2D 多尺度太阳辐射预测的时变功能建模框架
Chengdong Shi1, Wei Zhao2, Xiao-Jun Zeng1
1Department of Computer Science, University of Manchester, Manchester, M13 9PL, UK.
准确的太阳辐射预测需要理解多尺度数据. 一个新的2D时间变量函数建模 (2D-TFM) 框架通过将1D时间序列转换为2D函数序列来改进预测.
科学领域:
- 预测可再生能源的使用情况
- 时间序列分析时间序列分析
- 机器学习用于能源系统
背景情况:
- 太阳辐射预测对于能源管理至关重要.
- 现有的1D时间序列方法与多尺度的时间动态作斗争.
- 准确的长期太阳辐射预测仍然是一个挑战.
研究的目的:
- 引入一个新的二维时间变量函数建模 (2D-TFM) 框架.
- 克服1D表示在捕捉多尺度时间依赖性的局限性.
- 提高太阳辐射预测的准确性和可解释性.
主要方法:
- 使用B-spline基础函数扩展将1D太阳辐射时间序列转换为2D功能序列.
- 使用自适应局部复杂性 (ALC) 节点放置算法优化功能表示.
- 使用功能性的长短期内存 (LSTM) 网络来学习参数空间映射.
主要成果:
- 与Seq2Seq-LSTM等现有方法相比,2D-TFM框架显示出更高的预测准确性.
- 在每小时和每分钟的预测中,实现了根平均平方误差 (RMSE) 和平均绝对百分比误差 (MAPE) 的显著降低.
- 该模型在任意时间分辨率下提供无网格预测,增强实际应用性.
结论:
- 拟议的2D-TFM框架有效地捕捉了太阳辐射数据的短期波动和长期趋势.
- 2D-TFM提供了比传统方法更好的计算效率和可解释性.
- 该框架增强了用于能源管理系统的太阳辐射预测.
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
09:00Indoor Experimental Assessment of the Efficiency and Irradiance Spot of the Achromatic Doublet on Glass ADG Fresnel Lens for Concentrating Photovoltaics
Published on: October 27, 2017
相关概念视频
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
Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Precipitation Processes
Heating and Cooling Curves
For instance, the addition of heat raises the temperature of a solid; the amount of heat absorbed depends on the heat capacity of the solid (q = mcsolidΔT). According to thermochemistry, the relation between the amount of heat absorbed or released by a substance, q, and its...
Ampere-Maxwell's Law: Problem-Solving
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the...
Calculation of Electric Flux
