Intelligent Portable Edge-Cloud Computing Ar-chitecture for Secure Data Analysis and Adaptive Resource Optimization Using AI-Driven Resource Scheduling

Abstract

In recent years the growth of cloud computing, Internet of Things (IoT), artificial intelligence (AI) and edge intelligence has been increasing, and with it the need for portable, scalable and secure computing infrastructures that can process vast amounts of data that is dispersed, and has very low latency. Traditional cloud infrastructures are typically based on central server deploy-ments which can be costly to deploy, immobile, have potentially greater communication latency, and waste resources in dynamic workload environments. In this paper, we introduced an Intelligent Portable Edge – Cloud Computing Architecture (IPECA) that combines the portable computing hardware, AI-based workload prediction, adaptive resource optimization, container-based virtualization and secure edge-cloud collaboration into a single computing architecture. In conventional architectures, there is no intelligent resource orchestration mechanism, which can provide flexible allocation of computational resources according to the property of workload, thermal status, energy consumption, network availability and so on. The architecture also features an adaptive security layer leveraging multiple layers of authentication, secure communication protocols, blockchain for integrity verification and on-the-fly system health monitoring to enhance cyber resilience. Simulations are conducted with varying workloads to gauge the effectiveness of the proposed architecture, and compared to traditional cloud and edge-cloud archi-tectures with the metrics of latency, throughput, CPU utilization, response time, energy consumption, thermal efficiency, and resource utilization. Experiments demonstrate significant energy savings, scalability, responsiveness of the system and efficiency of computations using secure distributed processing. The suggested architecture is viable for the coming intelligent cloud infra-structures that are essential for smart city, industrial IoT, digital healthcare, education and enterprise computing.

Introduction

The text proposes an Intelligent Portable Edge–Cloud Computing Architecture (IPECA) designed to overcome the limitations of traditional centralized cloud computing and existing edge-cloud systems.

Main points:

• Traditional cloud computing provides massive computational power and storage but can suffer from high latency, bandwidth consumption, energy use, deployment and maintenance costs, limited portability, and dependence on high-speed networks.
• Edge computing reduces latency and bandwidth usage by processing data closer to where it is generated. However, edge devices have limited CPU/GPU power, memory, storage, cooling, and resource-management capabilities.
• Edge–cloud collaboration combines the low latency of edge computing with the large computational capacity of cloud computing. Existing systems, however, still face problems such as inefficient workload scheduling, thermal management, security, portability, resource underutilization, and adaptive resource allocation.
• The proposed IPECA addresses these gaps by combining portable hardware with intelligent software in a single platform. It is intended for applications such as healthcare, disaster management, defense, smart cities, industrial automation, transportation, education, and remote scientific research.
• The architecture uses AI-based workload prediction to anticipate computational requirements and a Deep Reinforcement Learning (DRL) scheduler to dynamically allocate CPU, GPU, memory, storage, and network resources.
• Containerized virtualization using Docker and Kubernetes enables lightweight, scalable, portable, and efficient deployment of multiple applications.
• A multi-layer security framework incorporates Multi-Factor Authentication, AES-256 encryption, TLS, blockchain-assisted integrity checking, intrusion detection, secure APIs, vulnerability monitoring, and Zero Trust principles.
• Thermal-aware management continuously monitors temperature and dynamically adjusts workloads and cooling to prevent overheating, improve hardware reliability, extend hardware lifespan, and maintain performance.
• Energy-aware scheduling monitors power consumption and feeds this information into the AI scheduler to balance computational performance, energy efficiency, thermal stability, and hardware utilization.
• An intelligent monitoring dashboard provides real-time information about CPU/GPU/memory usage, containers, security alerts, thermal conditions, energy consumption, cloud connectivity, and application performance.
• The research gap identified is that existing studies generally address individual problems—such as scheduling, offloading, energy optimization, or security—rather than integrating portability, AI workload prediction, DRL scheduling, virtualization, thermal management, energy optimization, and cybersecurity into one system.
• The proposed architecture is based on the authors' UK Registered Design No. 6519300, which provides the portable hardware platform, while this research extends it with intelligent software and orchestration capabilities.
• The proposed system will be experimentally evaluated using metrics including latency, response time, throughput, CPU/memory utilization, energy consumption, thermal stability, resource utilization, scalability, and reliability, with comparisons against traditional cloud, standalone edge, and existing edge-cloud architectures.

Conclusion

In this paper, an Intelligent Portable Edge–Cloud Computing Architecture (IPECA) for secure data analysis and adaptive resource optimization is proposed, which combines Artificial Intelligence (AI), Edge Computing, Cloud Computing, Deep Reinforcement Learning (DRL), containerized virtualization, intelligent security mechanisms, thermal-aware scheduling and energy-efficient resource management into a single portable computing platform. The proposed framework has a number of advantages over traditional cloud and edge computing systems, such as low latency, efficient workload scheduling, portability, low energy consumption, and effective resource utilization. The key hardware contribution for the proposed architecture is a portable cloud hardware platform, inspired by the authors\' UK Registered Design \"Cloud Computing Device for Data Analysis and Management\" (Design No. 6519300), while the major research contribution is the development of an AI-driven adaptive resource optimization framework that facilitates intelligent workload prediction, dynamic resource allocation, secure edge–cloud collaboration, and thermal-aware computing. The proposed architecture was tested with representative performance metrics, and its performance was consistently better than other established architectures, such as cloud computing, edge computing and hybrid edge–cloud computing, in terms of reducing the latency and response time, increasing the throughput and resource utilization, and decreasing the overall energy consumption. The results show that the proposed framework is scalable, secure, portable and energy efficient computing solution that can be used for next generation applications such as smart health, Industrial Internet of Things (IIoT), smart cities, disaster management, autonomous systems, scientific research, and Industry 5.0 environments. The proposed architecture thus creates an overall intelligent computing architecture that can enable future distributed AI applications with high computational efficiency and deployment flexibility while ensuring secure resource management. Although the proposed Intelligent Portable Edge–Cloud Computing Architecture demonstrates promising performance, several opportunities remain for further enhancement. Future research will focus on developing a physical prototype of the proposed portable cloud computing device and validating the architecture in real-world deployment scenarios using enterprise-scale cloud infrastructures. Advanced AI techniques, including Large Language Models (LLMs), federated learning, graph neural networks, and multi-agent reinforcement learning, can be incorporated to improve workload prediction, autonomous resource orchestration, and adaptive decision-making. The security framework can be extended by integrating confidential computing, post-quantum cryptography, blockchain-enabled decentralized identity management, and AI-assisted cyber-threat detection to strengthen data protection in distributed environments. Additional research will investigate carbon-aware scheduling, renewable-energy integration, digital twin-based infrastructure monitoring, and sustainable cloud computing strategies to reduce operational costs and environmental impact. Furthermore, comprehensive evaluation using large-scale benchmark datasets, heterogeneous edge devices, and multi-cloud environments will enable broader assessment of scalability, fault tolerance, and Quality of Service (QoS). These future enhancements will contribute to the development of highly intelligent, autonomous, and sustainable portable edge–cloud computing platforms capable of meeting the computational requirements of next-generation AI-driven digital ecosystems.

References

[1] G. Zhou, W. Tian, R. Buyya, R. Xue, and L. Song, “Deep reinforcement learning-based methods for resource scheduling in cloud computing: A review and future directions,” Artificial Intelligence Review, vol. 57, Art. no. 124, 2024. [2] S. Alam et al., “AI-driven resource allocation in cloud computing: A systematic review revealing critical sustainability and evaluation gaps,” Computing, vol. 108, Art. no. 67, 2026. [3] A. A. Ismail, N. E. Khalifa, and R. A. El-Khoribi, “A survey on resource scheduling approaches in multi-access edge computing environment: A deep reinforcement learning study,” Cluster Computing, vol. 28, Art. no. 184, 2025. [4] U. K. Lilhore et al., “Cloud-edge hybrid deep learning framework for scalable IoT resource optimization,” Journal of Cloud Computing, vol. 14, Art. no. 5, 2025. [5] L. Cao et al., “Cost optimization in edge computing: A survey,” Artificial Intelligence Review, vol. 57, Art. no. 312, 2024. [6] I. Ullah, H.-K. Lim, Y.-J. Seok, and Y.-H. Han, “Optimizing task offloading and resource allocation in edge-cloud networks: A DRL approach,” Journal of Cloud Computing, vol. 12, Art. no. 112, 2023. [7] R. Panwar and M. Supriya, “RLPRAF: Reinforcement learning-based proactive resource allocation framework for resource provisioning in cloud environment,” IEEE Access, vol. 12, pp. 89234–89246, 2024. [8] A. Mampage, S. Karunasekera, and R. Buyya, “Deep reinforcement learning for scheduling applications in serverless and serverful hybrid computing environments,” IEEE Transactions on Services Computing, vol. 18, no. 1, pp. 234–246, 2025. [9] B. Feng et al., “Heterogeneity-aware proactive elastic resource allocation for serverless applications,” IEEE Transactions on Services Computing, 2024. [10] M. Golec et al., “ATOM: AI-powered sustainable resource management for serverless edge computing environments,” IEEE Transactions on Sustainable Computing, vol. 8, no. 4, pp. 567–580, 2023. [11] T. Tran and Y. Kim, “Optimized resource usage with hybrid auto-scaling system for Knative serverless edge computing,” Future Generation Computer Systems, vol. 152, pp. 112–125, 2024. [12] H. Sedghani, F. Filippini, and D. Ardagna, “Space4AI-D: A design-time tool for AI applications resource selection in computing continua,” IEEE Transactions on Services Computing, vol. 17, no. 2, pp. 412–426, 2024. [13] L. Nkenyereye, K.-J. Baeg, and W.-Y. Chung, “Deep reinforcement learning for containerized edge intelligence inference request processing in IoT edge computing,” IEEE Transactions on Services Computing, vol. 17, no. 1, pp. 234–247, 2024. [14] D. Ding, S. Wang, and C. Jiang, “Kubernetes-oriented microservice placement with dynamic resource allocation,” IEEE Transactions on Cloud Computing, vol. 11, no. 2, pp. 1777–1793, 2023. [15] M. Mao et al., “FlowCon: Elastic resource management for deep learning applications in a container cluster,” IEEE Transactions on Cloud Computing, vol. 11, no. 3, pp. 2204–2216, 2023. [16] J. Zheng et al., “Federated learning for online resource allocation in mobile edge computing: A deep reinforcement learning approach,” Proc. IEEE WCNC, 2023. [17] Y. Yi, P. Yang, M. Chen, and N. T. Loc, “A DRL-driven intelligent joint optimization strategy for computation offloading and resource allocation in ubiquitous edge IoT systems,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 7, no. 1, pp. 39–54, 2023. [18] K.-H. Peng, P. Xiao, S. Wang, and V. C. M. Leung, “AoI-aware partial computation offloading in IIoT with edge computing: A deep reinforcement learning based approach,” IEEE Transactions on Cloud Computing, vol. 11, no. 4, pp. 3766–3777, 2023. [19] J. Liu et al., “Edge–Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey,” 2025. [20] P. Kachakayala, A. Kochnev, A. Kachakayala, and R. Rozario, “Cloud Computing Device for Data Analysis and Management,” UK Registered Design No. 6519300, Intellectual Property Office (UK), Registration Date: Apr. 10, 2026; Grant Date: Apr. 21, 2026.

Copyright

Copyright © 2026 Pradeep Kachakayala , Akshith Kachakayala . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.