Ikbal Taleb

Performance Evaluation of Mobile Web Services

Due to the advances on mobile technology, it is becoming feasible to host Web Services on a mobile device, making it perceived as potential data collector and provider. Hosting Web Services on mobile devices gains in importance when it comes to deliver real-time contextual data, such as current location or real-time heart rate. In addition to the characteristics of the available network, the usability of the Mobile Host depends on computational resources of the device itself. Currently, some emerging lightweight frameworks to host web services on mobile devices have been developed. They are recognized for their low resources footprint but they are barely tested. Consequently, the potential of utilizing them in real life settings is not known yet. In this paper, we address this issue and we propose to test the performance of Web Services hosted on mobile devices. We first propose an architecture that allows the deployment of Web Services on mobile devices. The architecture implements an important feature that provides the possibility of resuming and managing the connection state when disconnections happen. Then, we identify and evaluate the QoS of these web services such as response time, availability, throughput, and scalability. We also evaluate the overall performance of the mobile device host with main focus on the battery consumption. We applied our experiments to both SOAP and RESTful Web Services. The results we have obtained are promising and confirm the fact that RESTful Web Services are more convenient for mobile devices as their QoS does not degrade considerably and is kept at a satisfactory level. It also proves the potential hosting of Web Services on current mobile devices with acceptable battery consumption.

Towards a cloud-based framework for context management

With the advances in sensing technology and the proliferation of mobile devices and applications, provisioning of context information has been a particularly common research topic. Many research works have proposed, designed, and implemented frameworks and middleware infrastructures for context management. High-level context information is typically acquired from context services that aggregate raw context information sensed by sensors and mobile devices. Given the massive amount of context data processed and stored by context services and the widespread penetration of cloud computing technology in the industry, context providers now can leverage their services by deploying them on the cloud. In this paper, we describe a novel framework for context management that relies on cloud-based context services. One of the benefits of the approach is that context providers can scale up and down depending on current demand for context information.

An Hybrid Approach to Quality Evaluation across Big Data Value Chain

While the potential benefits of Big Data adoption are significant, and some initial successes have already been realized, there remain many research and technical challenges that must be addressed to fully realize this potential. The Big Data processing, storage and analytics, of course, are major challenges that are most easily recognized. However, there are additional challenges related for instance to Big Data collection, integration, and quality enforcement. This paper proposes a hybrid approach to Big Data quality evaluation across the Big Data value chain. It consists of assessing first the quality of Big Data itself, which involve processes such as cleansing, filtering and approximation. Then, assessing the quality of process handling this Big Data, which involve for example processing and analytics process. We conduct a set of experiments to evaluate Quality of Data prior and after its pre-processing, and the Quality of the pre-processing and processing on a large dataset. Quality metrics have been measured to access three Big Data quality dimensions: accuracy, completeness, and consistency. The results proved that combination of data-driven and process-driven quality evaluation lead to improved quality enforcement across the Big Data value chain. Hence, we recorded high prediction accuracy and low processing time after we evaluate 6 well-known classification algorithms as part of processing and analytics phase of Big Data value chain.

On the Performance of Hosting Web Services on Mobile Devices

Mobile devices and applications have traditionally been seen as data consumers. However, as their computation capabilities are increasing, they are becoming perceived as potential data collectors and providers, and even as hosts for web services. In fact, mobile web services gain in importance when it comes to deliver real-time contextual data, such as current location or real-time heart rate. Some emerging lightweight frameworks to host web services on mobile devices have been developed. They are recognized for their low resource footprint. However, they are barely tested and the potential of utilizing them in real-life settings is not known yet. In this paper, we present an architecture to test web services hosted on mobile devices as well as some preliminary results. We target to evaluate the QoS of these web services such as their response time, availability, throughput, and scalability and to evaluate the overall performance of mobile device host with main focus on the battery consumption.

Policy-Based QoS Enforcement for Adaptive Big Data Distribution on the Cloud.

Big Data distribution has benefited from the Cloud resources to accommodate applications QoS requirements. In this paper, we propose Big Data distribution scheme that matches the Cloud available resources to guarantee applications QoS given the continuously dynamic and varying resources of the Cloud infrastructure. We developed Two-Level QoS Policies (TLPS) for selecting clusters and nodes while satisfying the clients application QoS. We also proposed an adaptive data distribution algorithm to cope with changing QoS requirements. Experiments have been conducted to evaluate both the effectiveness and the communication overhead of our proposed distribution scheme and the results we have reported are convincing. Other experiments evaluated our TLPS algorithm against other single-based QoS data distribution algorithms and the results show that TLPS algorithm adapts to the customer QoS requirements.