Solar PV (photovoltaic) technology has advanced greatly in recent years due to advantages such as renewability, environmental friendliness, simple maintenance, and dependability. Nevertheless, a number of PV faults may appear and result in degradation, a decrease in output power, or even a storm surge at different levels, depending on the outside working conditions and regular weather changes that might cause harm to the production, dist. Solar PV (photovoltaic) technology has advanced greatly in recent years due to advantages such as renewability, environmental friendliness, simple maintenance, and dependability. Nevertheless, a number of PV faults may appear and result in degradation, a decrease in output power, or even a storm surge at different levels, depending on the outside working conditions and regular weather changes that might cause harm to the production, distribution, or setup, it is critical to monitor PVSs (PV systems) for their power generation efficiencies. IoT (Internet of Things) are evolving technologies that have been studied for enhanced fault detection and predictive analysis in the maintenance and environmental monitoring of solar power plants. This research work suggests a method based on MLTs (machine learning techniques) to analyze power data and predict faults for the maintenance of solar power plants. Input data from solar power plants consist of plant power generation and weather data which are first pre-processed and then trained using the suggested DT-LGB (Decision Trees with Light Gradient Boosting) algorithm to predict errors. The trained model was able to identify major/minor faults or anomalies present in input data. Conventionally these identifications require more effort in detection and maintenance. The results of this work showed that the suggested model obtained 8.74 MSEs ((Mean Square Errors), 2.96 RMSEs (Root Mean Square Errors), and R2 values of 0.9939 which is 12.8%, 6.8%, and 11.08% i. Solar photovoltaicInternet of thingsFault predictionDecision treesSolar PV technology has evolved significantly in recent decades as an important source of renewable energy, mainly due to benefits like efficient energy generation, environment friendliness, ease of maintenance, and reliability. However, according to the outdoor working circumstances and periodic fluctuations in climatic conditions the possible damages associated with production, distribution, or setting up, numerous PV defects may emerge resulting in various levels of deterioration, reductions in output powers, or even storm surges. To overcome these issues, it is imperative to monitor the power generations of PVSs [1,2]. Most conventional methods incorporate manual examinations and remotely connected tracking and have several limitations including time consumption and complexity. IoTs have emerged as forefront technologies for examining the maintenance of PVSs and environmental monitoring with respect to demands in solar power plants for improved fault diagnostics and predictive analyses [3,4]. The IoT facilitates communication and information sharing across a wide range of devices, systems, and services. Various studies have revealed that using IoT in the monitoring PVSs has several advantages, including better accuracy and efficiency, reduced human involvement, and hence lower costs. Furthermore, incorporating MLTs aids in large data points for electrical measurements, environmental data, or PV panel imaging [2,5].Solar Photovoltaic plants are being erected in large numbers across the globe at the moment, and these plants must be properly maintained and monitored on a continuous basis in order to remain safe and to sustain for longer periods. There are many different kinds of faults and failures that may occur in solar plants, and existing fault detection technologies are mostly utilized to protect and guard against certain problems like line-line, line-ground, arc and ground errors. Despite the existence of high universal standards (such as the IEC, NEC, and UL), undetected flaws endure to cause major difficulties in solar power plants. There are several fault detection methods for the solar power plants accessible in the literature, each with a distinct level of accuracy, network provided, and algorithm intricacy. Estimations faults in PVSs have been based on environment, climatic and satellite data. Moreover, few detection methods do not require any climatic data. An alternative strategy used is Electro Luminescence Images. Solar panels receive external excited currents through metal connections which act as light emitting diodes. The photons emitted by this strategy which near wavelengths beyond 850 nm can be imaged using capable Si-CCDs cameras.In recent times, smart systems combining AIs and the IOTs have been developed for monitoring, diagnostics and fault detections of PV solar power p. This work's suggested model analyzes outputs of solar power plants and predict faults and maintenance requirements in these plants. The input power data was used to detect faults in panels and thereby train the model based on MLTs to predict future incident occurrences. Fig. 1 shows this work's proposed model. Inputs are first pre-processed and fed.
