Journal
COMPLEX ADAPTIVE SYSTEMS 2012
Volume 12, Issue -, Pages 332-337Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.procs.2012.09.080
Keywords
Artificial intelligence; renewable energy; solar photovoltaic power forecasting; wavelet transform
Ask authors/readers for more resources
With increased penetration of solar as a variable energy resource (VER), solar photovoltaic (PV) power production is rapidly increasing into large-scale power industries. Since power output of PV systems depends critically on the weather, unexpected variations of their power output may increase the operating costs of the power system. Moreover, a major barrier in integrating this VER into the grid is its unpredictability, since steady output cannot be guaranteed at any particular time. This biases power utilities against using PV power since the planning and overall balancing of the grid becomes very challenging. Developing a reliable algorithm that can minimize the errors associated with forecasting the near future PV power generation is extremely beneficial for efficiently integrating VER into the grid. PV power forecasting can play a key role in tackling these challenges. This paper presents one-hour-ahead power output forecasting of a PV system using a combination of wavelet transform (WT) and artificial intelligence (AI) techniques by incorporating the interactions of PV system with solar radiation and temperature data. In the proposed method, the WT is applied to have a significant impact on ill-behaved PV power time-series data, and AI techniques capture the nonlinear PV fluctuation in a better way.
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