Journal
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
Volume 11, Issue 2, Pages 703-712Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSTE.2019.2903900
Keywords
Wind forecasting; Hidden Markov models; Predictive models; Wind power generation; Indexes; Correlation; Higher-order multivariate Markov chain; photovoltaic power forecast; power generation uncertainty; power system management and control; wind power forecast
Ask authors/readers for more resources
Due to their intermittency and unpredictability, increasing the penetration level of renewable energy (RE) resources to the power system leads to difficulties in operation. Reliable system operation requires a precise forecast of generated power by RE units. Photovoltaic (PV) and wind units are the significant portion of RE resources integrated into the power system. This paper proposes a forecast method for PV and wind generated power to achieve good prediction accuracy in different weather conditions. Not only is the relation between the wind and PV output power modeled, but the heat index (HI) is also taken into consideration as a useful meteorological variable to achieve the 15-min ahead precise expectation of PV/wind output power. Moreover, the input data are discretized in such a way that the best accuracy for the PV and wind power forecast is achieved. Comparing the results of the proposed method with the historical data recorded at actual PV and wind plants shows that the proposed forecast method results in high accuracy in PV and wind output power forecast. Moreover, the forecast model performance with HI consideration is compared with the model not using HI as an input variable.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available