Interpretable Multi-Sensor Fusion for Short-Term Energy Consumption Forecasting.
Saved in:
| Title: | Interpretable Multi-Sensor Fusion for Short-Term Energy Consumption Forecasting. |
|---|---|
| Authors: | Hasan, Rakibul1 (AUTHOR), Mansouri, Majdi2 (AUTHOR) m.mansouri@squ.edu.om, Arkhangelski, Jura1 (AUTHOR), Abdou Tankari, Mahamadou1,2 (AUTHOR) |
| Source: | Energies (19961073). May2026, Vol. 19 Issue 9, p2230. 21p. |
| Subject Terms: | *Multisensor data fusion, *Energy consumption forecasting, *Synchronization, *Machine learning |
| Abstract: | Accurate forecasting of energy consumption in sensor-rich environments remains challenging due to strong inter-sensor dependencies, temporal variability, and heterogeneous sensor behavior. This paper proposes a lightweight and interpretable multi-sensor fusion framework for short-term energy consumption forecasting. The heterogeneous sensor dataset is first preprocessed to handle missing values, outliers, and temporal misalignment, followed by synchronization of the multivariate signals on a common timeline to enable consistent learning. The proposed framework systematically investigates multiple strategies for exploiting information from synchronized multi-sensor data without performing explicit feature elimination or time-lag engineering. In particular, three fusion paradigms are considered: (i) Early Fusion, where all sensor measurements are jointly used as input features for a multivariate regression model; (ii) Late Fusion, where individual sensor predictors are trained independently and their outputs are combined using reliability-based weighting; and (iii) an attention-inspired fusion strategy, in which adaptive weights are assigned to sensor-level predictions based on their predictive reliability estimated from training errors and normalized via a softmax function. In addition, classical machine learning models including Random Forest (RF), Support Vector Regression (SVR), and Gradient Boosting (GB) are evaluated under the same experimental conditions to provide a consistent benchmark. Experimental results on a real-world building energy monitoring dataset consisting of nine heterogeneous sensors demonstrate that multi-sensor fusion approaches consistently improve forecasting performance compared to single-model baselines. Among the evaluated strategies, Late Fusion provides stable performance across strongly correlated loads, while the attention-inspired fusion strategy exhibits improved robustness when handling sensors with varying predictive reliability. To ensure robustness and reproducibility, results are reported using multiple chronological validation splits, with performance evaluated in terms of RMSE, MAE, and R 2 along with statistical measures including standard deviation and confidence intervals. The proposed framework provides a practical balance between predictive accuracy, interpretability, and computational efficiency, making it suitable for smart building energy management and real-world deployment scenarios. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: enr DbLabel: Energy & Power Source An: 193716126 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Interpretable Multi-Sensor Fusion for Short-Term Energy Consumption Forecasting. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Hasan%2C+Rakibul%22">Hasan, Rakibul</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mansouri%2C+Majdi%22">Mansouri, Majdi</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> m.mansouri@squ.edu.om</i><br /><searchLink fieldCode="AR" term="%22Arkhangelski%2C+Jura%22">Arkhangelski, Jura</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Abdou+Tankari%2C+Mahamadou%22">Abdou Tankari, Mahamadou</searchLink><relatesTo>1,2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. May2026, Vol. 19 Issue 9, p2230. 21p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Multisensor+data+fusion%22">Multisensor data fusion</searchLink><br />*<searchLink fieldCode="DE" term="%22Energy+consumption+forecasting%22">Energy consumption forecasting</searchLink><br />*<searchLink fieldCode="DE" term="%22Synchronization%22">Synchronization</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Accurate forecasting of energy consumption in sensor-rich environments remains challenging due to strong inter-sensor dependencies, temporal variability, and heterogeneous sensor behavior. This paper proposes a lightweight and interpretable multi-sensor fusion framework for short-term energy consumption forecasting. The heterogeneous sensor dataset is first preprocessed to handle missing values, outliers, and temporal misalignment, followed by synchronization of the multivariate signals on a common timeline to enable consistent learning. The proposed framework systematically investigates multiple strategies for exploiting information from synchronized multi-sensor data without performing explicit feature elimination or time-lag engineering. In particular, three fusion paradigms are considered: (i) Early Fusion, where all sensor measurements are jointly used as input features for a multivariate regression model; (ii) Late Fusion, where individual sensor predictors are trained independently and their outputs are combined using reliability-based weighting; and (iii) an attention-inspired fusion strategy, in which adaptive weights are assigned to sensor-level predictions based on their predictive reliability estimated from training errors and normalized via a softmax function. In addition, classical machine learning models including Random Forest (RF), Support Vector Regression (SVR), and Gradient Boosting (GB) are evaluated under the same experimental conditions to provide a consistent benchmark. Experimental results on a real-world building energy monitoring dataset consisting of nine heterogeneous sensors demonstrate that multi-sensor fusion approaches consistently improve forecasting performance compared to single-model baselines. Among the evaluated strategies, Late Fusion provides stable performance across strongly correlated loads, while the attention-inspired fusion strategy exhibits improved robustness when handling sensors with varying predictive reliability. To ensure robustness and reproducibility, results are reported using multiple chronological validation splits, with performance evaluated in terms of RMSE, MAE, and R 2 along with statistical measures including standard deviation and confidence intervals. The proposed framework provides a practical balance between predictive accuracy, interpretability, and computational efficiency, making it suitable for smart building energy management and real-world deployment scenarios. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=193716126 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/en19092230 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 21 StartPage: 2230 Subjects: – SubjectFull: Multisensor data fusion Type: general – SubjectFull: Energy consumption forecasting Type: general – SubjectFull: Synchronization Type: general – SubjectFull: Machine learning Type: general Titles: – TitleFull: Interpretable Multi-Sensor Fusion for Short-Term Energy Consumption Forecasting. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Hasan, Rakibul – PersonEntity: Name: NameFull: Mansouri, Majdi – PersonEntity: Name: NameFull: Arkhangelski, Jura – PersonEntity: Name: NameFull: Abdou Tankari, Mahamadou IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 05 Text: May2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 19961073 Numbering: – Type: volume Value: 19 – Type: issue Value: 9 Titles: – TitleFull: Energies (19961073) Type: main |
| ResultId | 1 |
