Photovoltaic energy generation systems monitoring and performance optimization using wireless sensors network and metaheuristics

The performance of photovoltaic energy generation systems is highly affected by exposure to different operating conditions. In order to optimize the power conversion efficiency in such conditions, the deviation from normal operation has to be detected. In this paper, an Adaptive Network Fuzzy Inference System (ANFIS) based model of the normal operation of the photovoltaic system is constructed and used as a reference for abnormal operation detection, where the training data of the ANFIS-based model has been acquired using a Wireless Sensor Network. The monitoring of the photovoltaic system uses the residual generated from the comparison between its actual state of operation and the output of the ANFIS model for the same operating conditions. As an optimal strategy that takes into account the different operating modes, a switching mechanism is designed to execute a con-ventional maximum power extraction technique in normal operating conditions and switches to a metaheuristic algorithm to search for global maximum power point when deviation from the normal operation is detected. Experimental results show the higher efficiency of the photovoltaic energy conversion system using the proposed monitoring and performance optimization approach in various environmental conditions.

Automated summary

This paper proposes a monitoring and performance optimization approach for photovoltaic energy conversion systems. An Adaptive Network Fuzzy Inference System (ANFIS) based model is used to detect abnormal operation by comparing the residual between the actual state and the output of the ANFIS model. A switching mechanism is designed to switch between maximum power extraction technique and metaheuristic algorithm based on the operation mode. Experimental results show that the proposed approach improves the efficiency of the photovoltaic energy conversion system in different environmental conditions.