Open AccessResearch on Deep Generative Model Application for Shortterm Load Forecasting of Enterprise Electricity
Author(s) -
Liwen Zhu,
Yujun Huang
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/687/1/012113
Subject(s) - generative grammar , computer science , baseline (sea) , electricity , artificial neural network , autoregressive integrated moving average , metric (unit) , deep learning , generative model , artificial intelligence , machine learning , complement (music) , quality (philosophy) , predictive modelling , time series , engineering , operations management , biochemistry , oceanography , chemistry , philosophy , epistemology , complementation , electrical engineering , gene , phenotype , geology
This paper mainly applies deep generative models for short-term load forecasting on the enterprise electricity consumption dataset. After data cleaning on the electricity use dataset with the help of related weather data, we complement missing data and improve the data quality to better implement neural network generative prediction models. We build DeepAR and Wavenet as the representative of deep generative models. The main result is that deep generative models perform better compared with other baseline models, such as ARIMA, machine learning and baseline neural networks, no matter what accuracy metric and prediction horizon. Further improvement is to test in higher frequency electricity dataset with better quality.