Vol. 4 No. 2 (2024): July−December 2024
Articles

Cloud-Enabled Trust-Aware Multi-Agent Reinforcement Learning Framework for Dynamic, Regulation-Compliant Border Patrol Resource Optimization

View PDF
  • Raj Sonani
Raj Sonani
SC Johnson College of Business, Cornell University, New York, USA

Published 2024-11-07

Keywords

  • Border patrol optimization,
  • Multi-Agent Reinforcement Learning,
  • cloud computing,
  • trust-aware communication,
  • real-time data sharing

How to Cite

Sonani, R. (2024). Cloud-Enabled Trust-Aware Multi-Agent Reinforcement Learning Framework for Dynamic, Regulation-Compliant Border Patrol Resource Optimization. Spectrum of Research, 4(2). Retrieved from https://spectrumofresearch.com/index.php/sr/article/view/18

Copyright (c) 2024 Spectrum of Research

Creative Commons License

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

Abstract

The problem of how to keep the balance between a country's national security and its obligation to human rights is an important issue for the border agencies all over the world, moreover, it is especially visible in the times of dynamically changing and uncertain migratory, geopolitics and environmental conditions. The traditional static resource allocation models because they have no flexibility, inefficient or hard-to-implement resource allocation processes, and do not include any form of real-time coordination, the limited ability of the resources. In this document the proposal is made of a Cloud-Enabled Trust-Aware Multi-Agent Reinforcement Learning (MARL) Framework, which is designed to achieve border patrol resource allocation optimization, meanwhile, compliance with the law and humanitarian principles remains. The proposed method utilizes cloud computing with its scalability and real-time features to deploy decentralized agents which represent patrol units, drones, and monitoring systems. These agents work within a dynamic, cloud-hosted environment which is the main driver for real-time data sharing, adaptive learning, and collaborative decision-making activities. The main idea behind the cloud is that it is also capable of hosting.  The trust-aware communication protocol is an evolving Aegis TAP that dynamically adjusts trust scores dependent on the accuracy and usefulness of the shared information. This system leads to a decrease in the number of redundant data exchanges, the lessening of communication overhead, and the boosting of coordination efficiency in the distributed agent network.

View PDF

References

  1. A. Asghari, M. K. Sohrabi, and F. Yaghmaee, "A cloud resource management framework for multiple online scientific workflows using cooperative reinforcement learning agents," Computer Networks, vol. 179, p. 107340, 2020.
  2. A. Belgacem, S. Mahmoudi, and M. Kihl, "Intelligent multi-agent reinforcement learning model for resources allocation in cloud computing," Journal of King Saud University-Computer and Information Sciences, vol. 34, no. 6, pp. 2391-2404, 2022.
  3. S. Nagarajan, P. S. Rani, M. Vinmathi, V. Subba Reddy, A. L. M. Saleth, and D. Abdus Subhahan, "Multi agent deep reinforcement learning for resource allocation in container‐based clouds environments," Expert Systems, 2023.
  4. H. Gao, R. Wang, S. He, L. Wang, J. Liu, and Z. Chen, "A Cloud-Edge Collaboration Solution for Distribution Network Reconfiguration Using Multi-Agent Deep Reinforcement Learning," IEEE Transactions on Power Systems, 2023.
  5. R. Rashidifar, F. F. Chen, M. Shahin, A. Hosseinzadeh, H. Bouzary, and A. Shahin, "Reinforcement learning-based model for optimization of cloud manufacturing-based multi objective resource scheduling: a review," in International Conference on Flexible Automation and Intelligent Manufacturing, 2023: Springer, pp. 133-140.
  6. H. U. Rehman et al., "Cloud based decision making for multi-agent production systems," in Progress in Artificial Intelligence: 20th EPIA Conference on Artificial Intelligence, EPIA 2021, Virtual Event, September 7–9, 2021, Proceedings 20, 2021: Springer, pp. 673-686.
  7. Y. Jin, M. Bouzid, D. Kostadinov, and A. Aghasaryan, "Resource management of cloud-enabled systems using model-free reinforcement learning," Annals of Telecommunications, vol. 74, pp. 625-636, 2019.
  8. M. A. N. Saif, S. Niranjan, B. A. H. Murshed, H. D. E. Al-Ariki, and H. M. Abdulwahab, "Multi-agent QoS-aware autonomic resource provisioning framework for elastic BPM in containerized multi-cloud environment," Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 9, pp. 12895-12920, 2023.
  9. T. Samad, S. Iqbal, A. W. Malik, O. Arif, and P. Bloodsworth, "A multi-agent framework for cloud-based management of collaborative robots," International Journal of Advanced Robotic Systems, vol. 15, no. 4, p. 1729881418785073, 2018.
  10. M. Afrin, J. Jin, A. Rahman, A. Rahman, J. Wan, and E. Hossain, "Resource allocation and service provisioning in multi-agent cloud robotics: A comprehensive survey," IEEE Communications Surveys & Tutorials, vol. 23, no. 2, pp. 842-870, 2021.
  11. S. Jung, W. J. Yun, M. Shin, J. Kim, and J.-H. Kim, "Orchestrated scheduling and multi-agent deep reinforcement learning for cloud-assisted multi-UAV charging systems," IEEE Transactions on Vehicular Technology, vol. 70, no. 6, pp. 5362-5377, 2021.
  12. Y. Wang et al., "Multi-objective workflow scheduling with deep-Q-network-based multi-agent reinforcement learning," IEEE access, vol. 7, pp. 39974-39982, 2019.
  13. A. Asghari and M. K. Sohrabi, "Combined use of coral reefs optimization and multi-agent deep Q-network for energy-aware resource provisioning in cloud data centers using DVFS technique," Cluster Computing, vol. 25, no. 1, pp. 119-140, 2022.
  14. N. Mishra, A. Singh, S. Kumari, K. Govindan, and S. I. Ali, "Cloud-based multi-agent architecture for effective planning and scheduling of distributed manufacturing," International Journal of Production Research, vol. 54, no. 23, pp. 7115-7128, 2016.
  15. R. Rashidifar, "Optimization of Multi-Objective Resource Scheduling in Cloud Manufacturing Environment via Integrating Reinforcement Learning and Deep Neural Network," The University of Texas at San Antonio, 2023.