Identifying household EV models via weighted power recurrence graphs
- Publisher:
- ELSEVIER SCIENCE SA
- Publication Type:
- Journal Article
- Citation:
- Electric Power Systems Research, 2023, 217
- Issue Date:
- 2023-04-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
1-s2.0-S037877962300010X-main.pdf | Published version | 2.62 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Electric vehicles (EVs) are becoming the mainstream transport means in the near future and will play an important role in smart grids with the benefit of energy storage and power factor improvement. Identifying the EV models connected to the power grid for accurate balance in Vehicle-to-Grid and Vehicle-for-Grid operations is crucial. This paper proposes a novel non-intrusive load monitoring (NILM) method based on Weighted Power Recurrence Graphs (WPRG) at a 16.5 kHz sampling rate to accomplish EV model identification irrespective of brand and state of charge (SOC). WPRG can consider the relationship between voltages and currents and thus increase the variance of original electrical current values by using the extracted current and voltage waveforms. The proposed method is tested in a synthetic dataset composed of simulated EV charging loads combined with SOC information and a real-world household appliance dataset. The proposed WPRG method is compared with two weighted-based methods in the NILM background. The proposed WPRG method shows superior performance in identifying EV models and other household appliances than the other two weighted-based methods, with an overall macro F1-score of 94.3% in identifying the whole charging loads in households.
Please use this identifier to cite or link to this item: