基于深度学习算法的电力系统负荷预测研究
Research on Power System Load Forecasting Based on Deep Learning Algorithms
曹刚1
作者信息
- 1. 内蒙古自治区能源技术中心,内蒙古通辽 028015
- 折叠
摘要
文章采用深度学习算法,对电力系统负荷预测展开深入研究.首先,充分分析电力系统历史数据,建立具有时空关联性的负荷数据集.其次,采用卷积神经网络(Convolutional Neural Networks,CNN)和长短期记忆网络(Long Short-Term Memory,LSTM)等深度学习模型,实现对负荷数据的高效特征提取和时序建模.最后,经过模型训练与验证,验证了所提算法在不同季节和负荷波动情况下的稳健性和准确性.
Abstract
This uses deep learning algorithm to carry out in-depth research on power system load forecasting.Firstly,the historical data of the power system is fully analyzed,and the load data set with temporal and spatial correlation is established.Secondly,deep learning models such as Convolutional Neural Networks and Long Short-Term Memory are used to achieve efficient feature extraction and temporal modeling of load data.Finally,after model training and validation,the robustness and accuracy of the proposed algorithm are verified under different seasons and load fluctuations.
关键词
深度学习算法/电力系统/负荷预测/卷积神经网络/长短期记忆网络Key words
deep learning algorithms/power system/load forecasting/convolutional neural network/long short-term memory引用本文复制引用
出版年
2024
NETL
NSTL
万方数据