Machine Learning-Based Renewable Energy Systems Fault Mitigation and Economic Assessment

Abstract

In an era increasingly focused on sustainability, the adoption of renewable energy stands as a promising avenue for fostering local economic growth. This study presents a novel approach, merging advanced fault mitigation techniques and machine learning, to assess the economic impact of renewable energy systems (RES) at the local level. Leveraging random forest, support vector machines (SVM), and gradient boosting, customized algorithms are deployed for regression analysis and defect identification. Hyperparameter optimization ensures optimal performance, with a linear regression meta-learner facilitating the fusion of predictions. An advanced anomaly detection component effectively identifies and rectifies errors within RES. Performance evaluation metrics, including an root mean square error (RMSE) of 2.18 and an overall system efficiency of 98%, underscore the success of the fault mitigation strategy. Precision, recall, and F1-score metrics further highlight its robustness. This comprehensive framework not only provides precise estimates of the financial impact of renewable energy adoption but also enhances the reliability of RES through sophisticated fault mitigation. Empowering decision-makers with actionable insights, it facilitates sustainable energy planning, effective policy implementation, and the establishment of resilient energy systems.

Keywords:

• Renewable energy systems (RES)
• machine learning
• economic assessment
• principal component analysis (PCA)
• random forest
• support vector machines (SVM)
• fault mitigation
• ensemble learning
• local economic gains

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Figure 1. Financial feasibility analysis and fault resolution of machine learning.

Figure 2. Economic dimensions of renewable energy sources.

Figure 3. Assessment of voltage distribution with distance.

Figure 4. Solar-photovoltaic assessment in RES environment.

Figure 5. Installations of RES (wind PV) in local regions.

Figure 6. Wind forces experienced by the horizontal turbine in windy environments in local regions.

Figure 7. Real-time economic assessments proposed optimal design.

Figure 8. Proposed modeling clusters of economic assessments of renewable energy sources.

Figure 9. Proposed GIS for RES.

Figure 10. Primary energy assessment for the RES.

Figure 11. Fault Scenario1 of the proposed wind system.

Figure 12. Fault Scenario2 of the proposed solar PV system.

Table 1. Factors associated with the choice of solar panels.

Additional information

Notes on contributors

Syed Ghyasuddin Hashmi

Syed Ghyasuddin Hashmi currently working as a Lecturer in the Department of College of Engineering and Computer Science, Jazan University, Jazan, KSA. He received his MCA degree from IGNOU India . He has worked as a counselor for IGNOU. He has published more than 10 research papers in different reputed international/national journals, conference proceedings and book chapters. His research interest includes Software Requirement Engineering, Software Engineering and Software Security. He extended his research area to IoT, Wireless Sensor Networks, Cloud Computing and Block chain.

V Balaji

V Balaji has 22 years of teaching experience. Now he is working as Associate Professor in the Department of ECSE at MAI –NEFHI COLLEGE OF ENGINEERING AND TECCHNOLOGY, Asmara, Eritrea. He completed his Post-Doctoral Fellow in the field of Artificial Intelligence at Srinivas University Mangalore. His current areas of research are model predictive control, process control, and Fuzzy and Neural Networks. He has received Dr. APJ Abdul Kalam Award for Young Scientist, Excellence in Education Award, Best Teacher Award, World’s greatest person Award He has published 110 research papers in national and international journals conferences, Six textbooks and 10 patents in the field of electrical and of Artificial Intelligence. www.vbalaji.com website was created by him and the study materials were uploaded. He has guided eight research scholars in various universities. He is an active member of ISTE, IAENG, IAOE, IACSIT, FMIAEME, LMIAOE, LM IACSIT, SMIRED, and MIIRJC. He is also serving as a Chief Editor, editorial board member and reviewer in the reputed National and International journals and conferences.

Mohamed Uvaze Ahamed Ayoobkhan

Mohamed Uvaze Ahamed Ayoobkhan obtained both Bachelor's and Master's degrees from Anna University, Chennai, India, furthered his academic journey by earning a PhD in Information Technology, honored with the Best PhD Thesis Award in 2018 from Multimedia University, Malaysia. With teaching roles at Sri Ramakrishna Engineering College and Jain University in India, he expanded his academic horizons to encompass positions in Iraq and Uzbekistan. Presently, he serves as an Assistant Professor at New Uzbekistan University, Tashkent. Dr. Mohamed's scholarly endeavors extend beyond teaching, boasting 6 international Intellectual Property Rights and a robust publication record exceeding 40 research papers in esteemed international journals and conferences. His research focuses primarily on Computer Vision and Machine Learning, particularly in Medical Imaging, Optimization, and Deep/Shallow Learning. Dr. Mohamed actively contributes to the academic community as a guest editor, advisory board member, and reviewer for prestigious international journals and conferences, reflecting his unwavering commitment to advancing knowledge in his field.

Mohammad Shabbir Alam

Mohammad Shabbir Alam is presently working as Senior Lecturer in College of Computer Science and Information Technology, Jazan University (Public University), Jazan, Kingdom of Saudi Arabia. He received his Master in Computer Science & Applications (MCA) in years 2007 from Aligarh Muslim University, India. More than 15 years of academic and industry experiences in area of Computer Science and Information Technology. He has published 1 UK Patents, 2 German Patents and 4 Australian patents, 4 Books, 1 Book chapter and more than 30+ research papers in reputed international journals and national/international conference proceedings. His areas of research interest include Deep learning, Blockchain, Machine Learning and Health Care.

R. Anilkuamr

R. Anilkuamr is currently working as an associate professor in the electronics and communication engineering department at Aditya College of Engineering Technology, Surampalem. He received a doctoral degree from JNTUK University, Kakinada. He published 25 technical papers in various international journals and presented seven technical papers at various conferences. He is an expert in wireless communications, signal processing, and ML and DS. He published six patents and one text book with title “5G Technology”. He is an associate member of IETE and ISTE.

Neerav Nishant

Neerav Nishant is working as Assistant Professor in department of CSE, School of Engineering, BBDU, Lucknow. He has completed his Master of Technology (M. Tech.) in Computer Science from BIT, Mesra, Ranchi, and pursuing Doctor of Philosophy (Ph. D.) in Computer Science & Engineering from MUIT, Lucknow, U.P., India. He has been teaching Computer Science subject for UG and PG science & engineering courses for approx 10 years. He has published many research papers in SCIE, Scopus, WOS, UGC Care-I and UGC Care-II indexed journals, 10 Indian patent publication, 4 UK design patent grant, and co-author in 5 books. He is a Fellow Member of IETE, Life Member of I.S.T.E., ISCA, IAENG and associated with various reputed computer science associations.

Jyoti Prasad Patra

Jyoti Prasad Patra is presently the Professor Head EE and EEE of Krupajal Engineering College KEC Pubasasan Prasanthi Vihar Kausalyaganga Near CIFA District Puri Odisha India Bhubaneswar. He Has To His Credit 35 Years Of Experience 47 Indian Published Patents 07 Indian/Uk Designs Registered 01 International Award Received 06 Text Books 01 E-Book Published 03 SCI 10 Scopus Journal Article Published 13 IEEE Conference Articles Published 12 M.Tech Theses Guided. He Was Born 12th September 1965 And Awarded Ph.D in Electrical Engineering in 2013 from SOA University Bhubaneswar Which Has NIRF Ranking Of 15 In University Category In 2023.

A. Rajaram

A. Rajaram received the B.E. degree in Electronics and Communication Engineering from the Government, College of Technology, Coimbatore, Anna University, Chennai, India, in 2006, the M.E. degree in Applied Electronics from the Government College of Technology, Anna University, Chennai, India, in 2008 and he received the Full Time Ph.D. degree in Electronics and Communication Engineering from the Anna University of Technology, Coimbatore, India in March 2011. He is currently working as a professor in Department of Electronics and Communication Engineering, E.G.S Pillay Engineering College, Nagapattinam. His research interests include Mobile Ad Hoc networks, wireless communication networks (WiFi, WiMax HighSlot GSM), novel VLSI NoC Design approaches to address issues such as low-power, cross-talk, hardware acceleration, Design issues includes OFDM MIMO and noise Suppression in MAI Systems, ASIC design, Control systems, Fuzzy logic and Networks, AI, Sensor Networks.