The focus on renewable energy sources is increasing tremendously,
which motivates studies concerning the integration of
renewable sources like wind and solar into existing energy systems.
When the conventional sources are used for power generation, the
generation is predominantly controlled by the machine ratings and
generation capacity of the plant. Hence, there is a lesser need for
short term generation forecasting. But in case of power generation
from renewable energy sources, the generation is uncertain because
the weather is erratic and the generation depends heavily on
weather conditions. Thus there is a dire need to build forecast
models for the generation in order to have better generation
scheduling. Therefore with greater penetration of renewable sources
in power generation, the focus is shifting towards generation
forecasting [1e3]. Considering the advantages of solar energy as a
sustainable energy, power prediction for photovoltaic installations
is a decisive factor. Thus, development and research on solar power
has been rising year by year. The predictions are used to optimize
usage of the solar energy and provide reasonably accurate knowledge
of the solar resource availability at any location [4].