Optimizing End to end Machine Learning Pipelines Using Hybrid Edge Cloud Architectures for Real Time Decision making Applications
Keywords:
Real-time decision, Edge computing, Cloud architecture, Machine learning, Scalability challengesAbstract
Real time decision making applications, such as those used in autonomous vehicles, smart cities, and industrial IoT, require fast, scalable, and accurate analytics to ensure timely responses and optimized operations. Traditional cloud-based systems face significant challenges in meeting these requirements due to high latency, limited scalability, and bottlenecks in data processing. This study explores the use of a hybrid Edge Cloud architecture to optimize End to end machine learning (ML) pipelines for real time applications. The proposed system offloads time-sensitive tasks to edge devices, while computationally intensive processes are handled by the cloud, ensuring efficient use of resources and reduced latency. Experimental results demonstrate that the hybrid model reduces inference latency by up to 70% compared to cloud-only systems, while maintaining model accuracy and increasing throughput. Additionally, the scalability of the hybrid architecture is highlighted, as it can handle large-scale data streams and adapt to varying workloads. The findings show that hybrid Edge Cloud architectures are well-suited for applications where fast decision making is critical, such as autonomous systems and real time analytics in smart cities. However, challenges remain in managing resources across edge and cloud systems, particularly in balancing computational loads and ensuring system reliability. Future research should focus on optimizing task partitioning, integrating advanced edge AI models, and exploring the use of 5G networks to enhance performance further. Overall, the study demonstrates the potential of hybrid Edge Cloud systems in overcoming the limitations of traditional cloud-based ML pipelines and provides insights into the future of real time data processing.
References
[1] S. Shukla, M. F. Hassan, D. C. Tran, R. Akbar, I. V. Paputungan, and M. K. Khan, “Improving latency in Internet-of-Things and cloud computing for real-time data transmission: a systematic literature review (SLR),” Cluster Comput., vol. 26, no. 5, pp. 2657 – 2680, 2023, doi: 10.1007/s10586-021-03279-3.
[2] W.-H. Choi and W.-J. Jung, “A Comparative Study of Computing Paradigms for Real-Time Image Processing: Cloud, Edge, And On-Device AI,” Int. J. Basic Appl. Sci., vol. 14, no. 3, pp. 332 – 337, 2025, doi: 10.14419/cbjvn374.
[3] A. Riyal, G. Kumar, and D. K. Sharma, “Background and Research Challenges for Fog Data Analytics and IoT,” Stud. Big Data, vol. 76, pp. 313 – 340, 2020, doi: 10.1007/978-981-15-6044-6_13.
[4] E. Ganesan, A. Roy, R. K. Tripathi, P. Sudan, P. M. Khandekar, and P. P. Nayak, “Fog Computing Architectures for Real-Time Data Processing and Edge Intelligence in Ubiquitous Applications,” J. Wirel. Mob. Networks, Ubiquitous Comput. Dependable Appl., vol. 16, no. 4, pp. 711 – 721, 2025, doi: 10.58346/JOWUA.2025.I4.042.
[5] S. Maiyya, F. Nawab, C. Sahin, V. Zakhary, D. Agrawal, and A. El Abbadi, “Efficient, consistent and secure global-scale data management,” in CEUR Workshop Proceedings, 2018. [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85066496072&partnerID=40&md5=c655f64eff55ab17ab155570bf354bb1
[6] T. B. Sivakumar, S. Lavanya, Y. M. M. John, M. K. Nageswaran, S. Kaliappan, and G. Manikandan, “Privacy-Preserving IoT Analytics using Federated Learning and Decentralized AI at the Edge,” in ICoICC 2025 - 3rd International Conference on Intelligent and Cloud Computing, 2025. doi: 10.1109/ICoICC64033.2025.11052159.
[7] M. Samal, S. Ray, and M. Dasgupta, “A Short Survey on Fog Computing and its Convergence with Internet of Things (IoT) Network,” in OCIT 2023 - 21st International Conference on Information Technology, Proceedings, 2023, pp. 132 – 137. doi: 10.1109/OCIT59427.2023.10430506.
[8] S. Al E’mari, Y. Sanjalawe, F. Fataftah, and F. Fataftah, Edge intelligence expanding BI architectures beyond the cloud. IGI Global, 2025. doi: 10.4018/979-8-3373-2125-7.ch004.
[9] P. Radhakrishnan, S. Kurian, V. B. Vijayan, M. Mahabooba, D. Pulugu, and D. Menaga, “A Scalable Hybrid Edge-Cloud Approach to Minimizing Latency in IoT Applications,” Int. J. Comput. Exp. Sci. Eng., vol. 11, no. 2, pp. 2217 – 2224, 2025, doi: 10.22399/ijcesen.946.
[10] R. Raffik, V. J. Balamurugan, and N. Gopinath Pandian, “Edge Computing for Real-Time Decision-Making in Industrial Automation Systems - A Comprehensive Review,” in 2025 3rd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2025, 2025. doi: 10.1109/ICAECA63854.2025.11012458.
[11] A. A. Al-Atawi, “Enhancing data management and real-time decision making with IoT, cloud, and fog computing,” IET Wirel. Sens. Syst., vol. 14, no. 6, pp. 539 – 562, 2024, doi: 10.1049/wss2.12099.
[12] M. A. K. M. Jabarullah, S. N. Chakka, and S. Kanungo, “Edge-Cloud Hybrid Architecture for Distributed AI Applications,” in 2025 International Conference on Computing Technologies and Data Communication, ICCTDC 2025, 2025. doi: 10.1109/ICCTDC64446.2025.11158770.
[13] A. K. Pallikonda et al., “OPTIMIZING REAL TIME IOT PROCESSING WITH HYBRID EDGE CLOUD ARCHITECTURE FOR ENHANCED LATENCY AND ENERGY EFFICIENCY,” J. Theor. Appl. Inf. Technol., vol. 103, no. 12, pp. 5227 – 5239, 2025, [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-105009784568&partnerID=40&md5=33eb5ff1f7e82b4cf9a33c1c01a55495
[14] V. Dankan Gowda, A. Sharma, K. D. V Prasad, P. Veeramanikandan, N. Anil Kumar, and B. S. Ingole, “A control system framework for IoT-integrated autonomous vehicles with machine learning optimization,” Lect. Notes Networks Syst., vol. 1379 LNNS, pp. 449–459, 2025, doi: 10.1007/978-981-96-5784-1_36.
[15] B. Singh, Featuring smart city solutions with machine learning for traffic management, object detection, and collision avoidance in autonomous driving. 2025. doi: 10.4018/979-8-3693-7984-4.ch019.
[16] A. Sinha and D. Das, Data-Driven Techniques for Fault Diagnosis and Predictive Maintenance. 2025. doi: 10.1201/9781003473442-3.
[17] T. Khan, W. Tian, G. Zhou, S. Ilager, M. Gong, and R. Buyya, “Machine learning (ML)-centric resource management in cloud computing: A review and future directions,” J. Netw. Comput. Appl., vol. 204, 2022, doi: 10.1016/j.jnca.2022.103405.
[18] C. Auer, M. Dolfi, A. Carvalho, C. B. Ramis, and P. W. J. Staar, “Delivering Document Conversion as a Cloud Service with High Throughput and Responsiveness,” in IEEE International Conference on Cloud Computing, CLOUD, 2022, pp. 363 – 373. doi: 10.1109/CLOUD55607.2022.00060.
[19] G. Ramesh et al., “A Comprehensive Review on Scaling Machine Learning Workflows Using Cloud Technologies and DevOps,” IEEE Access, vol. 13, pp. 148559 – 148594, 2025, doi: 10.1109/ACCESS.2025.3599281.
[20] D. Y. Yuan and T. Wildish, “Bioinformatics Application with Kubeflow for Batch Processing in Clouds,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12321 LNCS, pp. 355 – 367, 2020, doi: 10.1007/978-3-030-59851-8_24.
[21] A. Souza, N. Ng, T. Abdelzaher, D. Towsley, and P. Shenoy, “Unlocking Efficiency: Understanding End-to-End Performance in Distributed Analytics Pipelines,” in MILCOM 2023 - 2023 IEEE Military Communications Conference: Communications Supporting Military Operations in a Contested Environment, 2023, pp. 150 – 155. doi: 10.1109/MILCOM58377.2023.10356378.
[22] L. Wu, W. A. Hanafy, A. Souza, T. Abdelzaher, G. Verma, and P. Shenoy, “Enhancing Resilience in Distributed ML Inference Pipelines for Edge Computing,” in Proceedings - IEEE Military Communications Conference MILCOM, 2024. doi: 10.1109/MILCOM61039.2024.10773652.
[23] A. S. Rajawat, R. K. Arora, M. Muqeem, S. M. Faisal, and M. K. Jamal, “Enhancing IoT Efficiency by Minimizing Latency and Boosting Real-Time Processing with Edge Computing,” SN Comput. Sci., vol. 6, no. 6, 2025, doi: 10.1007/s42979-025-04192-x.
[24] P. Sharma, J. Shyamala Devi, K. Manikandan, R. Ani Minisha, R. Harini, and S. Karthik, “The Role of Edge Computing in Enhancing Cloud Performance and Reducing Latency,” in Proceedings of International Conference on Contemporary Computing and Informatics, IC3I 2024, 2024, pp. 1603 – 1608. doi: 10.1109/IC3I61595.2024.10829058.
[25] S. D. Govardhan, R. Pushpavalli, T. V. R. Kanth, and P. P. Selvam, “Advanced Computational Intelligence Techniques for Real-Time Decision-Making in Autonomous Systems,” Int. J. Comput. Exp. Sci. Eng., vol. 10, no. 4, pp. 928 – 937, 2024, doi: 10.22399/ijcesen.591.
[26] M. Pintus, F. Colucci, and F. Maggio, “Emerging Developments in Real-Time Edge AIoT for Agricultural Image Classification,” IoT, vol. 6, no. 1, 2025, doi: 10.3390/iot6010013.
[27] K. Ishwarya and J. James S., Hybrid deep learning–based edge intelligence and analytics. 2025. doi: 10.1201/9781003512066-11.
[28] P. Yadav, “Advancements in Machine Learning in Sensor Systems: Insights from Sensys-ML and TinyML Communities,” in Proceedings - 2024 IEEE 3rd Workshop on Machine Learning on Edge in Sensor Systems, SenSys-ML 2024, 2024, pp. 21 – 26. doi: 10.1109/SenSys-ML62579.2024.00009.
[29] Y. Y. Raghav and R. Kait, Edge computing empowering distributed computing at the edge. 2024. doi: 10.4018/979-8-3693-0900-1.ch003.
[30] A. Pradeep, “Exploring the Future of Edge Computing: Advantages, Limitations, and Opportunities,” Commun. Comput. Inf. Sci., vol. 1921 CCIS, pp. 196 – 209, 2023, doi: 10.1007/978-3-031-45124-9_15.
