Data-driven stochastic planning for network constrained energy sharing in microgrids

Zhang, Xihai, Zhou, Yue ORCID: https://orcid.org/0000-0002-6698-4714, Ge, Shaoyun, Liu, Hong and Yang, Baijie 2024. Data-driven stochastic planning for network constrained energy sharing in microgrids. Presented at: 2024 IEEE Power & Energy Society General Meeting, Seattle, WA, USA, 21-25 July 2024. 2024 IEEE Power & Energy Society General Meeting (PESGM). IEEE, pp. 1-5. 10.1109/pesgm51994.2024.10688976

Full text not available from this repository.

Abstract

Energy sharing within microgrids offers significant financial benefits to prosumers. However, the operational challenges arising from physical network constraints and the inherent randomness of photovoltaic (PV) generation pose significant difficulties. This paper proposes a data-driven stochastic planning approach for network-constrained energy sharing. Initially, the prosumer utility model explicitly incorporates physical network constraints, while Bayesian neural networks are employed to estimate the probabilistic distribution of PV generation. Subsequently, the application of definite integrals enables the reformulation of infinite-dimensional uncertainty optimization into a deterministic problem. Last but not least, a distributed primal-dual gradient method is introduced to manage the proposed energy-sharing scheme. Numerical results highlight the superior performance of the proposed approach in handling the stochastic nature of PV generation, surpassing deterministic optimization, robust optimization, and sample average approximation-based (SAA) stochastic planning techniques. Furthermore, the proposed method exhibits enhanced sample efficiency compared with the existing SAA-based approach.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Engineering
Publisher:	IEEE
ISBN:	979-8-3503-8183-2
Last Modified:	21 Oct 2024 15:40
URI:	https://orca.cardiff.ac.uk/id/eprint/173223

Actions (repository staff only)

Edit Item