Solar Photovoltaic Array's Shadow Evaluation Using Neural Network with On-Site Measurement

Dzung D. Nguyen, Brad Lehman, Sagar Kamarthi
2007 2007 IEEE Canada Electrical Power Conference  
This paper proposes a method to accurately predict the to installation in order to effectively determine whether the maximum output power of the solar photovoltaic arrays under the system is sufficiently cost efficient enough to install [2]. shadow conditions by using neural network, a combined method using In order to include the effects of shadowing on solar PV the multilayer perceptrons feed forward network and the back-. a propagation algorithm. Using the solar irradiation levels, the
more » ... t arrays, conventional methods use an approach to determie temperature and the sun's position angles as the input signals, and the the "shading factor," which is defined as the ratio of the nonmaximum output power of the solar photovoltaic array as an output shaded area to the total area ofthe solar arrays. signal, the training data for the neural network is received by In real operating conditions, solar PV arrays are connected measurement on a particular time, when solar panel is shaded. After training, the neural network model's accuracy and generalization are with Maximum Power Point Trackers to track maximum verified by the test data. This model, which is called the shading function, output power. The maximum output (MPP) power is often is able to predict the shadow effects on the solar PV arrays for long term assumed linearly proportional to solar irradiance. So shading with low computational efforts. factors also can be used to calculate MPP power of shaded
doi:10.1109/epc.2007.4520304 fatcat:jloadt3rxrhazjhu5zrplor2ti