A distributed data‐driven modelling framework for power flow estimation in power distribution systems. Issue 3 (10th August 2021)

• Record Type: Journal Article
• Authors: Dharmawardena, Hasala; Venayagamoorthy, Ganesh K.
• Other Names: Jiang Tao guestEditor.; Bai Linquan guestEditor.; Mu Yunfei guestEditor.; Venayagamoorthy Kumar guestEditor.; Zhang Yingchen guestEditor.; Teng Fei guestEditor.; Chen Peiyuan guestEditor.; Zhong Haiwang guestEditor.; Yao Wei guestEditor.; Wan Can guestEditor.
• Is Part Of: IET energy systems integration. Volume 3:Issue 3(2021)
• Page Start: 367
• Page End: 379
• Publication Date: 2021-08-10
• Subjects: distributed power generation -- distribution networks -- load flow -- power system simulation -- power distribution control -- smart power grids; Power resources -- Periodicals; Energy conservation -- Periodicals; Power resources; Energy conservation; Periodicals; 333.79
• DOI: 10.1049/esi2.12035
• Languages: English
• ISSNs: 2516-8401

Abstract

Abstract: The power distribution system has increasing importance and complexity as a result of the exponential growth in the adoption of smart grid technologies. The ability to model the power distribution system is critical to ensure a smooth transition to a sustainable power system. This study presents a distributed data‐driven framework based on Cellular Computational Networks (CCN) for power distribution system modelling where the CCN framework facilitates for system decomposition. The learning in CCN is distributed and asynchronous, thus adaptive models can be developed. The computational engine of the CCN cells is based on data‐driven, physics‐driven, or a hybrid approach. The CCN‐based distribution system modelling secures the privacy and security of the sensitive utility information, thus allowing third‐party application providers access to system models and behaviours. The application of a CCN‐based power flow model is illustrated on a modified IEEE 34 test system. Typical results show the suitability of the new approach in modelling the sample distribution system, as well as its enhanced performance when compared with the centralised modelling approach.