Edge-Cloud Collaboration in Real-Time AI Applications

References

[1] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646. https://doi.org/10.1109/JIOT.2016.2579198

[2] Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39. https://doi.org/10.1109/MC.2017.9

[3] Li, Y., Ota, K., & Dong, M. (2018). Deep learning for smart industry: Efficient manufacture inspection system with fog computing. IEEE Transactions on Industrial Informatics, 14(10), 46654673.https://doi.org/10.1109/TII.2018.2839676

[4] McMahan, H. B., Moore, E., Ramage, D., & Hampson, S. (2017). Communicationefficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) https://arxiv.org/abs/1602.05629 TensorFlow. (n.d.). TensorFlow Lite Guide. Retrieved from https://www.tensorflow.org/lite

[5] Microsoft. (n.d.). ONNX Runtime Documentation. Retrieved from https://onnxruntime.ai NVIDIA. (2021). Jetson Platform for Edge AI. Retrieved from https://developer.nvidia.com/embeddedcomputing

[6] Amazon Web Services (AWS). (2023). AWS IoT Greengrass.Retrievedfromhttps://docs.aws.amazon.com/greengrass/lat est/developerguide/

[7] MicrosoftAzure.(2023).

[8] AzureIoTEdgeDocumentation. Retrieved fromhttps://learn.microsoft.com/en-us/azure/iotedge

[9] Google Cloud. (2023). Edge TPU and Coral Documentation. Retrieved from https://coral.ai/docs

[10] LF Edge. (2022). Project EVE, EdgeX Foundry, and Open Horizon. Retrieved from https://www.lfedge.org/projects/ MLCommons. (2023). MLPerf Benchmarks. Retrieved from https://mlcommons.org/en/

[11] Rausch, T., Dustdar, S., & Rosello, D. (2019). Towards a model-driven approach for performance and resource-aware edge AI deployment. Proceedings of the 2019 IEEE International Conference on Cloud Engineering (IC2E), 4151.https://doi.org/10.1109/IC2E.2019.00017

[12] Zhang, C., Patras, P., & Haddadi, H. (2021). Deep learning in mobile and wireless networking: A survey. IEEE Communications Surveys & Tutorials, 21(3), 2224–2287.https://doi.org/10.1109/COMST.2021.3066567

@article{1709991,
      author = {Mohammed Abdus Salam},
      title = {Edge-Cloud Collaboration in Real-Time AI Applications},
      journal = {Iconic Research And Engineering Journals},
      year = {2024},
      volume = {8},
      number = {6},
      pages = {1125-1136},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1709991.pdf},
      abstract = {The proliferation of real-time artificial intelligence (AI) applications across domains such as autonomous vehicles, smart manufacturing, and healthcare demands computing infrastructures that balance low latency, high processing power, and scalability. Edge-cloud collaboration has emerged as a promising paradigm that leverages the proximity and responsiveness of edge computing with the computational capabilities and resource availability of cloud platforms. This paper explores the architecture, design principles, and operational strategies for effective edge-cloud collaboration in real-time AI systems. Key challenges such as data partitioning, model synchronization, latency constraints, security, and resource orchestration are analyzed, along with current solutions and open research directions. We present use cases that demonstrate the efficacy of collaborative edge-cloud AI, and highlight the trade-offs involved in deploying machine learning inference and training tasks across heterogeneous environments. Our study underscores the critical role of intelligent workload distribution and adaptive system design in enabling efficient, robust, and scalable real-time AI applications.},
      month = {December},
  }