Scholarlink

With the increasing threat of global climate problems and energy crisis, the human demand for renewable energy is increasingly urgent. This paper aims to build an accurate prediction model of wind turbine output power to meet this challenge. Grey prediction models and time series analysis methods were used to predict and their prediction error, computational accuracy and pass rate were compared. Through experimental data verification, time series analysis is used to find out the main time nodes of error. On the basis of the time series analysis, this paper innovatively gives weight to the prediction data, introduces the weighted moving average method, performs the weighted average processing, and then combines the results with the power average of the previous time point to improve the accuracy of the prediction. Through these methods, the study can better cope with the volatility of renewable energy and contribute to the development of sustainable energy.

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

Research on Wind Electric Power Prediction and Optimization Based on Big Data Machine Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Junyi Liu,
  • Yuming Xiang,
  • Xinrui He,
  • Chun Luo,
  • Jinyun Luo,
  • Yang Wang,
  • Zeyi Liu

摘要

With the increasing threat of global climate problems and energy crisis, the human demand for renewable energy is increasingly urgent. This paper aims to build an accurate prediction model of wind turbine output power to meet this challenge. Grey prediction models and time series analysis methods were used to predict and their prediction error, computational accuracy and pass rate were compared. Through experimental data verification, time series analysis is used to find out the main time nodes of error. On the basis of the time series analysis, this paper innovatively gives weight to the prediction data, introduces the weighted moving average method, performs the weighted average processing, and then combines the results with the power average of the previous time point to improve the accuracy of the prediction. Through these methods, the study can better cope with the volatility of renewable energy and contribute to the development of sustainable energy.