相关实验视频
Updated: Sep 16, 2025

13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.4K
深度学习和基于树的模型在电力需求预测中的比较分析:准确性,可解释性和计算效率
Bowen Yang1, Mustafa Gül1, Yuxiang Chen1
1Department of Civil and Environmental Engineering, University of Alberta, Edmonton, AB, Canada.
概括
评估用于建筑能源预测的机器学习 (ML) 模型需要的不仅仅是准确性. 本研究将深度学习 (DL) 和基于树的模型在准确性,可解释性和效率方面进行比较,以更好地预测负载.
科学领域:
- 建筑能源系统 建筑能源系统
- 计算智能是一种计算智能.
- 可持续的能源 可持续的能源
背景情况:
- 有效的建筑能源预测对于能源效率和电网可靠性至关重要.
- 机器学习 (ML),特别是深度学习 (DL),被广泛用于电力需求预测.
- 当前的评估往往忽视了模型的解释性和计算成本,阻碍了现实世界的应用.
研究的目的:
- 对用于建筑能源预测的ML模型进行多视角评估.
- 分析预测准确性,可解释性 (全球/本地) 和计算效率.
- 为选择适当的ML算法提供指导,用于负载预测.
主要方法:
- 对三个流行的DL模型 (RNN,GRU,LSTM) 和三个基于树的模型 (随机森林,XGBoost,LightGBM) 的比较分析.
- 评估指标包括预测准确性 (CV-RMSE),可解释性 (特征重要性,模型结构可视化) 和计算效率.
- 对不同电力需求水平的模型进行了评估.
主要成果:
- 模型性能随电力需求水平而变化;以树为基础的模型在较低的功耗下与DL模型竞争.
- 过去的电量使用和与时间相关的特征是关键预测因素;基于树的模型提供了更清晰的特征意义见解.
- DL模型通过隐藏状态可视化提供可解释性,而基于树的模型提供直观的决策规则.
结论:
- 在负载预测中选择ML模型时,多视角评估至关重要.
- 准确性,可解释性和计算效率之间的权衡应该指导模型选择.
- 这项研究为应用ML用于建筑能源预测提供了实用的见解.
相关概念视频
Survival Tree
166
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
166
Fast Decoupled and DC Powerflow
296
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
296
