Scholarlink

This article introduces a novel method for predicting solar energy production using an affordable data logger and the Artificial Neural Network (ANN) algorithm. The main goal of this research is to create a precise predictive model for solar energy output, addressing the critical need for accurate forecasting in the renewable energy industry. The study capitalizes on the accessibility and cost-efficiency of a low-cost data logger to collect detailed environmental and solar irradiance data. The ANN algorithm is utilized to analyze the collected dataset, providing a robust and effective approach for forecasting solar energy production. Extensive experiments demonstrate that the developed model achieves an impressive \(\hbox {R}^{2}\) score of 0.95, indicating a high degree of accuracy and reliability in predicting solar energy output. This significant \(\hbox {R}^{2}\)  score highlights the proposed methodology’s effectiveness, demonstrating its potential for practical applications in solar energy planning and management.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Solar Energy Production Using Low-Cost Data Logger and ANN Algorithm

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mourad Raif,
  • Younes Ledmaoui,
  • Mohamed El Aroussi,
  • Rachid Saadane,
  • Abdeslam Jakimi,
  • Abdellah Chehri

摘要

This article introduces a novel method for predicting solar energy production using an affordable data logger and the Artificial Neural Network (ANN) algorithm. The main goal of this research is to create a precise predictive model for solar energy output, addressing the critical need for accurate forecasting in the renewable energy industry. The study capitalizes on the accessibility and cost-efficiency of a low-cost data logger to collect detailed environmental and solar irradiance data. The ANN algorithm is utilized to analyze the collected dataset, providing a robust and effective approach for forecasting solar energy production. Extensive experiments demonstrate that the developed model achieves an impressive \(\hbox {R}^{2}\) score of 0.95, indicating a high degree of accuracy and reliability in predicting solar energy output. This significant \(\hbox {R}^{2}\)  score highlights the proposed methodology’s effectiveness, demonstrating its potential for practical applications in solar energy planning and management.