Scholarlink

This paper uses Multi-Layer Perceptron (MLP) neural networks to explore wind turbine power output prediction. Accurate forecasting of wind energy production is critical for grid stability and optimizing energy systems. The study compares various prediction techniques, including physical, statistical, and hybrid methods. The methodology employs real-world data sourced and uses records from 2016–2017. Data preprocessing includes filtering, seasonal decomposition, time series analysis, and dividing the dataset into training, validation, and testing sets. The model’s structure and hyperparameters were carefully tuned, employing 144 samples from the produced power as input, representing 24-hour cycles, to forecast the next hour. The study evaluated multiple MLP configurations, varying in hidden layer sizes and training strategies, to identify the optimal architecture for short-term wind power forecasting. The evaluation uses statistical metrics to assess prediction accuracy, including RMSE, NRMSE, and R2. Early stopping and randomized dataset splits were evaluated to increase model performance and robustness. The models obtained results between 94-95% for the coefficient of determination (R2). The main goal of this paper is to demonstrate the utility of MLP in forecasting wind power generation systems, contributing to grid stability and the efficient integration of renewable energy sources. However, the model’s accuracy could be further improved by incorporating additional environmental or meteorological variables and exploring deep-learning models.

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 Average Power Produced by Wind Turbines Using MLP Neural Networks

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Letícia Góes Campos,
  • Luiz E. Luiz,
  • Raphael Paulo Braga Poubel,
  • João Paulo Teixeira

摘要

This paper uses Multi-Layer Perceptron (MLP) neural networks to explore wind turbine power output prediction. Accurate forecasting of wind energy production is critical for grid stability and optimizing energy systems. The study compares various prediction techniques, including physical, statistical, and hybrid methods. The methodology employs real-world data sourced and uses records from 2016–2017. Data preprocessing includes filtering, seasonal decomposition, time series analysis, and dividing the dataset into training, validation, and testing sets. The model’s structure and hyperparameters were carefully tuned, employing 144 samples from the produced power as input, representing 24-hour cycles, to forecast the next hour. The study evaluated multiple MLP configurations, varying in hidden layer sizes and training strategies, to identify the optimal architecture for short-term wind power forecasting. The evaluation uses statistical metrics to assess prediction accuracy, including RMSE, NRMSE, and R2. Early stopping and randomized dataset splits were evaluated to increase model performance and robustness. The models obtained results between 94-95% for the coefficient of determination (R2). The main goal of this paper is to demonstrate the utility of MLP in forecasting wind power generation systems, contributing to grid stability and the efficient integration of renewable energy sources. However, the model’s accuracy could be further improved by incorporating additional environmental or meteorological variables and exploring deep-learning models.