Evaluation of Traditional and Data-Driven Algorithms for Energy Disaggregation Under Sampling and Filtering Conditions
Non-intrusive load monitoring (NILM) enables the disaggregation of appliance-level energy consumption from aggregate electrical signals, offering a scalable solution for improving efficiency. This study compared the performance of traditional NILM algorithms (Mean, CO, Hart85, FHMM) and deep neural...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Inventions |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2411-5134/10/3/43 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849471991874060288 |
|---|---|
| author | Carlos Rodriguez-Navarro Francisco Portillo Isabel Robalo Alfredo Alcayde |
| author_facet | Carlos Rodriguez-Navarro Francisco Portillo Isabel Robalo Alfredo Alcayde |
| author_sort | Carlos Rodriguez-Navarro |
| collection | DOAJ |
| description | Non-intrusive load monitoring (NILM) enables the disaggregation of appliance-level energy consumption from aggregate electrical signals, offering a scalable solution for improving efficiency. This study compared the performance of traditional NILM algorithms (Mean, CO, Hart85, FHMM) and deep neural network-based approaches (DAE, RNN, Seq2Point, Seq2Seq, WindowGRU) under various experimental conditions. Factors such as sampling rate, harmonic content, and the application of power filters were analyzed. A key aspect of the evaluation was the difference in testing conditions: while traditional algorithms were evaluated under multiple experimental configurations, deep learning models, due to their extremely high computational cost, were analyzed exclusively under a specific configuration consisting of a 1-s sampling rate, with harmonic content present and without applying power filters. The results confirm that no universally superior algorithm exists, and performance varies depending on the type of appliance and signal conditions. Traditional algorithms are faster and more computationally efficient, making them more suitable for scenarios with limited resources or rapid response requirements. However, significantly more computationally expensive deep learning models showed higher average accuracy (MAE, RMSE, NDE) and event detection capability (F1-SCORE) in the specific configuration in which they were evaluated. These models excel in detailed signal reconstruction and handling harmonics without requiring filtering in this configuration. The selection of the optimal NILM algorithm for real-world applications must consider a balance between desired accuracy, load types, electrical signal characteristics, and crucially, the limitations of available computational resources. |
| format | Article |
| id | doaj-art-99a5074820da4a0cade4524358d31c1d |
| institution | Kabale University |
| issn | 2411-5134 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Inventions |
| spelling | doaj-art-99a5074820da4a0cade4524358d31c1d2025-08-20T03:24:39ZengMDPI AGInventions2411-51342025-06-011034310.3390/inventions10030043Evaluation of Traditional and Data-Driven Algorithms for Energy Disaggregation Under Sampling and Filtering ConditionsCarlos Rodriguez-Navarro0Francisco Portillo1Isabel Robalo2Alfredo Alcayde3Department of Engineering, University of Almeria, ceiA3, 04120 Almeria, SpainDepartment of Engineering, University of Almeria, ceiA3, 04120 Almeria, SpainDepartment of Engineering, University of Almeria, ceiA3, 04120 Almeria, SpainDepartment of Engineering, University of Almeria, ceiA3, 04120 Almeria, SpainNon-intrusive load monitoring (NILM) enables the disaggregation of appliance-level energy consumption from aggregate electrical signals, offering a scalable solution for improving efficiency. This study compared the performance of traditional NILM algorithms (Mean, CO, Hart85, FHMM) and deep neural network-based approaches (DAE, RNN, Seq2Point, Seq2Seq, WindowGRU) under various experimental conditions. Factors such as sampling rate, harmonic content, and the application of power filters were analyzed. A key aspect of the evaluation was the difference in testing conditions: while traditional algorithms were evaluated under multiple experimental configurations, deep learning models, due to their extremely high computational cost, were analyzed exclusively under a specific configuration consisting of a 1-s sampling rate, with harmonic content present and without applying power filters. The results confirm that no universally superior algorithm exists, and performance varies depending on the type of appliance and signal conditions. Traditional algorithms are faster and more computationally efficient, making them more suitable for scenarios with limited resources or rapid response requirements. However, significantly more computationally expensive deep learning models showed higher average accuracy (MAE, RMSE, NDE) and event detection capability (F1-SCORE) in the specific configuration in which they were evaluated. These models excel in detailed signal reconstruction and handling harmonics without requiring filtering in this configuration. The selection of the optimal NILM algorithm for real-world applications must consider a balance between desired accuracy, load types, electrical signal characteristics, and crucially, the limitations of available computational resources.https://www.mdpi.com/2411-5134/10/3/43energy disaggregationnon-intrusive load monitoringMAERMSEF1-SCORENDE |
| spellingShingle | Carlos Rodriguez-Navarro Francisco Portillo Isabel Robalo Alfredo Alcayde Evaluation of Traditional and Data-Driven Algorithms for Energy Disaggregation Under Sampling and Filtering Conditions Inventions energy disaggregation non-intrusive load monitoring MAE RMSE F1-SCORE NDE |
| title | Evaluation of Traditional and Data-Driven Algorithms for Energy Disaggregation Under Sampling and Filtering Conditions |
| title_full | Evaluation of Traditional and Data-Driven Algorithms for Energy Disaggregation Under Sampling and Filtering Conditions |
| title_fullStr | Evaluation of Traditional and Data-Driven Algorithms for Energy Disaggregation Under Sampling and Filtering Conditions |
| title_full_unstemmed | Evaluation of Traditional and Data-Driven Algorithms for Energy Disaggregation Under Sampling and Filtering Conditions |
| title_short | Evaluation of Traditional and Data-Driven Algorithms for Energy Disaggregation Under Sampling and Filtering Conditions |
| title_sort | evaluation of traditional and data driven algorithms for energy disaggregation under sampling and filtering conditions |
| topic | energy disaggregation non-intrusive load monitoring MAE RMSE F1-SCORE NDE |
| url | https://www.mdpi.com/2411-5134/10/3/43 |
| work_keys_str_mv | AT carlosrodrigueznavarro evaluationoftraditionalanddatadrivenalgorithmsforenergydisaggregationundersamplingandfilteringconditions AT franciscoportillo evaluationoftraditionalanddatadrivenalgorithmsforenergydisaggregationundersamplingandfilteringconditions AT isabelrobalo evaluationoftraditionalanddatadrivenalgorithmsforenergydisaggregationundersamplingandfilteringconditions AT alfredoalcayde evaluationoftraditionalanddatadrivenalgorithmsforenergydisaggregationundersamplingandfilteringconditions |