Evaluating the Efficiency of Edge AI Deployment Strategies for Latency-Sensitive Applications in Hybrid Cloud Systems
Keywords:
Edge AI, hybrid cloud, latency-sensitive applications, deployment strategies, inference latency, distributed systemsAbstract
The proliferation of real-time and latency-sensitive applications such as autonomous vehicles, remote healthcare, and industrial automation, the need for efficient computational deployment frameworks has become paramount. Hybrid cloud systems — combining centralized cloud services with decentralized edge computing — offer a promising infrastructure for such applications. However, determining optimal Edge AI deployment strategies within these systems remains an open challenge. This paper evaluates various Edge AI deployment strategies, analyzing their performance in terms of latency, resource utilization, and system resilience. We present a comparative analysis using synthetic and real-world workloads, propose deployment guidelines, and suggest an optimization framework adaptable to varying application demands and network topologies.
References
Shi, Weisong, and Schahram Dustdar. “The Promise of Edge Computing.” Computer, vol. 49, no. 5, 2016, pp. 78–81.
Satyanarayanan, Mahadev, et al. “The Case for VM-Based Cloudlets in Mobile Computing.” IEEE Pervasive Computing, vol. 8, no. 4, 2017, pp. 14–23.
Kumar, Rahul, et al. “Cost-Efficient Edge AI Deployment for Latency-Sensitive Applications.” ACM Transactions on Internet Technology, vol. 19, no. 3, 2019, pp. 1–24.
Zhang, Yiming, et al. “Scalable Federated Learning at the Edge.” IEEE Journal on Selected Areas in Communications, vol. 39, no. 12, 2021, pp. 3622–3635.
Nguyen, Duc, Rahul Kumar, and Meena Patel. “Edge AI in Hybrid Cloud: A Survey of Deployment Strategies and Challenges.” IEEE Transactions on Cloud Computing, vol. 11, no. 2, 2023, pp. 121–136.
Kamadi, S. (2023). Identity-Driven Zero Trust Automation in GitOps: Policy-as-Code Enforcement for Secure Code Deployments. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 9(3), 893-902. https://doi.org/10.32628/CSEIT235148
Premsankar, Gautam, et al. “Edge Computing for the Internet of Things: A Case Study.” IEEE Internet of Things Journal, vol. 5, no. 2, 2018, pp. 1275–1284.
Li, Shiqiang, et al. “Learning-Driven Computation Offloading for Edge Computing.” IEEE Internet of Things Journal, vol. 5, no. 4, 2018, pp. 2835–2846.
Chen, Min, et al. “Edge Cognitive Computing Based Smart Healthcare System.” Future Generation Computer Systems, vol. 86, 2018, pp. 403–411.
Deng, Shiqiang, et al. “Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence.” IEEE Internet of Things Journal, vol. 7, no. 8, 2020, pp. 7457–7469.
Varghese, Blesson, and Rajkumar Buyya. “Next Generation Cloud Computing: New Trends and Research Directions.” Future Generation Computer Systems, vol. 79, 2018, pp. 849–861.
Mao, Yujia, et al. “A Survey on Mobile Edge Computing: The Communication Perspective.” IEEE Communications Surveys & Tutorials, vol. 19, no. 4, 2017, pp. 2322–2358.
