Submission Criteria:

• The abstracts must be expanded and written in French or English.
• The abstracts should include:
  • A clear and descriptive title
  • 3 to 5 relevant keywords
  • A brief description of the objectives, methodology, and results (achieved or expected).
• Include a paragraph on the results obtained or expected and the references consulted

Notes:

1. Abstracts for presentations must be submitted in PDF format through this platform (sciencesconf.org) or, if not possible, sent to the following address: icaia@eheec.ac.ma before May 7, 2025.
2. Accepted abstracts will be published in the HEEC school journal: Mid Journal.

Format : only the PDF file is accepted, following the model below:

2nd Edition of the International Conference on Artificial Intelligence and Its Applications (ICAIA25) _____________________________________________________________________________________________________

TITLE OF THE PAPER

First Name 1 Last Name1, First Name 2 Last Name2, First Name 3 Last Name3

Affiliation1*, Faculty, University (Country)

Affiliation2, Faculty, University (Country)

Email1*, Email2, Email3

Abstract
        The increasing integration of Artificial Intelligence (AI) into renewable energy systems has opened new avenues for enhancing energy efficiency and sustainability. AI technologies, such as machine learning and predictive analytics, are being utilized to optimize energy production, distribution, and consumption, particularly in smart grids and renewable energy sources like solar and wind [1]. However, challenges such as intermittent energy generation and resource management still persist, requiring innovative approaches to address these limitations [2].

        In this context, we propose a novel AI-driven framework for real-time energy optimization in renewable energy systems. This framework employs advanced predictive models to forecast energy demand and supply, allowing for dynamic adjustments to energy distribution and storage. By integrating IoT devices and Cloud Computing, the system collects and processes real-time data from energy sources and consumption points, ensuring precise decision-making [3][4].

      Additionally, the architecture incorporates edge computing to enable localized data processing, reducing latency and improving response times. Case studies conducted in smart cities demonstrate that the proposed framework significantly enhances energy efficiency and minimizes waste [5]. This research highlights the potential of AI in reshaping the renewable energy landscape and contributing to the transition toward a sustainable and low-carbon future [6].

Results
       The implementation of the proposed AI-driven framework for energy optimization in renewable energy systems demonstrated significant improvements in both energy efficiency and sustainability. Initial results from pilot deployments in smart cities show a marked reduction in energy waste, with optimized energy distribution leading to a 15% decrease in peak load demands. Predictive models successfully forecasted energy generation from renewable sources, allowing the system to better manage supply and demand, thus minimizing reliance on non-renewable energy sources during periods of high demand.

       The integration of IoT devices and Cloud Computing facilitated real-time data collection, while the use of edge computing reduced response times for energy adjustments, enhancing the overall responsiveness of the system. Furthermore, the hybrid architecture—combining static IoT devices with mobile units such as drones—proved effective in ensuring continuous monitoring and optimization across both urban and suburban areas, leading to more reliable energy supply in remote zones.

     These results suggest that the framework not only improves energy efficiency but also contributes to the resilience and sustainability of urban energy systems, offering a promising model for future energy management in smart cities.

Keywords

Artificial Intelligence (AI), Smart Grids, Machine Learning, Predictive Analytics, Internet of Things (IoT)

References

[1]  C. T. Yin, Z. Xiong, H. Chen, J. Y. Wang, D. Cooper, and B. David, “A literature survey on smart cities,” Science China Information Sciences, vol. 58, no. 10, pp. 1–18, 2015, doi: 10.1007/s11432-015-5397-4.

[2]  M. Lacinák and J. Ristvej, “Smart City, Safety and Security,” Procedia Eng, vol. 192, pp. 522– 527, 2017, doi: 10.1016/j.proeng.2017.06.090.

[3]   A. Mosaif and S. Rakrak, “A New System for Real-time Video Surveillance in Smart Cities Based on Wireless Visual Sensor Networks and Fog Computing,” Journal of Communications, vol. 16, no. 5, pp. 175–184, 2021, doi: 10.12720/jcm.16.5.175-184.

[4]  L. B. Elvas, B. M. Mataloto, A. L. Martins, and J. C. Ferreira, “Disaster Management in Smart Cities,” Smart Cities, vol. 4, no. 2, pp. 819–839, May 2021, doi: 10.3390/smartcities4020042.

[5]   A. A. N. P. Redi, B. M. Sopha, A. M. S. Asih, and R. I. Liperda, “Collaborative hybrid aerial and ground vehicle routing for post-disaster assessment,” Sustainability (Switzerland), vol. 13, no. 22, Nov. 2021, doi: 10.3390/su132212841.

[6]  R. Das and M. M. Inuwa, “A review on fog computing: Issues, characteristics, challenges, and potential applications,” Telematics and Informatics Reports, vol. 10. Elsevier B.V., Jun. 01, 2023. doi: 10.1016/j.teler.2023.100049.

_____________________________________________________________________________________________________

HEEC Marrakesh                                                                                                                                                      21/06/2025