In recent years, aerial infrared thermography (aIRT), as a cost-efficient inspection method, has been demonstrated to be a reliable technique for failure detection in photovoltaic (PV) systems. This method aims to quickly perform a comprehensive monitoring of PV power plants, from the commissioning phase through its entire operational lifetime. This paper provides a review of reported methods in the literature for automating different tasks of the aIRT framework for PV system inspection. The related studies were reviewed for digital image processing (DIP), classification and deep learning techniques. Most of these studies were focused on autonomous fault detection and classification of PV plants using visual, IRT and aIRT images with accuracies up to 90%. On the other hand, only a few studies explored the automation of other parts of the procedure of aIRT, such as the optimal path planning, the orthomosaicking of the acquired images and the detection of soiling over the modules. Algorithms for the detection and segmentation of PV modules achieved a maximum F1 score (harmonic mean of precision and recall) of 98.4%. The accuracy, robustness and generalization of the developed algorithms are still the main issues of these studies, especially when dealing with more classes of faults and the inspection of large-scale PV plants. Therefore, the autonomous procedure and classification task must still be explored to enhance the performance and applicability of the aIRT method.

This study presents a comprehensive multidisciplinary review of autonomous monitoring and analysis of large‐scale photovoltaic (PV) power plants using enabling technologies, namely artificial intelligence (AI), machine learning (ML), deep learning (DL), internet of things (IoT), unmanned aerial vehicle (UAV), and big data analytics (BDA), aiming to automate the entire condition monitoring procedures of PV systems. Autonomous monitoring and analysis is a novel concept for integrating various techniques, devices, systems, and platforms to further enhance the accuracy of PV monitoring, thereby improving the performance, reliability, and service life of PV systems. This review article covers current trends, recent research paths and developments, and future perspectives of autonomous monitoring and analysis for PV power plants. Additionally, this study identifies the main barriers and research routes for the autonomous and smart condition monitoring of PV systems, to address the current and future challenges of enabling the PV terawatt (TW) transition. The holistic review of the literature shows that the field of autonomous monitoring and analysis of PV plants is rapidly growing and is capable to significantly improve the efficiency and reliability of PV systems. It can also have significant benefits for PV plant operators and maintenance staff, such as reducing the downtime and the need for human operators in maintenance tasks, as well as increasing the generated energy.

Aerial Infrared Thermography (aIRT) is a nondestructive and cost-effective method for detecting faults in largescale PV plants. In this paper, a 1 MW multi-crystalline PV plantblock that was hit by a meteorological tsunami in Brazil in 2016, is inspected systematically using the aIRT method. The main objective was to validate this inspection technique for commercial application. Various failures like hotspots, bypassed substrings, short-circuited and disconnected PV strings were detected at the PV plant using aIRT inspection in less than one hour. The results have proven that this semi-autonomous method is very fast, reliable and effective for large scale PV plants.

In this paper, an innovative approach is represented in order to optimize the path planning during UAV flight in the monitoring of PV power plants. For this purpose, two algorithms are developed as static path planning and dynamic path planning. In static path planning, an optimum initial path is generated with image processing techniques. Subsequently, the waypoints are transmitted to UAV through the Radio Frequency (RF) channels for further actions. Dynamic path planning checks UAV's abilities after any specific maneuver. If UAV cannot complete the initial path, dynamic path planning enters in the loop to create a new optimum path according to UAV's position and endurance.

This article uses electroluminescence (EL) alongside Unmanned Aerial Vehicles (UAV) in photovoltaic (PV) power plants in order to detect faults quickly, efficiently and at the lowest possible cost. Different failures were analyzed using a low-cost aerial electroluminescence (aEL) alternative setup. To validate the equipment and the technique, an experiment was performed at night with an infrared thermographic (IRT) camera and both a high-quality and low-cost EL camera. It was shown that the same faults could be observed with both EL cameras, but not necessarily with the IRT method. The low-cost aerial EL camera presented a good fault detecting efficiency.