Search

Free Space Optical Communication (FSO) is a promising technology to address wired Data Center Network (DCN) challenges like power consumption, low scalability and flexibility, congestion and cabling. Scholars have developed indirect line-of-sight (LoS) FSO schemes by reflecting the FSO beams via switchable mirrors. These schemes have introduced extra overhead delay to establish indirect LoS links, defined herein as the rack-to-rack FSO link setup process. The purpose of this work is to study and model this setup process with the consideration of the DC workloads. We found that the process involves a sequence of i.i.d random variables that contribute differently to its delay. Also, the process shows a statistical characteristic close to M/M/K. However, the number of FSO links, K, is random with time, which necessitates careful modeling. Finally, the PDF of the process total response time is close to the hypoexponential distribution, and it maintains its main characteristics even with different distributions for the service time. [ABSTRACT FROM AUTHOR]

Middleboxes are critical components in today's networks. Due to the variety of network/security policies and the limitations of routing protocols, middleboxes are installed in multiple physical locations to face high traffic with few considerations for efficiency. Reducing the number of deployed middleboxes would reduce capital and operation costs. Moreover, some flows prefer to bypass one or more in-path middlebox where they provide useless services, such as payload compression for multimedia streams. These challenges can be partially tackled by network function virtualization (NFV) schemes with the costs of performance reduction and replacement expenses. Given the rapid growth and the wide adoption of software-defined networking solutions and the recent advances in managing middleboxes' configuration, the consolidation of middleboxes is becoming easier than before. We designed and evaluated SALMA, a new pre-NFV practical solution that systematically recreates the infrastructure of middleboxes by proposing the Integrated Middleboxes Subnets scheme. In this work, we attempted to reduce the number of installed middleboxes by implementing horizontal integration of middleboxes' functions, such as every pair of middleboxes being integrated into a dedicated hardware box. We support the motivation for creating SALMA with a practical survey of in-production middleboxes from 30 enterprises. Our solution addresses key challenges of middleboxes, including cost, utilization, flexibility, and load balancing. SALMA's performance has been evaluated experimentally as well. [ABSTRACT FROM AUTHOR]

Face recognition is required in various applications, and major progress has been witnessed in this area. Many face recognition algorithms have been proposed thus far; however, achieving high recognition accuracy and low execution time remains a challenge. In this work, a new scheme for face recognition is presented using hybrid orthogonal polynomials to extract features. The embedded image kernel technique is used to decrease the complexity of feature extraction, then a support vector machine is adopted to classify these features. Moreover, a fast-overlapping block processing algorithm for feature extraction is used to reduce the computation time. Extensive evaluation of the proposed method was carried out on two different face image datasets, ORL and FEI. Different state-of-the-art face recognition methods were compared with the proposed method in order to evaluate its accuracy. We demonstrate that the proposed method achieves the highest recognition rate in different considered scenarios. Based on the obtained results, it can be seen that the proposed method is robust against noise and significantly outperforms previous approaches in terms of speed. [ABSTRACT FROM AUTHOR]

In recent years, the occurrence of cascading failures and blackouts arising from cyber intrusions in the underlying configuration of power systems has increasingly highlighted the need for effective power management that is able to handle this issue properly. Moreover, the growing use of renewable energy resources demonstrates their irrefutable comparative usefulness in various areas of the grid, especially during cascading failures. This paper aims to first identify and eventually protect the vulnerable areas of these systems by developing a hybrid structure-based microgrid against malicious cyber-attacks. First, a well-set model of system vulnerability indices is presented to indicate the generation unit to which the lines or buses are directly related. Indeed, we want to understand what percentage of the grid equipment, such as the lines, buses, and generators, are vulnerable to the outage of lines or generators arising from cyber-attacks. This can help us make timely decisions to deal with the reduction of the vulnerability indices in the best way possible. The fact is that employing sundry renewable resources in efficient areas of the grid can remarkably improve system vulnerability mitigation effectiveness. In this regard, this paper proposes an outstanding hybrid-energy framework of AC/DC microgrids made up of photovoltaic units, wind turbine units, tidal turbine units, and hydrogen-based fuel cell resources, all of which are in grid-connect mode via the main grid, with the aim to reduce the percentage of the system that is vulnerable. To clearly demonstrate the proposed solution's effectiveness and ease of use in the framework, a cyber-attack of the false data injection (FDI) type is modeled and developed on the studied system to corrupt information (for instance, via settings on protective devices), leading to cascading failures or large-scale blackouts. Another key factor that can have a profound impact on the unerring vulnerability analysis concerns the uncertainty parameters that are modeled by the unscented transform (UT) in this study. From the results, it can be inferred that vulnerability percentage mitigation can be achieved by the proposed hybrid energy framework based on its effectiveness in the system against the modeled cyber-attacks. [ABSTRACT FROM AUTHOR]

Multiplication is one of the basic operations that influence the performance of many computer applications such as cryptography. The main challenge of the multiplication operation is the cost of the operation as compared to other basic operations such as addition and subtraction, especially when the size of the numbers is large. In this work, we investigate the use of the window strategy for multiplying a sequence of large integers to design an efficient sequential algorithm in order to reduce the number of bit-multiplication operations involved in multiplying a sequence of large integers. In our implementation, several parameters are considered and measured for their effect on the proposed algorithm and the best-known sequential algorithm in the literature. These parameters are the size of the sequence of integers, the size of the integers, the size of the window, and the distribution of the data. The experimental results prove the effectiveness of the proposed algorithm are compared to the ones of the best-known sequential algorithm, and the proposed algorithm is able to achieve a reduction in computing time greater than 50% in most cases. [ABSTRACT FROM AUTHOR]

LightFDG is an integrated approach to flow detection (FD) and flow grooming (FG) in optical wireless data center networks (DCNs), which is interconnected via wavelength division multiplexing (WDM) based free-space optical (FSO) links. Since forwarding bandwidth-hungry elephant flows (EFs) and delay-sensitive mice flows (MFs) on the same path can cause severe performance degradation, the LightFDG optically grooms flows of each class into rack-to-rack (R2R) flows. Then, R2R-MF and R2R-EF flows are separately forwarded over lightpaths of separate MF and EF virtual topologies, respectively. Lightpaths are provisioned by jointly determining the capacity and route based on flows’ arrival rate, size, and completion time request. To prevent EFs from congesting the MF lightpaths, high speed and accurate flow-detection mechanisms are also necessary for classifying EFs as soon as possible. Therefore, a fast-lightweight-and-accurate flow detection framework is developed by leveraging the transmission control protocol (TCP) behaviors. The proposed FD scheme has the flexibility of being implemented as in-network or centralized to classify flows of modifiable and unmodifiable hosts, respectively. Since the centralized scheme incurs considerable overhead, the processing and communication overhead is also mitigated by proposed techniques. Numerical results show that LightFDG outperforms traditional load balancers by about $3\times $ for EFs and $10\times $ for MFs. Along with the developed overhead mitigation methods, the centralized scheme is shown to provide up to $62\times $ lower overhead with 100% accuracy and with about $224\times $ higher detection speeds than the existing centralized solutions. [ABSTRACT FROM AUTHOR]

Traditional wired data center networks (DCNs) suffer from cabling complexity, lack flexibility, and are limited by the speed of digital switches. In this paper, we alternatively develop a top-down traffic grooming (TG) approach to the design and provisioning of mission-critical optical wireless DCNs. While switches are modeled as hybrid optoelectronic cross-connects, links are modeled as wavelength division multiplexing capable free-space optic channels. Using the standard TG terminology, we formulate the optimal mixed-integer TG problem considering the virtual topology, flow conversation, connection topology, non-bifurcation, and capacity constraints. Thereafter, we develop a fast yet efficient sub-optimal solution, which grooms mice flows (MFs), mission-critical flows (CFs), and forward on predetermined rack-to-rack (R2R) lightpaths. On the other hand, elephant flows (EFs) are forwarded over dedicated server-to-server express lightpaths whose routes and capacity are dynamically determined based on the availability of wavelength and capacity. To prioritize the CFs, we consider low and high-priority queues and analyze the delay characteristics such as waiting times, maximum hop counts, and blocking probability. As a result of grooming, the sub-wavelength traffic and adjusting the wavelength capacities, numerical results show that the proposed solutions can achieve significant performance enhancement by utilizing the bandwidth more efficiently, completing the flows faster than delay sensitivity requirements, and avoiding the traffic congestion by treating EFs and MFs separately. [ABSTRACT FROM AUTHOR]