- Award ID(s):
- 1931980
- NSF-PAR ID:
- 10165854
- Date Published:
- Journal Name:
- Transportation Research Board Annual Meeting
- Volume:
- 20-03461
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Extracting User Behavior at Electric Vehicle Charging Stations with Transformer Deep Learning ModelsMobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications are used by drivers to locate charging stations in public spaces, pay for charging transactions, and engage with other users. This activity generates a rich source of data about charging infrastructure and behavior. However, an increasing share of this data is stored as unstructured text—inhibiting our ability to interpret behavior in real-time. In this article, we implement recent transformer-based deep learning algorithms, BERT and XLnet, that have been tailored to automatically classify short user reviews about EV charging experiences. We achieve classification results with a mean accuracy of over 91% and a mean F1 score of over 0.81 allowing for more precise detection of topic categories, even in the presence of highly imbalanced data. Using these classification algorithms as a pre-processing step, we analyze a U.S. national dataset with econometric methods to discover the dominant topics of discourse in charging infrastructure. After adjusting for station characteristics and other factors, we find that the functionality of a charging station is the dominant topic among EV drivers and is more likely to be discussed at points-of-interest with negative user experiences.more » « less
-
By displacing gasoline and diesel fuels, electric cars and fleets offer significant public health benefits by reducing emissions from the transportation sector. However, public confidence in the reliability of charging infrastructure remains a fundamental barrier to adoption. Using large-scale social data and machine learning based on 12,720 U.S. electric vehicle charging stations, we provide national evidence on how well the existing charging infrastructure is serving the needs of the expanding population of EV drivers in 651 core-based statistical areas in the United States. Contrary to predictions, we find that stations at private charging locations do not outperform public charging locations provided by government. We also find evidence of higher negative sentiment in the dense urban centers, where issues of charge rage and congestion may be the most prominent. Overall, 40% of drivers using mobility apps have faced negative experiences at EV charging stations, a problem that needs to be fixed as the market expands.more » « less
-
Abstract Problems of poor network interoperability in electric vehicle (EV) infrastructure, where data about real-time usage or consumption is not easily shared across service providers, has plagued the widespread analysis of energy used for transportation. In this article, we present a high-resolution dataset of real-time EV charging transactions resolved to the nearest second over a one-year period at a multi-site corporate campus. This includes 105 charging stations across 25 different facilities operated by a single firm in the U.S. Department of Energy Workplace Charging Challenge. The high-resolution data has 3,395 real-time transactions and 85 users with both paid and free sessions. The data has been expanded for re-use such as identifying charging behaviour and segmenting user groups by frequency of usage, stage of adoption, and employee type. Potential applications include but are not limited to simulating and parameterizing energy demand models; investigating flexible charge scheduling and optimal power flow problems; characterizing transportation emissions and electric mobility patterns at high temporal resolution; and evaluating characteristics of early adopters and lead user innovation.
-
Charging infrastructure is the coupling link between power and transportation networks, thus determining charging station siting is necessary for planning of power and transportation systems. While previous works have either optimized for charging station siting given historic travel behavior, or optimized fleet routing and charging given an assumed placement of the stations, this paper introduces a linear program that optimizes for station siting and macroscopic fleet operations in a joint fashion. Given an electricity retail rate and a set of travel demand requests, the optimization minimizes total cost for an autonomous EV fleet comprising of travel costs, station procurement costs, fleet procurement costs, and electricity costs, including demand charges. Specifically, the optimization returns the number of charging plugs for each charging rate (e.g., Level 2, DC fast charging) at each candidate location, as well as the optimal routing and charging of the fleet. From a case-study of an electric vehicle fleet operating in San Francisco, our results show that, albeit with range limitations, small EVs with low procurement costs and high energy efficiencies are the most cost-effective in terms of total ownership costs. Furthermore, the optimal siting of charging stations is more spatially distributed than the current siting of stations, consisting mainly of high-power Level 2 AC stations (16.8 kW) with a small share of DC fast charging stations and no standard 7.7kW Level 2 stations. Optimal siting reduces the total costs, empty vehicle travel, and peak charging load by up to 10%.more » « less
-
Abstract Understanding the societal impacts caused by community disruptions (e.g., power outages and road closures), particularly during the response stage, with timeliness and sufficient detail is an underexplored, yet important, consideration. It is critical for effective decision‐making and coordination in disaster response and relief activities as well as post‐disaster virtual reconnaissance activities. This study proposes a semiautomated social media analytics approach for social sensing of Disaster Impacts and Societal Considerations (SocialDISC). This approach addresses two limitations of existing social media analytics approaches: lacking adaptability to the need of different analyzers or different disasters and missing the information related to subjective feelings, emotions, and opinions of the people. SocialDISC labels and clusters social media posts in each disruption category to facilitate scanning by analyzers. Analyzers, in this paper, are persons who acquire social impact information from social media data (e.g., infrastructure management personnel, volunteers, researchers from academia, and some residents impacted by the disaster). Furthermore, SocialDISC enables analyzers to quickly parse topics and emotion signals of each subevent to assess the societal impacts caused by disruption events. To demonstrate the performance of SocialDISC, the authors proposed a case study based on Hurricane Harvey, one of the costliest disasters in U.S. history, and analyzed the disruptions and corresponding societal impacts in different aspects. The analysis result shows that Houstonians suffered greatly from flooded houses, lack of access to food and water, and power outages. SocialDISC can foster an understanding of the relationship between disruptions of infrastructures and societal impacts, expectations of the public when facing disasters, and infrastructure interdependency and cascading failures. SocialDISC's provision of timely information about the societal impacts of people may help disaster response decision‐making.