.png){kind=icon}
返回
A residential load forecasting method for multi-attribute adversarial learning considering multi-source uncertainties
.png){kind=icon}
OA
AI
DOI：10.1016/j.ijepes.2023.109421.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The rapid development of the Internet of Things and device-level meters provides accurate energy consumption data for various household devices, and making full use of these data to achieve higher accuracy of residential load forecasting is an open problem. Moreover, the uncertainties and insufficient feature extraction of variables make it challenging for individual residential load forecasts. In this regard, this paper proposes a novel shortterm residential load forecasting method. It has the following aspects: (1) Considering the multi-source uncertainties, a multi-source uncertainties divide-and-conquer mechanism is proposed, which classifies the residential load from the device level according to different sources of uncertainties and forecasts separately. (2) Considering the multiple attributes of influencing variables, a multi-attribute adversarial learning mechanism based on the conditional Wasserstein generative adversarial network with gradient penalty (cWGAN-GP) is designed. In cWGAN-GP, this paper uses a long short-term memory network to implement the generator and uses a convolutional neural network to implement the discriminator. The former is used to extract temporal features, while the latter is used to extract spatial features, and they realize the fusion of multiple attributes through adversarial training to improve prediction accuracy. Compared with existing load forecasting methods, our proposed method's mean absolute percentage error decreased by 1.5-38.9%, mean square error decreased by 3.5-35.9%, normalized root MSE decreased by 1.7-19.9%, and mean absolute error decreased by 3.7-27.0%.
Keyword:
Residential load forecasting
Uncertainties
Generative adversarial networks
Long short -term memory
Convolutional neural networks
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5
论文数:
1.1W
被引数:
3.1W
机构
引用论文
分享收藏A Kalman filter-based bottom-up approach for household short-term load forecast.png)
APPLIED ENERGY
APPLIED ENERGYIF11
PREAI
分享收藏Short-term residential electric load forecasting: A compressive spatio-temporal approachENERGY AND BUILDINGS
ENERGY AND BUILDINGSIF7.1
PREAI
分享收藏Effective RNN-Based Forecasting Methodology Design for Improving Short-Term Power Load Forecasts: Application to Large-Scale Power-Grid Time Series有效的基于RNN的预测方法设计，以改善短期电力负荷预测: 在大规模电网时间序列中的应用OAAI
OAAI分享收藏Electricity load forecasting and feature extraction in smart grid using neural networks基于神经网络的智能电网电力负荷预测与特征提取
PREAI
分享收藏Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network基于LSTM循环神经网络的短期住宅负荷预测
PREAI
分享收藏Temporal structure of motor variability is dynamically regulated and predicts motor learning ability
OAAI
OAAI分享收藏Comparing Generative Adversarial Networks architectures for electricity demand forecastingENERGY AND BUILDINGS
ENERGY AND BUILDINGSIF7.1
PREAI
分享收藏
查看更多内容