|
Original research DYNAMIC RESOURCE ALLOCATION IN EDGE COMPUTING ENVIRONMENTS: A MACHINE LEARNING APPROACHPages 133-138 Arnika Gunjal, Rucha Pednekar, Snehal Kanere, Shivani Ruke Abstract
Edge computing is a promising paradigm that addresses the limitations of traditional cloud-centric architectures by placing computation near the data source. The main challenge is efficient resource allocation for various applications while optimizing resource utilization. This paper proposes a machine learning-based approach for dynamic resource allocation in edge computing environments. It uses machine learning algorithms to analyze real-time data traffic patterns, application demands, and edge node capabilities to dynamically allocate resources like compute, storage, and bandwidth. By continuously acquiring historical data and adjusting to varying workloads, the system improves overall system performance and user experience. Experimental evaluation and simulations show the effectiveness and efficiency of this approach in enhancing resource utilization, lowering latency, and improving scalability in edge computing environments.
Keywords: Edge Computing, Machine Learning, Dynamic Resource Allocation, Resource Management, Real-time Processing,
Latency Reduction, Performance Optimization.
.
|
PDF 