Browse and download academic research papers
Distributed cloud environments face significant challenges in efficiently allocating heterogeneous resources under dynamic workloads and failure conditions. This paper presents a scalable resource allocation framework that integrates adaptive load balancing, resource optimization, auto-scaling, and fault tolerance strategies to enhance system performance, scalability, and reliability. Experimental results demonstrate that the framework achieves CPU and memory utilizations of 84.6% and 87.1%, respectively, reduces average response time to 112 ms, and attains 99.1% service availability with a recovery time of 12 seconds.
Trust management is a critical challenge in distributed and cloud computing environments due to their decentralized architecture, dynamic resource sharing, and exposure to malicious entities. Traditional centralized trust models suffer from scalability limitations, single points of failure, and lack of transparency. This paper proposes a blockchain-enabled trust management framework that integrates on-chain identity management, smart contracts, reputation evaluation, and AI-assisted trust analysis to provide secure, transparent, and adaptive trust decisions.
Large-scale distributed cloud platforms are increasingly critical for modern computational workloads, yet they face significant challenges in ensuring task reliability and efficient resource utilization. Faults such as server failures, network delays, and task execution errors can severely degrade system performance if not properly managed. This study presents a fault-tolerant scheduling framework that dynamically monitors resources, detects potential failures, and optimizes task allocation to ensure minimal disruption in cloud operations.
Edge–cloud integrated distributed systems have emerged as a promising architecture to support latency-sensitive and computation-intensive applications. However, efficient load balancing remains a critical challenge due to dynamic workloads, heterogeneous resources, and varying network conditions across edge and cloud layers. This paper investigates load balancing techniques designed for edge–cloud environments, focusing on task allocation, resource utilization, and performance optimization.
Container-based microservices have emerged as a fundamental paradigm in cloud-native distributed systems due to their scalability, flexibility, and efficient resource utilization. This study presents a comprehensive performance analysis of container-based microservices, focusing on key metrics including resource utilization, scalability, latency, and response time. Using Docker and Kubernetes deployed across multi-cloud environments, the proposed evaluation framework systematically compares container-based architectures with traditional monolithic and virtual machine (VM)–based systems.
The rapid expansion of distributed cloud computing has enabled large-scale data storage and collaborative processing across multiple cloud platforms. However, ensuring secure data sharing in such decentralized environments remains a significant challenge due to risks such as unauthorized access, data leakage, and integrity breaches. This paper presents an overview of secure data sharing models in distributed cloud architectures, including blockchain-based frameworks, proxy re-encryption schemes, attribute-based encryption, and federated learning approaches.