17-10-2016, 02:49 PM
: Evaluation and Comparison of Adaptive security management of real-time storage applications over NAND based storage systems.
1459439958-editit.docx (Size: 15.43 KB / Downloads: 5)
1.Introduction
The goal of this project is to evaluate and compare the adaptive security management of real-time storage applications over NAND based storage systems using commonly used algorithms.Based on the appropriate constraints evaluation is done .The performance is tested on parameters which tells whether NAND is suitable or the adaptive security storage for a particular scenario.Evaluation of the results of a dynamic model that captures the vulnerability and utilization constraints in NAND-based storage systems
2.Motivation
As the growth in performance has begun to level off, there has been an increasing focus on optimizing system power consumption as well as raw performance. Furthermore, this has always been an important area of consideration in mobile and embedded systems, which are both areas which are experiencing rapid growth. Although there has been a good deal of research already put into hard-disk scheduling algorithms, and also methods of reducing hard-disk power consumption, there has been comparatively little done in the area of reducing hard-disk power consumption through the application of power-aware scheduling algorithms, and specifically very little has been done in terms of simulation. NAND based storage had become very important because of its own advantages. This is an interesting problem because the results of the research have the potential to greatly extend the battery life of mobile and embedded systems, and to reduce the amount of power consumed by other systems. Typically, the current approaches to this issue in the real-world involve simply suspending/powering down the hard-disk whenever there are no pending requests, or alternatively after a certain amount of idle time has passed. These approaches are not necessarily ideal, as they can result in lots of power-state transitions, or in leaving the disk fully powered for longer than is optimal.
3.Project Summary
In this project, we are interested in online optimization of security-sensitive storage applications over modern NVM-based embedded systems, whose workloads are unpredictable but have explicit timing constraint and certain security constraint. Sensitive data must be stored before a specific deadline, otherwise it will lose its validity. To address these challenges, this project presents a Feedback Vulnerability and Utilization Control (FVUC) mechanism.
4.Project Details
Comparison of security-critical storage applications based on security protection of NAND flash systems.Evaluation of the results of a dynamic model that captures the vulnerability and utilization constraints in NAND-based storage systems.Reporting a feedback control loop to guarantee security performance and soft real-time requirements
Conclusion
This analysis will investigate the performance of various hard-disk scheduling and power-management algorithms under a number of different situations, and attempt to discuss and compare the performance of each.. To address these challenges, this project presents a Feedback Vulnerability and Utilization Control (FVUC) mechanism. FVUC employs two proportional–integral controllers, the Utilization Controller and the Vulnerability Controller, to build a big feedback loop which dynamically monitors the system run-time status as well as decides how many flash pages would be encrypted by a cryptography service. Relied on the accurate model and design, FVUC can make a balance between the utilization and vulnerability, and achieve a better overall performance. Based on synthetic experiments, we obtain that FVUC can fully beat other three mechanisms on the overall performance with acceptable time overhead. Equipped with proportional–integral controller, FVUC can make the system more stable than the one with only proportional controller. The proposed mechanism can be utilized to resist on-line confidential attack and even achieve the off-line privacy protection when embedded devices are lost or stolen.