Contextual Sequence-to-Point Deep Learning for Household Energy Disaggregation
This paper examines a contextual paradigm for energy disaggregation using Non-Intrusive Load Monitoring (NILM). Due to numerous issues including low sampling rates, missing data, misaligned readings, and diverse combinations of nonlinear and multi-state appliances, this problem is challenging and co...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10188822/ |
| _version_ | 1797771727959228416 |
|---|---|
| author | Mohammed Ayub El-Sayed M. El-Alfy |
| author_facet | Mohammed Ayub El-Sayed M. El-Alfy |
| author_sort | Mohammed Ayub |
| collection | DOAJ |
| description | This paper examines a contextual paradigm for energy disaggregation using Non-Intrusive Load Monitoring (NILM). Due to numerous issues including low sampling rates, missing data, misaligned readings, and diverse combinations of nonlinear and multi-state appliances, this problem is challenging and complex. We proposed two different deep learning models for household energy disaggregation with shared parameter learning based on Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs). The proposed models utilize a sliding window of the main aggregate power readings to predict the per-appliance consumption at the end point of the sequence; using the entire input sequence gives more contextual information and reduces the prediction complexity in other problem settings. We evaluated the performance using two benchmark datasets, ENERTALK and UK-DALE, under different scenarios including sampling rates, imputation methods, cross-dataset generalization, and single and multi-target settings. The results demonstrate that the proposed models show better robustness and generalization capability than the other sequence-to-point models when no consumption information is discarded in the alignment process, especially for cross-domain disaggregation. |
| first_indexed | 2024-03-12T21:40:48Z |
| format | Article |
| id | doaj.art-d1c10ff6a26a46f6ac267c910f865bba |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T21:40:48Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d1c10ff6a26a46f6ac267c910f865bba2023-07-26T23:00:37ZengIEEEIEEE Access2169-35362023-01-0111755997561610.1109/ACCESS.2023.329755210188822Contextual Sequence-to-Point Deep Learning for Household Energy DisaggregationMohammed Ayub0https://orcid.org/0000-0002-1811-4933El-Sayed M. El-Alfy1https://orcid.org/0000-0001-6279-9776Department of Information and Computer Science, College of Computing and Mathematics, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi ArabiaSDAIA-KFUPM Joint Research Center for Artificial Intelligence (SDAIA JRC-AI), Dhahran, Saudi ArabiaThis paper examines a contextual paradigm for energy disaggregation using Non-Intrusive Load Monitoring (NILM). Due to numerous issues including low sampling rates, missing data, misaligned readings, and diverse combinations of nonlinear and multi-state appliances, this problem is challenging and complex. We proposed two different deep learning models for household energy disaggregation with shared parameter learning based on Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs). The proposed models utilize a sliding window of the main aggregate power readings to predict the per-appliance consumption at the end point of the sequence; using the entire input sequence gives more contextual information and reduces the prediction complexity in other problem settings. We evaluated the performance using two benchmark datasets, ENERTALK and UK-DALE, under different scenarios including sampling rates, imputation methods, cross-dataset generalization, and single and multi-target settings. The results demonstrate that the proposed models show better robustness and generalization capability than the other sequence-to-point models when no consumption information is discarded in the alignment process, especially for cross-domain disaggregation.https://ieeexplore.ieee.org/document/10188822/Smart meteringsmart gridsmart buildingsdeep learningsmart utilityenergy disaggregation |
| spellingShingle | Mohammed Ayub El-Sayed M. El-Alfy Contextual Sequence-to-Point Deep Learning for Household Energy Disaggregation IEEE Access Smart metering smart grid smart buildings deep learning smart utility energy disaggregation |
| title | Contextual Sequence-to-Point Deep Learning for Household Energy Disaggregation |
| title_full | Contextual Sequence-to-Point Deep Learning for Household Energy Disaggregation |
| title_fullStr | Contextual Sequence-to-Point Deep Learning for Household Energy Disaggregation |
| title_full_unstemmed | Contextual Sequence-to-Point Deep Learning for Household Energy Disaggregation |
| title_short | Contextual Sequence-to-Point Deep Learning for Household Energy Disaggregation |
| title_sort | contextual sequence to point deep learning for household energy disaggregation |
| topic | Smart metering smart grid smart buildings deep learning smart utility energy disaggregation |
| url | https://ieeexplore.ieee.org/document/10188822/ |
| work_keys_str_mv | AT mohammedayub contextualsequencetopointdeeplearningforhouseholdenergydisaggregation AT elsayedmelalfy contextualsequencetopointdeeplearningforhouseholdenergydisaggregation |