Denoising Masked Autoencoder-Based Missing Imputation within Constrained Environments for Electric Load Data
With recent advancements in data technologies, particularly machine learning, research focusing on the enhancement of energy efficiency in residential, commercial, and industrial settings through the collection of load data, such as heat, electricity, and gas, has gained significant attention. Never...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/24/7933 |
| _version_ | 1797381257984737280 |
|---|---|
| author | Jaeik Jeong Tai-Yeon Ku Wan-Ki Park |
| author_facet | Jaeik Jeong Tai-Yeon Ku Wan-Ki Park |
| author_sort | Jaeik Jeong |
| collection | DOAJ |
| description | With recent advancements in data technologies, particularly machine learning, research focusing on the enhancement of energy efficiency in residential, commercial, and industrial settings through the collection of load data, such as heat, electricity, and gas, has gained significant attention. Nevertheless, issues arising from hardware- or network-related problems can result in missing data, necessitating the development of management techniques to mitigate these challenges. Traditional methods for missing imputation face difficulties when operating in constrained environments characterized by short data collection periods and frequent consecutive missing. In this paper, we introduce the denoising masked autoencoder (DMAE) model as a solution to improve the handling of missing data, even in such restrictive settings. The proposed DMAE model capitalizes on the advantages of the denoising autoencoder (DAE), enabling effective learning of the missing imputation process, even with relatively small datasets, and the masked autoencoder (MAE), allowing for learning in environments with a high missing ratio. By integrating these strengths, the DMAE model achieves an enhanced performance in terms of missing imputation. The simulation results demonstrate that the proposed DMAE model outperforms the DAE or MAE significantly in a constrained environment where the duration of the training data is short, less than a year, and missing values occur frequently with durations ranging from 3 h to 12 h. |
| first_indexed | 2024-03-08T20:49:49Z |
| format | Article |
| id | doaj.art-703d9d8ac3c54cfba5bd28fc1dada4ce |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-08T20:49:49Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-703d9d8ac3c54cfba5bd28fc1dada4ce2023-12-22T14:05:33ZengMDPI AGEnergies1996-10732023-12-011624793310.3390/en16247933Denoising Masked Autoencoder-Based Missing Imputation within Constrained Environments for Electric Load DataJaeik Jeong0Tai-Yeon Ku1Wan-Ki Park2Energy ICT Research Section, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of KoreaEnergy ICT Research Section, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of KoreaEnergy ICT Research Section, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of KoreaWith recent advancements in data technologies, particularly machine learning, research focusing on the enhancement of energy efficiency in residential, commercial, and industrial settings through the collection of load data, such as heat, electricity, and gas, has gained significant attention. Nevertheless, issues arising from hardware- or network-related problems can result in missing data, necessitating the development of management techniques to mitigate these challenges. Traditional methods for missing imputation face difficulties when operating in constrained environments characterized by short data collection periods and frequent consecutive missing. In this paper, we introduce the denoising masked autoencoder (DMAE) model as a solution to improve the handling of missing data, even in such restrictive settings. The proposed DMAE model capitalizes on the advantages of the denoising autoencoder (DAE), enabling effective learning of the missing imputation process, even with relatively small datasets, and the masked autoencoder (MAE), allowing for learning in environments with a high missing ratio. By integrating these strengths, the DMAE model achieves an enhanced performance in terms of missing imputation. The simulation results demonstrate that the proposed DMAE model outperforms the DAE or MAE significantly in a constrained environment where the duration of the training data is short, less than a year, and missing values occur frequently with durations ranging from 3 h to 12 h.https://www.mdpi.com/1996-1073/16/24/7933denoising autoencodermasked autoencodermissing imputationelectric load data |
| spellingShingle | Jaeik Jeong Tai-Yeon Ku Wan-Ki Park Denoising Masked Autoencoder-Based Missing Imputation within Constrained Environments for Electric Load Data Energies denoising autoencoder masked autoencoder missing imputation electric load data |
| title | Denoising Masked Autoencoder-Based Missing Imputation within Constrained Environments for Electric Load Data |
| title_full | Denoising Masked Autoencoder-Based Missing Imputation within Constrained Environments for Electric Load Data |
| title_fullStr | Denoising Masked Autoencoder-Based Missing Imputation within Constrained Environments for Electric Load Data |
| title_full_unstemmed | Denoising Masked Autoencoder-Based Missing Imputation within Constrained Environments for Electric Load Data |
| title_short | Denoising Masked Autoencoder-Based Missing Imputation within Constrained Environments for Electric Load Data |
| title_sort | denoising masked autoencoder based missing imputation within constrained environments for electric load data |
| topic | denoising autoencoder masked autoencoder missing imputation electric load data |
| url | https://www.mdpi.com/1996-1073/16/24/7933 |
| work_keys_str_mv | AT jaeikjeong denoisingmaskedautoencoderbasedmissingimputationwithinconstrainedenvironmentsforelectricloaddata AT taiyeonku denoisingmaskedautoencoderbasedmissingimputationwithinconstrainedenvironmentsforelectricloaddata AT wankipark denoisingmaskedautoencoderbasedmissingimputationwithinconstrainedenvironmentsforelectricloaddata |