Summary of Location Based Probabilistic Load Forecasting Of Ev Charging Sites: Deep Transfer Learning with Multi-quantile Temporal Convolutional Network, by Mohammad Wazed Ali (intelligent Embedded Systems (ies) et al.
Location based Probabilistic Load Forecasting of EV Charging Sites: Deep Transfer Learning with Multi-Quantile Temporal Convolutional Network
by Mohammad Wazed Ali, Asif bin Mustafa, Md. Aukerul Moin Shuvo, Bernhard Sick
First submitted to arxiv on: 18 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a deep learning-based model to forecast the charging demand of electric vehicles (EVs) at various locations, taking into account diverse user profiles and energy demand patterns. The Multi-Quantile Temporal Convolutional Network (MQ-TCN) model is designed to overcome limitations of previous data-driven load models by being simultaneously adaptive, cost-effective, and able to transfer knowledge among different EV charging sites. The authors conducted experiments on data from four charging sites, achieving a remarkable 28.93% improvement over the XGBoost model for day-ahead load forecasting at one site, with a prediction interval coverage probability (PICP) score of 93.62%. By applying transfer learning, the MQ-TCN model achieved a PICP score of 96.88% for another site using only two weeks of data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores ways to reduce fossil fuel usage and environmental pollution by developing a better understanding of electric vehicle charging demand patterns. The authors use a deep learning-based model called Multi-Quantile Temporal Convolutional Network (MQ-TCN) to forecast EV charging demands at different locations. They find that this approach can improve predictions compared to previous methods, even when using limited data. |
Keywords
» Artificial intelligence » Convolutional network » Deep learning » Probability » Transfer learning » Xgboost
