A Study on the Influence Mechanism of User Demand Response and Service Experience in Urban New Energy Charging Market Based on Multi-model Fusion: A Case Study of Urumqi

Wenlin Liu

doi:10.54097/s0tf1q27

Authors

Wenlin Liu

DOI:

https://doi.org/10.54097/s0tf1q27

Keywords:

New energy vehicles, Charging facilities, User behavior, Satisfaction model, Multi-model integration.

Abstract

To address the rapid expansion of the new energy vehicle market and the challenges it poses to urban charging infrastructure, this study takes Urumqi as an example, aiming to deeply analyze user charging behavior engineering and the core influence mechanisms of charging service satisfaction in the new energy charging market. Based on an analysis of 978 valid user questionnaires and using multiple linear regression, K-prototype clustering, structural equation modeling (SEM), and random forest models, the research constructs a multi-dimensional and multi-level integrated analysis framework. The findings indicate that the rational distribution of charging stations (β=0.249) and charging speed (β=0.247) are the primary factors influencing user satisfaction, with their importance surpassing that of charging costs. User groups can be clearly classified into three types: “high-frequency practical users,” “price-sensitive users,” and “tech enthusiasts,” with significant differences in charging behaviors, technology preferences, and policy attitudes among them. Additionally, the random forest model identifies that public expectations for the market outlook (feature importance: 63.6%) and perceptions of the speed of charging facility construction (feature importance: 30.3%) are the key psychological drivers of support for new energy policies. By quantifying the impact paths and weights of these key factors, this study reveals the central contradictions in the current urban charging market and the heterogeneous needs of user groups, providing scientific data support and decision-making references for optimizing charging network planning, formulating precise operational strategies, and enhancing policy effectiveness.

References

[1]Ding C, Ren J. Global energy transition in an ageing World: The strategic role of Chinese renewable energy products[J]. Case Studies in Thermal Engineering, 2025, 74106791-106791.

[2]Niu B, Xue X, Sai Y, et al. Corrigendum to “Impact of digitalization inputs on CO2 emissions in China’s construction industry under the “Dual Carbon” goal”. [Energy Build. 344 (2025) 116014][J]. Energy & Buildings, 2025, 346116197-116197.

[3]Wang C, Bian J, Yuan R. Reactive Power Optimization Model of Active Distribution Network with New Energy and Electric Vehicles[J]. Energy Engineering,2025,122(3):985-1003.

[4]Guo B, Geng Y, Ren J, et al. Comparative assessment of circular economy development in China’s four megacities: The case of Beijing, Chongqing, Shanghai and Urumqi[J]. Journal of Cleaner Production, 2017,162234-24.

[5]Meng F, Sun L. An Empirical Study on the Impact of RMB Exchange Rate Fluctuation on China's Outward Foreign Direct Investment—Based on Panel Data of 58 Countries along the “Belt and Road”[J]. Journal of Economics and Public Finance, 2025, 11(3).

[6]Han Y, Gu H, Shen Y, et al. Research on the Operation Mode and Path Optimization of Mobile Charging Service for New Energy Vehicles[J]. American Journal of Industrial and Business Management,2024,14(12):1724-1746.

[7]Thirumalai M, Yuvaraj T, Bajaj M, et al. Multi-objective coordinated optimization of renewable-based EV charging stations with user-centric scheduling and grid support in distribution networks[J]. e-Prime - Advances in Electrical Engineering, Electronics and Energy,2025,14101111-101111.

[8]Yanhua L, Hongjuan L. Dynamic Evaluation and Regional Differences Analysis of the NEV Industry Development in China[J]. Sustainability,2022,14(21):13864-13864.

[9]O. Abu-Znad, M. Zhai, L. Du and R. Fan, "Market Participation Strategies for Fast-Charging Stations to Enhance Individual Profitability and Grid Reliability," 2025 IEEE/AIAA Transportation Electrification Conference and Electric Aircraft Technologies Symposium (ITEC+EATS), Anaheim, CA, USA, 2025, pp. 1-6.

[10]Mayilvahanan P. Estimation of Regression Coefficients Using Geometric Mean of Squared Error for Single Index Linear Regression Model[J]. International Journal of Artificial Intelligence & Applications,2016,7(6):75-84.

[11]Song J, Oon J, Mepparambath M R, et al.Quantifying the benefits of urban amenities in Singapore with consideration of the effects of spatial heterogeneity[J]. Environment and Planning B: Urban Analytics and City Science, 2025, 52(8): 1832-1851.

[12]Thulasipriya B, Rodrigues J L. Entrepreneurship Characteristics, Moderate Marketing Strategies, Marketing Challenges and Tech Startup Financial Performance[J]. Journal of Enterprising Culture,2025,33(02).

[13]D. J. Crosss Sihombing, D. C. Othernima, J. Manurung and J. R. Sagala, "Comparative Models of Price Estimation Using Multiple Linear Regression and Random Forest Methods," 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), Jakarta, Indonesia, 2023, pp. 478-483.

[14]B. Peng and Y. Liu, "Research on Power System Load Clustering based on Signal Analysis and K-Prototypes," 2023 3rd International Conference on Electrical Engineering and Control Science (IC2ECS), Hangzhou, China, 2023, pp. 233-240.

[15]H. Amal, I. M’barek, E. H. Zouhair, H. Soumaia, H. Hanaa and E. K. Yousfi Mohammed, "Treatment of Correlated Errors in Structural Equation Models," 2021 7th International Conference on Optimization and Applications (ICOA), Wolfenbüttel, Germany, 2021, pp. 1-6.