Search

Cloud computing has become popular in various application domains based on infrastructure, platform, and software as a service model. Rapid deployment, high scalability, on-demand, and (theoretically) infinite resources have driven the industry towards the wide adoption of cloud computing services. However, the difficulty of cross-provider resource allocation and seamless resource transition is a major concern for such services. Therefore, the segregated cloud market forces its clients to use provider-specific and pre-configured options for their required resources and services. Thus, the overall market, even with the presence of multiple cloud service providers, operates as a direct service from the providers to the clients, and with non-negotiable pricing strategies for the cloud services. In this article, we propose Bepari, a cost-driven model for opaque service platforms for cloud computing. Bepari acts as a negotiation-based approach to deliver composite cross-provider cloud-based services to the end-users. Bepari provides a detailed service-oriented architecture for multiple cloud service providers to provide cross-platform and composite services. Furthermore, Bepari delivers a detailed cost model and comparison between establishing a cloud service vs. an opaque cloud service. Our empirical framework allows a Bepari service provider to analyze the profit model and create a market niche accordingly. Simulation results are provided, which validate the efficiency of a negotiated pricing strategy in terms of maximized resource utilization and profits for cloud service providers and cost reduction for the cloud users.

Crowdsourcing is an efficient and scalable way for the service providers (SP) to provide a broad range of services with a low initial service setup cost. With its growing popularity, people are continuously introducing new crowdsourcing-based applications and searching for suitable crowd platforms for the deployment of those applications as a service. Consequently, a contributor participates in multiple platforms from different SPs and concurrently executes various tasks in a time interval. As the number of SP increases, managing and monitoring each contributor separately becomes a primary challenge for each SP. Moreover, upgrading a service, ensuring service scalability, and migration is tough for any crowd-based service provider. Frequently, a service provider has difficulty finding the appropriate contributors that will satisfy their service specifications. Besides, as a contributor, it is also hard to decide whether or not they should participate in a task offered by an SP. Therefore, in this paper, we introduced CrowdPick, a middleware that provides a crowdsourced platform for the people who want to provide a crowdsourcing-based service. Each SP contacts CrowdPick for initiating any service chooses an appropriate application package from its repository and specifies its service requirements. Instead of joining individually to each SP, the contributor needs to register into CrowdPick. All the tasks associated with services are scheduled and monitored by CrowdPick, and the CrowdPick decides the corresponding monetary incentives. Along with providing a detailed cost-benefit analysis of an SP and a contributor, we describe the service level agreement (SLA) policies. We simulate our model to show that implementing CrowdPick in real life is viable, and beneficial for both an SP and a contributor.

In recent years, cloud computing has gained considerable notoriety because it provides access to shared system resources, allowing for high computing power at low management effort. With the widespread availability of mobile and Internet-of-Things (IoT) devices, we can now form cloud instantly without considering a dedicated infrastructure. However, the resource-constrained IoT devices are quite infeasible for installing virtual machines. Therefore, the mobile cloud can be used only for the tasks that require distributed sensing or computation. In order to solve this problem, we introduce IoTDoc, an architecture of mobile cloud composed of lightweight containers running on distributed IoT devices. To explore the benefits of running containers on low-cost IoT-based cloud system, we use Docker to create and orchestrate containers and run on a cloud formed by cluster of IoT devices. We provide a detail operational model of IoTDoc that illustrates cloud formation, resource allocation, container distribution, and migration. We test our model using the benchmark program Sysbench and compare the performance of IoTDoc with Amazon EC2. Our experimental result shows that IoTDoc is a viable option for cloud computing and is a more affordable, cost-effective alternative to large platform cloud computing services, specifically as a learning platform than Amazon EC2.

In recent years, the concept of the Internet of Things (IoT) has already been implemented in numerous application domains, such as smart city, intelligent healthcare assistant, and smart transportation management. Researchers or developers associated with these domains frequently require diverse types of IoT devices to implement or test their IoT related innovations. However, building an IoT-testbed by purchasing these IoT devices in every few months is infeasible considering that most of them will be used only for a small amount of time and will become obsolete with the arrival of an upgraded version of those devices. Instead, a better approach would be rented out the IoT devices in on-demand, just-in-time, and pay for only the time the devices are used basis. Therefore, in this paper, we propose IoTbed – an architecture to deliver a large scale Testbed as a service using the IoT devices located in the users' proximal networks. IoTbed enables testbed providers to build their testbeds in the edge of the network and allows easy and secure access for IoT service providers to run experiments on those testbeds. IoTbed presents an economic model that offers monetary incentives to the device owners for using their devices in the testbed experiments. We posit that such an incentive model will encourage more testbed providers to rent out their smart devices through IoTbed. To demonstrate the feasibility of IoTbed, we implemented a prototype of IoTbed to run on Contiki powered IoT devices and evaluated the performance.

Finding parking at a desired spot and time is tough, especially in an urban area. Users may also want to pay more to get a parking spot during urgent need. Although the existing infrastructure-based approaches can solve this problem partially, they require a high initial investment and maintenance cost. As a consequence, deploying such approaches on a large scale in the real world is infeasible. A more economically feasible solution is using crowdsourcing-based approaches where a user near a free parking spot informs the interested users about the available parking spot in exchange for some forms of incentives. However, most of the crowdsourced approaches suffer due to the lack of proper models for price negotiation, information verification, and assurance. In this paper, we propose ParkBid, a crowdsourcing-based parking service for automobiles where the information of free parking is circulated among the interested users following a bidding process. ParkBid determines the incentives for providing any parking information based on several primitives, such as time, location, reputation, urgency, etc. Along with a detailed discussion about the challenges in ParkBid for both the users and information providers, we provide a set of policies as countermeasures. Also, we present an extensive simulation to evaluate the impact of ParkBid for users under different circumstances. Our experimental results show that users can save a significant amount of time and can have more success rate during searching for a free parking spot using ParkBid.

Mobile cloud computing has become popular because of its flexible infrastructure and easily accessible storage, sensing, and computing services. However, scheduling and allocating resources for the tasks provided by the cloud user are major challenges in the mobile cloud. The existing scheduling algorithms in the mobile cloud primarily focus on dividing and distributing a single task among multiple devices participating in the mobile cloud. However, when the load on the mobile cloud increases, multiple requests from different users can come at a single time point. The existing scheduling algorithms for distributed systems cannot be implemented in the mobile cloud, because the available resources differ extensively in the mobile cloud depending upon the time, geographic location, incentive policy, etc. While some cloud users' tasks are computed by their specified deadlines, the others suffer heavily. Therefore, we propose ROSAC, a fair scheduling approach based on the complexity of the cloud users' assigned task that minimizes the average delay between the task computation time and users' specified deadline. ROSAC works by round wise task division and distribution where the estimated time of all the subtasks in each round are the same. We design a simulated platform for a mobile cloud and compare the performance of ROSAC with some of the widely used scheduling approaches for distributed systems.

The Internet of Things (IoT) have become popular in diverse domains because of their accessibility and mobility as well as cost-efficient manufacturing, deployment, and maintenance process. The widespread deployment of IoT devices makes them an attractive target for an attacker trying to gain unauthorized access to an IoT-based system. An adversary clones a real hardware device or compromises embedded software to impersonate a legitimate device, and thus gains unauthorized access to sensitive information and performs security-critical operations. The existing security schemes for the mobile systems cannot be applied directly to an IoT-enabled infrastructure since devices are resource constrained regarding storage, processing power, and communication bandwidth. Additionally, the current security approaches for the IoT systems are unable to identify physically compromised IoT devices. In this paper, we propose HSC-IoT, a resource-efficient Physical Unclonable Function (PUF)-based security protocol that ensures both software and hardware integrity of IoT devices. HSC-IoT also provides a lightweight mutual authentication scheme for the resource-limited devices based on Elliptic Curve Cryptography. We present a detailed analysis of the security strength of HSC-IoT. We implemented a prototype of HSC-IoT on IoT devices powered by Contiki OS and provided an extensive comparative analysis of HSC-IoT with contemporary IoT security protocols.

Cloud computing has emerged as the primary and popular computing paradigm recently. Since cloud users move continuously, sustaining the required quality of service (QoS) in a cost effective manner is very challenging. For maintaining the required QoS for a moving user, the current cloud systems use some of the existing service replication or/and migration strategies. However, those policies become inefficient when a user frequently moves among multiple places. The primary reason for the failure of the existing migration strategies is they overlook several critical parameters associated with users' context during the service migration or replication. In this paper, we analyze the users' context thoroughly to determine their mobility and content usage patterns. We identify the key factors that affect the time and cost associated with the content storage and migration and design a model considering those factors. Based on our model CACROS (Context-Aware Cloud content Roaming Service), a cloud provider can perform the cost-benefit analysis between service migration and replication, and determine an efficient point for service hosting. We test our model with different potential scenarios using a real and simulated testbed and show that the model can provide a cost efficient solution for mobile cloud users while maintaining the desired level of quality of service.

With the emergence of high-speed 4G networks along with reachable Wi-fi systems, cloud computing frameworks can greatly leverage mobile domains. However, obtaining a temporary storage service in a communication-challenged area is difficult due to the unavailability of any secure third-party cloud systems. Although the existing ad hoc cloud architectures facilitate distributed computation and sensing operations, such systems fail to deliver secure ad hoc storage as a service when a client requests for secure storage. The absence of a proper centralized monitoring system in the existing ad hoc clouds is a major obstacle for convincing a client to trust the neighboring mobile nodes for content offloading. In case a client and an outsourced node get disconnected, retrieving the offloaded contents along with ensuring their confidentiality and integrity becomes non-trivial. Additionally, providing a feasible and justified monetary incentive is a complex process for such ad hoc mobile frameworks. In this paper, we propose SASCloud, a centrally controlled ad hoc cloud system that provides a secure and reliable storage service for mobile clients. Our proposed system uses the contextual information of mobile users along with partial environmental knowledge and forms a temporal cloud using the resources of neighboring mobile devices. Along with the detailed reasoning of possible threats in our model, we provide a secure framework for content distribution and retrieval. We provide extensive analysis of our model using simulated experimental modules and demonstrate the feasibility of providing a secure storage service in a network-disconnected area using SASCloud.

Cloud computing provides software, platform, and infrastructure as a service that helps organizations to perform several resource intensive tasks. The services offered by a cloud service provider are limited by provider-specific options in terms of the pre-specified configurations. Moreover, it is sometimes expensive to pay a fixed amount of money without any format of negotiation or price-matching deals for the cloud-based services and resources. Conversely, the negotiator-based model for opaque services has gained popularity in various markets, such as, for flights, hotels, and rentals. We posit that a similar opaque inventory for cloud-based services and resources is the next generation niche for consumer acquisition and service delivery in the cloud computing market. Such a model will facilitate the clients with flexible resource and service provisioning at reasonable prices, and will also allow a higher revenue and increase resource utilization for cloud service providers. In this paper, we propose Litigo, a cost-driven model for opaque service platforms for cloud computing. The Litigo component acts as a middle-man to deliver cloud-based services from a set of cloud service providers to the end users. We present a detailed cost model and comparison between establishing a cloud service vs. an opaque cloud service. Our empirical framework allows a Litigo service provider to analyze the profit model and creates the market niche accordingly. We performed extensive analysis using simulated model verification for Litigo. The proposed model delivers an opaque cloud as a service to clients at a reasonable price by maximizing the resource utilization and revenue of cloud service providers.

Cloud computing has become the industry standard for rapid application deployment, scalable server support, mobile and distributed services, and it provides access to (theoretically) infinite resources. Unfortunately, researchers are still trying to converge towards cross-provider cloud computing frameworks to enable compatibility and seamless resource transition between cloud providers. Moreover, users are restricted to using the provider-specific pre-configured options of resources and services, irrespective of their current needs. At the same time, cloud services are provided as a direct service from the providers to the clients. This creates a segregated cloud market clientele, and non-negotiable pricing strategies for the cloud services. In this paper, we propose Jugo, a generic architecture for cloud composition and negotiated service delivery for cloud users. Jugo acts as a match-maker for service specifications from the users with the currently available assets from the cloud providers. The engagement of a middle-man as an opaque cloud service provider will create a better opportunity for cloud users to find cheaper deals, price-matching, and flexible resource specifications, with increased revenue and higher resource utilization for the cloud service providers.

The field of communications networks continues to emerge, thus leading to the rapid growth in the field of wireless sensor networks (WSNs). WSNs are noticeably different from traditional Ad hoc networks. The conspicuous difference between WSNs and traditional Ad hoc networks is that they (WSNs) are strictly constrained by limited supply of energy, capacity of storage, power of computation, and bandwidth. Because of these constraints and random deployment in some cases, it has become a challenge for the researchers to design an unblemished routing layer protocol for wireless sensor networks. In this paper we studied the motivation and design issues for routing protocols in WSNs with the limitations of existing routing protocols for WSNs. We also used GloMoSim-2.03 to find the shortcomings of traditional ad hoc routing protocols (DSR, WRF, AODV) when those are applied to WSN and to find out certain specific scenarios (considering low traffic networks and high traffic networks) of WSN where it is better to employ an existing Ad hoc routing protocol rather than developing a new one.

The Universal Networking Language (UNL) is a world wide generalizes form of human interactive language in a machine independent digital platform for defining, recapitulating, amending, storing and dissipating knowledge or information among people of different affiliations. The theoretical and applied research associated with this interdisciplinary endeavor facilitates in a number of practical applications in most domains of human activities such as creating globalization trends of markets or geopolitical interdependence among nations. In our research work we are presenting a pioneer work that aims to contribute with Development of Models for Bangla Dictionary Entries and Analysis of Grammatical Attributes of Bangla words such as Bangla Roots, Krit Prottoy and Kria Bivokti which will help to create a doorway for converting the Bangla Sentence to UNL and vice versa and subside the barrier between Bangla to other

Gathering information and providing remote assistant is a common trend as it saves time and cost associated with visiting the actual location in person. The widely available mobile sensors are used in collecting information during a task processing. However, gathering information from a remote place, or an area of disaster, is not trivial, given the unavailability of appropriate infrastructure. Existing delay tolerant networking approaches address this issue but suffer from unsatisfactory performance due to the lack of sufficient user participation. We propose the Delay-tolerant Cloud Computing framework (D-CLOC), a cloud framework utilizing the contextual information of a mobile client. Our proposed architecture combines crowdsourcing and the cellular network and forms a temporal delay tolerant cloud. D-CLOC uses a bidding incentive model to ensure and promote user participation in the cloud. We provide a detailed reasoning of the security and feasibility of our model, and delineate probable approaches for solving the various security related aspects. The paper includes the design and implementation of a realistic-simulation model for D-CLOC. The simulation scenario incorporates an example face recognition task for evaluating the performance of our proposed model. Our experimental results show that D-CLOC performs quite well compared to some of the existing DTN approaches and can be deployed for solving any real life problems using crowdsourcing within a delay tolerant cloud infrastructure.

Cloud computing has become the dominant computing paradigm in recent years. As clouds evolved, researchers have explored the possibility of building clouds out of loosely associated mobile computing devices. However, most such efforts failed due to the lack of a proper incentive model for the mobile device owners. In this paper, we propose CellCloud - a practical mobile cloud architecture which can be easily deployed on existing cellular phone network infrastructure. It is based on a novel reputation-based economic incentive model in order to compensate the phone owners for the use of their phones as cloud computing nodes. CellCloud offers a practical model for performing cloud operations, with lower costs compared to a traditional cloud. We provide an elaborate analysis of the model with security and economic incentives as major focus. Along with a cost equation model, we discuss detailed results to prove the feasibility of our proposed model. Our simulation results show that CellCloud creates a win-win scenario for all three stakeholders (client, cloud provider, and mobile device owners) to ensure the formation of a successful mobile cloud architecture.

Different approaches have been proposed for digital display of bangla numerals and also characters. But a complete and accurate scheme not has been done yet. We approach a complete low cost and fair design to display bangla numerals, bangla characters (vowel, consonant and shortened form of these characters), also English and Arabic numerals and all English character's represented as 120 character displayed by only 34 segments with tiny bits of binary code and differently usable architecture made this approach favorable. This scheme can be effectively used instead of other alternatives as less complex, economic and complete. With this framework, other characters also can be displayed as manufacturer specification.

This paper describes a method for the development of Bangla Enconversion within the framework of the Universal Networking Language (UNL). We also discuss some issues and problems related to the UNL representation that affect the quality of generation. Additionally, the ling ware engineering is introduced as a technique to enhance the quality and increase the development efficiency. In this paper a pioneer work is proposes that analyzes the Bangla words morphologically from which we obtain Roots and Primary suffixes (Krit Prottoy) and develops some rules for Bangla Root, and Primary Suffix for the UNL. This paper also describes grammatical attributes for Bangla root and Primary suffixes and use of morphological analysis. UNL Expression of the Bangla attributes is also thoroughly discussed in this paper.

Since its birth wireless communication became an indispensible part of the modern society. One major area that has a gigantic impact on the performance of wireless sensor networks (WSNs) is the Medium Access Control (MAC) layer. Many random access protocols exist in wireless sensor networks. Some of these protocols include Carrier Sense Multiple Access (CSMA), Multiple Access with Collision Avoidance (MACA), Multiple Access with Collision Avoidance for wireless (MACAW) and IEEE 802.11. All the protocols mentioned above except CSMA use Request To Send/Clear To Send (RTS/CTS) packets to avoid collisions (hidden terminal problem) which was a great problem for CSMA and that is the reason CSMA is almost obsolete for wireless communications. But after using RTS/CTS packets the protocols have to encounter some extra problems such as, energy consumption and end-to-end delay. The objective of this paper is to show the pros and cons of using RTS/CTS packets by comparing CSMA (does not use RTS/CTS) and IEEE 802.11 (uses RTS/CTS packets). We also portray that under some specific scenario the IEEE 802.11 is outperformed by CSMA which is also the novelty and contribution of this research work. This observation suggests that a lot of works have to be done to consider IEEE 802.11 an approximate perfect MAC layer protocol for WSNs.