Reinforcement learning algorithms are increasingly utilized across diverse domains within power systems. One notable challenge in training and deploying these algorithms is the acquisition of large, realistic datasets. It is imperative that these algorithms are trained on extensive, realistic datasets over numerous iterations to ensure optimal performance in real-world scenarios. In pursuit of this goal, we curated a comprehensive dataset capturing electric vehicle (EV) charging details over a span of 29,600 days within a designated parking facility. This dataset encompasses necessary information such as connection times, charging durations, and energy consumption of individual EVs. The methodology involved employing conditional tabular generative adversarial networks (CTGAN) to craft a pool of synthetic dataset from a smaller initial dataset collected from an EV charging facility located on the Caltech campus. Subsequently, multiple post-processing techniques were implemented to extract data from this pool, ensuring compliance with the charging station's capacity constraint while maintaining a realistic daily EV demand profile derived from historical data. Using kernel density estimation (KDE), the distributional characteristics of the historical data, especially concerning the timing of EV connections, were faithfully replicated. The developed dataset is specifically useful in training offline reinforcement learning algorithms.

Applied Cybernetics University of Hradec Králové Hradec Králové Czechia

Electrical and Computer Engineering University of Alberta Edmonton Alberta Canada T6G 2R3

Zobrazit více v PubMed

Gholizadeh N., Musilek P. Electric vehicle charging dataset. Mendeley Data. 2024:V2. doi: 10.17632/5zrtmp7gwd.2. DOI

Yan L., Chen X., Chen Y., Wen J. A cooperative charging control strategy for electric vehicles based on multiagent deep reinforcement learning. IEEE Trans. Ind. Inform. 2022;18:8765–8775. doi: 10.1109/TII.2022.3152218. DOI

Zhao Z., Lee C.K.M. Dynamic pricing for EV charging stations: a deep reinforcement learning approach. IEEE Trans. Transport. Electrif. 2022;8:2456–2468. doi: 10.1109/TTE.2021.3139674. DOI

Amara-Ouali Y., Goude Y., Massart P., Poggi J.-M., Yan H. A review of electric vehicle load open data and models. Energies. 2021;14:2233. doi: 10.3390/en14082233. DOI

Jang J., Han J., Kim J. K-mixup: data augmentation for offline reinforcement learning using mixup in a Koopman invariant subspace. Expert Syst. Appl. 2023;225 doi: 10.1016/j.eswa.2023.120136. ISSN 0957-4174. DOI

Liu T., Chen H., Hu J., Yang Z., Yu B., Du X., Miao Y., Chang Y. Generalized multi-agent competitive reinforcement learning with differential augmentation. Expert Syst. Appl. 2024;238(Part C) doi: 10.1016/j.eswa.2023.121760. ISSN 0957-4174. DOI

Wang Y., Jia Y., Zhong Y., Huang J., Xiao J. Balanced incremental deep reinforcement learning based on variational autoencoder data augmentation for customer credit scoring. Eng. Appl. Artif. Intell. 2023;122 doi: 10.1016/j.engappai.2023.106056. ISSN 0952-1976. DOI

Lin R., Chen J., Xie L., Su H. Accelerating reinforcement learning with case-based model-assisted experience augmentation for process control. Neural Netw. 2023;158:197–215. doi: 10.1016/j.neunet.2022.10.016. ISSN 0893-6080. PubMed DOI

Laskin M., Lee K., Stooke A., Pinto L., Abbeel P., Srinivas A. Reinforcement learning with augmented data. Proceedings of the 34th International Conference on Neural Information Processing Systems; Red Hook, NY, USA; Curran Associates Inc.; 2020.

J. Tobin, R. Fong, A. Ray, J. Schneider, W. Zaremba, P. Abbeel, Domain randomization for transferring deep neural networks from simulation to the real world, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2017), Vancouver, BC, Canada, 23–30, doi: 10.1109/IROS.2017.8202133. DOI

Rizzato M., Morizet N., Maréchal W., Geissler C. Stress testing electrical grids: generative adversarial networks for load scenario generation. Energy AI. 2022;9 doi: 10.1016/j.egyai.2022.100177. ISSN 2666-5468. DOI

Liu J., Zang H., Zhang F., Cheng L., Ding T., Wei Z., Sun G. A hybrid meteorological data simulation framework based on time-series generative adversarial network for global daily solar radiation estimation. Renew. Energy. 2023;219 doi: 10.1016/j.renene.2023.119374. ISSN 0960-1481. DOI

Xu L., Skoularidou M., Cuesta-Infante A., Veeramachaneni K. Modeling tabular data using conditional GAN. Proceedings of the 33rd International Conference on Neural Information Processing Systems; Red Hook, NY, USA; Curran Associates Inc.; 2019.

Lee Z.J., Li T., Low S.H. ACN-data: analysis and applications of an open EV charging dataset. Proceedings of the Tenth ACM International Conference on Future Energy Systems (e-Energy '19); New York, NY, USA; Association for Computing Machinery; 2019. pp. 139–149. DOI