Multimedia Storage System Research Articles

An auto-scaling mechanism for cloud-based multimedia storage systems: a fuzzy-based elastic controller

An auto-scaling mechanism for cloud-based multimedia storage systems: a fuzzy-based elastic controller

Cyber defence triage for multimedia data intelligence: Hellsing, Desert Falcons and Lotus Blossom APT campaigns as case studies

Advanced persistent threats (APTs) refer to sophisticated attacks to businesses and individuals in which adversaries use multiple attack vectors to achieve their objectives. The main challenge regarding APT analysis and defence is that all research body about APTs is fragmented; only a few scientific papers have discussed APT features. In order to defend against APTs, it is necessary to have a complete understanding of their tactics, techniques, and procedures (TTPs). In this paper, we analyse TTPs of three APT groups, namely Hellsing, Desert Falcons and Lotus Blossom, that actively targeted multimedia data storage and multimedia systems. Adopting three attack attribution models (i.e., Lockheed Martin cyber kill-chain, diamond model and course of action matrix) we provide a comprehensive cyber defence triage process (CDTP) against the considered APTs. The CDTP highlights steps undertaken by these APT groups, uncovers factors that have influenced achieving their objectives and suggests possible mitigations against them.

Multiservice Load Balancing with Hybrid Particle Swarm Optimization in Cloud-Based Multimedia Storage System with QoS Provision

Load balancing is a method of workload distribution across various computers or instruction data centres for maximizing throughput and minimizing work load on resources. To perform load balancing techniques in cloud computing environments, various challenges such as data security, and proper distribution exist which requires serious attention. The most important challenge posed by cloud applicationsis the provision of Quality of Service (QoS) provision as it develops the problem of resource allocation to the application so as to guarantee a service level along dimensions such as performance, availability and reliability. A centralized hierarchical Cloud-based Multimedia System (CMS) consisting of a resource manager, cluster heads, and server clusters is being considered by which the resource manager assigns clients' requests to server clusters for performing multimedia service tasks based on the job features after which each the job is assigned to the servers within its server cluster by the cluster head. Designing an effective load balancing algorithm for CMS however being a complicated and challenging task, enables spreading of multimedia service job load on servers at the minimal cost for transmitting multimedia data between server clusters and clients without exceeding the maximal load limit of each server cluster. In the present work, the Multiple Kernel Learning with Support Vector Machine (MKL-SVM) approach is proposed to quantify the disturbance in the utilization of multiple resources on a resource manager at client side and then verifying at the server side in the each cluster. Also, Fuzzy Simple Additive Weighting (FSAW) method is introduced for QoS provision for improving the system performance. The proposed model CMSdynMLB serves as the multiservice load balancing while considering the integer linear programming problem having unevenness measurement. In order to solve the problem of dynamic load balancing, Hybrid Particle Swarm Optimization (HSPO) is proposed as it holds well for dynamic problems. From the simulation results, it is determined that proposed MKL-SVM algorithm can efficiently manage the dynamic multiservice load balancing.

Scalable Multimedia Archive Storage System Research

In the traditional file system, The lack of contact between the file name and the data content led to waste a lot of availability storage space, especially in large data archive storage system. This paper designs and implements a scalable multimedia archive storage system, called IMCAS. IMCAS use CAS store the archive data and use real-time monitor program automatically extract metadata information. through dynamic loading extraction module, the system can support variety of multimedia form.

Approximation algorithms for data placement on parallel disks

We study an optimization problem that arises in the context of data placement in a multimedia storage system. We are given a collection of M multimedia objects (data objects) that need to be assigned to a storage system consisting of N disks d 1 , d 2 …, d N . We are also given sets U 1 , U 2 ,…, U M such that U i is the set of clients seeking the i th data object. Each disk d j is characterized by two parameters, namely, its storage capacity C j which indicates the maximum number of data objects that may be assigned to it, and a load capacity L j which indicates the maximum number of clients that it can serve. The goal is to find a placement of data objects to disks and an assignment of clients to disks so as to maximize the total number of clients served, subject to the capacity constraints of the storage system. We study this data placement problem for two natural classes of storage systems, namely, homogeneous and uniform ratio . We show that an algorithm developed by Shachnai and Tamir [2000a] for data placement achieves the best possible absolute bound regarding the number of clients that can always be satisfied. We also show how to implement the algorithm so that it has a running time of O (( N + M ) log( N + M )). In addition, we design a polynomial-time approximation scheme, solving an open problem posed in the same paper.

A novel distributed architecture of large-scale multimedia storage system using autonomous object-based storage devices

In a large-scale multimedia storage system (LMSS) where the user requests for different multimedia objects may have different demands, placement and replication of the objects is an important factor, as it may result in an imbalance in loading across the system. Since replica management and load balancing is a crucial issue in multimedia systems, normally this problem is handled by centralized servers, e.g., metadata servers (MDS) in distributed file systems. Each object-based storage device (OSD) responds to the requests coming from the centralized servers independently and has no communication with other OSDs among the system. In this paper, we design a novel distributed architecture of LMSS, in which the OSDs have some kind of intelligences and can cooperate to achieve a high performance. Such an OSD, named as autonomous object-based storage device (AOSD), can replicate the objects to and balance the requests among other AOSDs, and handle fail-over and recovery autonomously. In the proposed architecture, we move the request balancing from centralized MDS to AOSDs and make the system more scalable, flexible, and robust. Based on the proposed architecture, we propose two different object replication and load balancing algorithms, named as “Minimum Average Waiting Time” (MAWT) and “One of the Best Two Choices” (OBTC), respectively. We validate the performance of the algorithms via rigorous simulations with respect to several influencing factors. Our findings conclusively demonstrate that the proposed architecture minimizes the average waiting time and at the same time carries out load balancing across servers.

On the Design of Distributed Object Placement and Load Balancing Strategies in Large-Scale Networked Multimedia Storage Systems

In a large-scale multimedia storage system (LMSS) where client requests for different multimedia objects may have different demands, placement and replication of the objects is an important factor, as it may result in an imbalance in server loading across the system. Since replica management and load balancing is all the more a crucial issue in multimedia systems, in the literature this problem is handled by centralized servers. Each object storage server (OSS) responses the requests coming from the centralized servers independently and has no communication with other OSSs among the system. In this paper, we design a novel distributed load balancing strategy of LMSS, in which the OSSs can cooperate together to achieve a high performance. Such OSS modeled as an M/M/m system, can replicate the objects to and balance the requests among other servers to achieve an optimal average waiting time (AWT) of the requests in the system. We validate the performance of the system via rigorous simulations with respect to several influencing factors and prove that our proposed strategy is scalable, flexible and efficient for the real-life applications.

Ferroelectric Random Access Memory as a Non-Volatile Cache Solution in a Multimedia Storage System

AbstractWe demonstrate that ferroelectric memory is very eligible to become a non-volatile cache solution, in particular, in a multimedia storage system such as solid-state disk. It could provide benefits both of performance and of reliability. In performance, a FRAM cache allows us to rid overhead of power-off recovery. Random WRITE performance has been improved by 250%. In assertion of endurance, we investigate acceleration factors to evaluate cycle-to-failure of the ferroelectric memory both in device-level and in capacitor-level. What has been found is that ferroelectric memory cells have 6.0×1014 of the cycle-to-failure at the operational condition of 85 o C and 2.0V. This cycle-to-failure is well above lifetime READ/WRITE cycles of 9.5×1013 in such system. From 2-dimensional stress simulation, it has also been concluded that the number of dummy cells plays a critical role in qualifying the high temperature life tests.

Research and Design of a Cluster Multimedia Storage System

Research and Design of a Cluster Multimedia Storage System

Algorithms for non-uniform size data placement on parallel disks

We study an optimization problem that arises in the context of data placement in a multimedia storage system. We are given a collection of M multimedia objects (data items) that need to be assigned to a storage system consisting of N disks d 1 , d 2 , … , d N . We are also given sets U 1 , U 2 , … , U M such that U i is the set of clients seeking the ith data item. Data item i has size s i . Each disk d j is characterized by two parameters, namely, its storage capacity C j which indicates the maximum total size of data items that may be assigned to it, and a load capacity L j which indicates the maximum number of clients that it can serve. The goal is to find a placement of data items to disks and an assignment of clients to disks so as to maximize the total number of clients served, subject to the capacity constraints of the storage system. We study this data placement problem for homogeneous storage systems where all the disks are identical. We assume that all disks have a storage capacity of k and a load capacity of L. Previous work on this problem has assumed that all data items have unit size, in other words s i = 1 for all i. Even for this case, the problem is NP-hard. For the case where s i ∈ { 1 , … , Δ } for some constant Δ, we develop a polynomial time approximation scheme (PTAS). This result is obtained by developing two algorithms, one that works for constant k and one that works for arbitrary k. The algorithm for arbitrary k guarantees that a solution where at least ( ( k − Δ ) ( k + Δ ) ) ( 1 − 1 ( 1 + k ( 2 Δ ) ) 2 ) -fraction of all clients are assigned to a disk (under certain assumptions). In addition we develop an algorithm for which we can prove tight bounds when s i ∈ { 1 , 2 } . In fact, we can show that a ( 1 − 1 ( 1 + ⌊ k / 2 ⌋ ) 2 ) -fraction of all clients can be assigned (under certain natural assumptions), regardless of the input distribution.

Storage system support for continuous-media applications. 1. Requirements and single-disk issues

A multimedia storage system plays a vital role for the performance and scalability of multimedia servers. To handle the server load imposed by increased user access to on-demand multimedia streaming applications, new storage system solutions are needed. Multimedia storage systems store and retrieve data from storage devices and manage related issues including data placement, scheduling, file management, continuous data delivery, memory buffering, and prefetching. For high-data-rate multimedia systems, storage systems have long been viewed as a primary bottleneck for two reasons. First, multimedia applications have a much higher storage system load than previous applications. Second, storage devices have become only marginally faster compared to increased processor and network performance. This increasing speed mismatch has fueled a search for new storage structures and file system storage and retrieval mechanisms

Storage system support for continuous media applications. 2. Multiple disks, memory, and integration

To meet multimedia servers' increasing performance and scalability requirements, researchers must design multimedia storage system components that adapt to various workloads and requirements. They must also develop strategies for combining components into a single high-performance system.

Unified Read Requests

Most work on multimedia storage systems has assumed that clients will be serviced using a round-robin strategy. The server services the clients in rounds and each client is allocated a time slice within that round. Furthermore, most such algorithms are evaluated on the basis of a tightly specified cost function. This is the basis for well known algorithms such as FCFS, SCAN, SCAN-EDF, etc. In this paper, we describe a Request Merging (RM) module that takes as input, a set of client requests, and a set of constraints on the desired performance such as client waiting time or maximum disk bandwidth, and a cost function. It produces as output, a Unified Read Request (URR), telling the storage server which data items to read, and when the clients would like these data items to be delivered to them. Given a cost function cf, a URR is optimal if there is no other URR satisfying the constraints with a lower cost. We present three algorithms in this paper, each of which accomplishes this kind of request merging. The first algorithm OptURR is guaranteed to produce minimal cost URRs with respect to arbitrary cost functions. In general, the problem of computing an optimal URR is NP-complete, even when only two data objects are considered. To alleviate this problem, we develop two other algorithms, called GreedyURR and FastURR that may produce sub-optimal URRs, but which have some nicer computational properties. We will report on the pros and cons of these algorithms through an experimental evaluation.

Performance Tradeoffs in Scheduling Techniques for Mixed Workloads

Many modern multimedia applications require the retrieval of different “classes” of data with drastically different characteristics. For instance, digital libraries type systems must be designed to deliver not only text files and still images, but voice and video as well. These applications can benefit from the sharing of resources such as disk and network bandwidth, instead of the conservative approach of partitioning the resources according to the characteristics of each type of data being retrieved. Continuous and non-continuous media applications, require different performance metrics to be achieved, so that the necessary quality of service (QoS) is satisfied. As a consequence, the proper managing of resources is a major issue in order to provide the complete sharing of resources and yet reaching the QoS goals. This work focuses on multimedia storage systems that are capable of serving a mixture of continuous and non-continuous workloads. Our main objective is to expose and investigate the tradeoffs involved in managing the system resources, in particular, I/O bandwidth. The performance metrics of interest are the mean and variance of response time for non-continuous media requests and the probability of missing an imposed deadline for continuous media workloads. Different scheduling algorithms are considered and tradeoffs to achieve performance goals are studied, including those involving buffer sizing.

Tertiary storage in multimedia systems: staging or direct access?

Multimedia applications that are required to manipulate large collections of objects are becoming increasingly common. Moreover, the size of multimedia objects, which are already huge, are getting even bigger as the resolution of output devices improve. As a result, many multimedia storage systems are not likely to be able to keep all of their objects disk-resident. Instead, a majority of the less popular objects have to be off-loaded to tertiary storage to keep costs down. The speed at which objects can be accessed from tertiary storage is thus an important consideration. In this paper, we propose an adaptive data retrieval algorithm that employs a combination of staging and direct access in servicing tertiary storage retrieval requests. At retrieval time, an object that resides in tertiary storage can either be staged to and then played back from disks, or the object can be accessed directly from the tertiary drives. We show that a simplistic policy that adheres strictly to staging or direct access does not exploit the full retrieval capacity of both the tertiary library and the secondary storage. To overcome the problem, we propose a data retrieval algorithm that dynamically chooses between staging and direct access, based on the relative load on the tertiary versus secondary devices. A series of simulation experiments confirms that the algorithm achieves good access times over a wide range of workloads and resource configurations. Moreover, the algorithm is very responsive to changing load conditions.

Special Issue on Multimedia Storage Systems

Special Issue on Multimedia Storage Systems

Architecture issues in multimedia storage systems

Next generation storage systems will need to provide support for both textual data and other types of multimedia data (e.g., images, video, audio). These two types of data differ in their characteristics, and hence require different techniques for their organization and management. In this paper, we provide an overview of 1) how storage systems can be architectured to support multimedia data, and 2) what are the main challenges in devising new algorithms to manage multimedia data. In order to provide rate guarantees for continuous media data, an admission control scheme must be employed that determines, for each client, whether there are sufficient resources available to service that client. To maximize the number of clients that can be admitted concurrently, the various system resources must be allocated and scheduled carefully. In terms of disks, we use algorithms for retrieving/storing data from/to disks that reduce seek latency time and eliminate rotational delay, thereby providing high throughput. In terms of main-memory, we use buffer management schemes that exploit the sequential access patterns for continuous media data, thereby resulting in efficient replacement of buffer pages from the cache.

A tight upper bound of the lumped disk seek time for the Scan disk scheduling policy

A tight upper bound of the lumped disk seek time for the Scan disk scheduling policy is presented. The tight upper bound is based on an accurate disk seek time model. One of the most important applications of the tight upper bound is in multimedia storage system design. Without a tight upper bound based on an accurate disk seek time model, the designers of multimedia storage systems would be forced to use more conservative approaches, i.e. loose upper bounds, to guarantee satisfaction of real-time requirements. This, in turn, would result in underutilization of disk bandwidth.

A multimedia storage system for on-demand playback

This paper presents the design of a multimedia storage system for on-demand playback. The design stresses effective utilization of disk bandwidth with minimal data buffer to minimize overall system costs. The design procedure is most distinctive in the following two aspects: it bases on a tight upper bound of the lumped disk seek time for the Scan disk scheduling algorithm to achieve effective utilization of the disk bandwidth; and it starts with a general two-level hierarchical disk array structure to derive the optimal configuration for specific requirements. >