Enhancing Edge Data Deduplication With Robust Optimization Amidst Uncertainties

Abstract

The rapid expansion of data generated by mobile and Internet-of-Things (IoT) devices has placed immense pressure on traditional cloud infrastructures, particularly in terms of latency and storage efficiency. Mobile Edge Computing (MEC) has emerged as a promising paradigm by relocating computation and storage resources closer to end users. However, the limited capacity of edge servers introduces new challenges in data management. This paper presents a robust optimization-based data deduplication framework tailored for MEC environments. The proposed system incorporates uncertainty-aware mechanisms to handle dynamic factors such as user mobility, fluctuating workloads, and edge server failures. Two algorithms—uEDDE-C and uEDDE-A—are introduced to balance accuracy and computational efficiency. Experimental insights indicate that the framework significantly improves storage utilization, reduces latency, and enhances system reliability under uncertain conditions.