Science AI Journal
Engineering · Research topic

Open research questions in Electric Vehicles and Infrastructure

38 unresolved questions extracted from the limitations and future-work sections of 565 Electric Vehicles and Infrastructure papers in our library. Each links back to the study that raised it.

What the literature leaves open

  • While effective in well-connected regions, this tendency often leads to infeasible choices when charging opportunities are sparse, since the agent does not explicitly account for the energy constraints that govern long-distance EV travel.

    Adaptive primal–dual Q-learning for electric vehicle route optimization on real-world charging networks · 2026 · DOI

  • Logistics shared electric vehicles (LSEVs) enhance emergency flexibility, yet competition and sustainability between incumbent and entrant LSEV operators remain underexplored.

    The Complexity of Dynamic Pricing in the Logistics‐Shared Electric Vehicle Market Under the Circumstances of Operator Platform Game Cooperation and Total Carbon Emission Control and Its Application · 2026 · DOI

  • Jaspreet Singh1, Smitha Girja2 1Research Scholar, Department School of Management, GD Goenka University, 2 Professor, Dean School of Management, Department School of Management GD Goenka…

    Adoption Barriers of EV Infrastructure in India: A Stakeholder Perspective · 2026 · DOI

  • In Jakarta, Indonesia, the rated power of public electric vehicle charging stations varies widely from 7 kW to 480 kW, indicating diverse charging service levels.

    Data-Driven Classification of Public Electric Vehicle Charging Station Power Using K-Means Clustering: A Case Study in Jakarta, Indonesia · 2026 · DOI

  • All traditional single-type energy storage technologies have inherent, irreconcilable flaws: the power density of pure battery energy storage is insufficient to withstand the peak load shocks of fast-charging stations, while pure supercapacitor energy storage has low energy density and high full-lifecycle costs, which makes it unable to independently meet the operational requirements of long-duration fast-charging services.

    MULTI-OBJECTIVE OPTIMIZATION OF HYBRID BATTERY-SUPERCAPACITOR ENERGY STORAGE SYSTEMS: MACHINE LEARNING-ENHANCED PERFORMANCE FOR FAST-CHARGING ELECTRIC VEHICLE INFRASTRUCTURE · 2026 · DOI

  • 6 Conclusions, scalability and limitations of this study, and future work This study designed an ocean energy-supported energy sharing network via EVs between the office and hotel buildings, using a combined approach of TRNSYS 18 and JEplus + EA to optimise the design of the ocean energy system for the stakeholders to maximise both economic and environmental objectives. Thus, the number of EVs is a sensitive variable for the proposed EV-based energy sharing system, and its number should be limited to a small range to facilitate effective energy usage efficiency for such a RE-based system.

    NSGA-II-based cost-optimal design for renewable energy sharing systems between urban buildings via electric vehicles · 2026 · DOI

  • Conclusion In this paper we presented a working EV route planning system that brings together three pieces: a physics- grounded synthetic data pipeline that makes it possible to train models without proprietary driving logs, a Gradient Boosting Regressor whose predictions land above 0.95 R² and are clamped to physically sensible bounds, and a greedy routing algorithm with practical safeguards against loops, backward detours, and battery exhaustion. The three-tier architecture, Flutter on the phone, FastAPI on the server, real-time APIs filling in the gaps, keeps each component replaceable. If better training data comes along, we can retrain the model without touching the app. If a smarter routing algorithm is developed, it slots into the backend without any changes to the frontend. The user-facing degradation slider adds a personal touch that most existing tools lack.

    Intelligent Electric Vehicle Route Planning System with ML-Based Energy Consumption Prediction · 2026 · DOI

  • 1) Collect real driving data through OBD-II dongles and retrain the model on actual telemetry. 2) Replace the greedy algorithm with energy-aware shortest-path methods like those in and. 3) Incorporate live charger availability and power output through the OCPP protocol. Page 630 www.rsisinternational.org INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING, MANAGEMENT & APPLIED SCIENCE (IJLTEMAS) ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue IV, April 2026 4) Add real-time traffic data from services like TomTom or HERE Maps. 5) Support multi-stop trips where the driver wants to visit specific places along the way. 6) Explore federated learning so that multiple users can improve the model without sharing raw data. 7) Investigate vehicle-to-grid (V2G) aware charging that considers electricity grid demand. 8) Experiment with deep reinforcement learning for adaptive, self-improving route optimization. ACKNOWLEDGMENT We would like to thank the Department of AI and Data Science at Vasantdada Patil Pratishthan’s College of Engineering and Visual Arts for providing the computing resources and academic support that made this project possible. REFERENCES 1. IEA, “Global EV Outlook 2024,” Paris, 2024. 2. A. Artmeier et al., “Optimal routing for EVs,” KI 2010, pp. 309–316. 3. M. Baum et al., “Energy-optimal EV routes,” 21st SIGSPATIAL, pp. 54–63, 2013. 4. T. Chen, C. Guestrin, “XGBoost,” 22nd KDD, pp. 785–794, 2016. 5. J. Friedman, “Gradient boosting,” Ann. Stat., vol. 29, pp. 1189–1232, 2001. 6. S. De Cauwer et al., “Energy prediction,” Energies, vol. 10, p. 1013, 2017. 7. F. Pedregosa et al., “Scikit-learn,” JMLR, vol. 12, pp. 2825–2830, 2011. 8. S. Ramírez, “FastAPI,” 2024. 9. OSM, “Nominatim,” 2024. 10. D. Luxen, C. Vetter, “OSRM,” 19th SIGSPATIAL, pp. 513–516, 2011. 11. OpenChargeMap, “API docs,” 2024. 12. OpenWeatherMap, “Weather API,” 2024. 13. Flutter Team, “Flutter,” Google, 2024. 14. J. Vepsäläinen et al., “Electric bus energy,” Energy, vol. 169, pp. 433–443, 2019. 15. R. Galvin, “Speed effects on EVs,” Trans. Res. D, vol. 53, pp. 234–248, 2017. 16. A. Fetene et al., “Big data EV energy,” Trans. Res. D, vol. 54, pp. 1–11, 2017. 17. M. Steinstraeter et al., “Low temp EVs,” World EV J., vol. 12, p. 115, 2021. 18. J. Betz et al., “Autonomous driving,” IEEE Access, vol. 10, pp. 99131–99168, 2022. 19. P. Keil, A. Jossen, “Li-ion aging,” World EV J., vol. 7, pp. 41–51, 2015. 20. D. Wang et al., “EV battery degradation,” J. Power Sources, vol. 332, pp. 193–203, 2016.

    Intelligent Electric Vehicle Route Planning System with ML-Based Energy Consumption Prediction · 2026 · DOI

  • While EV-Planner was validated across 10 US states, the paper explicitly identifies the need to apply the SA Clustering method and multi-objective optimization approach to additional geographic regions beyond these states to establish broader geographic applicability and generalization of the proposed methods.

    EV-Planner: a machine learning approach to electric vehicle charging infrastructure planning · 2026 · DOI

  • The EV-Planner optimization uses static snapshots of EV locations to determine charging demand, ignoring temporal and spatial dynamics. Incorporation of diurnal patterns, peak load timing coinciding with commuting hours, and dynamic EV movement patterns would improve solution quality, though at increased computational complexity.

    EV-Planner: a machine learning approach to electric vehicle charging infrastructure planning · 2026 · DOI

  • Accessibility in the EV-Planner model is quantified purely as Euclidean distance thresholds (2-10 miles) without incorporating socioeconomic and demographic factors. Integration of census data, income levels, and community demographics into the station placement optimization is needed to ensure equitable EV charging infrastructure access across different population segments.

    EV-Planner: a machine learning approach to electric vehicle charging infrastructure planning · 2026 · DOI

  • The charging technology types incorporated into EV-Planner (level 1/2/3 chargers) are treated uniformly across clusters without differentiation. Associating charger-type vectors with each cluster requires additional empirical data regarding the breakdown of EV populations by compatible charger types, which was not collected or analyzed in this study.

    EV-Planner: a machine learning approach to electric vehicle charging infrastructure planning · 2026 · DOI

  • The EV-Planner formulation currently incorporates only three core metrics (accessibility, coverage, and load balancing) for EV charging station placement. Land and construction costs, local power grid capacity constraints, and grid infrastructure limitations need to be integrated into the multi-objective optimization formulation to reflect real-world deployment considerations.

    EV-Planner: a machine learning approach to electric vehicle charging infrastructure planning · 2026 · DOI

  • One is that the traffic flow information from the commercial intelligent transportation system (ITS) is insufficient to accurately predict future driving conditions, which is alleviated by introducing the computer vision-based detection method for traffic flow density.

    Real-Time Global Optimal Energy Management Strategy for Connected PHEVs Based on Traffic Flow Information · 2024 · DOI

  • Social perception V2G technology serves the community in many social aspects including public health, operating cost savings and job creations Despite these benefits, the high upfront costs of EVs make it only affordable to high-income users leading to social inequalities Other barriers affecting public acceptance and adoption rates of EVs include those related to changes in transportation habits and concerns about charging availability and anxiety…

    Analysis of multidimensional impacts of electric vehicles penetration in distribution networks · 2024 · DOI

  • To study other aspects rising from EV penetration into the grid, this section presents other impacts that are crosslinked together including regulatory (political), economic, social and environmental ones in addition to their respective challenges, research gaps and potential recommendations as summarized in Tables 13, 14, 15 and 16 respectively.

    Analysis of multidimensional impacts of electric vehicles penetration in distribution networks · 2024 · DOI

  • Different technical impacts resulting from EV integration into the grid are thoroughly studied including problems and corresponding mitigation techniques as well as perspective benefits. Furthermore, related research challenges and potential measures are presented. Technical problems of EV integration to grid and mitigation strategies Utility companies encounter notable challenges because of the extensive electric vehicle integration on the distribution network, which disrupts the stability of the grid. The negative consequences stem from voltage level variations and imbalance, grid instability, excessive harmonics introduction and alteration of the load profile and equipment overloading, as indicated in Fig. 5. The overabundance of EVs can lead to serious power quality issues, increased peak loads and challenges in terms of power regulation. Considerable research has been conducted to evaluate the consequences of severe electric vehicle charging, predominantly on the distribution network, since the most severe impacts can be exhibited at this level. Moreover, numerous hardware solutions and software techniques to mitigate these negative impacts have been introduced in the literature. Fig. 4. Perspectives of the influence of EV charging. Scientific Reports | (2024) 14:27854 | https://doi.org/10.1038/s41598-024-77662-6 7 www.nature.com/scientificreports/ Fig. 5. Negative technical impacts of EVs on the distribution electrical grid. Fig. 6. Mitigation techniques for voltage magnitude variations resulting from excessive EV penetration.

    Analysis of multidimensional impacts of electric vehicles penetration in distribution networks · 2024 · DOI

  • 35 36 37 38 39 40 41 42 AI-Based Smart Grid Systems (AI-SMS) Enhances self-healing properties; integrates distributed energy resources. Requires significant infrastructure changes; dependency on advanced technologies.

    Optimizing demand response and load balancing in smart EV charging networks using AI integrated blockchain framework · 2024 · DOI

  • To improve sustainability, the DR-LB-AI framework may investigate the possibility of incorporating solar and wind power into the intelligent EV charging infrastructure. Improving demand forecasting and Load Balancing while taking renewable energy supply fluctuations into consideration might be achieved with the help of advanced AI algorithms. To further improve the system’s scalability and worldwide acceptance, the Blockchain foundation should be extended to include interoperability between various energy suppliers and cross-border energy trade. To ensure the framework’s usefulness and flexibility to changing energy landscapes, it is important to test and refine it under diverse grid situations and increase EV adoption. Scientific Reports | (2024) 14:31768 | https://doi.org/10.1038/s41598-024-82257-2 18 www.nature.com/scientificreports/ Fig. 14. The Analysis of Trust and Transparency. S.

    Optimizing demand response and load balancing in smart EV charging networks using AI integrated blockchain framework · 2024 · DOI

  • While for the latter several models exist, forecasting individual EV charging profiles is still underexplored in literature.

    Electric Vehicle Charging Profile Forecasting Using Hybrid Models · 2026

  • The conflict filtering mechanism only addresses simultaneous arrivals within a 5-minute window; more sophisticated queuing and scheduling strategies could be investigated.

    Research on Vehicle Scheduling of Battery Swap Stations Based on Online Information Platforms · 2026 · DOI

  • A further methodological limitation is that the applied model does not account for noncompensatory decision rules - situations in which a respondent considers one attribute so essential that it overrides all other considerations.

    Identifying segments of consumers willing to buy an electric car using Choice Based Conjoint method · 2025 · DOI

  • Compared with traditional fuel vehicles, EVs are limited by their limited battery capacity and require reasonable charging planning to complete the designated routes efficiently.

    Electric Vehicle Routing Problem: A Review of Recent Approaches and Algorithms · 2025 · DOI

  • Data on future truck costs are scarce and uncertain, complicating assessments of the future role of zero-emission truck (ZET) technologies.

    Rapidly declining costs of truck batteries and fuel cells enable large-scale road freight electrification · 2024 · DOI

  • Promotion for clean mobility Shifting from fossil fuel vehicles to e-mobility reduce emissions besides enhancing energy security by lessening reliance on fossil fuel which is an appealing factor…

    Analysis of multidimensional impacts of electric vehicles penetration in distribution networks · 2024 · DOI

Most-cited papers in Electric Vehicles and Infrastructure

Most recent work

Find a gap in your own Electric Vehicles and Infrastructure sub-topic

This page shows what the Electric Vehicles and Infrastructure literature already flags as unresolved. To narrow it to your specific question, run the guided finder — it searches the gap library on demand and checks candidates against 250M+ OpenAlex works.

Open the Research Gap Finder →

Related topics in Engineering

Traffic and Road Safety
143 open questions
Spatial Cognition and Navigation
95 open questions
Smart Cities and Technologies
89 open questions
BIM and Construction Integration
87 open questions
Design Education and Practice
86 open questions
Engineering Education and Curriculum Development
82 open questions
Digital Transformation in Industry
81 open questions
Perovskite Materials and Applications
78 open questions
38 open questions have been extracted from the limitations and future-work passages of 565 Electric Vehicles and Infrastructure papers in our library. Each one below links back to the study that raised it, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 120,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? A Tier 1–5 acceptance probability in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck prior-publication & salami-slicing risk across 8 sources.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.