Table 4 Comparison of the proposed algorithm with other related researches.

Proposed RNA algorithm

Max \(P_{out} = 247.4\) W, a fast rise time of 0.052 s, \(\eta =98.9\%\)

Proposed RNA algorithm under PSC-pattern A

Max \(P_{out} = 167\) W, a rise time of 0.07 s, \(\eta =98.06\%\)

Proposed RNA algorithm under PSC-pattern B

Max \(P_{out} = 129.7~W\), a rise time of 0.09 s, \(\eta =98.48\%\)

MPPT of PV under partail shaded through a colony of fireflies¹²

\(\eta = 99\%\), with a tracking speed of 2.1 s under PSC

Comparison between neural network and P &O method for PV cell¹⁹

Pin=196 W for G = 1000 W/m\(^2\), and 200 W PV, \(\eta =98\%\) with fast tracking time

Neural network approach to MPPT control and irradiance estimation²⁶

Track MPP with an error of 0.001% with a faster convergence speed

ANFIS current voltage controlled MPPT algorithm²⁷

Pin = 247 W for G = 1000 W/m\(^2\), \(\eta =98.8\%\), Rise time of 0.3 s

SAR Algorithm method in PV system using MPPT²⁸

The proposed raised the MPP efficiency from 61.7 to 80.85% with less energy loss