Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Transfer Learning Trained LSTM Models for Household Load Profile Forecasting

Conference ·
; ;
Grid edge renewable energy resources, such as rooftop solar photovoltaics, closely interact with consumer load profiles. Therefore, forecasting future electricity demand, ideally at the individual household level, is indispensable. In this paper, we present a transfer learning enhanced household load profile forecasting method. First, we tune a long short-term memory forecasting model to perform day-ahead prediction of household electricity load profiles. Then we improve these individualized models using transfer learning, and we use k-means clustering to create optimal source data sets. We find average improvements of 4.38% (largest improvement of 10.71%) when the entire data set was used to train the source model and 2.45% (largest improvement of 11.57%) in the mean absolute error when households were first clustered and used to train separate source models for each cluster. We find that transfer learning with clustered data can effectively boost the forecasting performance of the LSTM models. We use realistic household power measurements for 148 real residential households in Austin, Texas.
Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Sponsoring Organization:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Transportation Office. Vehicle Technologies Office
DOE Contract Number:
AC36-08GO28308
OSTI ID:
2558978
Report Number(s):
NREL/CP-5D00-94351; MainId:96133; UUID:dfa7f2ff-3ca8-4bb2-bf84-d5942b61694e; MainAdminId:76656
Country of Publication:
United States
Language:
English

References (15)

Socio-demographic Characteristics Prediction Using Soft Clustering of Load Consumption Data book October 2021
A hybrid transfer learning model for short-term electric load forecasting journal March 2020
Transfer learning in demand response: A review of algorithms for data-efficient modelling and control journal January 2022
Transfer learning with seasonal and trend adjustment for cross-building energy forecasting journal April 2018
A survey on long short-term memory networks for time series prediction journal January 2021
The National Solar Radiation Data Base (NSRDB) journal June 2018
Six unique load shapes: A segmentation analysis of Illinois residential electricity consumers journal November 2019
Individualized Short-Term Electric Load Forecasting With Deep Neural Network Based Transfer Learning and Meta Learning journal January 2021
Transfer learning for time series classification conference December 2018
An Innovative Approach for Forecasting of Energy Requirements to Improve a Smart Home Management System Based on BLE journal March 2017
A Survey on Transfer Learning journal October 2010
Short-Term Load Forecasting With Deep Residual Networks journal July 2019
Clustering of Load Profiles of Residential Customers Using Extreme Points and Demographic Characteristics journal January 2021
Monthly Electric Load Forecasting Using Transfer Learning for Smart Cities journal August 2020
Performance of Deep Learning models with transfer learning for multiple-step-ahead forecasts in monthly time series journal December 2022

Similar Records

Related Subjects

LSTM
MATHEMATICS AND COMPUTING
POWER TRANSMISSION AND DISTRIBUTION
deep learning
load profile forecasting
transfer learning