Browsing by Author "Qureshi, Basit"
Now showing 1 - 10 of 13
Results Per Page
Sort Options
- APEnergy: Application Profile-Based Energy-Efficient Framework for SaaS CloudsPublication . Qureshi, Basit; Koubaa, AnisIn the past decade, there has been a steady increase in the focus on green initiatives for data centers. Various energy efficiency measures have been proposed and adopted, however the optimal tradeoff between performance and energy efficiency of data centers is yet to be achieved. Addressing this issue, we present APEnergy, an Application Profile-based energy efficient framework for small to medium scale data centers. The proposed framework leverages information on the completed application with certain workloads in the data center to build profiles for workflows. The framework utilizes a novel scheduler to obtain a near-optimal mapping for placement of workflow tasks in the data center based on three criteria including CPU utilization, power cost and task completion time. We compare the performance of the proposed scheduler to similar RTC and HEFT schedulers. Extensive simulation studies are carried out to verify the scalability and efficiency of APEnergy framework. Results show that the proposed Scheduler is 2% and 14% more energy efficient than RTC and HEFT respectively.
- A clustering market-based approach for multi-robot emergency response applicationsPublication . Trigui, Sahar; Koubâa, Anis; Cheikhrouhou, Omar; Qureshi, Basit; Youssef, HabibIn this paper, we address the problem of multi-robot systems in emergency response applications, where a team of robots/drones has to visit affected locations to provide rescue services. In the literature, the most common approach is to assign target locations individually to robots using centralized or distributed techniques. The problem is that the computation complexity increases significantly with the number of robots and target locations. In addition, target locations may not be assigned uniformly among the robots. In this paper, we propose, CMMTSP, a clustering market-based approach that first groups locations into clusters, then assigns clusters to robots using a market-based approach. We formulate the problem as multipledepot MTSP and address the multi-objective optimization of three objectives namely, the total traveled distance, the maximum traveled distance and the mission time. Simulations show that CM-MTSP provides a better balance among the three objectives as compared to a single objective optimization, in particular an enhancement of the mission time, and reduces the execution time to at least 80% as compared to a greedy approach.
- A Commodity SBC-Edge Cluster for Smart CitiesPublication . Qureshi, Basit; Kawlaq, Kamal; Koubaa, Anis; Sultan, Basel; Younis, MohammadThe commodity Single Board Computers (SBCs) are increasingly becoming powerful and can execute standard operating systems and mainstream workloads. In the context of cloud-based smart city applications, SBCs can be utilized as Edge computing devices reducing the network communication. In this paper, we investigate the design and implementation of a SBC based edge cluster (SBC-EC) framework for a smart parking application. Since SBCs are resource constrained devices, we devise a container based framework for a lighter foot-print. Kubernetes was used as an orchestration tool to orchestrate various containers in the framework. To validate our approach, we implemented a proof-of-concept of the SBC based Edge cluster for a smart parking application, as a possible ioT use-case.Our implementation shows that, the use of SBC devices at the edge of a cloud based smart parking application is a cost effective and low energy, green computing solution. The proposed framework can be extended to similar cloud based applications in the context of a smart city.
- Cyber-physical systems clouds: A surveyPublication . Rihab, Chaari; Ellouze, Fatma; Koubâa, Anis; Qureshi, Basit; Pereira, Nuno; Youssef, Habib; Tovar, EduardoCyber-Physical Systems (CPSs) represent systems where computations are tightly coupled with the physical world, meaning that physical data is the core component that drives computation. Industrial automation systems, wireless sensor networks, mobile robots and vehicular networks are just a sample of cyber-physical systems. Typically, CPSs have limited computation and storage capabilities due to their tiny size and being embedded into larger systems. With the emergence of cloud computing and the Internet-of-Things (IoT), there are several new opportunities for these CPSs to extend their capabilities by taking advantage of the cloud resources in different ways. In this survey paper, we present an overview of research efforts on the integration of cyber-physical systems with cloud computing and categorize them into three areas: (1) remote brain, (2) big data manipulation, (3) and virtualization. In particular, we focus on three major CPSs namely mobile robots, wireless sensor networks and vehicular networks.
- Dronemap Planner: A Service-Oriented Cloud-Based Management System for the Internet-of-DronesPublication . Koubaa, Anis; Qureshi, Basit; Sriti, Mohamed-Foued; Allouch, Azza; Javed, Yasir; Alajlan, Maram; Cheikhrouhou, Omar; Khalgui, Mohamed; Tovar, EduardoLow-cost Unmanned Aerial Vehicles (UAVs), also known as drones, are increasingly gaining interest for enabling novel commercial and civil Internet-of-Things (IoT) applications. However, there are still open challenges that restrain their real-world deployment. First, drones typically have limited wireless communication ranges with the ground stations preventing their control over large distances. Second, these low-cost aerial platforms have limited computation and energy resources preventing them from running heavy applications onboard. In this paper, we address this gap and we present Dronemap Planner (DP), a service-oriented cloud-based drone management system that controls, monitors and communicates with drones over the Internet. DP allows seamless communication with the drones over the Internet, which enables their control anywhere and anytime without restriction on distance. In addition, DP provides access to cloud computing resources for drones to offload heavy computations. It virtualizes the access to drones through Web services (SOAP and REST), schedules their missions, and promotes collaboration between drones. DP supports two communication protocols: (i.) the MAVLink protocol, which is a lightweight message marshaling protocol supported by commodities Ardupilot-based drones. (ii.) the ROSLink protocol, which is a communication protocol that we developed to integrate Robot Operating System (ROS)-enabled robots into the IoT. We present several applications and proof-of-concepts that were developed using DP. We demonstrate the effectiveness of DP through a performance evaluation study using a real drone for a real-time tracking application.
- DroneTrack: Cloud-Based Real-Time Object Tracking Using Unmanned Aerial Vehicles Over the InternetPublication . Koubaa, Anis; Qureshi, BasitLow-cost drones represent an emerging technology that opens the horizon for new smart Internet-of-Things (IoT) applications. Recent research efforts in cloud robotics are pushing for the integration of low-cost robots and drones with the cloud and the IoT. However, the performance of real-time cloud robotics systems remains a fundamental challenge that demands further investigation. In this paper, we present DroneTrack, a real-time object tracking system using a drone that follows a moving object over the Internet. The DroneTrack leverages the use of Dronemap planner (DP), a cloud-based system, for the control, communication, and management of drones over the Internet. The main contributions of this paper consist in: (1) the development and deployment of the DroneTrack, a real-time object tracking application through the DP cloud platform and (2) a comprehensive experimental study of the real-time performance of the tracking application. We note that the tracking does not imply computer vision techniques but it is rather based on the exchange of GPS locations through the cloud. Three scenarios are used for conducting various experiments with real and simulated drones. The experimental study demonstrates the effectiveness of the DroneTrack system, and a tracking accuracy of 3.5 meters in average is achieved with slow-speed moving targets.
- MyBot: Cloud-Based Service Robot using Service-Oriented ArchitecturePublication . Koubâa, Anis; Sriti, Mohamed-Foued; Javed, Yasir; Alajlan, Maram; Qureshi, Basit; Ellouze, Fatma; Mahmoud, AbdelrahmanThis paper presents a viable solution for the development of service robots by leveraging cloud and Web services technologies, modular software architecture design, and Robot Operating System (ROS). The contributions of this paper are two- folded (1) Design of ROS Web services to provide new abstract interfaces to service robots that makes easier the interaction with and the development of service robots applications, and (2) Integration of the service robot to the cloud using the ROSLink protocol. We demonstrate through real-world implementation on the MyBot robot the effectiveness of these software abstraction layers in developing applications for service robots through the Internet and the cloud, and in accessing them through Internet. We believe that this work represents an important step towards a more popular use of service robots.
- On Energy Efficiency and Performance Evaluation of Single Board Computer Based Clusters: A Hadoop Case StudyPublication . Qureshi, Basit; Koubâa, AnisEnergy efficiency in a data center is a challenge and has garnered researchers interest. In this study, we addressed the energy efficiency issue of a small scale data center by utilizing Single Board Computer (SBC)-based clusters. A compact layout was designed to build two clusters using 20 nodes each. Extensive testing was carried out to analyze the performance of these clusters using popular performance benchmarks for task execution time, memory/storage utilization, network throughput and energy consumption. Further, we investigated the cost of operating SBC-based clusters by correlating energy utilization for the execution time of various benchmarks using workloads of different sizes. Results show that, although the low-cost benefit of a cluster built with ARM-based SBCs is desirable, these clusters yield low comparable performance and energy efficiency due to limited onboard capabilities. It is possible to tweak Hadoop configuration parameters for an ARM-based SBC cluster to efficiently utilize resources. We present a discussion on the effectiveness of the SBC-based clusters as a testbed for inexpensive and green cloud computing research.
- On Power Consumption Profiles for Data Intensive Workloads in Virtualized Hadoop ClustersPublication . Qureshi, Basit; Alwehaibi, Sultan; Koubâa, AnisAlthough reduction in operating costs remains to be a key motivation for migration to Cloud environments, Power consumption is a big concern for data centers and cloud service providers. Many big data applications execute on Hadoop MapReduce framework for processing large workloads. In this paper, we investigate the tradeoff between energy consumption and workload running on Hadoop clusters using multiple virtual machines. We characterize power consumption profiles for various data intensive workloads and correlate these to quality of service (QoS) metrics such as job execution time. Based on experiments, we ascertain that power consumption profiles for big data applications can be used to optimize energy efficiency in data centers. We infer that these profiles can be used by Cloud service providers and consumers to specify green metrics in Service Level Agreements (SLA).
- On the Robot Path Planning using Cloud Computing for Large Grid MapsPublication . Chaari, Imen; Koubâa, Anis; Qureshi, Basit; Youssef, Habib; Severino, Ricardo; Tovar, EduardoGlobal path planning consists in finding the optimal path for a mobile robot with the lowest cost in the minimum amount of time, without colliding with the obstacles scattered in the workspace. In this paper, we investigate the benefits of offloading path planning algorithms to be executed in the cloud rather than in the robot. The contribution consists in developing a vertex-centric implementation of RA∗ [1], a version of A∗ that we developed for grid maps and that was proven to be much faster than A∗, using the distributed graph processing framework Giraph that rely on Hadoop. We also developed a centralized cloud-based C++ implementation of the algorithm for benchmarking and comparison purposes. Experimental results on a real cloud shows that the distributed graph processing Giraph fails to provide faster execution as compared to centralized C++ implementation for different map sizes and configuration due to non-real time properties of Hadoop.