AI-Driven Smart Grid Optimization Using Deep Learning and Iot-Enabled Electrical Systems Framework
DOI:
https://doi.org/10.31838/NJAP/08.02.05Keywords:
Optimized Resource, Electrical Systems, Smart Grid OptimizationAbstract
Rising worldwide energy consumption and the integration of renewable energy sources are driving the rapid rise of smart grids, necessitating the use of resource allocation systems that are intelligent, flexible, and energy-efficient. Due to their inability to handle real-time grid dynamics, traditional energy management systems that rely on static models or heuristic algorithms can result in significant energy waste, poor energy distribution, and high operating costs. This study introduces a state-of-the-art solution that combines these issues: GBMIN-QSO (Gradient boosting machine with inception network and Quakka swarm optimization). For proactive power flow control, the framework makes use of both historical and real-time data; however, IoT-enabled sensors use edge and cloud computing infrastructure to provide constant monitoring and low-latency reaction. Predictive modeling, real-time analytics, and artificial intelligence with optimization are the main drivers of these performance improvements. GBMIN-QSO creates a scalable, dependable, and sustainable energy management system by fusing AI-driven decision-making, IoT sensing, and adaptive learning. The framework is a significant advancement in smart grid optimization and establishes the foundation for further innovations including cybersecurity protections, enhancements to reinforcement learning, and integration with edge computing. The effectiveness of GBMIN-QSO is confirmed by experimental findings indicate a total energy demand of 2412.61 MWh, with 1418.51 MWh (94.88% efficiency) met by renewable energy sources. The grid operates stably, with a Grid Stability Index of 97.78%. Predictive models achieve high accuracy (98.12%), enabling efficient energy management. The operational cost is $54,171.28, suggesting effective resource allocation and cost management. These indicators show that the smart grid system is well-optimized, stable, and capable of making predictions. It also uses a lot of renewable energy.
References
1. Tabassum, Saleha, Attuluri R. Vijay Babu, and Dharmendra Kumar Dheer. "A comprehensive exploration of IoT-enabled smart grid systems: power quality issues, solutions, and challenges." Science and Technology for Energy Transition 79 (2024): 62.
2. Alaba, Fadele Ayotunde, Usman Sani, Emmanuel Gbenga Dada, and Baydaa Hashim Mohammed. "AIoT-enabled smart grids: advancing energy efficiency and renewable energy integration." In Artificial intelligence of things for achieving sustainable development goals, pp. 59-79. Cham: Springer Nature Switzerland, 2024.
3. Ojadi, Jessica Obianuju, Chinekwu Somtochukwu Odionu, Ekene Cynthia Onukwulu, and Olumide Akindele Owulade. "AI-Enabled Smart Grid Systems for Energy Efficiency and Carbon Footprint Reduction in Urban Energy Networks." International Journal of Multidisciplinary Research and Growth Evaluation 5, no. 1 (2024): 1549-1566.
4. Scholapurapu, Prem Kumar. "Power Electronics for IoT-Enabled Smart Grids and Industrial Automation." DOI 10 (2025): 9789349552111-08.
5. Prem, N., Ranjana Devi, Reena Josephine SS, and S. Birundha. "AI Driven Software and Hardware Solutions for Smart Grid Energy Optimization." In 2025 3rd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), pp. 1702-1709. IEEE, 2025.
6. Pal, Gourab. "IoT and AI for smart grid optimization in urban areas." Soft Computing Fusion with Applications 2, no. 1 (2025): 54-61.
7. Clement, Mateo. "Optimizing Smart Grid Infrastructure through AI and IoT for Enhanced Renewable Energy Utilization." (2025).
8. Sasilatha, T., Adolf Asih Suprianto, and Hamdani Hamdani. "AI-Driven Approaches to Power Grid Management: Achieving Efficiency and Reliability." International Journal of Advances in Artificial Intelligence and Machine Learning 2, no. 1 (2025): 27-37.
9. Singh, Arvind R., M. S. Sujatha, Akshay D. Kadu, Mohit Bajaj, Hailu Kendie Addis, and Kota Sarada. "A deep learning and IoT-driven framework for real-time adaptive resource allocation and grid optimization in smart energy systems." Scientific Reports 15, no. 1 (2025): 19309.
10. Ojo, Oluwafemi Tayo, Temitope James Dada, Yusuff Afees Ademola, Gbenga Olurankinse, Eguzoroh Emmanuel Ebuka, Benedict Boakye Acka, and Flourish Chiwendu Kujah. "Smart Grids And IOT-Enabled Renewable Energy Integration." Path of Science 11, no. 1 (2025): 8012-8022.
11. Arun, M., Debabrata Barik, Nashwan Adnan Othman, Seepana Praveenkumar, and Kapura Tudu. "Investigating the performance of AI-driven smart building systems through advanced deep learning model analysis." Energy Reports 13 (2025): 5885-5899.
12. James, Paul. "AI-POWERED INTRUSION DETECTION SYSTEMS FOR SMART GRID EDGE DEVICES." (2025).
13. Tsegaye, Shewit, Kifle Godana Heyi, Mimi Tsegaye Endaylalu, Zemenu Addis Melaku, and Kasech Tsegaye Turufi. "Deep Neural Networks in Smart Grid Digital Twins: Evolution, Challenges, and Future Outlooks." IEEE Access (2025).
14. Ghanem, Mohamed Chahine, and Said Salloum. "Integrating AI-driven deep learning for energy-efficient smart buildings in Internet of Thing-based Industry 4.0." Babylonian Journal of Internet of Things 2025, no. 7 (2025): 121-130.
15. Malleeshwaran, T., and T. Prasanna. "Ai-driven iot framework for optimal energy management in consumer devices." In 2024 3rd International Conference on Sentiment Analysis and Deep Learning (ICSADL), pp. 746-751. IEEE, 2024.
16. Singh, Tushar, Sudhakar Kumar, Sunil K. Singh, Vanshika Chilkoti, Shavi Bansal, Kwok Tai Chui, and Brij B. Gupta. "Intelligent FaultEdge: AI-Driven Fault-Tolerant Edge Framework for Smart Grid Monitoring in IoT." In 2024 IEEE 12th International Conference on Intelligent Systems (IS), pp. 1-6. IEEE, 2024.
17. Alijoyo, Franciskus Antonius. "AI-powered deep learning for sustainable industry 4.0 and internet of things: Enhancing energy management in smart buildings." Alexandria Engineering Journal 104 (2024): 409-422.
18. Mohamed, Azza, Ibrahim Ismail, and Mohammed AlDaraawi. "IoT-Driven Intelligent Energy Management: Leveraging Smart Monitoring Applications and Artificial Neural Networks (ANN) for Sustainable Practices." Computers 14, no. 7 (2025): 269.
19. Gupta, Gaurav, Abhishek Tomar, Saigurudatta Pamulaparthyvenkata, and Anandaganesh Balakrishnan. "A Comprehensive Review of Machine Learning Techniques for Smart Grid Optimization." Secure Energy Optimization: Leveraging Internet of Things and Artificial Intelligence for Enhanced Efficiency (2025): 29-60.
20. Shobeiry, Seyed Mohammad. "Ai-enabled modern power systems: Challenges, solutions, and recommendations." In Artificial Intelligence in the Operation and Control of Digitalized Power Systems, pp. 19-67. Cham: Springer Nature Switzerland, 2024.
21. Ben Dhaou, Imed, Alaeddine Mihoub, and Moez Krichen. "Lightweight AI-Driven Real-Time Intruder Detection System for IoT-Enabled Smart Meters." In International Conference on Service-Oriented Computing, pp. 251-262. Singapore: Springer Nature Singapore, 2024.
