Method of monitoring and detection of failures in PV system based on machine learning

Benavides, Darío; Arévalo-Cordero, Paul; González, L.G.; Hernández-Callejo, Luís; Aguado, José A.

doi:10.17533/udea.redin.20200694

Cited by 6 publications

(6 citation statements)

References 16 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent work by Benavides et al [12] used ML to predict the energy produced from three different photovoltaic systems and the supervision of measurement sensors. e authors investigated the energy production in response to changes in the climatic variables of the site under study.…”

Section: Related Workmentioning

confidence: 99%

Using Machine Learning for Performance Classification and Early Fault Detection in Solar Systems

Refaee

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The steady increase in the world’s population has directly influenced global climate change, resulting in catastrophic environmental consequences. This has created an immediate need for scientists from interdisciplinary domains like clean technology innovation in solar energy and computer science to join in the effort to save the world for future generations. As such, the United Nations has set a goal to ensure global access to affordable, sustainable, and clean energy. As a leading influential G20 economy, Saudi Arabia has recently established the Green Saudi initiative to align with the UN goal for enhancing the use of green energy. However, research in this area is sparse and greater effort is still required. This work is among the first to address the issue of enhancing and expanding the use of clean energy by means of studying the data collected from solar plants around Saudi. We used machine learning-based methods to assess the energy output performance of solar plants and employed the collected data to train the models to make early detection of faults. Our models achieved the highest performance at an accuracy score of 98.85% and 0.98 weighted F-score using the J48 model trained on a publicly available dataset of 874 instances collected from 26 different sites across Saudi. We anticipate that the findings of this work to serve as testbed to facilitate further research in this area and enhance the early fault detection in solar energy stations.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Machine Learning for Performance Classification and Early Fault Detection in Solar Systems

Refaee

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Each data set should not have any missing parts. When total data is stored correctly, then the data should be kept as numerical, whether production data or variables [17].…”

Section: Data Processingmentioning

confidence: 99%

“…Most of the existing techniques also have threshold values. So, the main aim is to introduce the relative performance of the various methods [16,17].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Approach on Time Series for PV-Solar Energy

Sivakumar

Neeraja²,

Rani³

et al. 2022

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

Solar energy is the kind of alternative energy that a photovoltaic (PV) system may generate. The PV system depends on the environmental conditions present at the moment, such as the humidity level, surface temperature of the PV system, and wind speed. These are the most important characteristics to consider when calculating the amount of electricity generated by the PV system. Therefore, the calculation of power production is not a simple task. In the meanwhile, we are working on developing the machine learning algorithm that will be used to estimate electricity production using the fundamental characteristics that are now accessible. Now, we begin the process of machine learning by developing a time series model since the essential parameters will change over time. We get preliminary information from four distinct locations around the country. We arrived at this conclusion by using the ANN and regression modeling approaches for best to create the most significant overall performance across all cities.

show abstract

“…In above equation (10), the class mean vector is represented as 𝑚 and fitness value is computed as in equation ( 11)…”

Section: Figure 2: Process In Opgcmmentioning

confidence: 99%

“…The significance of stuff and orientation in the modern pivoting and transport apparatus applications. In this way the computerized bearing and stuff part condition checking strategies got the significance in the field of examination [10]. In these new years, public power enterprises of different nations from Asia, Europe and others are showing a great deal of interest in the difference in current power matrix framework to new time of cutting edge smart correspondence framework.…”

Section: Introductionmentioning

confidence: 99%

Smart Grid Sensor Monitoring Based on Deep Learning Technique with Control System Management in Fault Detection

Awasthi¹,

Mahesh²,

Joshi³

et al. 2022

Int. j. commun. netw. inf. secur.

View full text Add to dashboard Cite

The smart grid environment comprises of the sensor for monitoring the environment for effective power supply, utilization and establishment of communication. However, the management of smart grid in the monitoring environment isa difficult process due to diversifieduser request in the sensor monitoring with the grid-connected devices. Presently, context-awaremonitoring incorporates effective management of data management and provision of services in two-way processing and computing. In a heterogeneous environment context-aware, smart grid exhibits significant performance characteristics with the grid-connected communication environment for effective data processing for sustainability and stability. Fault diagnoses in the automated system are formulated to diagnose the fault separately. This paper developed anoptimized power grid control model (OPGCM) model for fault detection in the control system model for grid-connected smart home appliances. OPGCM model uses the context-aware power-awarescheme for load management in grid-connected smart homes. Through the adaptive smart grid model,power-aware management is incorporated with the evolutionary programming model for context-awareness user communication. The OPGCM modelperforms fault diagnosis in the grid-connected control system initially, Fault diagnosis system comprises of a sequential process with the extraction of the statistical features to acquirea sustainable dataset with effective signal processing. Secondly, the features are extracted based on the sequential process for the acquired dataset with a reduction of dimensionality. Finally, the classification is performed with the deep learning model to predict or identify the fault pattern. With the OPGCM model, features are optimized with the whale optimization model to acquire features to perform fault diagnosis and classification. Simulation analysis expressed that the proposed OPGCM model exhibits ~16% improved classification accuracy compared with the ANN and HMM model.

show abstract

Method of monitoring and detection of failures in PV system based on machine learning

Cited by 6 publications

References 16 publications

Using Machine Learning for Performance Classification and Early Fault Detection in Solar Systems

Using Machine Learning for Performance Classification and Early Fault Detection in Solar Systems

Machine Learning Approach on Time Series for PV-Solar Energy

Smart Grid Sensor Monitoring Based on Deep Learning Technique with Control System Management in Fault Detection

Contact Info

Product

Resources

About