Optimizing Cloud Storage Costs: Introducing the Pre-Evaluation-Based Cost Optimization (PECSCO) Mechanism

Innovative cloud computing system offers cutting-edge storage models that prioritize the importance of data, adaptive algorithms for controlling data flow, and cost-effective computational procedures. Current models often encounter difficulties in effectively managing the trade-off between cost reduction and performance enhancement, especially when dealing with substantial amounts of data and unexpected access patterns. Nonetheless, cloud service providers impose fees on users based on the volume of data transmitted to and from cloud storage, resulting in elevated storage costs. Consequently, assessing and confirming the significance of packets (data) before its synchronization with cloud storage becomes imperative. The major contribution of this work lies in the develop of Prior Evaluation Cloud Storage Cost Optimization called (PECSCO) mechanism to optimize the cloud cost with least overhead. The proposed algorithm aimed at reducing cloud storage cost by strategically determining the best locations for evaluators within a network of nodes for efficient monitoring, particularly in surveillance contexts indicated by the mention of CCTVs. The core of the algorithm utilizes a Genetic Algorithm (GA) to find the optimal position for the first evaluator by minimizing the total distance between this evaluator and all CCTV nodes, aiming for surveillance efficiency. A similar process is undertaken for the second evaluator, with the goal of minimizing the distance to critical logic output nodes, ensuring crucial areas are under effective oversight. The Evaluation of the effectiveness of PECSCO mechanism was done by comparing it with existing algorithms like ODAF-TS and OCOA. The results revealed that PECSCO has demonstrated the ability to excel in sensor networks and computational jobs that need both high efficiency and the capacity to handle a significant number of operations. The use of evaluators in the PECSCO mechanism to pre-assess data prior to synchronization with cloud storage has been shown to substantially decrease cloud expenses. Nevertheless, this economical approach poses the difficulty of preserving system responsiveness and the expandability of the assessment procedure.