Massive integration of renewable resources into the electric distribution systems has led to new trends in power exchanges at the interface between Transmission & Distribution systems. An accurate prediction of power exchanges at Transmission–Distribution interfaces is crucial for both the Transmission System Operators (TSOs) and the Distribution System Operators (DSOs) considering the short-term operational control and long-term planning perspectives.
In our new research published in the Electric Power System Research journal, we proposed a novel 𝗣𝗵𝘆𝘀𝗶𝗰𝘀-𝗜𝗻𝗳𝗼𝗿𝗺𝗲𝗱 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 (PIML) model 𝘁𝗼 𝗲𝗻𝗵𝗮𝗻𝗰𝗲 𝘁𝗵𝗲 𝗽𝗿𝗲𝗱𝗶𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝗽𝗼𝘄𝗲𝗿 𝗲𝘅𝗰𝗵𝗮𝗻𝗴𝗲𝘀 𝗮𝘁 𝗧𝗿𝗮𝗻𝘀𝗺𝗶𝘀𝘀𝗶𝗼𝗻–𝗗𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻 𝗶𝗻𝘁𝗲𝗿𝗳𝗮𝗰𝗲𝘀. Novelty of the proposed model lies in its combination of an Inverse Load Flow formulation, which defines an 𝗲𝗾𝘂𝗶𝘃𝗮𝗹𝗲𝗻𝘁 𝗺𝗼𝗱𝗲𝗹 𝗼𝗳 𝘁𝗵𝗲 𝗱𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻 𝗻𝗲𝘁𝘄𝗼𝗿𝗸, 𝘄𝗶𝘁𝗵 𝘁𝗵𝗲 𝗰𝗹𝗮𝘀𝘀𝗶𝗰𝗮𝗹 𝗱𝗮𝘁𝗮-𝗱𝗿𝗶𝘃𝗲𝗻 𝗿𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻 𝘁𝗲𝗰𝗵𝗻𝗶𝗾𝘂𝗲𝘀.
Simulation results conducted on a modified version of the Oberrhein MV network highlight 𝘁𝗵𝗲 𝘀𝘂𝗽𝗲𝗿𝗶𝗼𝗿𝗶𝘁𝘆 𝗼𝗳 𝘁𝗵𝗲 𝗽𝗿𝗼𝗽𝗼𝘀𝗲𝗱 𝗣𝗜𝗠𝗟 𝗮𝗽𝗽𝗿𝗼𝗮𝗰𝗵 𝗼𝘃𝗲𝗿 𝘁𝗵𝗲 𝗳𝘂𝗹𝗹 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴-𝗯𝗮𝘀𝗲𝗱 𝗺𝗲𝘁𝗵𝗼𝗱𝘀, as demonstrated by the statistical indicators.
In addition, this research adopts the TSO perspective through a 2-step Optimal Power Flow analysis that integrates power predictions and enables the calculation of production and deviation costs linked to predicted powers.
This research is authored by Arnaud Rosseel, Bashir Bakhshideh Zad, Francois Vallee and Zacharie De Grève from the Electrical Power Engineering unit of UMONS. The paper is accessible (for free over the next 50 days) at: https://www.sciencedirect.com/science/article/pii/S0378779624009829?dgcid=author