PROJECT TITLE :

A Data-Driven Load Fluctuation Model for Multi-Region Power Systems

ABSTRACT:

For studies such as power system generation control studies and probabilistic load flows, we present in this work a data-driven load fluctuation model based on high-resolution historical demand data from multi-regional systems. Independent Gaussian random variables are used to describe load changes, but unlike previous research that assumed the standard deviation and base demand in each region were known a priori, we do not. According to our framework for short-term demand uncertainty and base demand, we can determine the link between these variables. Real-time demand data from the New York and New Zealand power systems was used to test the created framework. Proposed models outperform those that have been employed in prior studies. Using the sample scenarios, the parameters of similar multi-region systems can be derived from the included coefficients.