Validation of Genetic Algorithm Optimized Hidden Markov Model for Short-term Photovoltaic Power Prediction

Abstract

A substantial amount of renewable energy (RE)-based electrical power is generated over the last ten years due to global warming issues. Solar photovoltaic (PV) is being incredibly utilized because of its boundless quality. However, the inherent intermittency of PV power production at high penetration level to the grid leads to complications related grid reliability, stability and transportable unit of electric power. A viable approach to addressing this problem is to develop a reliable power forecast model for the short-term horizon related to scheduling and transmission. Based on an existing forecast model built on genetic algorithm (GA)-optimized hidden Markov model (HMM), this paper implements the model validation process using more recent input dataset. Model evaluation is based on the computation of normalized root mean square error (nRMSE). As the validation result, HMM+GA is sufficient to accurately forecast PV Po under clear sky day (CSD) condition. Contrariwise, for cloudy days (CDs) presenting instantaneous changes in solar irradiance (Gs) between some hours of the day, HMM+GA adapted with a correction factor (ξ); articulated as HMM+GA+ξ; is adequate to forecast the Po more precisely when the average change in the absolute value of (Formula presented) in the morning (Formula presented) is greater than 128% and/or when (Formula presented) in the evening (Formula presented) exceeds 90%. Particularly, the average nRMSE of 2.63% showed that HMM+GA with or without ξ are suitable techniques for forecasting PV Po on an hourly basis. Therefore, the validation results are in harmony with those of the baseline models.