Efficient Storage Approach for Big Data Analytics: An Iterative-Probabilistic Method for Dynamic Resource Allocation of Big Satellite Images

Abstract

Satellite images play a crucial role in ecology as they provide rich information about the Earth’s surface. The deep analysis of satellite images presents a vast challenge due to the sheer size of the data that needs to be managed. Sophisticated storage solutions are required to handle the ever-increasing velocity of incoming data and to deal with potential latency or data loss. Storage balancing ensures efficient allocation and distribution of storage capacity across a system, which involves monitoring, analyzing, and adjusting how data is stored to optimize performance, minimize downtime, and maximize cost savings. Additionally, storage balancing helps avoid data bottlenecks by automatically redistributing data across multiple resources. While many solutions have been proposed to balance storage, no polynomial solution is available. This paper addresses the issue of transmitting a considerable amount of satellite images across the network to various storage supports. The challenge is to find an effective way to schedule these satellite images to the storage supports that lead to equitable results in distribution. Many heuristics and enhancement methods are proposed to solve this problem. The effectiveness of the algorithms presented in this paper was tested and analyzed through extensive testing. The experimental study shows that the proposed heuristics outperform those developed in the literature. Indeed, in 73.8% of cases, the best-proposed algorithm, the best iterative-selection satellite images algorithm ( $BIS$ ), reached the best solution compared to the best algorithm in the literature and the other proposed algorithms. The $BIS$ algorithm obtained an average gap of 0.147 in an average running time of 1.0654 s.

Keywords

• Satellite images
• big data
• storage load balancing
• heuristics
• algorithms
• approximate solutions