Decentralized Edge-AI Strategies for Micro-Datacenter Optimization and Resource-Conscious Query Execution
Keywords:
Edge-AI, micro-datacenter, decentralized optimization, federated learning, query execution, energy efficiency, edge computingAbstract
The proliferation of Internet-of-Things (IoT) devices and latency-sensitive applications has sparked a surge in micro-datacenter (µDC) deployments at the network edge. While these µDCs enhance computational proximity, they also pose challenges in orchestration, resource allocation, and energy efficiency. In this paper, we explore decentralized Edge-AI strategies for optimizing µDC resource management and enabling resource-conscious query execution. Leveraging federated learning, multi-agent systems, and dynamic workload profiling, our framework decentralizes decision-making and prioritizes minimal energy overhead and bandwidth utilization. Experimental insights suggest significant improvements in query response time (18–35%) and energy savings (12–22%) across edge workloads. The proposed approach supports low-latency operations, sustainable computing, and privacy-preserving data workflows at the edge.
References
Deng, Ruilong, Rongxing Lu, Chenglin Lai, Tinghe Luan, and Hao Liang. "Optimal workload allocation in fog-cloud computing toward balanced delay and power consumption." IEEE Internet of Things Journal, vol. 3, no. 6, 2019, pp. 1171–1181.
Pulivarthy, P. (2024). Gen AI Impact on the Database Industry Innovations. International Journal of Advances in Engineering Research (IJAER), 28(III), 1–10.
McMahan, Brendan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agüera y Arcas. "Communication-efficient learning of deep networks from decentralized data." Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), vol. 54, 2017, pp. 1273–1282.
Satyanarayanan, Mahadev, Paramvir Bahl, Ramón Cáceres, and Nigel Davies. "The case for VM-based cloudlets in mobile computing." IEEE Pervasive Computing, vol. 8, no. 4, 2017, pp. 14–23.
Pulivarthy, P. (2024). Optimizing Large Scale Distributed Data Systems Using Intelligent Load Balancing Algorithms. AVE Trends in Intelligent Computing Systems, 1(4), 219–230.
Shi, Weisong, Jie Cao, Quan Zhang, Youhuizi Li, and Lanyu Xu. "Edge computing: Vision and challenges." IEEE Internet of Things Journal, vol. 3, no. 5, 2020, pp. 637–646.
Xiong, Wenxuan, Kejiang Zhang, and Rajkumar Buyya. "Edge computing resource management and pricing: A review and taxonomy." ACM Computing Surveys, vol. 54, no. 7, 2021, pp. 1–40.
Xu, Xiaoxuan, Hao Wu, Ming Ding, Wei Li, and Rajkumar Buyya. "Resource management in Edge AI: A reinforcement learning perspective." IEEE Communications Surveys & Tutorials, vol. 23, no. 4, 2021, pp. 2293–2324.
Zhang, Kejiang, and Rajkumar Buyya. "Decentralized resource management in edge computing: A multi-agent reinforcement learning perspective." Journal of Systems and Software, vol. 181, 2021, article no. 111057.
Pulivarthy, P. (2023). ML-driven automation optimizes routine tasks like backup and recovery, capacity planning and database provisioning. Excel International Journal of Technology, Engineering and Management, 10(1), 22–31. https://doi.uk.com/7.000101/EIJTEM
Li, Fan, Chao Huang, and Xiang Su. "Energy-efficient service placement and scheduling for micro datacenters in edge computing." Future Generation Computer Systems, vol. 123, 2021, pp. 179–191.
Abbas, Nasir, Yousaf Bin Zikria, Shuja Iqbal, Muhammad Khalil Afzal, and Sung Won Kim. "A comprehensive survey on clustering-based routing protocols for wireless sensor networks." Journal of Network and Computer Applications, vol. 142, 2019, pp. 111–142.
Vemulapalli, G., Pulivarthy, P.: Integrating Green Infrastructure With AI-Driven Dynamic Workload Optimization: Focus on Network and Chip Design. In: Integrating Blue-Green Infrastructure Into Urban Development, pages. 26. IGI Global (2025). https://doi.org/10.4018/979-8-3693-8069-7.ch018
Varghese, Blesson, Nan Wang, and Rajkumar Buyya. "Feasibility of fog computing." arXiv preprint, 2017. arXiv:1701.05451
