A Flow-Based Model for Conditional and Probabilistic Electricity Consumption Profile Generation and Prediction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xia, Weijie, Wang, Chenguang, Palensky, Peter, Vergara, Pedro P.
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Systems and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866909870228242432
author	Xia, Weijie Wang, Chenguang Palensky, Peter Vergara, Pedro P.
author_facet	Xia, Weijie Wang, Chenguang Palensky, Peter Vergara, Pedro P.
contents	Residential Load Profile (RLP) generation and prediction are critical for the operation and planning of distribution networks, especially as diverse low-carbon technologies (e.g., photovoltaic and electric vehicles) are increasingly adopted. This paper introduces a novel flow-based generative model, termed Full Convolutional Profile Flow (FCPFlow), which is uniquely designed for both conditional and unconditional RLP generation, and for probabilistic load forecasting. By introducing two new layers--the invertible linear layer and the invertible normalization layer--the proposed FCPFlow architecture shows three main advantages compared to traditional statistical and contemporary deep generative models: 1) it is well-suited for RLP generation under continuous conditions, such as varying weather and annual electricity consumption, 2) it demonstrates superior scalability in different datasets compared to traditional statistical models, and 3) it also demonstrates better modeling capabilities in capturing the complex correlation of RLPs compared with deep generative models.
format	Preprint
id	arxiv_https___arxiv_org_abs_2405_02180
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	A Flow-Based Model for Conditional and Probabilistic Electricity Consumption Profile Generation and Prediction Xia, Weijie Wang, Chenguang Palensky, Peter Vergara, Pedro P. Machine Learning Systems and Control Residential Load Profile (RLP) generation and prediction are critical for the operation and planning of distribution networks, especially as diverse low-carbon technologies (e.g., photovoltaic and electric vehicles) are increasingly adopted. This paper introduces a novel flow-based generative model, termed Full Convolutional Profile Flow (FCPFlow), which is uniquely designed for both conditional and unconditional RLP generation, and for probabilistic load forecasting. By introducing two new layers--the invertible linear layer and the invertible normalization layer--the proposed FCPFlow architecture shows three main advantages compared to traditional statistical and contemporary deep generative models: 1) it is well-suited for RLP generation under continuous conditions, such as varying weather and annual electricity consumption, 2) it demonstrates superior scalability in different datasets compared to traditional statistical models, and 3) it also demonstrates better modeling capabilities in capturing the complex correlation of RLPs compared with deep generative models.
title	A Flow-Based Model for Conditional and Probabilistic Electricity Consumption Profile Generation and Prediction
topic	Machine Learning Systems and Control
url	https://arxiv.org/abs/2405.02180