Dynamic Load Distribution and Replica Placement Strategies in Distributed Cloud-Native Architectures
Keywords:
Cloud-native, Replica placement, Load balancing, Microservices, Distributed systems, Kubernetes, Edge computing, Resilience, Scalability, Service meshAbstract
As cloud-native architectures gain traction, the efficient distribution of workloads and strategic placement of replicas have become critical for enhancing system performance, resilience, and scalability. This paper explores strategies for dynamic load distribution and replica placement across distributed cloud-native systems. It highlights challenges associated with microservice decomposition, Kubernetes orchestration, latency optimization, and geo-distributed environments. By analyzing existing research, we identify gaps in adaptive load balancing, cost-aware replication, and cross-cloud federation strategies, proposing a framework that dynamically adjusts to real-time workload metrics and network topologies. Furthermore, we present a layered architectural model that integrates telemetry-driven decision-making with service mesh control to orchestrate replicas at scale. Through simulation-based experimentation, we demonstrate how dynamic strategies significantly reduce response latency and improve service availability. The insights from this study aim to guide future implementations of intelligent orchestration mechanisms in complex, globally distributed systems.
References
Kratzke, Nane. “About the Complexity to Transfer Cloud Applications at Runtime.” International Conference on Cloud Computing and Services Science, 2017.
Yu, Guozheng, et al. “Microscaler: Cost-Effective Scaling for Microservice Applications.” IEEE Transactions on Cloud Computing, 2020.
Santos, J., et al. “Resource Provisioning in Fog Computing Through Deep Reinforcement Learning.” IFIP/IEEE International Symposium on Integrated Network Management, 2021.
Sarrigiannis, I., et al. “Online VNF Lifecycle Management.” IEEE Internet of Things Journal, 2019.
Tarasov, Vasily, et al. “CNSBench: A Cloud Native Storage Benchmark.” USENIX Conference on File and Storage Technologies, 2021.
Sharma, Rahul, and Atyab, M. Cloud-Native Microservices with Apache Pulsar, Springer, 2021.
Zhao, Hao, et al. “Distributed Redundant Placement for Microservice-Based Applications at the Edge.” IEEE Transactions on Parallel and Distributed Systems, 2020.
Ambroszkiewicz, Stanisław, et al. “Functionals in the Clouds.” arXiv preprint arXiv:2105.10362, 2021.
Merenstein, A., et al. “CNSBench: Cloud Native Storage Benchmark.” USENIX FAST, 2021.
Bhaskaran, S.V. “Integrating Data Quality Services in Big Data Ecosystems.” Journal of Applied Big Data Analytics, 2020.
Chandrasekaran, G., et al. “CASE: A Context-Aware Storage Placement Ecosystem.” IEEE, 2021.
Goniwada, S.R. Cloud Native Data Architecture, Springer, 2021.
Sharma, R., and Atyab, M. Cloud Native Microservices with Apache Pulsar, Springer, 2021.
Garcia-Arellano, Carlos, et al. “Db2 Event Store: An IoT Database Engine.” Proceedings of the VLDB Endowment, 2020.
Lu, J., et al. “5G Enhanced Service-Based Core Design.” IEEE Wireless Communications and Networking Conference, 2019.
