Real Time Machine Learning Based Voltage Regulation Model for Smart Agriculture

Abstract

The problem of voltage regulation in smart agriculture unit is well studied. There exists number of approaches to support voltage regulation in agriculture sector. However, the methods consider only the number of motors share the voltage as the key in regulating the artificial voltage to the agriculture unit. The methods suffer to achieve higher performance in smart agriculture. To solve this issue, an efficient Machine Learning Based Voltage Regulation Model (MLVRM) is presented in this paper. The method maintains the agriculture trace and uses them to compute mean voltage utilization (MVU) at various duty cycles. With the information like no of smart motors connected, average voltage utilization of motors, and other features, the method computes MVU value. The method trains the neural network with the features extracted. The network is designed with number of intermediate layers where each layer neuron computes the value of MVU according to the features available. The output layer neurons produces number of MVU value. Based on the MVU values obtained, the method computes Optimal Regulation Voltage (ORV) for the current input voltage according to the required voltage for the smart motor connected. The proposed model improves the performance of voltage regulation and smart agriculture.