User-Level Large Scale Load Forecasting Based on GPU

Load forecasting is an essential part in power system management and planning. In recent years, more and more researchers started to focus on the behavior of terminal customers, trying to improve the accuracy of load forecasting. This paper proposes to use the neuron network model to predict each us...

Full description

Saved in:
Bibliographic Details
Published in2023 9th Annual International Conference on Network and Information Systems for Computers (ICNISC) pp. 282 - 286
Main Authors Qi, Jinshan, Wang, Jiangtao, Liang, Xun, Xu, Zhiming
Format Conference Proceeding
LanguageEnglish
Published IEEE 27.10.2023
Subjects
Computational modeling
GPU
Graphics processing units
Load forecasting
neural network
Neurons
Planning
Power system management
Predictive models
user-level
Online AccessGet full text

Cover

More Information
Summary:Load forecasting is an essential part in power system management and planning. In recent years, more and more researchers started to focus on the behavior of terminal customers, trying to improve the accuracy of load forecasting. This paper proposes to use the neuron network model to predict each user's load first, and then aggregate all the forecasting results to get higher-level prediction. In order to speed up the process, we also design a model based on CUDA. We conducted several experiments on real-world data (160 thousand consumers' load profiles) and the results confirm the effectiveness and efficiency of our method.
DOI:10.1109/ICNISC60562.2023.00017