☆ 3.8 Article

Anomaly Detection in Renewable Energy Big Data Using Deep Learning

International Journal of Intelligent Information Technologies (2023)

Related references

Note: Only part of the references are listed.

Article Energy & Fuels

Evaluation of Machine Learning Algorithms for Supervised Anomaly Detection and Comparison between Static and Dynamic Thresholds in Photovoltaic Systems

Thitiphat Klinsuwan et al.

Summary: The use of photovoltaic systems has been on the rise due to cost reduction and improved performance. However, these systems are prone to faults that can decrease efficiency and energy output. To mitigate these issues, preventive or predictive maintenance and effective monitoring are crucial. This paper proposes a new framework that utilizes machine learning algorithms to predict energy production and detect anomalies in photovoltaic plants by comparing predicted and measured power values.

ENERGIES (2023)

Add to Collection

Article Automation & Control Systems

A Scalable Framework for Annotating Photovoltaic Cell Defects in Electroluminescence Images

Urtzi Otamendi et al.

Summary: This article proposes a method that combines state-of-the-art data-driven techniques to address the lack of anomaly segmentation annotations in the literature and introduces a golden standard benchmark. The proposed method stands out for its adaptability to new PV cell types, cost-efficient fine-tuning, and leveraging public datasets to generate advanced annotations. The methodology has been validated in the annotation of a widely used dataset, achieving a 60% reduction in annotation cost.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2023)

Add to Collection

Proceedings Paper Green & Sustainable Science & Technology

State-of-the-Art Deep Learning Anomaly Detection Method for Analyzing Electroluminescence Images of Solar Cells

Roya Rahimzadeh et al.

Summary: In response to the rapid growth of the solar energy industry, updating and automating quality control and defect detection processes is essential. This study applied PatchCore, a state-of-the-art deep learning method, to detect anomalies in electroluminescence images of solar cells. Experimental results showed that PatchCore achieved an AUROC score of 0.97 for detecting anomalies in a dataset of polycrystalline EL images, indicating its high performance as an anomaly detection method in EL image inspection processes.

SILICONPV 2022, THE 12TH INTERNATIONAL CONFERENCE ON CRYSTALLINE SILICON PHOTOVOLTAICS (2023)

Add to Collection

Article Energy & Fuels

Machine Learning Schemes for Anomaly Detection in Solar Power Plants

Mariam Ibrahim et al.

Summary: This paper evaluates the performance of different machine learning schemes and applies them to detect anomalies on photovoltaic components, providing models to identify healthy and abnormal behaviors in photovoltaic systems and offering clear insights for solving complex anomaly detection problems.

ENERGIES (2022)

Add to Collection

Article Energy & Fuels

Automated defect identification in electroluminescence images of solar modules*

Xin Chen et al.

Summary: We developed a rapid automatic computer vision pipeline to analyze defects in solar photovoltaic (PV) modules and achieved defect identification using machine learning models. Our methods performed well on real-world validation and testing sets and were applied to analyze the spatial distribution of defects on solar cells in a field survey.

SOLAR ENERGY (2022)

Add to Collection

Article Energy & Fuels

Towards efficient and effective renewable energy prediction via deep learning

Zulfiqar Ahmad Khan et al.

Summary: Accurate prediction of renewable energy is crucial for the integration into smart grids. This study proposes a lightweight ESNCNN model that combines ESN and CNN layers to improve prediction accuracy, achieving state-of-the-art performance on renewable energy and electricity consumption datasets.

ENERGY REPORTS (2022)

Add to Collection

Article Energy & Fuels

Towards efficient and effective renewable energy prediction via deep learning

Zulfiqar Ahmad Khan et al.

Summary: The article introduces a lightweight ESNCNN model developed to accurately predict renewable energy production, addressing the challenge of integrating renewable energy into smart grids due to its randomness, intermittency, and volatility. The ESNCNN model combines ESN for learning nonlinear mapping relationships and CNN for extracting spatial information from renewable energy data, achieving state-of-the-art performance in experiments.

ENERGY REPORTS (2022)

Add to Collection

Article Physics, Multidisciplinary

Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection

Kamil Faber et al.

Summary: The research introduces a framework that utilizes neuroevolution methods to enhance anomaly detection models' accuracy. By combining multiple models, each model operating on a subset of data sensors. Neuroevolution aims to optimize model architecture and hyperparameters to improve the anomaly detection performance of deep learning models.

ENTROPY (2021)

Add to Collection

Review Green & Sustainable Science & Technology

Potential measurement techniques for photovoltaic module failure diagnosis: A review

Md Momtazur Rahman et al.

Summary: Various characterization methods are used to detect defects in photovoltaic modules, but the results can vary depending on the measuring apparatus and data acquisition system, leading to uncertainties. Identifying and quantifying degraded solar panels promptly can prevent costly module failures. This paper discusses the challenges of solar panel defect detection techniques and reviews conventional and emerging technologies for accurately identifying degradation sources and extending the useful lifetime of PV modules.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Add to Collection

Review Energy & Fuels

Artificial intelligence based anomaly detection of energy consumption in buildings: A review, current trends and new perspectives

Yassine Himeur et al.

Summary: This paper provides a comprehensive review of existing anomaly detection frameworks for building energy consumption based on artificial intelligence, introducing a comprehensive taxonomy and discussing unresolved challenges and future research directions.

APPLIED ENERGY (2021)

Add to Collection

Article Green & Sustainable Science & Technology

Anomaly Detection with Machine Learning Algorithms and Big Data in Electricity Consumption

Simona-Vasilica Oprea et al.

Summary: This paper analyzes a large dataset of readings from smart meters in a trial study in Ireland using a hybrid approach. An unsupervised ML technique is applied to detect anomalies in the time series, establish a threshold, and label the time series as suspicious or not. By training the model, the capability of detecting suspicious consumers is achieved with an accuracy of 90%, precision score of 0.875, and F1 score of 0.894.

SUSTAINABILITY (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Solar Radiation Prediction Using Different Machine Learning Algorithms and Implications for Extreme Climate Events

Liexing Huang et al.

Summary: Solar radiation plays a crucial role in Earth's climate systems and ecosystems, making accurate prediction of it essential for the solar industry and climate research. Machine learning models can effectively predict solar radiation, with meteorological factors being key factors influencing model predictions.

FRONTIERS IN EARTH SCIENCE (2021)

Add to Collection

Article Chemistry, Analytical

Anomaly Detection and Automatic Labeling for Solar Cell Quality Inspection Based on Generative Adversarial Network

Julen Balzategui et al.

Summary: This work presents a methodology for developing a robust inspection system in the context of solar cell manufacturing, utilizing anomaly detection and Fully Convolutional Network to achieve defect detection and classification without manual labeling. The results show that automatic annotations generated from anomaly detection can serve as labels for training supervised models, resulting in comparable segmentation and classification performance to models trained with manual labels.

SENSORS (2021)

Add to Collection

Article Computer Science, Information Systems

Deep Learning Enhanced Solar Energy Forecasting with AI-Driven IoT

Hangxia Zhou et al.

Summary: A new method using deep learning techniques to solve the PV energy generation forecasting problem is proposed in this study, which combines clustering techniques, convolutional neural network (CNN), long short-term memory (LSTM) neural network, and attention mechanism. Experimental results show significantly higher prediction accuracy rates compared to existing methods.

WIRELESS COMMUNICATIONS & MOBILE COMPUTING (2021)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic

Anomaly Detection in Electricity Consumption Data using Deep Learning

Mohammad Kardi et al.

Summary: This paper presents a novel deep learning based approach to detect anomalies in electricity consumption data one hour ahead of time. The method consists of two stages, utilizing Long Short-Term Memory (LSTM) and LSTM autoencoder. The results demonstrate a significant increase in electricity consumption during anomalous periods, with the temporal and lag features improving the efficiency of the proposed method.

2021 21ST IEEE INTERNATIONAL CONFERENCE ON ENVIRONMENT AND ELECTRICAL ENGINEERING AND 2021 5TH IEEE INDUSTRIAL AND COMMERCIAL POWER SYSTEMS EUROPE (EEEIC/I&CPS EUROPE) (2021)

Add to Collection

Article Multidisciplinary Sciences

Designing a long short-term network for short-term forecasting of global horizontal irradiance

Sourav Malakar et al.

Summary: LSTM models based on specialized deep neural network-based architecture have become important in time series forecasting, but without clear design guidelines affecting performance. This study focuses on short-term forecasting of global horizontal irradiance, highlighting the importance of temporal order of data, LSTM model statefulness, and input data variability on forecasting accuracy.

SN APPLIED SCIENCES (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks

Jecinta Mulongo et al.

APPLIED ARTIFICIAL INTELLIGENCE (2020)

Add to Collection

Article Energy & Fuels

Tailored Algorithms for Anomaly Detection in Photovoltaic Systems

Pedro Branco et al.

ENERGIES (2020)

Add to Collection

Review Thermodynamics

Renewable energy resources and workforce case study Saudi Arabia: review and recommendations

E. M. Barhoumi et al.

JOURNAL OF THERMAL ANALYSIS AND CALORIMETRY (2020)

Add to Collection

Article Energy & Fuels

Deep learning based automatic defect identification of photovoltaic module using electroluminescence images

Wuqin Tang et al.

SOLAR ENERGY (2020)

Add to Collection

Article Automation & Control Systems

Electromagnetic Induction Heating and Image Fusion of Silicon Photovoltaic Cell Electrothermography and Electroluminescence

Ruizhen Yang et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2020)

Add to Collection

Proceedings Paper Energy & Fuels

Evaluation of unsupervised anomaly detection approaches on photovoltaic monitoring data

Sebastian Hempelmann et al.

2020 47TH IEEE PHOTOVOLTAIC SPECIALISTS CONFERENCE (PVSC) (2020)

Add to Collection

Article Energy & Fuels

An unsupervised monitoring procedure for detecting anomalies in photovoltaic systems using a one-class Support Vector Machine

Fouzi Harrou et al.

SOLAR ENERGY (2019)

Add to Collection

Article Energy & Fuels

Automatic classification of defective photovoltaic module cells in electroluminescence images

Sergiu Deitsch et al.

SOLAR ENERGY (2019)

Add to Collection

Article Green & Sustainable Science & Technology

Hierarchical Anomaly Detection and Multimodal Classification in Large-Scale Photovoltaic Systems

Yingying Zhao et al.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2019)

Add to Collection

Review Thermodynamics

A current perspective on the accuracy of incoming solar energy forecasting

Robert Blaga et al.

PROGRESS IN ENERGY AND COMBUSTION SCIENCE (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Anomaly detection and predictive maintenance for photovoltaic systems

Massimiliano De Benedetti et al.

NEUROCOMPUTING (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised Anomaly Detection in Energy Time Series Data using Variational Recurrent Autoencoders with Attention

Joao Pereira et al.

2018 17TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA) (2018)

Add to Collection

Proceedings Paper Computer Science, Interdisciplinary Applications

SolarClique: Detecting Anomalies in Residential Solar Arrays

Srinivasan Iyengar et al.

PROCEEDINGS OF THE 1ST ACM SIGCAS CONFERENCE ON COMPUTING AND SUSTAINABLE SOCIETIES (COMPASS 2018) (2018)

Add to Collection

Review Green & Sustainable Science & Technology

Machine learning methods for solar radiation forecasting: A review

Cyril Voyant et al.

RENEWABLE ENERGY (2017)

Add to Collection

Article Physics, Applied

Solar-cell radiance standard for absolute electroluminescence measurements and open-circuit voltage mapping of silicon solar modules

Toshimitsu Mochizuki et al.

JOURNAL OF APPLIED PHYSICS (2016)

Add to Collection

Article Energy & Fuels

Assessment of solar radiation resources in Saudi Arabia

Erica Zell et al.

SOLAR ENERGY (2015)

Add to Collection

Proceedings Paper Physics, Applied

Intelligent system for a remote diagnosis of a photovoltaic solar power plant

M. A. Sanz-Bobi et al.

25TH INTERNATIONAL CONGRESS ON CONDITION MONITORING AND DIAGNOSTIC ENGINEERING (COMADEM 2012) (2012)

Add to Collection

Article Physics, Applied

Photographic surveying of minority carrier diffusion length in polycrystalline silicon solar cells by electroluminescence

T Fuyuki et al.

APPLIED PHYSICS LETTERS (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.