Noura Limam

Assessing Software Service Quality and Trustworthiness at Selection Time

The integration of external software in project development is challenging and risky, notably because the execution quality of the software and the trustworthiness of the software provider may be unknown at integration time. This is a timely problem and of increasing importance with the advent of the SaaS model of service delivery. Therefore, in choosing the SaaS service to utilize, project managers must identify and evaluate the level of risk associated with each candidate. Trust is commonly assessed through reputation systems; however, existing systems rely on ratings provided by consumers. This raises numerous issues involving the subjectivity and unfairness of the service ratings. This paper describes a framework for reputation-aware software service selection and rating. A selection algorithm is devised for service recommendation, providing SaaS consumers with the best possible choices based on quality, cost, and trust. An automated rating model, based on the expectancy-disconfirmation theory from market science, is also defined to overcome feedback subjectivity issues. The proposed rating and selection models are validated through simulations, demonstrating that the system can effectively capture service behavior and recommend the best possible choices.

Resource and service discovery in large-scale multi-domain networks

With the increasing need for networked applications and distributed resource sharing, there is a strong incentive for an open large-scale service infrastructure operating over multidomain and multi-technology networks. Service discovery, as an essential support function of such an infrastructure, is a crucial current research challenge. Although a few survey papers have been published on this subject, our contribution focuses on comparing and analyzing key discovery approaches in the context of large-scale and multidomain networks. The comparison is conducted based on a set of well-defined criteria, leading to a selection of few approaches that can serve as the guide in designing a global service discovery system for large-scale and multi-technology networks.

QoS and reputation-aware service selection

The advent of service-oriented architectures has created a unique opportunity for business providers and consumers to establish more versatile and flexible interactions across the Internet by means of a new generation of services that are discoverable, composable, configurable, and reusable. In order to support such services all along their life cycle, underlying service-oriented infrastructures have to provide various functionalities, including service discovery. In large scale environments, like the Internet, a discovery process may result in a very large number of matching services. Service quality, cost and reputation are substantial aspects for differentiating between similar services. In order to help users select the most appropriate service, an automated service selection algorithm is proposed. The devised algorithm helps to accurately predict service suitability to quality requirements while taking into account the reputation parameter.

Service naming in large-scale and multi-domain networks

The increasing availability of high-performance network resources creates a rich breeding ground for widely-distributed applications that span multiple network domains or administrative domains. Such applications provide services that can be accessed by remote users. Discovery and management of these systems require the ability to name the provided services. In light of these requirements, we distill a set of criteria for comparison of naming schemes: readability, extensibility, namespace size, naming authority, name resolution architecture, name persistence, and standardization. Based on these criteria, we summarize and compare a representative set of existing naming and name resolution approaches. We analyze the approaches based on our criteria, and select a number of candidate technologies for the design of a naming and name resolution mechanism suitable to a multi-domain, Internet-scale environment.

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the explosion in the availability of data, significant improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML has been applied to various mundane and complex problems arising in network operation and management. There are various surveys on ML for specific areas in networking or for specific network technologies. This survey is original, since it jointly presents the application of diverse ML techniques in various key areas of networking across different network technologies. In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing and classification, congestion control, resource and fault management, QoS and QoE management, and network security. Furthermore, this survey delineates the limitations, give insights, research challenges and future opportunities to advance ML in networking. Therefore, this is a timely contribution of the implications of ML for networking, that is pushing the barriers of autonomic network operation and management.

Scheduled sampling for robust sensing

We consider the problem of optimizing the sensing strategy of a monitoring system in the presence of faulty sensors. We develop ORSg, an efficient data-driven algorithm for computing sampling strategies that nearly maximize the submodular utility of sensing with only a fraction of active and fault-prone sensors. Our approach combines techniques from information theory, game theory and submodular optimization. We empirically evaluate our algorithm with a real-world sensing scenario.