Abstract The increasing presence of intermittent renewables in modern power systems motivates the development of methods for renewables forecasting. More accurate forecasts may implicate less operational costs for power systems. In this context, this paper proposes a family of architectures based on fully convolutional neural networks for wind speed prediction, the ComPonentNet (CPNet) family. The CPNet produces multi-site spatio-temporal forecasting for phenomena which may be decomposed into multiple components (e.g., wind, which may be decomposed into u- and v-wind). The CPNet family includes three architectures - the core CPNet, the fully-fused CPNet and the bottom-fused CPNet. Each architecture processes the components of the phenomenon in a different manner - in separate branches of convolutional operations, in the same branch, or mixing separate and joint branches. This paper investigates the performance of each CPNet architecture in forecasting multi-site spatio-temporal wind speed. Moreover, the CPNet framework is compared against the U-Net architecture. The results indicate that the proposed framework is promising, and that splitting the processing of wind components may be beneficial to spatio-temporal forecasting, with results that outperform the U-Net.

中文翻译：

---

Componentnet：处理用于时空风速预测的 U 和 V 分量

摘要 现代电力系统中间歇性可再生能源的日益增多推动了可再生能源预测方法的发展。更准确的预测可能意味着电力系统的运营成本更低。在此背景下，本文提出了一系列基于全卷积神经网络的用于风速预测的架构，即 ComPonentNet (CPNet) 系列。CPNet 对可以分解为多个分量（例如，风，可以分解为 u- 和 v-wind）的现象进行多站点时空预测。CPNet 系列包括三种架构——核心 CPNet、全融合 CPNet 和底部融合 CPNet。每个架构都以不同的方式处理现象的组成部分——在卷积运算的不同分支中，在同一分支中，或混合单独和联合分支。本文研究了每个 CPNet 架构在预测多站点时空风速方面的性能。此外，CPNet 框架与 U-Net 架构进行了比较。结果表明，所提出的框架是有前途的，并且拆分风分量的处理可能有利于时空预测，其结果优于 U-Net。