Performance of ATM Switch Fabrics Using Cross-Point Buffers

Bin Zhou,M. Atiquzzaman 한국통신학회 1995 Asia-Pacific Conference on Communications Vol.2 No.1

Performance Analysis of Shared Buffer ATM Switches Under Hot Spot Traffic

Mahmoud Saleh,Mohammed Atiquzzaman 한국통신학회 1995 Asia-Pacific Conference on Communications Vol.2 No.1

Smart government framework with geo-crowdsourcing and social media analysis

Witanto, Joseph Nathanael,Lim, Hyotaek,Atiquzzaman, Mohammed North-Holland 2018 Future generations computer systems Vol.89 No.-

<P><B>Abstract</B></P> <P>Smart government utilizes data to improve services provided to the citizen. Smart city may benefit from citizen engagement through crowdsourcing and social media. This paper proposes a city event’s prediction with map-based visualization utilizing crowdsourced geodata collected from citizen’s report. Data is aggregated according to geo-position and used to predict next day’s event. Mindmap-based visualization utilizing social media processed with topic modeling and topic similarity calculation is also proposed in this work. Proof-of-concept application and proposed system’s processing time is evaluated to prove the feasibility of the system. Proposed system utilizes geo-crowdsourcing for event prediction visualization for government instead of direct services to citizen. Proposed social media visualization use topic modeling specifically created for short text which is appropriate for social media data.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Proposes map-based reporting for government-related activities based on geo-crowdsourced data. </LI> <LI> Proposes mindmap-based reporting for social media analysis. </LI> <LI> Evaluates smart city frameworks, geo-crowdsourcing and social media analysis applications. </LI> </UL> </P>

A new content-defined chunking algorithm for data deduplication in cloud storage

Widodo, R.N.S.,Lim, H.,Atiquzzaman, M. North-Holland 2017 Future generations computer systems Vol.71 No.-

<P>Chunking is a process to split a file into smaller files called chunks. In some applications, such as remote data compression, data synchronization, and data deduplication, chunking is important because it determines the duplicate detection performance of the system. Content-defined chunking (CDC) is a method to split files into variable length chunks, where the cut points are defined by some internal features of the files. Unlike fixed-length chunks, variable-length chunks are more resistant to byte shifting. Thus, it increases the probability of finding duplicate chunks within a file and between files. However, CDC algorithms require additional computation to find the cut points which might be computationally expensive for some applications. In our previous work (Widodo et al., 2016), the hash-based CDC algorithm used in the system took more process time than other processes in the deduplication system. This paper proposes a high throughput hash-less chunking method called Rapid Asymmetric Maximum (RAM). Instead of using hashes, RAM uses bytes value to declare the cut points. The algorithm utilizes a fix-sized window and a variable-sized window to find a maximum-valued byte which is the cut point. The maximum-valued byte is included in the chunk and located at the boundary of the chunk. This configuration allows RAM to do fewer comparisons while retaining the CDC property. We compared RAM with existing hash-based and hash-less deduplication systems. The experimental results show that our proposed algorithm has higher throughput and bytes saved per second compared to other chunking algorithms. (C) 2017 Elsevier B.V. All rights reserved.</P>

Adaptive selection of dynamic VM consolidation algorithm using neural network for cloud resource management

Witanto, Joseph Nathanael,Lim, Hyotaek,Atiquzzaman, Mohammed Elsevier 2018 Future generation computer systems Vol.87 No.-

<P><B>Abstract</B></P> <P>Cloud resource management becomes more important with the increasing usage of cloud resources. With various cloud options available, cloud provider may have different priority in managing the resource through resource scheduling and provisioning. Dynamic VM (Virtual Machine) consolidation algorithm is one of the techniques which can be used to reduce energy consumption through VM migration. Higher VM migration may lead to lower energy consumption and higher SLA violation. Although previous research has successfully decreased energy consumption and SLA violation, cloud providers may need to manage trade-offs between energy and SLA violation through availability of priority in the system. This paper proposes neural network-based adaptive selection of VM consolidation algorithms which adaptively chooses appropriate algorithm according to cloud provider’s goal priority and environment parameters. Dataset generation and performance evaluation using simulations on real-world PlanetLab VMs workload trace showed that adaptive selector produced better average performance score than independent methods on various evaluation priority.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Studies on multiple dynamic VM consolidation algorithms on cloud environment. </LI> <LI> Discusses about trade-off between energy and SLA violation due to VM migration. </LI> <LI> Proposes adaptive system which chooses best algorithm based on provider’s priority. </LI> <LI> Evaluates performance of proposed system and individual VM migration algorithms. </LI> </UL> </P>

SDM: Smart deduplication for mobile cloud storage

Widodo, R.N.S.,Lim, H.,Atiquzzaman, M. North-Holland 2017 Future generations computer systems Vol.70 No.-

<P>Cloud storages can be used to solve limited storage on mobile devices. The stored data can be reached from anywhere if network access is available. Network access can be costly, especially for mobile devices, which have limited power source. One of the solutions to reduce the amount of data transfer is data deduplication. This paper proposes a deduplication system called Smart Deduplication for Mobiles (SDM) for mobile devices. SDM chooses the best deduplication method without specific configurations for any file type. We compared our system to existing deduplication systems available on mobile devices. Results show that SDM achieves higher deduplication accuracy and faster deduplication speed over existing systems for mobile devices with negligible additional time in most scenarios. The additional time required by our system is negligible when compared to the power saved from uploading fewer data to a cloud storage. (C) 2016 Elsevier B.V. All rights reserved.</P>

Secure and efficient protocol for fast handover in 5G mobile Xhaul networks

Sharma, Vishal,You, Ilsun,Leu, Fang-Yie,Atiquzzaman, Mohammed Academic Press 2018 Journal of network and computer applications Vol.102 No.-

<P><B>Abstract</B></P> <P>Mobile networks are observing an all time increase in the number of users and services. These networks have hit the 5G requisites in no time. Current service providers are aiming at resolving issues of subsisting networks by exploiting the capacity and coverage enhancement features of 5G. With a broad spectrum, it has now become more facile to accommodate an astronomically immense number of devices each having multiple applications authoritatively mandating network accessibility. Despite these advantages, such networks suffer from several issues cognate to smooth operations of fronthaul and backhaul, such as interference management, link-reliability, flatness, security and flexibility. Integrating fronthaul and backhaul together as a Xhaul is suggested as one of the efficient solutions for handling these issues. Xhaul forms integrated planes which use heterogeneous switches for high optical transmissions. Despite being efficient, Xhaul links are weak in terms of security. The situations will be more serious, particularly when a massive number of User Equipment (UE) and IoT devices are now connected to it. This issue is further raised when the terminal fortifying the fronthaul and backhaul moves leading to the formation of mobile Xhaul network. The current security solutions for WiFi, WiMax, WiBro, 4G/LTE are unable to fortify privacy and perfect forward secrecy in mobile Xhaul network, which is a quandary targeted in this paper. To resolve these issues, a novel key exchange and authentication protocol is proposed, which is capable of securing Xhaul links for a moving terminal in the network. The proposed approach is tested utilizing mobile ground node and drone as moving terminal across multiple hubs. The formal analysis utilizing BAN logic and AVISPA tool slake the security requisites and performance evaluation justifies the efficiency in comparison with the existing solutions.</P>

Energy efficient device discovery for reliable communication in 5G-based IoT and BSNs using unmanned aerial vehicles

Sharma, V.,Song, F.,You, I.,Atiquzzaman, M. Academic Press 2017 JOURNAL OF NETWORK AND COMPUTER APPLICATIONS - Vol.97 No.-

<P>Connectivity among real-world entities is one of the primary requirements of the upcoming Fifth Generation Public Private Partnership (5G-PPP). Both Internet of Things (IoT) and Body Sensor Networks (BSNs) are major applications of 5G networks. However, over-consumption of energy for device discovery, which includes registration, removal, querying, routing etc, quickly depletes the resources of a node, which may further influence the whole network. There are a number of approaches which provide energy efficient mechanisms for the selection of devices in a network operating with different types of nodes; however, these approaches are unable to maintain a high transmission capacity along with energy conservation and fault-tolerance. In this paper, an energy efficient approach for device discovery in 5G-based IoT and BSNs using multiple Unmanned Aerial Vehicles (UAVs) is presented. A functional architecture is proposed, which utilizes XML charts to perform device discovery on the basis of networks state cost and available energy. The significant gains achieved in energy consumption, end to end delays and packet loss show that our solution is capable of providing energy efficient device discovery with 78.4% reduction in the overall energy consumption compared to existing solutions. The advantage of UAVs in energy efficient networking is illustrated using numerical analysis which suggests 75% enhancement in the energy-asymptote of the existing networks.</P>

Novel web agent framework to support seamless mobility for data networks

Lee, Y.J.,Lee, D.W.,Atiquzzaman, M. IET 2009 IET COMMUNICATIONS Vol.3 No.12

<P>In this study, the authors address a mobile Web agent framework based on stream control transmission protocol (SCTP) to overcome the deficiencies, which the typical mobile Web agent framework based on transmission control protocol (TCP) suffers from, such as performance degradation, head-of-line blocking and unsupported mobility in mobile wireless environment. The proposed SCTP-based mobile Web agent framework supports seamless transport layer mobility in a ubiquitous environment. It consists of an application engine and a transport engine, to use the hypertext transfer protocol and to deploy SCTP with dynamic address reconfiguration, respectively. The authors explore and describe the components necessary to implement the proposed mobile Web agent framework in an ubiquitous environment. The performance of the proposed SCTP-based mobile Web agent is compared with that of a typical TCP-based mobile Web agent using ns-2 simulator. The simulation results show that the proposed Web agent based on SCTP has a remarkably lower mean response time than a typical Web agent based on TCP.</P>