The idea of smart cities is a viable answer to the problems that urbanization is posing to cities worldwide, and artificial intelligence (AI) is a key component of this change. With an emphasis on its six primary domains—smart mobility, smart environment, smart governance, smart living, smart economics, and smart people—this study reviews the literature on AI solutions used in smart cities. The Scoop-available publications from 2021 to 2024 are included in the analysis. This study looks at how AI is being used in each field and notes its challenges, developments, and potential paths forward. The analysis\'s objectives were as follows: (1) to find applications and solutions that use AI in smart cities; (2) to find the obstacles that prevent AI from being implemented in smart cities; and (3) to investigate potential future directions for AI use in smart cities.
Introduction
I. Overview
Smart cities are a response to the growing challenges of urbanization, aiming to improve sustainability, efficiency, and quality of life. Artificial Intelligence (AI) is a central enabler of this transformation, impacting areas such as:
Resource management
Governance
Economic development
Transportation systems
Public services
Smart cities integrate IoT devices, data analytics, and digital infrastructure to deliver smart solutions across sectors like energy, healthcare, education, mobility, and government.
II. Literature Review
A growing body of research highlights AI's wide-ranging applications in smart cities. Key themes include:
Citizen Participation: Feher (2021) emphasized the role of public engagement and fostering a "smart mentality" for successful AI adoption.
Environmental Sustainability:
AI tools like Greencoin promote eco-conscious behavior.
AI is used in air quality modeling, load forecasting, and energy optimization.
Low-cost sensing systems and predictive models assist under-resourced areas.
Cybersecurity & Governance:
AI supports secure e-governance and cyberattack detection in IoT systems.
Social Well-being: AI frameworks address issues like cyberbullying in urban digital environments.
Urban Energy Management: Neural networks are used for forecasting energy usage and improving grid efficiency.
Despite these advances, common challenges include:
Data governance
Algorithmic bias
Integration complexity
Ethical concerns
III. Methodology
The study uses a literature review approach based on Scopus-indexed papers from 2021 to January 2024. Key findings include:
Over 773 papers combine the keywords "artificial intelligence" and "smart city".
Selection aimed at focusing on recent advancements in the AI–smart city intersection.
IV. Key Domain Focus – Smart Environment
AI in smart environments emphasizes:
Energy conservation
Smart metering
Load forecasting using recurrent neural networks
Smart grid optimization
Energy theft detection
V. Future Directions
The paper outlines areas for further research, including:
Multi-agent and multi-scale simulations
AI-powered urban planning
Integration with digital twins
Ethical and policy-driven AI design
Human behavior modeling in urban systems
Conclusion
The swift development of artificial intelligence offers smart cities enormous potential to solve urban problems and enhance citizens\' quality of life. This study has determined the key uses, implementation challenges, and future paths of AI solutions in the six primary domains of smart cities—smart mobility, smart environment, smart governance, smart living, smart economy, and smart people—by analyzing the literature from 2021 to January 2024.
This study\'s reliance on peer-reviewed sources and possible linguistic bias favoring English publications are among its research weaknesses. Furthermore, the methodology of this study, which centers on a literature review approach, can restrict the breadth of analysis and the applicability of the results to all smart cities worldwide. The selection of keywords is also linked to a research constraint. Only the fundamental terms \"artificial intelligence\" and \"smart city\" have been selected. It is possible to use more specific keywords, for
example, “urban AI”, “smart governance AI”, “public safety AI”, etc., in future, more
detailed research.
References
[1] The McKinsey International Institute. In 2018, the McKinsey Company published Smart Cities: Digital Solutions for a More Livable Future in New York, USA.
[2] Incentives for the Internet of Things: A survey by Maddikunta, P.K.R., Pham, Q.-V., Nguyen, D.C., Huynh-The, T., Aouedi, O., Yenduri, G., Bhattacharya, S., and Gadekallu, T.R. 206, 103464; J. Netw. Comput. Appl. 2022. [Reference]
[3] Making a Smart City Legible (Pilling, F.; Akmal, H.A.; Lindley, J.; Coulton, P.); Wiley: Hoboken, NJ, USA, 2022
[4] Feher, K. Expectation of smart mentality and citizen participation in technology-driven cities. Smart Struct. Syst. Int. J. 2021, 27, 435–445.
[5] Obracht-Prondzy´ nska, H.; Duda, E.; Anacka, H.; Kowal, J. Greencoin as an AI-Based Solution Shaping Climate Awareness. Int. J. Environ. Res. Public Health 2022, 19, 11183. [CrossRef] [PubMed]
[6] Bokhari, S.A.A.; Myeong, S. Artificial Intelligence\'s Impact on Cybersecurity and E-Government in Smart Cities: A Stakeholder\'s Viewpoint. 69783–69797 in IEEE Access 2023, 11. [Reference]
[7] Jhanjhi, N.Z.; Masud, M.; Alqhatani, A.; Prabakar, D.; Sundarrajan, M.; Manikandan, R. IoT-Powered Cyberattack Detection Using Energy Analysis and Artificial Intelligence in a Sustainable Smart City. Sustainability 15, 6031 (2023). [Reference]
[8] Al-Marghilani, A. Cyberbullying-Free Online Social Networks in Smart Cities using Artificial Intelligence. Comput. Intell. Syst. Int. J. 2022, 15, 9. [Reference]
[9] Stecu?a, K.; Wolniak, R.; Grebski, W.W. AI-Driven Urban Energy Solutions—From Individuals to Society: A Review.
[10] Subramanian, M. Leveraging Digitalization for Improving Energy Efficiency; Springer: Singapore, 2023. 2023, Energies 16, 7988. [Reference]
Elsevier: Amsterdam, The Netherlands, 2024.
[11] Kapoor, N.R.; Kumar, A.; Kumar, A.; Arora, H.C. Air Quality Modeling for Smart Cities of India by Nature Inspired AI—A Sustainable Approach.
[12] Bainomugisha, E.; Ssematimba, J.; Okure, D. A Distributed Low-Cost Air Quality Sensing System for Urban Environments with Limited Resources: Design Considerations. Atmosphere 14, 354 (2023). [Reference]
[13] Comparative Analysis Study for Air Quality Prediction in Smart Cities Using Regression Techniques, Al-Eidi, S.; Amsaad, F.; Darwish, O.; Tashtoush, Y.; Alqahtani, A.; Niveshitha, N. In 2023, IEEE Access 11, 115140–115149. [Reference]