skip to main content

Explore Research Products in the NSF-PAR

Title: Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation
Electric Vehicle (EV) charging recommendation that both accommodates user preference and adapts to the ever-changing external environment arises as a cost-effective strategy to alleviate the range anxiety of private EV drivers. Previous studies focus on centralized strategies to achieve optimized resource allocation, particularly useful for privacy-indifferent taxi fleets and fixed-route public transits. However, private EV driver seeks a more personalized and resource-aware charging recommendation that is tailor-made to accommodate the user preference (when and where to charge) yet sufficiently adaptive to the spatiotemporal mismatch between charging supply and demand. Here we propose a novel Regularized Actor-Critic (RAC) charging recommendation approach that would allow each EV driver to strike an optimal balance between the user preference (historical charging pattern) and the external reward (driving distance and wait time). Experimental results on two real-world datasets demonstrate the unique features and superior performance of our approach to the competing methods.  more » « less
Award ID(s):
1724227
NSF-PAR ID:
10488011
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
Springer, Cham
Date Published:
Journal Name:
Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022
Subject(s) / Keyword(s):
["actor critic","charging recommendation","electric vehicle (EV)","user preference","external reward"]
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ( , Machine Learning and Knowledge Discovery in Databases)
    Amini, MR ; Canu, S. ; Fischer, A. ; Guns, T. ; Kralj Novak, P. ; Tsoumakas, G. (Ed.)
    Electric Vehicle (EV) charging recommendation that both accommodates user preference and adapts to the ever-changing external environment arises as a cost-effective strategy to alleviate the range anxiety of private EV drivers. Previous studies focus on centralized strategies to achieve optimized resource allocation, particularly useful for privacy-indifferent taxi fleets and fixed-route public transits. However, private EV driver seeks a more personalized and resource-aware charging recommendation that is tailor-made to accommodate the user preference (when and where to charge) yet sufficiently adaptive to the spatiotemporal mismatch between charging supply and demand. Here we propose a novel Regularized Actor-Critic (RAC) charging recommendation approach that would allow each EV driver to strike an optimal balance between the user preference (historical charging pattern) and the external reward (driving distance and wait time). Experimental results on two real-world datasets demonstrate the unique features and superior performance of our approach to the competing methods. 
    more » « less
  2. ; ; ; ( , Transportation Research Board Annual Meeting)
    There is a growing interest in applying computational tools to the automatic discovery of social and economic behavior. For example, with decisions involving resource allocation related to public infrastructure, the ability to predict failures can allow for more efficient policy responses. In this paper, we use social data from a popular electric vehicle (EV) driver app to characterize the emerging EV charging station infrastructure. We introduce a typology of EV charging experiences collected from user reviews and deploy text classification algorithms, including convolutional neural networks (CNN), to automatically learn about potential failures. We use machine learning techniques as a pre-processing tool for econometric analyses on the quality of service delivery. After classifying the reviews into 9 main user topics and 34 subtopics, we find that the dominant issues in EV charging relate to station functionality and availability, which drive negative consumer experience. Contrary to the public discourse about EVs, range anxiety was not of large concern to existing EV drivers. Based on our findings, we move towards automated identification of failures in public charging infrastructure that can significantly reduce research evaluation costs through relatively simple computational solutions. 
    more » « less
  3. ; ( , Beyond: Undergraduate Research Journal)
    An analysis was done to find the emerging location(s) for the electrical vertical takeoff and landing (eVTOL) industry. The VTOL and eVTOL industries are aiming to replace short private jet travel as helicopters will have the ability to cut out some of the driving. For instance, it can bring a client to the top of a skyscraper because heliports and vertiports can be positioned almost anywhere making them more accessible than private jets. Initially, a numerical analysis was done to see how the past could predict the future, which showed electric vehicle (eV) charging stations have been exponentially rising while heliports have been declining. This was used in the analysis when choosing the criteria to analyze. It was determined that the final recommendation for the emerging location of the eVTOL industry would use the following: 25% Flexjet data, 25% eV charging stations, 25% population density, and 25% median household income. The Flexjet flight data reflected the busiest airports for flights 30 minutes or less for departures and arrivals. The eV charging station data showed which states have the largest number of charging stations at parking lots or garages, since they can be converted to vertiports in the future. The population density and median household income showed the top 10 cities in the US for each, respectively. This led to a final score given for every state and showed New York would be the emerging location for the eVTOL industry based on the data and scoring. This led to recommendations given to OneSky for New York. 
    more » « less
  4. ; ; ; ; ; ( , Proceedings of the AAAI Conference on Artificial Intelligence)
    Hashtags can greatly facilitate content navigation and improve user engagement in social media. Meaningful as it might be, recommending hashtags for photo sharing services such as Instagram and Pinterest remains a daunting task due to the following two reasons. On the endogenous side, posts in photo sharing services often contain both images and text, which are likely to be correlated with each other. Therefore, it is crucial to coherently model both image and text as well as the interaction between them. On the exogenous side, hashtags are generated by users and different users might come up with different tags for similar posts, due to their different preference and/or community effect. Therefore, it is highly desirable to characterize the users’ tagging habits. In this paper, we propose an integral and effective hashtag recommendation approach for photo sharing services. In particular, the proposed approach considers both the endogenous and exogenous effects by a content modeling module and a habit modeling module, respectively. For the content modeling module, we adopt the parallel co-attention mechanism to coherently model both image and text as well as the interaction between them; for the habit modeling module, we introduce an external memory unit to characterize the historical tagging habit of each user. The overall hashtag recommendations are generated on the basis of both the post features from the content modeling module and the habit influences from the habit modeling module. We evaluate the proposed approach on real Instagram data. The experimental results demonstrate that the proposed approach significantly outperforms the state-of-theart methods in terms of recommendation accuracy, and that both content modeling and habit modeling contribute significantly to the overall recommendation accuracy. 
    more » « less
  5. ; ; ; ; ; ( , BuildSys '22: Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation)
    The fast development of electric vehicles (EV) and EV chargers introduces many factors that affect the grid. EV charging and charge scheduling also bring challenges to EV drivers and grid operators. In this work, we propose a human-centric, data-driven, city-scale, multivariate optimization approach for the EV-interfaced grid. This approach takes into account user historical driving and charging habits, user preferences, EV characteristics, city-scale mobility, EV charger availability and price, and grid capacity. The user preferences include the trade-off between cost and time to charge, as well as incentives to participate in different energy-saving programs. We leverage deep reinforcement learning (DRL) to make recommendations to EV drivers and optimize their welfare while enhancing grid performance. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email