Scholarlink

In this paper, we present IoT-enabled portable devices to collect weather data which includes irradiance, wind speed, and wind direction. Furthermore, a solar panel is used with voltage and current sensors to find the approximate amount of energy that can be generated. All of these data are then fed to a Long Short-Term Memory (LSTM)-based deep learning model, which can be used on this time-series data to predict the generation of solar energy from photovoltaic cells. The proposed model achieves an RMSE of 0.1577 with a loss of 0.0249 for 1000 epochs, demonstrating its effectiveness in predicting future solar energy generation.

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

Portable IoT-Based Prediction of Solar Energy Generation Using Deep Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Matthews Ankon Baroi,
  • Sheikh Shafi-Ul Hasan Sami,
  • Md. Monwar Hossain,
  • K. M. Safin Kamal,
  • Ahmed Wasif Reza

摘要

In this paper, we present IoT-enabled portable devices to collect weather data which includes irradiance, wind speed, and wind direction. Furthermore, a solar panel is used with voltage and current sensors to find the approximate amount of energy that can be generated. All of these data are then fed to a Long Short-Term Memory (LSTM)-based deep learning model, which can be used on this time-series data to predict the generation of solar energy from photovoltaic cells. The proposed model achieves an RMSE of 0.1577 with a loss of 0.0249 for 1000 epochs, demonstrating its effectiveness in predicting future solar energy generation.