skip to main content
10.1145/3503047.3503132acmotherconferencesArticle/Chapter ViewAbstractPublication PagesaissConference Proceedingsconference-collections
research-article

Prediction of power of a photovoltaic system in height using hybrid models of Shinkrage regularization with RFE and SFS

Published:19 January 2022Publication History

ABSTRACT

Today is clean and renewable energy systems are attractive for the various applications that use non-renewable energy, as they provide better performance as well as a low long-term cost of electrical energy consumption. The analysis of these systems using artificial intelligence algorithms helps to improve sustainability and to produce energy efficiently. In this research, a photovoltaic system was analyzed with multiparametric regression models using step-by-step selection techniques such as RFE and SFS adding Shinkrage regularization, thus proposing a hybrid model for the analysis of the 14 independent variables used in this study. The division of the data by cross-validation was 80% for training and 20% for testing, seeds were applied in the randomization of data to obtain a better performance obtaining seed of 8849. The proposed hybrid models RFE-Ridge-Bayesian, RFE -Lasso, and RFE-Ridge discarded the variables: Total energy ',' Daily energy 'and' Irradiance ', while for the proposed hybrid models SFS-Ridge-Bayesian, SFS-Lasso, and SFS-Ridge eliminated:' Frequency ',' Energy daily 'and' Irradiance '. The optimal hyperparameters for the Ridge and Lasso models were also calculated, obtaining alpha values ​​of 1.538 and 0.01 respectively. To validate all the proposed hybrid models, the analysis of linearity, normality of the error terms, non-autocorrelation of the error terms, and homoscedasticity was performed, all models satisfying said validation. The variable to predict with an accuracy of 99.97% in all cases was the active power.

References

  1. Omar Abuodeh, Jamal Abdalla, and Rami Hawileh. 2019. Prediction of Compressive Strength of Ultra-High Performance Concrete using SFS and ANN. 2019 8th International Conference on Modeling Simulation and Applied Optimization (ICMSAO), pp. 1-5, doi: 10.1109/ICMSAO.2019.8880452Google ScholarGoogle ScholarCross RefCross Ref
  2. Martin Garaj, Henry Chung, Alan Wai-lun Lo, and Huai Wang. 2019. Analysis of solar panel's lumped equivalent circuit parameters using LASSO. 2019 IEEE Energy Conversion Congress and Exposition (ECCE). pp. 3427-3432, doi: 10.1109/ECCE.2019.8912913Google ScholarGoogle ScholarCross RefCross Ref
  3. Maryam Imani. 2021. Polarimetric SAR Classification Using Ridge Regression-Based Polarimetric-Spatial Feature Extraction. 2021 26th International Computer Conference, Computer Society of Iran (CSICC) pp. 1-5, doi: 10.1109/CSICC52343.2021.9420603Google ScholarGoogle Scholar
  4. Abhinaw Kumar, Pratyush Kumar Das, Ranjan Kumar Mallick, and Pravati Nayak. 2020. Islanding Detection of Micro-grid using Ridge Regression. 2020 International Conference on Computational Intelligence for Smart Power System and Sustainable Energy (CISPSSE), pp. 1-5, doi: 10.1109/CISPSSE49931.2020.9212236.Google ScholarGoogle ScholarCross RefCross Ref
  5. Birol Kuyumcu, Basak Buluz, and Yavuz Kömeçoğlu. 2019. Author Identification in Turkish Documents with Ridge Regression Analysis. 2019 27th Signal Processing and Communications Applications Conference (SIU), pp. 1-4, doi: 10.1109/SIU.2019.8806242Google ScholarGoogle Scholar
  6. Raksha Ramakrishna, Anna Scaglione, Andreas Spanias, and Cihan Tepedelenlioglu. 2019. Distributed Bayesian Estimation with Low-rank Data: Application to Solar Array Processing. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4440-4444, doi: 10.1109/ICASSP.2019.8682854.Google ScholarGoogle ScholarCross RefCross Ref
  7. Canhua Wang, Zhiyong Xiao, Baoyu Wang, and Jianhua Wu. 2019. Identification of Autism Based on SVM-RFE and Stacked Sparse Auto-Encoder. in IEEE Access, vol. 7, pp. 118030-118036, doi: 10.1109/ACCESS.2019.2936639.Google ScholarGoogle ScholarCross RefCross Ref
  8. Ahmad Fikri Zulfikar, Dede Supriyadi, Yaya Heryadi, and Lukas. 2019. Comparison Performance of Decision Tree Classification Model for Spam Filtering with or without the Recursive Feature Elimination (RFE) Approach. 2019 4th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), pp. 311-316, doi: 10.1109/ICITISEE48480.2019.9004001Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. Prediction of power of a photovoltaic system in height using hybrid models of Shinkrage regularization with RFE and SFS
          Index terms have been assigned to the content through auto-classification.

          Recommendations

          Comments

          Login options

          Check if you have access through your login credentials or your institution to get full access on this article.

          Sign in
          • Published in

            cover image ACM Other conferences
            AISS '21: Proceedings of the 3rd International Conference on Advanced Information Science and System
            November 2021
            526 pages
            ISBN:9781450385862
            DOI:10.1145/3503047

            Copyright © 2021 ACM

            Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

            Publisher

            Association for Computing Machinery

            New York, NY, United States

            Publication History

            • Published: 19 January 2022

            Permissions

            Request permissions about this article.

            Request Permissions

            Check for updates

            Qualifiers

            • research-article
            • Research
            • Refereed limited

            Acceptance Rates

            Overall Acceptance Rate41of95submissions,43%
          • Article Metrics

            • Downloads (Last 12 months)9
            • Downloads (Last 6 weeks)1

            Other Metrics

          PDF Format

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader

          HTML Format

          View this article in HTML Format .

          View HTML Format