TY  - JOUR
T1  - Energy Forecasting for Grid Connected Solar PV System Based on Weather
Classification
AU - Kumar Sahoo, Ashwin 
JO  - Asian Journal of Information Technology
VL  - 15
IS  - 23
SP  - 4861
EP  - 4874
PY  - 2016
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2016.4861.4874
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2016.4861.4874
KW  - solar PV forecasting
KW  -Roof top grid connected PV system
KW  -weather classification
KW  -artificial neural network
KW  -back propagation algorithm
KW  -weather classification
AB  - In recent years focus has been on environmental pollution issue resulting from consumption of fossil
fuels, e.g., coal and oil. Thus introduction of an alternative energy source such as solar Photo Voltaic (PV)
energy is gaining momentum. Short-term photovoltaic power generation forecasting is an important task in
renewable energy power system planning and operation. Based on seasonal weather classification, the Back
Propagation (BP) Artificial Neural Network (ANN) approach is utilized to forecast the next 24 h PV power
outputs, using weather database which include global irradiance, temperature, wind speed and humidity data
of Chennai city (South-East coast of India) using a data acquisition system. The estimated results of the
proposed PV power forecasting model coincide well with measurement data for a 10 kW roof top grid connected
PV system. The future DC and AC power outputs are predicted for any given day. The proposed approach
achieves better prediction accuracy for hot and humid climatic region.
ER  -