ILP Optimized LSTM-based Autoscaling and Scheduling of Containers in Edge-cloud Environment

Authors

  • Shivan Singh KLE Technological University, Hubballi, Karnataka, India
  • Narayan D.G. KLE Technological University, Hubballi, Karnataka, India
  • Sadaf Mujawar KLE Technological University, Hubballi, Karnataka, India https://orcid.org/0009-0007-5434-0114
  • G.S. Hanchinamani KLE Technological University, Hubballi, Karnataka, India
  • P.S. Hiremath KLE Technological University, Hubballi, Karnataka, India

DOI:

https://doi.org/10.26636/jtit.2025.2.2088

Keywords:

autoscaling, edge computing, ILP optimization, Kubernetes, LSTM, resource efficiency, scheduling, throughput

Abstract

Edge computing is a decentralized computing paradigm that brings computation and data storage closer to data sources, enabling faster processing and reduced latency. This approach is critical for real-time applications, but it introduces significant challenges in managing resources efficiently in edge-cloud environments. Issues such as increased response times, inefficient autoscaling, and suboptimal task scheduling arise due to the dynamic and resource-constrained nature of edge nodes. Kubernetes, a widely used container orchestration platform, provides basic autoscaling and scheduling mechanisms, but its default configurations often fail to meet the stringent performance requirements of edge environments, especially in lightweight implementations like KubeEdge. This work presents an ILP-optimized, LSTM-based approach for autoscaling and scheduling in edge-cloud environments. The LSTM model forecasts resource demands using both real-time and historical data, enabling proactive resource allocation, while the integer linear programming (ILP) framework optimally assigns workloads and scales containers to meet predicted demands. By jointly addressing auto-scaling and scheduling challenges, the proposed method improves response time and resource utilization. The experimental setup is built on a KubeEdge testbed deployed across 11 nodes (1 cloud node and 10 edge nodes). Experimental results show that the ILP-enhanced framework achieves a 12.34% reduction in response time and a 7.85% increase in throughput compared to the LSTM-only approach.

Downloads

Download data is not yet available.

References

[1] L.H. Phuc, L.-A. Phan, and T. Kim, "Traffic-aware Horizontal Pod Autoscaler in Kubernetes-based Edge Computing Infrastructure", IEEE Access, vol. 10, pp. 18966-18977, 2022.
View in Google Scholar

[2] S.T. Singh, M. Tiwari, and A.S. Dhar, "Machine Learning based Workload Prediction for Auto-scaling Cloud Applications", 2022 OPJU International Technology Conference on Emerging Technologies for Sustainable Development (OTCON), Raigarh, India, 2023.
View in Google Scholar

[3] I. Ahmad, M.G. AlFailakawi, A. AlMutawa, and L. Alsalman, "Container Scheduling Techniques: A Survey and Assessment", Journal of King Saud University - Computer and Information Sciences, vol. 34, pp. 3934-3947, 2022.
View in Google Scholar

[4] K. Senjab, S. Abbas, N. Ahmed, and A.R. Khan, "A Survey of Kubernetes Scheduling Algorithms", Journal of Cloud Computing, vol. 12, art. no. 87, 2023.
View in Google Scholar

[5] K. Zhu et al., "Proactive Hybrid Autoscaling for Container-Based Edge Applications in Kubernetes", Lecture Notes of the Institute for Computer Sciences, vol. 574, pp. 330-345, 2024.
View in Google Scholar

[6] Z. Wang, Q. Zhu, and Y. Hou, "Multiworkflow Scheduling in Edge-cloud Computing by African Vulture Optimization Algorithm", 2024 11th International Forum on Electrical Engineering and Automation (IFEEA), Shenzhen, China, 2024.
View in Google Scholar

[7] J. Li, P. Singh, and S. Toor, "Proactive Autoscaling for Edge Computing Systems with Kubernetes", Proc. of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion (UCC’21), art. no. 22, pp. 1-8, 2022.
View in Google Scholar

[8] L.H. Phuc et al., "Node-based Horizontal Pod Autoscaler in KubeEdge-based Edge Computing Infrastructure", IEEE Access, vol. 10, pp. 134417-134426, 2022.
View in Google Scholar

[9] J. Dogani and F. Khunjush, "Proactive Auto-scaling Technique for Web Applications in Container-based Edge Computing Using Federated Learning Model", Journal of Parallel and Distributed Computing, vol. 187, art. no. 104837, 2024.
View in Google Scholar

[10] T.-X. Do and V.K.N. Tan "Hybrid Autoscaling Strategy on Container-Based Cloud Platform", International Journal of Software Innovation, vol. 10, 2022, pp. 1-12..
View in Google Scholar

[11] X. Feng et al., "Adaptive Container Auto-scaling for Fluctuating Workloads in Cloud", Future Generation Computer Systems, vol. 172, art. no. 107872, 2025.
View in Google Scholar

[12] S.D. Konidena, "Efficient Resource Allocation in Kubernetes Using Machine Learning", International Journal of Innovative Science and Research Technology, vol. 9, 2024.
View in Google Scholar

[13] J. Zhou, S. Pal, C. Dong, and K. Wang, "Enhancing Quality of Service Through Federated Learning in Edge-cloud Architecture", Ad Hoc Networks, vol. 156, art. no. 103430, 2024.
View in Google Scholar

[14] S.-H. Kim and T. Kim, "Local Scheduling in KubeEdge-based Edge Computing Environment", Sensors, vol. 23, art. no. 1522, 2023.
View in Google Scholar

[15] M. Raeisi-Varzaneh, O. Dakkak, A. Habbal, and B.-S. Kim, "Resource Scheduling in Edge Computing: Architecture, Taxonomy, Open Issues and Future Research Directions", IEEE Access, vol. 11, pp. 25329-25350, 2023.
View in Google Scholar

[16] Z. Shi and Z. Shi, "Multi-node Task Scheduling Algorithm for Edge Computing Based on Multi-Objective Optimization", Journal of Physics: Conference Series, vol. 1607, art. no. 012017, 2020.
View in Google Scholar

[17] K. Wang et al., "Computing Aware Scheduling in Mobile Edge Computing System", Wireless Networks, vol. 27, pp. 4229-4245, 2021.
View in Google Scholar

[18] G. Vijayasekaran and M. Duraipandian, "Resource Scheduling in Edge Computing IoT networks Using Hybrid Deep Learning Algorithm", System Research and Information Technologies, pp. 86-101, 2022.
View in Google Scholar

[19] Y. Lu et al., "EA-DFPSO: An Intelligent Energy-efficient Scheduling Algorithm for Mobile Edge Networks", Digital Communications and Networks, vol. 8, pp. 237-246, 2022.
View in Google Scholar

[20] P. Khoshvaght et al., "A Multi-objective Deep Reinforcement Learning Algorithm for Spatio-temporal Latency Optimization in Mobile IoT-enabled Edge Computing Networks", Simulation Modelling Practice and Theory, vol. 143, art. no. 103161, 2025.
View in Google Scholar

[21] P. Vishesh et al., "Optimized Placement of Service Function Chains in Edge Cloud with LSTM and ILP", SN Computer Science, vol. 6, art. no. 44, 2024.
View in Google Scholar

[22] Z. Ding and Q. Huang, "COPA: A Combined Autoscaling Method for Kubernetes", 2021 IEEE International Conference on Web Services (ICWS), Chicago, USA, 2021.
View in Google Scholar

Cover page 2/2025

Downloads

Published

2025-06-30

Issue

No. 2 (2025)

Section

ARTICLES FROM THIS ISSUE

License

Copyright (c) 2025 Shivan Singh, Narayan D. G., Sadaf Mujawar, G.S. Hanchinamani, P.S. Hiremath

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
S. Singh, N. . D.G., S. Mujawar, G. Hanchinamani, and P. Hiremath, “ILP Optimized LSTM-based Autoscaling and Scheduling of Containers in Edge-cloud Environment”, JTIT, vol. 100, no. 2, pp. 56–68, Jun. 2025, doi: 10.26636/jtit.2025.2.2088.