Edge AI for real-time anomaly classification in solar photovoltaic systems

dc.contributorBressan, Michael
dc.contributorGiraldo Trujillo, Luis Felipe
dc.contributorGonzález Mancera, Andrés Leonardo
dc.contributorLópez Jiménez, Jorge Alfredo
dc.creatorRobinson Luque, Christian Edward
dc.date.accessioned2023-08-11T15:15:05Z
dc.date.accessioned2023-09-07T01:19:11Z
dc.date.available2023-08-11T15:15:05Z
dc.date.available2023-09-07T01:19:11Z
dc.date.created2023-08-11T15:15:05Z
dc.date.issued2023-06-30
dc.identifierhttp://hdl.handle.net/1992/69649
dc.identifierinstname:Universidad de los Andes
dc.identifierreponame:Repositorio Institucional Séneca
dc.identifierrepourl:https://repositorio.uniandes.edu.co/
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8728262
dc.description.abstractThis study details the development and deployment of a real-time anomaly classification system on edge AI devices for solar systems. We used a neural network model, fine-tuned using the keras-tuner library, resulting in an average accuracy of 97.95%. Our optimal model demonstrated a robust performance with an accuracy of 97.84% and a small size (31.531 kB). We applied quantization as a model reduction technique, substantially decreasing the model size to 7.455 kB while maintaining similar accuracy. The reduced model was successfully implemented on various edge AI platforms, with STM32F767 Nucleo-144 proving to be the most cost-effective and energy-efficient. The study suggests further research on different solar systems and a comprehensive cost-effectiveness analysis for large-scale deployment.
dc.languageeng
dc.publisherUniversidad de los Andes
dc.publisherMaestría en Ingeniería Eléctrica
dc.publisherFacultad de Ingeniería
dc.publisherDepartamento de Ingeniería Eléctrica y Electrónica
dc.relationCollin Barker, Sam Cipkar, Tyler Lavigne, Cameron Watson, and Maher Azzouz. Real-Time Nuisance Fault Detection in Photovoltaic Generation Systems Using a Fine Tree Classifier. Sustainability, 13(4):2235, January 2021. Number: 4 Publisher: Multidisciplinary Digital Publishing Institute.
dc.relationMassimiliano De Benedetti, Fabio Leonardi, Fabrizio Messina, Corrado Santoro, and Athanasios Vasilakos. Anomaly detection and predictive maintenance for photovoltaic systems. Neurocomputing, 310:59-68, October 2018.
dc.relationJoshuva Arockia Dhanraj, Ali Mostafaeipour, Karthikeyan Velmurugan, Kuaanan Techato, Prem Kumar Chaurasiya, Jenoris Muthiya Solomon, Anitha Gopalan, and Khamphe Phoungthong. An Effective Evaluation on Fault Detection in Solar Panels. Energies, 14(22):7770, January 2021. Number: 22 Publisher: Multidisciplinary Digital Publishing Institute.
dc.relationDigikey. NUCLEO-F767ZI STMicroelectronics | Development Boards, Kits, Programmers | DigiKey.
dc.relationDigikey. NVIDIA JETSON ORIN NANO DEV KIT
dc.relationDigikey. STM32H745I-DISCO.
dc.relationGoogle. Dev Board.
dc.relationMojgan Hojabri, Samuel Kellerhals, Govinda Upadhyay, and Benjamin Bowler. IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods. Energies, 15(6):2097, Jan uary 2022. Number: 6 Publisher: Multidisciplinary Digital Publishing Institute.
dc.relationIRENA. World Energy Transitions Outlook 2022: 1.5°C Pathway. Technical report, 2022.
dc.relationIRENA. World Energy Transitions Outlook 2023: 1.5°C Pathway; Preview. Technical report, 2023.
dc.relationVaraha Satra Bharath Kurukuru, Ahteshamul Haque, Mohammed Ali Khan, Subham Sahoo, Azra Malik, and Frede Blaabjerg. A Review on Artificial Intelligence Applications for Grid-Connected Solar Pho tovoltaic Systems. Energies, 14(15):4690, January 2021. Number: 15 Publisher: Multidisciplinary Digital Publishing Institute.
dc.relationF. Mallor, Teresa Leon, Liesje De Boeck, Stefan Gulck, Michel Meulders, and Bart Meerssche. A method for detecting malfunctions in PV solar panels based on electricity production monitoring. Solar Energy, 153:51-63, September 2017.
dc.relationAndré Eugênio Lazzaretti, Clayton Hilgemberg da Costa, Marcelo Paludetto Rodrigues, Guilherme Dan Yamada, Gilberto Lexinoski, Guilherme Luiz Moritz, Elder Oroski, Rafael Eleodoro de Goes, Robson Ribeiro Linhares, Paulo Cézar Stadzisz, Júlio Shigeaki Omori, and Rodrigo Braun dos Santos. A Monitoring System for Online Fault Detection and Classification in Photovoltaic Plants. Sensors, 20(17):4688, January 2020. Number: 17 Publisher: Multidisciplinary Digital Publishing Institute.
dc.relationAdel Mellit. An embedded solution for fault detection and diagnosis of photovoltaic modules using thermographic images and deep convolutional neural networks. Engineering Applications of Artificial Intelligence, 116:105459, November 2022.
dc.relationAdel Mellit, Omar Herrak, Catalina Rus Casas, and Alessandro Massi Pavan. A Machine Learning and Internet of Things-Based Online Fault Diagnosis Method for Photovoltaic Arrays. Sustainability, 13(23):13203, January 2021. Number: 23 Publisher: Multidisciplinary Digital Publishing Institute.
dc.relationSampurna Lakshmi P, Sivagamasundari S, and Manjula Sri Rayudu. IoT based solar panel fault and maintenance detection using decision tree with light gradient boosting. Measurement: Sensors, 27:100726, June 2023.
dc.relationAli Reza Sajun, Salsabeel Shapsough, Imran Zualkernan, and Rached Dhaouadi. Edge-based individualized anomaly detection in large-scale distributed solar farms. ICT Express, 8(2):174-178, June 2022.
dc.relationJiaqi Shi, Nian Liu, Yujing Huang, and Liya Ma. An Edge Computing-oriented Net Power Forecasting for PV-assisted Charging Station: Model Complexity and Forecasting Accuracy Trade-off. Applied Energy, 310:118456, March 2022.
dc.relationH. Walker, Eric Lockhart, Jal Desai, Kristen Ardani, Geoff Klise, Olga Lavrova, Tom Tansy, Jessie Deot, Bob Fox, and Anil Pochiraju. Model of Operation-and-Maintenance Costs for Photovoltaic Systems. Technical Report NREL/TP-5C00-74840, 1659995, MainId:6662, June 2020.
dc.relationYingxin Xie, Xiangguang Chen, and Jun Zhao. Adaptive and Online Fault Detection Using RPCA Algorithm in Wireless Sensor Network Nodes. In 2012 Second International Conference on Intelligent System Design and Engineering Application, pages 1371-1374, January 2012.
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional
dc.rightshttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.titleEdge AI for real-time anomaly classification in solar photovoltaic systems
dc.typeTrabajo de grado - Maestría


Este ítem pertenece a la siguiente institución