Genetic algorithm based tuning of sliding mode controllers for a boost converter of PV system using internet of things environment

Abstract

This paper proposes a novel controller optimization of boost converter by tunning two controllers of voltage and current in PV (Photovoltaic) boost converters: Sliding Mode Control (SMC) or Sliding Mode plus Proportional-Integrative. Genetic Algorithm (GA) optimization is applied in a Internet of Things (IoT) context, in which the server side consists of running the GA and thereafter used to tune the SMC and SMPIC of the PV plant boost converter. Communication between the IoT (PV plant) and cloud server comprises to the acquired currents and voltages from PV to the server and controllers parameters from server to IoT. Data from the IoT is applied to calculate the fitness function for a given solution, which learns the solar plant (machine learning). Experimental results using hardware are considered, in order to evaluate the performance, and results are compared between heuristic and deterministic parameters from SMC or SMPIC, proving the reduction of overshoot and settling time.

Keywords

• Photovoltaic
• Boost converter
• Maximum power point tracking
• Genetic algorithm
• Sliding mode control