An instance based multi-source transfer learning strategy for building’s short-term electricity loads prediction under sparse data scenarios
Authors:
- Borui WeiBWBorui Wei
- Kangji LiKangji Li
- Shiyi ZhouSZShiyi Zhou
- Wenping XueWenping Xue
- Gang TanGTGang Tan
- 8 February 2024
- journal article
- research article
- Published by Elsevier in Journal of Building Engineering
- Vol. 85
Abstract
No abstract availableKeywords
Funding Information
- Six Talent Climax Foundation of Jiangsu
- National Natural Science Foundation of China
This publication has 34 references indexed in Scilit:
- A review of the-state-of-the-art in data-driven approaches for building energy predictionEnergy and Buildings, 2020
- A bi-directional missing data imputation scheme based on LSTM and transfer learning for building energy dataEnergy and Buildings, 2020
- Statistical investigations of transfer learning-based methodology for short-term building energy predictionsApplied Energy, 2020
- Similarity-Based Chained Transfer Learning for Energy Forecasting With Big DataIEEE Access, 2019
- A learning framework based on weighted knowledge transfer for holiday load forecastingJournal of Modern Power Systems and Clean Energy, 2018
- A hybrid model based on selective ensemble for energy consumption forecasting in ChinaEnergy, 2018
- A survey of transfer learningJournal of Big Data, 2016
- Boosting for transfer learning2007
- Long Short-Term MemoryNeural Computation, 1997
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997