Authors | Avinash Kumar1, Chetan More2, Namita K. Shinde2, Nikale Vasant Muralidhar3, Anurag Shrivastava4, Ch. Venkata Krishna Reddy5, P. William6 |
Affiliations |
1Guru Gobind Singh Educational Society's Technical Campus, Bokaro Jharkhand- 827013, Jharkhand University of Technology, Ranchi, India 2Department of E&TC, Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, India 3Department of Physics, Rayat Shikshan Sanstha's Dada Patil Mahavidyalaya, Karjat Dist Ahmednagar, Maharashtra, India 4Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, Tamilnadu, India 5Department of Electrical and Electronics Engineering, Chaitanya Bharathi Institute of Technology, Hyderabad, India 6Department of Information Technology, Sanjivani College of Engineering, SPPU, Pune, India |
Е-mail | william160891@gmail.com |
Issue | Volume 15, Year 2023, Number 4 |
Dates | Received 14 June 2023; revised manuscript received 18 August 2023; published online 30 August 2023 |
Citation | Avinash Kumar, Chetan More, Namita K. Shinde, и др., J. Nano- Electron. Phys. 15 No 4, 04022 (2023) |
DOI | https://doi.org/10.21272/jnep.15(4).04022 |
PACS Number(s) | 88.05.Np |
Keywords | Electromagnetic radiation (4) , Energy consumption, Machine learning (ML), Linear discriminant analysis (LDA), Enhanced attribute-scaled naive Bayesian (EASNB). |
Annotation |
Using a sophisticated resembling based machine learning (ML) algorithm, this research looks at the direction of renewable energy generation based on distributed electromagnetic radiation and how it relates to the consumption of traditional energy sources. For a feasibility analysis of the energy system design strategy, a forecasting model for renewable energy with a long-time horizon may be used. In this paper, an enhanced attribute-scaled naive Bayesian (EASNB) method is proposed for assessing sustainable renewable energy. For this study, we first collect a dataset on renewable energy sources, and then we normalize the actual data as a pre-processing step to get an accurate energy assessment. Then, the relevant attributes from the pre-processed data are extracted using linear discriminant analysis (LDA). Consequently, the efficient assessment of sustainable renewable energy is accomplished using the suggested EASNB approach. The suggested method's ability is measured in terms of R2 value, MASE, AMRE, accuracy indicators, and is compared with that of existing approaches. The findings of this research indicate that, when it refers to the evaluation of sustainable renewable energy, our method performs better than the ones currently in use. A healthy environment results from determining the exact and appropriate consumption of energy and promoting the use of sustainable energy. Future estimates expect the consumption of renewable energy at around 79.03 EJ in 2025 as well as 55% of energy output on average in 2040. |
List of References |