Intelligent IoT Platform for Multiple PV Plant Monitoring
Abstract
:1. Introduction
- Intelligent IoT platform architecture to monitor multiple PV plants.
- Method to perform AI-based next-day power generation prediction in multiple PV plants.
- Adaptive threshold Isolation Forest for detecting sensor malfunctions in multiple PV plants.
2. Literature Review
3. Methodology
3.1. Intelligent IoT Platform Architecture
3.1.1. Message Queuing
3.1.2. Data Storage
3.1.3. Intelligent Services
3.1.4. User Administration Services
- Site user: intended for users that are authorized to control only one specific PV plant.
- Group user: intended for the user to control multiple PV plants that belong to the same group or ownership.
- Admin user: intended for administrator users who can control and manage all registered PV plants.
3.1.5. PV Plant Administration Services
3.1.6. Individual PV Plant Monitoring Services
3.2. AI Model for PV Power Generation Prediction
3.2.1. Recurrent Neural Network (RNN)
3.2.2. Long Short-Term Memory (LSTM)
3.2.3. Bidirectional LSTM (BiLSTM)
3.2.4. Convolutional LSTM
3.2.5. BiLSTM-Multi Dense
3.3. Isolation Forest for Anomaly Detection
Algorithm 1 Adaptive Threshold Isolation Forest for Anomaly Detection in Streaming Data |
Input: D—the streaming data (at time t) W—the size of the sliding window N—a factor used to calculate the adaptive threshold I—the frequency of updating the model R—the threshold for contamination ratio or the anomaly rate Output: A—a list of indices where anomalies were detected
|
4. Results and Discussion
4.1. Intelligent IoT Platform Development
4.2. PV Power Generation Prediction Performance
Algorithm 2 Method to train AI models on multiple PV plants |
Input: M—The list of the AI model P—list of monitored PV plant W—weather dataset for each PV plant —generated power of each PV plant Output:—a set of trained model weights for each PV plant
|
Algorithm 3 Method to train individual AI models |
Input: Temperature as input data Humidity as input data Wind speed in x direction as input data Wind speed in y direction as input data Solar radiation intensity as input data Cloud density as input data Duration of sunshine as input data Generated PV power as target data Model structure and hyperparameter Output: Predicted 24-h ahead PV power generation
|
4.3. Anomaly Detection Performance
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Renewable Energy—Powering a Safer Future. Available online: https://www.un.org/en/climatechange/raising-ambition/renewable-energy (accessed on 21 May 2023).
- Center for Sustainable Systems, University of Michigan. Photovoltaic Energy Factsheet; University of Michigan: Ann Arbor, MI, USA, 2021; Pub. No. CSS07-08. [Google Scholar]
- International Energy Agency Photovoltaic Power Systems (IEA PVPS). 2023 Snapshot of Global PV Markets; IEA PVPS: London, UK, 2023. [Google Scholar]
- Jaeger-Waldau, A. Snapshot of photovoltaics—February 2022. EPJ Photovolt. 2022, 13, 9. [Google Scholar] [CrossRef]
- Center for Sustainable Systems, University of Michigan. U.S. Renewable Energy Factsheet; University of Michigan: Ann Arbor, MI, USA, 2021; Pub. No. CSS03-12. [Google Scholar]
- Best Research-Cell Efficiency Chart. Available online: https://www.nrel.gov/pv/cell-efficiency.html (accessed on 21 May 2023).
- Kumar, B.P.; Pillai, D.S.; Rajasekar, N.; Chakkarapani, M.; Ilango, G.S. Identification and Localization of Array Faults With Optimized Placement of Voltage Sensors in a PV System. IEEE Trans. Ind. Electron. 2021, 68, 5921–5931. [Google Scholar] [CrossRef]
- Miao, W.; Lam, K.H.; Pong, P.W.T. A String-Current Behavior and Current Sensing-Based Technique for Line–Line Fault Detection in Photovoltaic Systems. IEEE Trans. Magn. 2021, 57, 6100206. [Google Scholar] [CrossRef]
- Pamungkas, R.F.; Utama, I.B.K.Y.; Jang, Y.M. A Novel Approach for Efficient Solar Panel Fault Classification Using Coupled UDenseNet. Sensors 2023, 23, 4918. [Google Scholar] [CrossRef] [PubMed]
- Memon, S.A.; Javed, Q.; Kim, W.-G.; Mahmood, Z.; Khan, U.; Shahzad, M. A Machine-Learning-Based Robust Classification Method for PV Panel Faults. Sensors 2022, 22, 8515. [Google Scholar] [CrossRef] [PubMed]
- Eltuhamy, R.A.; Rady, M.; Almatrafi, E.; Mahmoud, H.A.; Ibrahim, K.H. Fault Detection and Classification of CIGS Thin-Film PV Modules Using an Adaptive Neuro-Fuzzy Inference Scheme. Sensors 2023, 23, 1280. [Google Scholar] [CrossRef] [PubMed]
- Emamian, M.; Eskandari, A.; Aghaei, M.; Nedaei, A.; Sizkouhi, A.M.; Milimonfared, J. A Cloud Computing and IoT Based Intelligent Monitoring System for Photovoltaic Plants Using Machine Learning Techniques. Energies 2022, 15, 3014. [Google Scholar] [CrossRef]
- Portalo, J.M.; González, I.; Calderón, A.J. A Monitoring System for Tracking a PV Generator in an Experimental Smart Microgrid: An Open-Source Solution. Sustainability 2021, 13, 8182. [Google Scholar] [CrossRef]
- Ahsan, L.; Baig, M.J.A.; Iqbal, M.T. A Low-Cost, Open-Source, Emoncms-Based SCADA System for a Large Grid-Connected PV System. Sensors 2022, 22, 6733. [Google Scholar] [CrossRef] [PubMed]
- Paredes-Parra, J.M.; Jiménez-Segura, R.; Campos-Peñalver, D.; Mateo-Aroca, A.; Ramallo-González, A.P.; Molina-García, A. A Democratization of PV Micro-Generation System Monitoring Based on Narrowband-IoT. Sensors 2022, 22, 4966. [Google Scholar] [CrossRef] [PubMed]
- González, I.; Portalo, J.M.; Calderón, A.J. A Configurable IoT Open-Source Hardware and Software I-V Curve Tracer for Photovoltaic Generators. Sensors 2021, 21, 7650. [Google Scholar] [CrossRef] [PubMed]
- Yao, T.; Wang, J.; Wang, Y.; Zhang, P.; Cao, H.; Chi, X.; Shi, M. A Very short-term forecasting of distributed PV power using GSTANN. CSEE J. Power Energy Syst. 2022; early access. [Google Scholar] [CrossRef]
- Alharkan, H.; Habib, S.; Islam, M. A Solar Power Prediction Using Dual Stream CNN-LSTM Architecture. Sensors 2023, 23, 7650. [Google Scholar] [CrossRef] [PubMed]
- Sajun, A.R.; Shapsough, S.; Zualkernan, I.; Dhaouadi, R. A Edge-based individualized anomaly detection in large-scale distributed solar farms. ICT Express 2022, 8, 175–178. [Google Scholar] [CrossRef]
- Ibrahim, M.; Alsheikh, A.; Awaysheh, F.M.; Alshehri, M.D. A Machine Learning Schemes for Anomaly Detection in Solar Power Plants. Energies 2023, 15, 1082. [Google Scholar] [CrossRef]
- Rumelhart, D.; Hinton, G.; Williams, R. Learning representations by back-propagating errors. Nature 1986, 323, 533–536. [Google Scholar] [CrossRef]
- Hochreiter, S.; Schmidhuber, J. Long Short-Term Memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef] [PubMed]
- Shi, X.; Chen, Z.; Wang, H.; Yeung, D.Y.; Wong, W.K.; Woo, W.C. Convolutional LSTM Network: A machine learning approach for precipitation nowcasting. In Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada, 7–12 December 2015; Volume 1. [Google Scholar]
- Liu, F.T.; Ting, K.M.; Zhou, Z.H. Isolation Forest. In Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy, 15–19 December 2008. [Google Scholar] [CrossRef]
Number of Clients | Message Size (bytes) | Number of Message | Total Transmitted Messages | Average Transmission Time (s) | Total Received Messages | Error Rate (%) |
---|---|---|---|---|---|---|
38 | 500 | 5 | 238,000 | 0.142 | 238,000 | 0 |
AI Model | MSE | MAPE | MAE | |
---|---|---|---|---|
RNN | 0.0272 | 0.3152 | 0.1084 | 0.8866 |
LSTM | 0.0152 | 0.2334 | 0.0755 | 0.9215 |
BiLSTM | 0.0072 | 0.1982 | 0.0542 | 0.9664 |
Convolutional LSTM | 0.0172 | 0.2974 | 0.0980 | 0.9202 |
BiLSTM-Multi dense | 0.0125 | 0.2243 | 0.0662 | 0.9526 |
Data Split | Total Sample | Normal | Anomaly |
---|---|---|---|
Training | 39,345 | 38,976 | 369 |
Testing | 20,000 | 19,814 | 186 |
Anomaly Detection Techniques | Training Time (s) | Precision | Recall |
---|---|---|---|
Proposed method | 3.318 | 0.9517 | 0.998 |
HBOS | 2.113 | 0.822 | 0.969 |
LOF | 1.182 | 0.672 | 0.539 |
MCD | 0.04 | 0.824 | 0.769 |
OCSVM | 209.499 | 0.920 | 0.999 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Utama, I.B.K.Y.; Pamungkas, R.F.; Faridh, M.M.; Jang, Y.M. Intelligent IoT Platform for Multiple PV Plant Monitoring. Sensors 2023, 23, 6674. https://doi.org/10.3390/s23156674
Utama IBKY, Pamungkas RF, Faridh MM, Jang YM. Intelligent IoT Platform for Multiple PV Plant Monitoring. Sensors. 2023; 23(15):6674. https://doi.org/10.3390/s23156674
Chicago/Turabian StyleUtama, Ida Bagus Krishna Yoga, Radityo Fajar Pamungkas, Muhammad Miftah Faridh, and Yeong Min Jang. 2023. "Intelligent IoT Platform for Multiple PV Plant Monitoring" Sensors 23, no. 15: 6674. https://doi.org/10.3390/s23156674