EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

NEXT-GENERATION SUSTAINABLE ENVIRONMENTAL MONITORING USING AI-DRIVEN EDGE INTELLIGENCE

K. Dilip, Y. Surendar Reddy, Swetha Kumar Chowhan, Shaik Janimiya

International Journal of AI Electrical Civil and Mechanical engineering · 2025

DOI: 10.64751/bxm2aa87 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of AI Electrical Civil and Mechanical engineering, 2025. Verfasst von K. Dilip und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Environmental monitoring has become increasingly important due to rapid urbanization, industrial expansion, climate change, and the growing need for sustainable resource management. Traditional cloud-centric monitoring systems often face challenges related to high communication latency, excessive bandwidth consumption, energy inefficiency, and limited real-time responsiveness. These limitations hinder the effective deployment of large-scale environmental monitoring applications that require continuous data collection and immediate decision-making. To address these challenges, this study proposes a Next-Generation Sustainable Environmental Monitoring Framework Using AI-Driven Edge Intelligence, which integrates artificial intelligence, edge computing, and Internet of Things (IoT) technologies to enable efficient, scalable, and sustainable environmental monitoring. The proposed framework utilizes distributed edge nodes equipped with intelligent data processing capabilities to perform real-time analysis of environmental parameters such as air quality, temperature, humidity, noise levels, water quality, and pollutant concentrations. Advanced machine learning and deep learning models are deployed at the edge to perform anomaly detection, environmental forecasting, pattern recognition, and predictive analytics while minimizing reliance on centralized cloud infrastructure. By processing data closer to the source, the framework reduces network traffic, lowers latency, enhances privacy, and improves energy efficiency. Furthermore, a sustainable resource management layer dynamically optimizes computational workloads and power consumption to support long-term environmental monitoring operations. Experimental evaluation was conducted using benchmark environmental datasets and simulated smart city scenarios. The results demonstrate that the proposed AI-driven edge intelligence framework significantly improves monitoring accuracy, response time, energy efficiency, and data processing performance compared with conventional cloud-based monitoring systems. The framework achieves enhanced scalability while maintaining reliable real-time environmental awareness and decision support capabilities. The findings indicate that AIenabled edge intelligence can serve as a key enabler for sustainable environmental management and smart city development. The proposed framework provides a robust foundation for next-generation intelligent environmental monitoring systems capable of supporting ecological sustainability, public health protection, and data-driven environmental governance.

Zitieren

APA

Dilip, K., Reddy, Y. S., Chowhan, S. K., & Janimiya, S. (2025). NEXT-GENERATION SUSTAINABLE ENVIRONMENTAL MONITORING USING AI-DRIVEN EDGE INTELLIGENCE. International Journal of AI Electrical Civil and Mechanical engineering. https://doi.org/10.64751/bxm2aa87

Vancouver

Dilip K, Reddy YS, Chowhan SK, Janimiya S. NEXT-GENERATION SUSTAINABLE ENVIRONMENTAL MONITORING USING AI-DRIVEN EDGE INTELLIGENCE. International Journal of AI Electrical Civil and Mechanical engineering. 2025. doi:10.64751/bxm2aa87

BibTeX
@article{Dilip2025,
  author = {Dilip, K. and Reddy, Y. Surendar and Chowhan, Swetha Kumar and Janimiya, Shaik},
  title = {NEXT-GENERATION SUSTAINABLE ENVIRONMENTAL MONITORING USING AI-DRIVEN EDGE INTELLIGENCE},
  journal = {International Journal of AI Electrical Civil and Mechanical engineering},
  year = {2025},
  doi = {10.64751/bxm2aa87}
}
Kostenlos starten →