Effect of Daily Forecasting Frequency on Rolling-Horizon-Based EMS Reducing Electrical Demand Uncertainty in Microgrids

Accurate forecasting is a crucial task for energy management systems (EMSs) used in microgrids. Despite models destined to EMSs having been largely investigated, the analysis of criteria practical execution this task, framework an algorithm, has not properly investigated yet. On such basis, paper aims at exploring effect daily frequency on performance rolling-horizon devised reduce demand uncertainty microgrids by adhering reference planned profile. Specifically, sample EMS, where committed nonlinear autoregressive network with exogenous inputs (NARX) artificial neural (ANN), studied under different frequencies, revealing representative trend relating EMS and reduction electrical demand. basis trend, it possible establish how often convenient repeat obtaining increasing EMS. The obtained results have generalized extending test scenarios, whose found coherent identified trend.