基于软传感器数据预处理和变量模态分解的LSTM短期风力发电预测方法
Peng Lei1,2, Fanglan Ma2,3, Changsheng Zhu2
1Network & Information Center, Lanzhou University of Technology, Lanzhou 730050, China.
这项研究使用长短期记忆 (LSTM) 网络与变量模态分解 (VMD) 结合,提高了风力发电预测. 这种方法通过分解数据和减少噪音来显著提高准确性,从而使短期风力发电预测更可靠.
科学领域:
- 可再生能源系统可再生能源系统
- 人工智能在能源中的作用
- 电力系统的信号处理.
背景情况:
- 精确的实时风能功率预测对于电网稳定性和调度至关重要.
- 传统的方法难以应对风力发电的瞬间测量挑战.
- 短期风力发电预测为当天电网管理提供了必要的数据.
研究的目的:
- 开发一个先进的软传感器模型,以提高风力发电预测准确度.
- 将数据预处理技术与长期短期存储器 (LSTM) 网络集成,以提高预测.
- 利用变量模态分解 (VMD) 来降低风力发电数据中的噪声和信号分解.
主要方法:
- 数据预处理包括异常检测 (隔离森林) 和缺失值的多重归算.
- 变量模态分解 (VMD) 用于分解风力发电数据并减少噪声.
- 长短期内存 (LSTM) 网络使用Adam优化算法来预测单个模态组件并重建最终预测.
主要成果:
- 带有Adam优化器的LSTM网络表现出卓越的收精度.
- 变量模态分解 (VMD) 有效地降低了噪音,并防止了模态别名,显示出出色的分解结果.
- 结合LSTM-VMD方法实现了平均绝对百分比误差 (MAPE) 的显著降低,降低了9.3508%.
结论:
- 拟议的软传感器模型整合了LSTM和VMD,在风力发电预测准确度方面得到了大幅改善.
- 当与LSTM用于时间序列预测相结合时,VMD的降噪和分解能力非常有效.
- 这种方法为当天电网调度提供了更可靠的参考,增强了风能的整合.
更多相关视频
09:55Surface Renewal: An Advanced Micrometeorological Method for Measuring and Processing Field-Scale Energy Flux Density Data
Published on: December 12, 2013
10:28Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information
Published on: June 13, 2020
相关概念视频
Wind Turbine Machine Models
Induction machines interact through the rotating magnetic field generated by the stator and the rotor. The key parameter is slip, which is the difference between synchronous speed and rotor speed relative to synchronous speed. Slip is...
Energy and Power Signals
Magnetostatic Boundary Conditions
Maxwell-Boltzmann Distribution: Problem Solving
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
Linear Approximation in Time Domain
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
Response Surface Methodology
The process of RSM involves several key steps:
