Deep-Based Conditional Probability Density Function Forecasting of Residential Loads

This paper proposes a direct model for conditional probability density forecasting of residential loads, based on a deep mixture network. Probabilistic residential load forecasting can provide comprehensive information about future uncertainties in demand. An end-to-end composite model comprising co...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on smart grid 2020-07, Vol.11 (4), p.3646-3657
Main Authors: Afrasiabi, Mousa, Mohammadi, Mohammad, Rastegar, Mohammad, Stankovic, Lina, Afrasiabi, Shahabodin, Khazaei, Mohammad
Format: Article
Language:English
Subjects:
Artificial neural networks
Computer simulation
conditional probabilistic load forecasting
Conditional probability
Convolution
convolutional neural network
deep mixture network
Economic forecasting
Forecasting
gated recurrent unit
Load
Load forecasting
Load modeling
Predictive models
Probabilistic methods
Probabilistic models
Probability density function
Probability density functions
Residential density
Residential load forecasting
Statistical analysis
Time series analysis
Training
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a direct model for conditional probability density forecasting of residential loads, based on a deep mixture network. Probabilistic residential load forecasting can provide comprehensive information about future uncertainties in demand. An end-to-end composite model comprising convolution neural networks (CNNs) and gated recurrent unit (GRU) is designed for probabilistic residential load forecasting. Then, the designed deep model is merged into a mixture density network (MDN) to directly predict probability density functions (PDFs). In addition, several techniques, including adversarial training, are presented to formulate a new loss function in the direct probabilistic residential load forecasting (PRLF) model. Several state-of-the-art deep and shallow forecasting models are also presented in order to compare the results. Furthermore, the effectiveness of the proposed deep mixture model in characterizing predicted PDFs is demonstrated through comparison with kernel density estimation, Monte Carlo dropout, a combined probabilistic load forecasting method and the proposed MDN without adversarial training.
ISSN:1949-3053
1949-3061
DOI:10.1109/TSG.2020.2972513