Error Analysis of ON-OFF and ANN Controllers Based on Evapotranspiration

Abstract

This paper presents error analysis of ON-OFF controller as well as ANN controller which is applied to an automated irrigation system. Controlling irrigation system was conducted  based on revised Penman-Monteith evapotranspiration and compared to a reference of soil moisture. Input parameters of the evapotranspiration included temperature, heat radiation, atmosphere pressure and wind speed. The output data of evapotranspiration was then used as input variable of ON-OFF controller as well as ANN controller. The performance of such controllers were evaluated and compared based on error of both controllers. The simulation results show that the error of the ON-OFF controller can be adjusted by setting the sampling time of the dead zone discretization. Error of ON-OFF controller with sampling time of 0.05 second is equal to error of ANN controller, that is 14.3% of reference signal amplitude.