 |
| [13] | Ho, J., Jain, A. and Abbeel, P. (2020) Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6-12 December 2020, 6840-6851. |
| [14] | Li, Y., Han, M., Shahidehpour, M., Li, J. and Long, C. (2023) Data-Driven Distributionally Robust Scheduling of Community Integrated Energy Systems with Uncertain Renewable Generations Considering Integrated Demand Response. Applied Energy, 335, Article ID: 120749. https://doi.org/10.1016/j.apenergy.2023.120749 |
| [15] | Wang, S., Wang, Z., Cheng, X. and Zhang, Z. (2023) A Double-Layer Fault Diagnosis Strategy for Electric Vehicle Batteries Based on Gaussian Mixture Model. Energy, 281, Article ID: 128318. https://doi.org/10.1016/j.energy.2023.128318 |
| [16] | 马浩天, 胡俊杰, 童宇轩. 考虑灵活性的数据中心微网两阶段鲁棒规划方法[J]. 中国电机工程学报, 2023, 43(19): 7396-7409. |
| [17] | 孙旭, 邱晓燕, 张志荣, 等. 基于数据驱动的交直流配电网分布鲁棒优化调度[J]. 电网技术, 2021, 45(12): 4768-4778. |
| [18] | 张智浩, 王聪, 张宏立, 等. 时间生成对抗网络样本扩增下的风电功率预测[J/OL]. 电力系统及其自动化学报: 1-12. https://link.cnki.net/doi/10.19635/j.cnki.csu-epsa.001588, 2025-02-27. |
