skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Black Swan Event Small-Sample Transfer Learning (BEST-L) and its Case Study on Electrical Power Prediction in COVID-19

Journal Article · · Applied Energy

The black swan event will usually cause a great impact on the normal operation of society. The scarcity of such events leads to a lack of relevant data and challenges in dealing with related problems. Different situations also make the traditional methods invalid. In this paper, a transfer learning framework and a convolutional neuron network are proposed to deal with the black swan small-sample events (BEST-L). Taking the COVID-19 as a typical black swan event, the BEST-L is utilized to achieve accurate mid-term load forecasting using the relationship between economy and electricity consumption. The experiment results show that the transfer learning model can effectively learn the basic knowledge about the relationship between the adopted input and output data and use a relatively small amount of data during the black swan event to improve the target areas' generalization. The approach and results can provide an effective approach to respond and react to sudden changes quickly and effectively in similar open problems.

Research Organization:
National Renewable Energy Lab. (NREL), Golden, CO (United States)
Sponsoring Organization:
USDOE Office of Energy Efficiency and Renewable Energy (EERE)
DOE Contract Number:
AC36-08GO28308
OSTI ID:
1843373
Report Number(s):
NREL/JA-5D00-82003; MainId:82776; UUID:45e6d037-f755-4286-a613-f9c10db6f16e; MainAdminID:63773
Journal Information:
Applied Energy, Vol. 309
Country of Publication:
United States
Language:
English

References (33)

Deep transfer learning for reducing health care disparities arising from biomedical data inequality journal October 2020
A Survey on Transfer Learning journal October 2010
A survey of transfer learning journal May 2016
Improved TrAdaBoost and its Application to Transaction Fraud Detection journal October 2020
Deep transfer Q-learning with virtual leader-follower for supply-demand Stackelberg game of smart grid journal August 2017
Equilibrium-inspired multiagent optimizer with extreme transfer learning for decentralized optimal carbon-energy combined-flow of large-scale power systems journal March 2017
COVID-19: immunopathology and its implications for therapy journal April 2020
The socio-economic implications of the coronavirus pandemic (COVID-19): A review journal June 2020
COVID-19 and the policy sciences: initial reactions and perspectives journal April 2020
Characterizing the Propagation of Situational Information in Social Media During COVID-19 Epidemic: A Case Study on Weibo journal April 2020
COVID ‐19 and economy journal April 2020
COVID-19: Impact analysis and recommendations for power sector operation journal December 2020
Cascading risks: Understanding the 2021 winter blackout in Texas journal July 2021
What does the GB power outage on 9 August 2019 tell us about the current state of decarbonised power systems? journal November 2020
Transfer learning with seasonal and trend adjustment for cross-building energy forecasting journal April 2018
Domain adaptation transfer learning soft sensor for product quality prediction journal September 2019
Development of Adversarial Transfer Learning Soft Sensor for Multigrade Processes journal August 2020
A concise peephole model based transfer learning method for small sample temporal feature-based data-driven quality analysis journal May 2020
Potential analysis of the transfer learning model in short and medium-term forecasting of building HVAC energy consumption journal February 2020
Deep learning and transfer learning models of energy consumption forecasting for a building with poor information data journal September 2020
Deep learning applications and challenges in big data analytics journal February 2015
Going deeper with convolutions conference June 2015
A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction journal March 2018
Research on Influence Factors and Behavioral Willing of User PrivacyConcern on Social Network Platform journal August 2013
Standardization and Its Effects on K-Means Clustering Algorithm journal September 2013
A Cross-Domain Approach to Analyzing the Short-Run Impact of COVID-19 on the US Electricity Sector journal November 2020
Trend analyses of electricity load changes in Brazil due to COVID-19 shutdowns journal April 2021
On electricity consumption and economic growth in China journal September 2017
Prediction-based analysis on power consumption gap under long-term emergency: A case in China under COVID-19 journal February 2021
Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming journal February 2011
machine. journal October 2001
Problematic standard errors and confidence intervals for skewness and kurtosis journal February 2011
Statistical notes for clinical researchers: assessing normal distribution (2) using skewness and kurtosis journal January 2013