Field-Deployable Kubernetes Cluster for Enhanced Computing Capabilities in Remote Environments
Source abstract
Abstract
This paper presents a portable cluster architecture based on a lightweight Kubernetes distribution designed to provide enhanced computing capabilities in isolated environments. The architecture is validated in two operational scenarios: (1) machine learning operations (MLOps) for on-site learning, fine-tuning and retraining of models and (2) web hosting for isolated or resource-constrained networks, providing resilient service delivery through failover and load balancing. The cluster leverages low-cost Raspberry Pi 4B units and virtualized nodes, integrated with Docker containerization, Kubernetes orchestration, and Kubeflow-based workflow optimization. System monitoring with Prometheus and Grafana offers continuous visibility into node health, workload distribution, and resource usage, supporting early detection of operational issues within the cluster. The results show that the proposed dual-mode cluster can function as a compact, field-deployable micro-datacenter, enabling both real-time Artificial Intelligence (AI) operations and resilient web service delivery in field environments where autonomy and reliability are critical. In addition to performance and availability measurements, power consumption, scalability bottlenecks, and basic security aspects were analyzed to assess the feasibility of such a platform under constrained conditions. Limitations are discussed, and future work includes scaling the cluster, evaluating GPU/TPU-enabled nodes, and conducting field tests in realistic tactical environments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: IoT and Edge/Fog Computing · Cloud Computing and Resource Management · Software-Defined Networks and 5G
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Telecommunications, Information Technology and Cyber Security, “Nicolae Bălcescu” Land Forces Academy, 550170 Sibiu, Romania
Faculty of Electrical Engineering, Helmut-Schmidt-Universität/Universität der Bundeswehr Hamburg, 22043 Hamburg, Germany
Department of Surveillance and Air Defense, “Henri Coandă” Air Force Academy, 500183 Brașov, Romania
References (43)
Show source-provided references
1. ML-Driven User Activity-Based GNSS Activation for Power Optimization in Resource-Constrained Environments10.1109/TIM.2025.3593579 ↗
2. Aragão, M., González, P., de Farias, C., and Delicato, F. (2024, January 5–8). AFRODITE—Optimizing Federated Learning in Resource-Constrained Environments Through Data Sampling Techniques. Proceedings of the 2024 IEEE Conference on Pervasive and Intelligent Computing (PICom), Boracay Island, Philippines.10.1109/PICom64201.2024.00021 ↗
3. CacheIEE: Cache-Assisted Isolated Execution Environment on ARM Multi-Core Platforms10.1109/TDSC.2023.3251418 ↗
4. Kalyani, Y., and Collier, R. (2021). A Systematic Survey on the Role of Cloud, Fog, and Edge Computing Combination in Smart Agriculture. Sensors, 21.10.3390/s21175922 ↗
5. Offloading Using Traditional Optimization and Machine Learning in Federated Cloud–Edge–Fog Systems: A Survey10.1109/COMST.2023.3239579 ↗
6. An open ecosystem for mobile-cloud convergence10.1109/MCOM.2015.7060484 ↗
7. A Multi-Domain Survey on Time-Criticality in Cloud Computing10.1109/TSC.2025.3539197 ↗
8. Masip-Bruin, X., Marín-Tordera, E., Sánchez-López, S., García, J., Jukan, A., Ferrer, A., Queralt, A., Salis, A., Bartoli, A., and Cankar, M. (2021). Managing the Cloud Continuum: Lessons Learnt from a Real Fog-to-Cloud Deployment. Sensors, 21.10.20944/preprints202104.0074.v1 ↗
9. Li, H., Liu, X., and Zhao, W. (2023). Research on Lightweight Microservice Composition Technology in Cloud-Edge Device Scenarios. Sensors, 23.10.3390/s23135939 ↗
10. Gkonis, P., Giannopoulos, A., Trakadas, P., Masip-Bruin, X., and D’Andria, F. (2023). A Survey on IoT-Edge-Cloud Continuum Systems: Status, Challenges, Use Cases, and Open Issues. Future Internet, 15.10.20944/preprints202311.0532.v1 ↗
11. Trakadas, P., Masip-Bruin, X., Facca, F., Spantideas, S., Giannopoulos, A., Kapsalis, N., Martins, R., Bosani, E., Molinas-Ramón, J., and Prats, R. (2022). A Reference Architecture for Cloud–Edge Meta-Operating Systems Enabling Cross-Domain, Data-Intensive, ML-Assisted Applications: Architectural Overview and Key Concepts. Sensors, 22.10.3390/s22229003 ↗
12. Sturzinger, E., Lowrance, C., Faber, I., Choi, J., and MacCalman, A. (2021, January 12–17). Improving the performance of AI models in tactical environments using a hybrid cloud architecture. Proceedings of the Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III, Online.10.1117/12.2587932 ↗
13. Kubernetes distributions for the edge: Serverless performance evaluation10.1007/s11227-022-04430-6 ↗
14. Kubernetes in Action: Exploring the Performance of Kubernetes Distributions in the Cloud10.1002/spe.70000 ↗
15. Usman, M., Ferlin, S., and Brunstrom, A. (2024, January 4–7). Performance Analysis of Lightweight Container Orchestration Platforms for Edge-Based In Proceedings of the IoT Applications. 2024 IEEE/ACM Symposium on Edge Computing (SEC), Rome, Italy.10.1109/SEC62691.2024.00032 ↗
16. (2025, August 11). MicroK8s. Available online: https://microk8s.io.
17. Koziolek, H., and Eskandani, N. (2023, January 15–19). Lightweight Kubernetes Distributions: A Performance Comparison of MicroK8s, k3s, k0s, and Microshift. Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering, Coimbra, Portugal.10.1145/3578244.3583737 ↗
18. Adapting Containerized Workloads for the Continuum Computing10.1109/ACCESS.2024.3434585 ↗
19. Network-aware container scheduling in edge computing10.1007/s10586-024-04733-8 ↗
20. HERCULE: High-Efficiency Resource Coordination Using Kubernetes and Machine Learning in Edge Computing for Improved QoS and QoE10.1109/ACCESS.2025.3563161 ↗
21. Mondal, S., Zheng, Z., and Cheng, Y. (2024). On the Optimization of Kubernetes toward the Enhancement of Cloud Computing. Mathematics, 12.10.3390/math12162476 ↗
22. Proactive monitoring and security in cloud infrastructure: Leveraging tools like Prometheus, Grafana, and HashiCorp Vault for Robust DevOps Practices10.30574/wjaets.2024.13.2.0543 ↗
23. Chakraborty, M., and Kundan, A.P. (2021). Grafana. Monitoring Cloud-Native Applications, Apress.10.1007/978-1-4842-6888-9 ↗
24. Seyidbayli, C. (2025). Bit Depth in Energy Consumption: Comparing 32-Bit and 64-Bit Operating System Architectures in Raspberry Pi Systems, Technical University Clausthal.
25. KubePipe: A container-based high-level parallelization tool for scalable machine learning pipelines10.1007/s11227-025-06956-x ↗
26. Koukis, G., Skaperas, S., Kapetanidou, I., Mamatas, L., and Tsaoussidis, V. (2024, January 26–29). Performance Evaluation of Kubernetes Networking Approaches across Constraint Edge Environments. Proceedings of the 2024 IEEE Symposium on Computers and Communications (ISCC), Paris, France.10.1109/ISCC61673.2024.10733726 ↗
27. Development of Kubeflow Components in DevOps Framework for Scalable Machine Learning Systems10.22214/ijraset.2021.36419 ↗
28. Kropp, A., and Torre, R. (2020). Docker: Containerize your application. Computing in Communication Networks, Elsevier.10.1016/B978-0-12-820488-7.00026-8 ↗
29. Chen, L., Xian, M., and Liu, J. (2020, January 10–12). Monitoring System of OpenStack Cloud Platform Based on Prometheus. Proceedings of the 2020 International Conference on Computer Vision, Image and Deep Learning (CVIDL), Chongqing, China.10.1109/CVIDL51233.2020.0-100 ↗
30. Mehdi, A., Bali, M., Abbas, S., and Singh, M. (2023, January 6–8). Unleashing the Potential of Grafana: A Comprehensive Study on Real-Time Monitoring and Visualization. Proceedings of the 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India.10.1109/ICCCNT56998.2023.10306699 ↗
31. (2025, September 12). Available online: https://github.com/Teodorhack/Microk8s-cluster-from-scratch-/tree/step-2.
32. (2025, August 11). Kaggle Database—NSL-KDD. Available online: https://www.kaggle.com/code/josiagiven/network-security-attack-classification/notebook.
33. (2025, September 12). Available online: https://github.com/Teodorhack/AIanomaly.
34. Nguyen, Q., Phan, L., and Kim, T. (2022). Load-Balancing of Kubernetes-Based Edge Computing Infrastructure Using Resource Adaptive Proxy. Sensors, 22.10.3390/s22082869 ↗
35. Wayan, I., Pinastawa, R., Pradana, M., and Maulana, N. (2024, January 20–21). Web Server Performance Evaluation: Comparing Nginx and Apache Using K6 Testing Methods for Load, Spike, Soak, and Performance. Proceedings of the 2024 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), Jakarta, Indonesia.10.1109/ICIMCIS63449.2024.10956402 ↗
36. Song, Y., Zhang, W., Ni, H., and Zha, Q. (2011). Benchmarking Apache on Multi-Core Network Processor Platform. International Conference on Computer Technology and Development, ASME Press. [3rd ed.].10.1115/1.859919.paper51 ↗
37. Morić, Z., Dakić, V., and Čavala, T. (2025). Security Hardening and Compliance Assessment of Kubernetes Control Plane and Workloads. J. Cybersecur. Priv., 5.10.3390/jcp5020030 ↗
38. (2025, November 26). Kubernetes Documentation. Using RBAC Authorization. Available online: https://kubernetes.io/docs/reference/access-authn-authz/rbac.
39. Navigating the Challenges and Best Practices in Securing Microservices and Kubernetes Environments
40. Klaermann, S. (2022). Evaluating the Suitability of Kubernetes for Edge Computing. [Master’s Thesis, Technische Universität München].
41. Fair Federated Learning for Multi-Task 6G NWDAF Network Anomaly Detection10.1109/TITS.2024.3461679 ↗
42. Magid, Y., Etzion, O., and Shmueli, O. (2019). Image Classification on IoT Edge Devices. arXiv.
43. Reidy, C., Mohammadi, M., Elbtity, M.E., and Zand, R. (2023). Efficient Deployment of Transformer Models on Edge TPU. OpenReview, Available online: https://openreview.net/pdf/648914b56e5c4dc27b0a2905008b88750a48bfe1.pdf.